2.1 STACK in a Nutshell

The STACK team addresses challenges related to the management and advanced usages of Utility Computing infrastructures (i.e., Cloud, Fog, Edge, and beyond). More specifically, the team is interested in delivering appropriate system abstractions to operate and use massively geo-distributed infrastructures, from the lowest (system) levels to the highest (application development) ones, and addressing crosscutting dimensions such as energy or security. 1 These infrastructures are critical for the emergence of new kinds of applications related to the digitalization of the industry and the public sector (a.k.a. the Industrial and Tactile Internet).

2.2 Toward a STACK for Geo-Distributed Infrastructures

With the advent of Cloud Computing, modern applications have been developed on top of advanced software stacks composed of low-level system mechanisms, advanced middleware and software abstractions. While each of these layers has been designed to enable developers to efficiently use ICT resources without dealing with the burden of the underlying infrastructure aspects, the complexity of the resulting software stack has become a key challenge. As an example, Map/Reduce frameworks such as Hadoop have been developed to benefit from the cpu/storage capacities of distinct servers. Running such frameworks on top of a virtualized cluster (i.e., in a Cloud) can lead to critical situations if the resource management system decides to consolidate all the VMs on the same physical machine  99. In other words, self-management decisions taken in isolation at one level (infrastructure, middleware, or application) may indirectly interfere with the decisions taken by another layer, and globally affect the performance of the whole stack. Considering that geo-distributed ICT infrastructures significantly differ from the Cloud Computing ones regarding heterogeneity, resiliency, and the potential massive distribution of resources and networking environments  63, 60, we can expect that the complexity of the software stacks is going to increase. Such an assumption can be illustrated, for instance, by the sotfware architecture proposed in 2016 by the ETSI Mobile edge computing Industry Specification Group  88. This architecture is structured around a new layer in charge of orchestrating distinct independent cloud systems, a.k.a. Virtual Infrastructure Managers (VIMs) in their terminology. By reusing VIMs, ETSI targets an edge computing resource management that behaves in the same fashion as Cloud Computing ones. While mitigating development requirements, such a proposal hides all the management decisions that might be taken in the VIM of one particular site and thus may lead to conflicting decisions and consequently to non-desired states overall.

Through the STACK team, we propose to investigate the software stack challenge as a whole. We claim it is the only way to limit as much as possible the complexity of the next generation software stack of geo-distributed ICT infrastructures. To reach our goal, we will identify major building blocks that should compose such a software stack, how they should be designed (i.e., from the internal algorithms to the APIs they should expose), and finally how they should interact with each other.

Delivering such a software stack is an ambitious objective that goes beyond the activities of one research group. However, our expertise, our involvements in different consortiums (such as OpenStack) as well as our participation in different collaborative projects enable STACK members to contribute to this challenge in terms of architecture models, distributed system mechanisms and software artefacts, and finally, guideline reports on opportunities and constraints of geo-distributed ICT infrastructures.

3.1 Overview

STACK research activities have been organized around four research topics. The two first ones are related to the resource management mechanisms and the programming support that are mandatory to operate and use ICT geo-distributed resources (compute, storage, network, and IoT devices). They are transverse to the System/Middleware/Application layers, which generally compose a software stack, and nurture each other (i.e., the resource management mechanisms will leverage abstractions/concepts proposed by the programming support axis and reciprocally). The third and fourth research topics are related to the Energy and Security dimensions (both also crosscutting the three software layers). Although they could have been merged with the first two axes, we identified them as independent research directions due to their critical aspects with respect to the societal challenges they represent. In the following, we detail the actions we plan to do in each research direction.

3.2 Resource Management

The challenge in this axis is to identify, design or revise mechanisms that are mandatory to operate and use a set of massively geo-distributed resources in an efficient manner  47. This covers considering challenges at the scale of nodes, within one site (i.e., one geographical location) and throughout the whole geo-distributed ICT infrastructure. It is noteworthy that the network community has been investigating similar challenges for the last few years  69. To benefit from their expertise, in particular on how to deal with intermittent networks, STACK members have recently initiated exchanges and collaborative actions with some network research groups and telcos (see Sections 9.1 and 10). We emphasize, however, that we do not deliver contributions related to network equipments/protocols. The scientific and technical achievements we aim to deliver are related to the (distributed) system aspects.

3.3 Programming Support

We pursue two main research directions relative to new programming support: first, developing new programming models with appropriate support in existing languages (libraries, embedded DSLs, etc.) and, second, providing new means for deployment and reconfiguration in geo-distributed ICT environments, principally supporting the mapping of software onto the infrastructure. For both directions two levels of challenges are considered. On the one hand, the generic level refers to efforts on programming support that can be applied to any kind of distributed software, application or system. On this level, contributions could thus be applied to any of the three layers addressed by STACK (i.e., system, middleware or application). On the other hand, the corresponding generic programming means may not be appropriate in practice (e.g., requirements for more dedicated support, performance constraints, etc.), even if they may lead to interesting general properties. For this reason, a specific level is also considered. This level could be based on the generic one but addresses specific cases or domains.

3.4 Energy

The overall electrical consumption of DCs grows according to the demand of Utility Computing. Considering that the latter has been continuously increasing since 2008, the energy footprint of Cloud services overall is nowadays critical with about 91 billion kilowatt-hours of electricity   91. Besides the ecological impact, the energy consumption is a predominant criterion for providers since it determines a large part of the operational cost of their infrastructure. Among the different appraoches that have been investigated to reduce the energy footprint, some studies have been ingestigating the use of renewable energy sources to power microDCs  64. Workload distribution for geo-distributed DCs is also another promising approach  66, 78, 97. Our research will extend these results with the ultimate goal of considering the different opportunities to control the energy footprint across the whole stack (hardware and software opportunities, renewable energy, thermal management, etc.). In particular, we identified several challenges that we will address in this context within the STACK framework.

First, we propose to evaluate the energy efficiency of low-level building blocks, from the viewpoints of computation (VMs, containers, microkernel, microservices)  55 and data (hard drives, SSD, in-memory storage, distributed file systems). For computations, in the continuity of our previous work  53, 73, we will investigate workload placement policies according to energy (minimizing energy consumption, power capping, thermal load balancing, etc.). Regarding the data dimension, we will investigate, in particular, the trade-offs between energy consumption and data availability, durability and consistency  48, 94. Our ambition is to propose an adaptive energy-aware data layout and replication scheme to ensure data availability with minimal energy consumption. It is noteworthy that these new activities will also consider our previous work on DCs partially powered by renewable energy (see the SeDuCe project, in Section 7.2), with the ultimate goal of reducing the CO${}_2$ footprint.

Second, we will complete current studies to understand pros and cons of massively geo-distributed infrastructures from the energy perspective. Addressing the energy challenge is a complex task that involves considering several dimensions such as the energy consumption due to the physical resources (CPU, memory, disk, network), the performance of the applications (from the computation and data viewpoints), and the thermal dissipation caused by air conditioning in each DC. Each of these aspects can be influenced by each level of the software stack (i.e., low-level building blocks, coordination and autonomous loops, and finally application life cycle). In previous projects, we have studied and modeled the consumption of the main components, notably the network, as part of a single microDC. We plan to extend these models to deal with geo-distribution. The objective is to propose models that will enable us to refine our placement algorithms as discussed in the next paragraph. These models should be able to consider the energy consumption induced by all WAN data exchanges, including site-to-site data movements as well as the end users' communications for accessing virtualized resources.

Third, we expect to implement green-energy-aware balancing strategies, leveraging the aforementioned contributions.

Although the infrastructures we envision increase complexity (because WAN aspects should also be taken into account), the geo-distribution of resources brings several opportunities from the energy viewpoint. For instance, it is possible to define several workload/data placement policies according to renewable energy availability. Moreover, a tightly-coupled software stack allows users to benefit from such a widely distributed infrastructure in a transparent way while enabling administrators to balance resources in order to benefit from green energy sources when available.

An important difficulty, compared to centralized infrastructures, is related to data sharing between software instances. In particular, we will study issues raised by the distribution and replication of services across several microDCs. In this new context, many challenges must be addressed: where to place the data (Cloud, Edge) in order to mitigate dat a movements? What is the impact in terms of energy consumption, network and response time of these two approaches? How to manage the consistency of replicated data/services? All these aspects must be studied and integrated into our placement algorithms.

Fourth, we will investigate the energy footprint of the current techniques that address failure and performance variability in large-scale systems. For instance, stragglers (i.e., tasks that take a significantly longer time to finish than the normal execution time) are natural results of performance variability, they cause extra resource and energy consumption. Our goal is to understand the energy overhead of these techniques and introduce new handling techniques that take into consideration the energy efficiency of the platform  86.

Finally, in order to answer specific energy constraints, we want to reify energy aspects at the application level and propose a metric related to the use of energy (Green SLA  31), for example to describe the maximum allowed CO${}_2$ emissions of a Fog/Edge service. Unlike other approaches  67, 36, 65 that attempt to identify the best trade-off, we want to offer to developers/end-users the opportunity to select the best choice between application performance, correctness and energy footprint. Such a capability will require reifying the energy dimension at the level of big-data and interactive applications. Besides, with the emergence of renewable energy (e.g., solar panels for microDC), investigating the energy consumption vs performance trade-off  70 and the smart usage of green energy for ICT geo-distributed services seems promising. For example, we want to offer the opportunity to developers/end-users to control the scaling of the applications based on this trade-off instead of current approaches that only considered application load. Providing such a capability will also require appropriate software abstractions.

3.5 Security

Because of its large size and complex software structure, geo-distributed applications and infrastructures are particularly exposed to security and privacy issues  90. They are subject to numerous security vulnerabilities that are frequently exploited by malicious attackers in order to exfiltrate personal, institutional or corporate data. Securing these systems require security and privacy models and corresponding techniques that are applicable at all software layers in order to guard interactions at each level but also between levels. However, very few security models exist for the lower layers of the software stack and no model enables the handling of interactions involving the complete software stack. Any modification to its implementation, deployment status, configuration, etc., may introduce new or trigger existing security and privacy issues. Finally, applications that execute on top of the software stack may introduce security issues or be affected by vulnerabilities of the stack. Overall, security and privacy issues are therefore interdependent with all other activities of the STACK team and constitute an important research topic for the team.

As part of the STACK activities, we consider principally security and privacy issues related to the vertical and horizontal compositions of software components forming the software stack and the distributed applications running on top of it. Modifications to the vertical composition of the software stack affect different software levels at once. As an example, side-channel attacks often target virtualized services (i.e., services running within VMs); attackers may exploit insecure hardware caches at the system level to exfiltrate data from computations at the higher level of VM services  84, 98. Security and privacy issues also affect horizontal compositions, that is, compositions of software abstractions on one level: most frequently horizontal compositions are considered on the level of applications/services but they are also relevant on the system level or the middleware level, such as compositions involving encryption and database fragmentation services.

The STACK members aim at addressing two main research issues: enabling full-stack (vertical) security and per-layer (horizontal) security. Both of these challenges are particularly hard in the context of large geo-distributed systems because they are often executed on heterogeneous infrastructures and are part of different administrative domains and governed by heterogeneous security and privacy policies. For these reasons they typically lack centralized control, are frequently subject to high latency and are prone to failures.

Concretely, we will consider two classes of security and privacy issues in this context. First, on a general level, we strive for a method for the programming and reasoning about compositions of security and privacy mechanisms including, but not limited to, encryption, database fragmentation and watermarking techniques. Currently, no such general method exists, compositions have only been devised for specific and limited cases, for example, compositions that support the commutation of specific encryption and watermarking techniques  76, 45. We provided preliminary results on such compositions  46 and have extended them to biomedical, notably genetic, analyses in the e-health domain  38. Second, on the level of security and privacy properties, we will focus on isolation properties that can be guaranteed through vertical and horizontal composition techniques. We have proposed first results in this context in form of a compositional notion of distributed side channel attacks that operate on the system and middleware levels  34.

It is noteworthy that the STACK members do not have to be experts on the individual security and privacy mechanisms, such as watermarking and database fragmentation. We are, however, well-versed in their main properties so that we can integrate them into our composition model. We also interact closely with experts in these techniques and the corresponding application domains, notably e-health for instance, in the context of the PrivGen project8, see Section 10.

More generally, we highlight that security issues in distributed systems are very closely related to the other STACK challenges, dimensions and research directions. Guaranteeing security properties across the software stack and throughout software layers in highly volatile and heterogeneous geo-distributed systems is expected to harness and contribute results to the self-management capabilities investigated as part of the team's resource management challenges. Furthermore, security and privacy properties are crosscutting concerns that are intimately related to the challenges of application life cycle management. Similarly, the security issues are also closely related to the team's work on programming support. This includes new means for programming, notably in terms of event and stream programming, but also the deployment and reconfiguration challenges, notably concerning automated deployment. As a crosscutting functionality, the security challenges introduced above must be met in an integrated fashion when designing, constructing, executing and adapting distributed applications as well as managing distributed resources.

4.1 Overview

Supporting industrial actors and open-source communities in building an advanced software management stack is a key element to favor the advent of new kinds of information systems as well as web applications. Augmented reality, telemedecine and e-health services, smart-city, smart-factory, smart-transportation and remote security applications are under investigations. Although, STACK does not intend to address directly the development of such applications, understanding their requirements is critical to identify how the next generation of ICT infrastructures should evolve and what are the appropriate software abstractions for operators, developers and end-users. STACK team members have been exchanging since 2015 with a number of industrial groups (notably Orange Labs and Airbus), a few medical institutes (public and private ones) and several telecommunication operators in order to identify both opportunities and challenges in each of these domains, described hereafter.

4.2 Industrial Internet

The Industrial Internet domain gathers applications related to the convergence between the physical and the virtual world. This convergence has been made possible by the development of small, lightweight and cheap sensors as well as complex industrial physical machines that can be connected to the Internet. It is expected to improve most processes of daily life and decision processes in all societal domains, affecting all corresponding actors, be they individuals and user groups, large companies, SMEs or public institutions. The corresponding applications cover: the improvement of business processes of companies and the management of institutions (e.g., accounting, marketing, cloud manufacturingi, etc.); the development of large “smart” applications handling large amounts of geo-distributed data and a large set of resources (video analytics, augmented reality, etc.); the advent of future medical prevention and treatment techniques thanks to the intensive use of ICT systems, etc. We expect our contributions will favor the rise of efficient, correct and sustainable massively geo-distributed infrastructures that are mandatory to design and develop such applications.

4.3 Internet of Skills

The Internet of Skills is an extension of the Industrial Internet to human activities. It can be seen as the ability to deliver physical experiences remotely (i.e., via the Tactile Internet). Its main supporters advocate that it will revolutionize the way we teach, learn, and interact with pervasive resources. As most applications of the Internet of Skills are related to real time experiences, latency may be even more critical than for the Industrial Internet and raise the locality of computations and resources as a priority. In addition to identifying how Utility Computing infrastructures can cope with this requirement, it is important to determine how the quality of service of such applications should be defined and how latency and bandwidth constraints can be guaranteed at the infrastructure level.

4.4 e-Health

The e-Health domain constitutes an important societal application domain of the two previous areas. The STACK teams is investigating distribution, security and privacy issues in the fields of systems and personalized (aka. precision) medicine. The overall goal in these fields is the development of medication and treatment methods that are tailored towards small groups or even individual patients.

We are working, as part of the ongoing PrivGen CominLabs collaborative project on new means for the sharing of genetic data and applications in the Cloud. More generally, we are applying and developing corresponding techniques for the medical domains of genomics, immunobiology and transplantalogy in the international network SHLARC and the regional networks SysMics and Oncoshare (see Section 10): there, we investigate how to secure and preserve privacy if potentially sensitive personal data is moved and processed by distributed biomedical analyses.

We are also involved in the SyMeTRIC regional initiative where preliminary studies have been conducted in order to build a common System Medicine computing infrastructure to accelerate the discovery and validation of bio-markers in the fields of oncology, transplantation, and chronic cardiovascular diseases. The challenges were related to the need of being able to perform analyses on data that cannot be moved between distinct locations.

The STACK team will continue to contribute to the e-Health domain by harnessing advanced architectures, applications and infrastructures for the Fog/Edge.

4.5 Network Virtualization and Mobile Edge Services

Telecom operators have been among the first to advocate the deployment of massively geo-distributed infrastructures, in particular through working groups such as Mobile Edge Computing at the European Telecommunication Standards Institute9. The initial reason is that geo-distributed infrastructures will enable Telecom operators to virtualize a large part of their resources and thus reduce capital and operational costs. As an example, we are investigating through the I/O Lab, the joint lab between Orange and Inria, how can a Centralized Radio Access Networks (a.k.a. C-RAN or Cloud-RAN) be supported for 5G networks. We highlight that our expertise is not on the network side but rather on where and how we can deploy, allocate and reconfigure software components, which are mandatory to operate a C-RAN infrastructure, in order to guarantee the quality of service expected by the end-users. Finally, working with actors from the network community is a valuable advantage for a distributed system research group such as STACK. Indeed, achievements made within one of the two communities serve the other.

5.1 Footprint of research activities

In addition to the international travels10, the environmental footprint of our research activities is linked to our intensive use of large-scale testbeds such as Grid'5000 (STACK members are often in the top10 list of the largest consummers). Although the access to such facilities is critical to move forward in our research roadmap, it is important to recognize that they have a strong environmental impact as decribed in the next paragraph.

5.2 Impact of research results

The environmental impact of digital technology is a major scientific and societal challenge. Even though the software remains virtual objects, it is executed on very real hardware contributing to the carbon footprint. This impact materializes during the manufacture / destruction of hardware infrastructure (estimated at 45% of digital consumption in 2018 by the The Shift Project) and during the software use phase via terminals, networks and data centers. data (estimated at 55%). Stack members have been studying various approaches for several years to reduce the energy footprint of digital infrastructures during the use phase. The work carried out revolves around two main axes: (i) reducing the energy footprint of infrastructures and (ii) adapting the software applications hosted by these infrastructures according to the energy available. More precisely, this second axe investigates possible improvements that could be made by the end-users of the software themselves. At scale, involving end-users in decision-making processes concerning energy consumption would lead to more frugal Cloud computing. For instance, in the GL4MA project (cf. Section 10), we propose that the end-users customize the software in SaaS mode to contribute to reducing their carbon footprint by using either fewer resources or resources powered directly by renewable energy.

6.1 Awards

In 2020, the team has received one individual award:

• Adrien Lebre received the IEEE TCC Editorial Excellence and Eminence Award to recognize his exceptional contributions to the TCC Editorial Board.

We would like also to highlight two elements that underline the visibility and recognition of the team nationally and internationally. First, at the national level, the team has obtained two grants from the Appel ANR générique 2020 for the SeMaFoR and PICNIC projects. The former's objective is to model, design and develop a generic and decentralised solution for the self-management of Fog resources using a Fog Architecture Description Language, a collaborative/consensual decision-making process and an automatic reconfiguration coordination mechanism. The latter addresses the problem of transferring large data-sets between two geographically distant sites. More precisely, the objective is to develop network mechanisms in the linux kernel to sending in parallel a file by breaking the VM bottleneck by using the property that the file is (all or part) duplicated on several disks.

Second, at the international level, Helene Coullon obtained a 20% Adjunct Professor position at the Arctic University of Norway in Tromsø (UiT)13. This position has been offered to Helene after an invited talk (at the end of 2019), and discussions on collaborations with the team involved in the DAO project14 leaded by Otto Anshus. The position has started in september 2020 and will end in august 2022. Helene has the responsability to give a few courses to the UiT students (Masters and PhD) in advanced distributed systems. Furthermore, this position facilitates interactions for research collaborations on the DAO project in which Helene brings an expertise in dynamic software configuration and reconfiguration.

7.1 New software

7.2 New platforms

8.1 Resource Management

Participants: Adwait Jitendra Bauskar, Ronan-Alexandre Cherrueau, Bastien Confais, Marie Delavergne, David Espinel, David Guyon, Shadi Ibrahim, Remous Aris Koutsiamanis, Thomas Lambert, Adrien Lebre, Karim Manaouil, Javier Rojas Balderrama, Matthieu Simonin, Alexandre Van Kempen.

In 2020, we had multiple contributions in the field of resource management of geo-distributed cloud infrastructures, with a particular focus on Fog and Edge computing. First, we present contributions regarding the resource placement problem, for both traditional and data streaming applications. We then address issues regarding the network complications in Fog/Edge computing regarding the network itself and storage. To improve reproducibility and experimentation in resource management we also introduce a new simulation tool for edge computing use-cases. Following our multi-year work on this subject we then re-evaluate past suggested best practices and the readiness of modern resource management systems (Kubernetes) for the edge-computing case. Finally, we also start addressing the IoT part of the Cloud $\leftrightarrow$ IoT continuum by presenting a scheduler for wireless IoT network resources.

In 5, we presented a survey of current research conducted on Service Placement Problem (SPP) in the Fog/Edge Computing. To support the large and various applications generated by the Internet of Things (IoT), Fog Computing has been introduced to complement the Cloud Computing and offer Cloud-like services at the edge of the network with low latency and real-time responses. Large-scale, geographical distribution and heterogeneity of edge computational nodes make service placement in such infrastructure a challenging issue. Diversity of user expectations and IoT devices characteristics also complexify the deployment problem. Based on a new classification scheme, we analysed current proposals and discussed issues and challenges our community should deal with.

In 21, we propose a model to evaluate Maximum Sustainable Throughput (MST) for operators placement in the Edge, with a strong focus on the heterogeneous nature of network. We then introduce an optimal operators placement for stream data applications in the Edge using constraint programming. Through simulations, we show how existing placement strategies that target overall communications reduction often fail to keep up with the rate of data streams. Importantly, the constraint programming-based operators placement is able to sustain up to 5x increased data ingestion compared to baseline strategies including resource-aware placements and graph partitioning-based placement.

In 13, we introduce DIMINET, a distributed module to interconnect independent networking resources across multiple locations in an automatized and transparent manner. It is nowadays accepted that the deployment of a geo-distributed cloud infrastructure , leveraging for instance Point-of-Presences at the edge of the network, could better fit the requirements of Network Function Virtualization services and Internet of Things applications. The envisioned architecture to operate such a widely distributed infrastructure relies on executing one instance of a Virtual Infrastructure Manager (VIM) per location and implement appropriate code to enable collaborations between them when needed. However, delivering the mechanisms that allow the collaborations is complex and error prone task. This is particularly true for the one in charge of establishing connectivity among VIM instances on-demand. Besides the reconfiguration of the network equipment, the main challenge is to design a mechanism that can offer usual network virtualization operations to the users while dealing with scalability and intermittent network properties of geo-distributed infrastructures. To deal with these challenges, we designed DIMINET, a DIstributed Module for Inter-site NETworking services. DIMINET relies on a decentralized architecture where each agent communicates with others only if needed. Moreover, there is no global view of all networking resources but each agent is in charge of interconnecting resources that have been created locally. This approach enables us to mitigate management traffic and keep each site operational in case of network partitions. A promising approach to make other cloud-services collaborative on-demand.

In 22, we describe in detail the storage solution we designed between 2017 and 2019 for Fog/Edge infrastructures. Our initial proposal consisted in coupling an object store system and a scale-out NAS (Network Attached Storage) allowing both scalability and performance. This architecture has been extended with a new protocol inspired from the Domain Name System (DNS) to manage replicas in a context of mobility. The different versions have been evaluated over Grid'5000, presenting each time promising performance.

In 12, we introduce a simulation engine dedicated to the evaluation and comparison of scheduling and data movement policies for edge computing use-cases. Although several strategies have been proposed, they have been evaluated through ad-hoc simulator extensions that are, when available, usually not maintained. This is a critical problem because it prevents researchers to-easily-perform fair comparisons between different proposals. We proposed to address this limitation by developping an extension to the Batsim/SimGrid toolkit. Our tool includes a plug-in system that allows researchers to add new models in order to cope with the diversity of edge computing devices. Moreover, it includes an injector that allows the simulator to replay a series of events captured in real infrastructures. We demonstrated the relevance of such a simulation toolkit by studying two scheduling strategies with four data movement policies on top of a simulated version of the Qarnot Computing platform, a production edge infrastructure based on smart heaters. We chose this use-case as it illustrates the heterogeneity as well as the uncertainties of edge infrastructures. Our ultimate goal is to gather industry and academics around a common simulator so that efforts made by one group can be factorised by others.

In 26, we present a break through apporach in the design of resource management systems (RMSes) for the edge. Two years ago, at HotEdge'18, we alerted our community of the importance of delivering a RMS to favor the advent of the edge computing paradigm. While new initiatives have been proposed, they are far from offering the expected features to administrate and use geo-distributed infrastructures. However, we claim our community can move forward by focusing on the collaborations of mutliple instances of the same RMS instead of developping a new solution from scratch. Our proposal leverages service concepts, dynamic composition as well as programming software abstractions. Beyond the development of a resource management system for edge infrastructures, our proposal may lead to a new way of distributing applications where intermittent network is the norm.

In 28, we provide reflections regarding how Kubernetes, the well-known container orchestration platform can cope with edge infrastructure specifics. With the advent of Edge Computing era, DevOps expect to find features that made the success of containerized applications in the cloud, also at the edge. However, orchestration systems have not been designed to deal with resources geo-distribution aspects such as latency, intermittent networks, locality-awareness, etc. In other words, it is unclear whether they could be directly used on top of such massively distributed infrastructures or whether they must be revised. To provide the first elements of answers, we conducted an experimental campaign to analyze the impact of WAN links on the vanilla Kubernetes. This study raised several challenges our community should consider in order to better address geo-distribution concerns in orchestration platforms.

In 19, we propose and evaluate a flexible centralized controller for scheduling wireless networks. The context of this work encompasses wireless networks within the wider Internet of Things (IoT) field and in particular addresses the requirements and limitations within the narrower Industrial Internet of Things (IIoT) sub-field. The overall aim of this work is to produce wireless networking solutions for industrial applications. The challenges include providing high reliability and low latency guarantees, comparable to existing wired solutions, within a noisy wireless medium and using generally computationally-and energy-restrained network nodes. We describe the development of a centralized controller for Wireless Industrial Networks, currently aimed at IEEE Std 802.15.4-2015 Time Slotted Channel Hopping protocol. Our controller takes a high-level network-centric problem description as input, translates it to a low-level representation and uses that to retrieve a solution from a Satisfiability Modulo Theories (SMT) solver, translating the solution back to a higher-level network-centric representation. The advantages of our solution are the ability to gain the added flexibility, higher ease of deployment, and lower deployment cost offered by wireless networks by generating configurable and flexible schedules for these applications.

8.2 Programming Support

Participants: Maverick Chardet, Hélène Coullon, Jolan Philippe.

In 2020, our contributions on programming support are related to two aspects, at first glance without any link. Yet, they both are related to the autonomic adaptation of systems. One can note that making distributed systems autonomous in their deployment and management is of high importance at the scale of Fog and Edge computing, to avoid human errors and guarantee safety properties. It is usual when speaking about autonomic to introduce the MAPE-K loop, where (M) is the monitoring of systems and environment, (A) is the analysis of the situation and the decision of new adaptations, (P) is the planning phase of the adaptation and (E) is the execution of the plan. These 4 steps share a knowledge (K). The first contribution detailed below answers the (A) phase, in the specific case of low-code platforms, by computing the most adapted parallelism and configuration strategy according to the current state (i.e., application, environment). The second publication contribute to building a generic model and tool to build efficient and safe execution of distributed systems adaptation (E), i.e., reconfiguration. By formalizing its semantics and offering performance prediction tools, this second contribution also open the door to automated computation of a reconfiguration plan (P).

In 14 we discuss programming support to automate the choice of the most adequate parallelism strategy and distributed configuration for Low-code development platforms. Low-code development platforms are taking an important place in the model-driven engineering ecosystem, raising new challenges, among which transparent efficiency or scalability. Indeed, the increasing size of models leads to difficulties in interacting with them efficiently. To tackle this scalability issue, some tools are built upon specific computational strategies exploiting reactivity, or parallelism. However, their performances may vary depending on the specific nature of their usage. Choosing the most suitable computational strategy for a given usage is a difficult task which should be automated. Besides, the most efficient solutions may be obtained by the use of several strategies at the same time. This paper motivates the need for a transparent multi-strategy execution mode for model-management operations. We present an overview of the different computational strategies used in the model-driven engineering ecosystem, and use a running example to introduce the benefits of mixing strategies for performing a single computation. This example helps us present our design ideas for a multi-strategy model-management system. The code-related and DevOps challenges that emerged from this analysis are also presented.

In 11 the dynamic reconfiguration of distributed software systems is tackled. Reconfiguration is nowadays gaining interest because of the emergence of dynamic IoT and smart applications as well as large scale dynamic infrastructures (e.g., Fog and Edge computing). When quality of service and experience is of prime importance, efficient reconfiguration is necessary, as well as performance predictability to decide when a reconfiguration should occur. This paper tackles the problem of efficient execution of a reconfiguration plan and its predictability with Concerto, a reconfiguration model supporting a high level of parallelism in reconfiguration operations. Evaluation performed on synthetic cases and on two real production scenarios show that Concerto provides better performance than state-of-the-art systems with accurate time estimation.

8.3 Energy-aware computing

Participants: Emile Cadorel, Hélène Coullon, Remous Aris Koutsiamanis, Thomas Ledoux, Jean-Marc Menaud, Jonathan Pastor, Dimitri Saingre, Yewan Wang.

In 2020, we achieved three contributions in the field of Energy-aware computing. First, we have addressed blockchain-based solutions and proposed a framework to benchmark different blockchain technologies (e.g., CPU consumption). Then, tackling the problem of scheduling multiuser workflows from the Cloud provider point of view, we have proposed an algorithm that optimizes two metrics: the energy consumption and the fairness between users. Finally, we have adressed the issue of network energy consumption in the context of IoT devices.

Over the last years, research activities on blockchain technologies have fairly increased. Firstly introduced with Bitcoin, some projects have since emerged to create or improve blockchain features like privacy while others propose to overcome technical limitations such as scalability and energy consumption. New proposals are often evaluated with ad hoc tools and experimental environments. Reproducibility and comparison of these new contributions with the state of the art of the blockchain technologies are therefore complicated. To the best of our knowledge, only a few tools partially address the design of a generic benchmarking of blockchain technologies (e.g., load generation). In 15, we introduce BCTMark, a generic framework for benchmarking blockchain technologies on an emulated network in a reproducible way. To illustrate the portability of experiments using BCTMark, we have conducted some experiments on two different testbeds: a cluster of Dell PowerEdge R630 servers (Grid’5000) and one of Raspberry Pi 3+. Experiments have been conducted on three different blockchain systems (Ethereum Clique/Ethash and Hyperledger Fabric) to measure their CPU consumption and energy footprint for different numbers of clients.

In 10, we deal with the problem of scheduling multiuser scientific workflows with unpredictable random arrivals and uncertain task execution times in a Cloud environment from the Cloud provider point of view. The solution consists in a deadline sensitive online algorithm, named NEARDEADLINE, that optimizes two metrics: the energy consumption and the fairness between users. Scheduling workflows in a private Cloud environment is a difficult optimization problem as capacity constraints must be fulfilled additionally to dependencies constraints between tasks of the workflows. Furthermore, NEARDEADLINE is built upon a new workflow execution platform. As far as we know no existing work tries to combine both energy consumption and fairness metrics in their optimization problem. The experiments conducted on a real infrastructure (clusters of Grid'5000) demonstrate that the NEARDEADLINE algorithm offers real benefits in reducing energy consumption, and enhancing user fairness.

In 18, we propose a set of extensions to a popular routing protocol for Industial IoT devices to improve the energy consumption and reduce the waiting time for devices joining the network. The IPv6 Routing Protocol for Low-Power and Lossy Networks (RPL) is the de facto routing protocol for Low Power and Lossy Networks (LLNs). It is a proactive and link-layer agnostic routing protocol standardized as RFC 6550 by the Internet Engineering Task Force (IETF). Based on the distance-vector technique, RPL builds a Destination Oriented Directed Acyclic Graph (DODAG) topology. To establish and maintain the routes, RPL uses DODAG Information Object (DIO) control packets, that are transmitted in broadcast, for RPL nodes to propagate the DODAG related information, while its transmission frequency depends on Trickle timer algorithm, i.e., the less stable the network the more DIOs are transmitted. Thus, when a new node intends to join the RPL DODAG, it listens for a DIO message from nearby nodes, which may take a very long time if the network is in a stable state. Therefore, RFC 6550 is equipped with the DODAG Informational Solicitation (DIS) message to solicit DIOs from nearby RPL nodes, similar to the Router Solicitation in IPv6 Neighbor Discovery. However, the solicitation procedure is not the most efficient one, since it resets the Trickle timers in the nodes that receive the DIS message and, thus, they transmit an unnecessarily large number of DIOs that congest the network and consume energy in the nodes. In this paper, we propose to augment RFC 6550, the RPL routing protocol, with additional DIS flags and options that allow a RPL node to better control how the nearby RPL nodes will respond to its solicitation for DIOs. Our performance evaluation in Contiki-NG & COOJA demonstrates that we can reduce the control packets in the network by up to 45.5%.

In 20, we propose and evaluate three different ways of implementing multi-path routing in Industial IoT devices to improve reliability, latency and energy consumption. The IPv6 Routing Protocol for Low-Power and Lossy Networks (RPL) networks is designed for Internet of Things (IoT) networks to generate routes between devices with minimal processing. This protocol creates a DODAG (Destination Oriented Directed Acyclic Graph) network topology through the use of DODAG Information Object (DIO) control packets. The DODAG routes the data packets upstream to the destination device. In order to obtain a reliable network, we implement Packet Replication and Elimination (PRE) to perform multi-path data transmission via multiple parent devices. However, there is no standard way to select an alternative path. This document presents three types of Alternative Parent (AP) selection following a braided model. We focus on analyzing its performance in terms of delay and compromise between network traffic and reliability.

Finally, Yewan Wang defended in March her PhD 23 on the evaluation and the modelisation of the energy impacts of data centers, in terms of hardware / software architecture and associated environment. The main contribution is a global power modeling to estimate the overall energy consumption of a cluster using informations such as ambient temperature, cooling system configurations and server loads.

8.4 Security and Privacy

Participants: Fatima Zahra Boujdad, Wilmer Edicson Garzon Alfonso, Sirine Sayadi, Mario Südholt.

This year the team has continued work on the protection of sensitive data and the security of distributed biomedical analyses in the context of the PhD theses of Fatima-zahra Boujdad (in cooperation with partners informaticiens and geneticiens working at INSERM laboratories in Brest), Wilmer Garzon (in cooperation with a Colombian technical university) and Sirine Sayadi (in cooperation with a medical group from the university hospital Nantes).

We have provided solutions to the problem of preserving privacy of sensitive data in distributed biomedical analyses, notably in the field of precision medicine, that is, analyses and treatments tailored to small groups of patients or even individual patients. 16

An important aspect of precision medicine consists in patient-centered contextualization analyses that are used as part of biomedical interactive tools. Such analyses often harness data of large populations of patients from different research centers and can often benefit from a distributed implementation. However, performance and the security/privacy concerns of sharing sensitive biomedical data can become a major issue.

We have investigated these issues in the context of the Kidney Transplantation Application (KITAPP). We presented a motivation for distributed implementations in this context, notably for computing percentiles for contextualization. We motivated privacy and performance issues and presented a novel system architecture as well as a distributed implementation to tackle them. Its evaluation in a realistic multi-site environment has shown that our approach reduces data sharing to a large extent, and thus enables imposing strong data privacy guarantees on distributed biomedical analyses.

9.1 Bilateral contracts with industry

Participants: Ronan-Alexandre Cherrueau, Marie Delavergne, Adrien Lebre, Karim Manaouil, Matthieu Simonin.

• Strengthen the Enos framework and the resulting EnosLib solution (see Section 6.4 and Section 6.5).
• Define an experimental protocol allowing the automatized and reproducible evaluation of resource management/orchestrations systems in a WANWide context.
• Develop a DSL to reify location aspects at the CLI level in order to create new resources (image, VM, etc.) through a set of OpenStack instances while guaranteeing a notion of master copy.

10.1 International initiatives

10.2 International research visitors

10.3 European initiatives

10.4 National initiatives

10.5 Regional initiatives

11.1 Promoting scientific activities

11.2 Teaching - Supervision - Juries

11.3 Popularization

12.1 Major publications

• 1 articleFarahF. Ait Salaht, FrédéricF. Desprez and AdrienA. Lebre. An overview of service placement problem in Fog and Edge ComputingACM Computing Surveys533June 2020, Article 65, 35 pages
  HALDOIback to text
• 2 inproceedings EmileE. Cadorel, HélèneH. Coullon and Jean-MarcJ.-M. Menaud. Online Multi-User Workflow Scheduling Algorithm for Fairness and Energy Optimization CCGrid2020 : 20th International Symposium on Cluster, Cloud and Internet Computing Melbourne, Australia November 2020
  HAL DOI back to text
• 3 inproceedings MaverickM. Chardet, HélèneH. Coullon and ChristianC. Pérez. Predictable Efficiency for Reconfiguration of Service-Oriented Systems with Concerto CCGrid 2020 : 20th IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing Melbourne, Australia IEEE May 2020
  HAL DOI back to text
• 4 inproceedingsDavidD. Sarmiento, AdrienA. Lebre, LucasL. Nussbaum and AbdelhadiA. Chari. Multi-site Connectivity for Edge Infrastructures DIMINET:DIstributed Module for Inter-site NETworkingCCGRID 2020 - 20th IEEE/ACM International Symposium on Cluster, Cloud and Internet ComputingIEEE and The University of MelbourneMelbourne, AustraliaMay 2020, 1-10
  HALback to text

12.2 Publications of the year

12.3 Cited publications

• 29 miscAkamai Cloudlets(Accessed: 2018-03-08)2018, URL: http://cloudlets.akamai.com
  back to text
• 30 miscAmazon Lambda@Edge(Accessed: 2018-03-08)2018, URL: https://aws.amazon.com/lambda/edge/
  back to text
• 31 articleC. Atkinson, T. Schulze and S. Klingert. Facilitating Greener IT through Green SpecificationsIEEE Software313May 2014, 56-63URL: http://dx.doi.org/10.1109/MS.2014.19
  DOIback to text
• 32 articleF. Baude, D. Caromel, Cé.C. Dalmasso, M. Danelutto, V. Getov, L. Henrio and C. Pérez. GCM: a grid extension to Fractal for autonomous distributed componentsannals of telecommunications641-22009, 5-24URL: http://dx.doi.org/10.1007/s12243-008-0068-8
  DOIback to textback to text
• 33 article FrançoiseF. Baude, LudovicL. Henrio and CristianC. Ruz. Programming distributed and adaptable autonomous components--the GCM/ProActive framework Software: Practice and Experience May 2014
  HAL back to text
• 34 inproceedings Mohammad-MahdiM.-M. Bazm, MarcM. Lacoste, MarioM. Südholt and Jean-MarcJ.-M. Menaud. Side-Channels Beyond the Cloud Edge : New Isolation Threats and Solutions IEEE International Conference on Cyber Security in Networking (CSNet) 2017 Rio de Janeiro, Brazil October 2017
  HAL back to text
• 35 articleGordonG. Blair, ThierryT. Coupaye and Jean-BernardJ.-B. Stefani. Component-based architecture: the Fractal initiativeAnnals of telecommunications641February 2009, 1--4URL: https://doi.org/10.1007/s12243-009-0086-1
  DOIback to text
• 36 inproceedingsPeterP. Bodik, ReanR. Griffith, CharlesC. Sutton, ArmandoA. Fox, Michael I.M. Jordan and David A.D. Patterson. Automatic Exploration of Datacenter Performance RegimesProceedings of the 1st Workshop on Automated Control for Datacenters and CloudsACDC '09New York, NY, USABarcelona, SpainACM2009, 1--6URL: http://doi.acm.org/10.1145/1555271.1555273
  DOIback to text
• 37 inproceedingsFlavioF. Bonomi, RodolfoR. Milito, JiangJ. Zhu and SateeshS. Addepalli. Fog computing and its role in the internet of thingsProceedings of the first edition of the MCC workshop on Mobile cloud computingACM2012, 13--16
  back to text
• 38 inproceedingsFatima-zahraF.-z. Boujdad and MarioM. Südholt. Constructive Privacy for Shared Genetic DataCLOSER 2018 - 8th International Conference on Cloud Computing and Services ScienceProceedings of CLOSER 2018Funchal, Madeira, PortugalMarch 2018, 1-8
  HALback to text
• 39 inproceedingsOliverO. Braċevac, SebastianS. Erdweg, GuidoG. Salvaneschi and MiraM. Mezini. CPL: A Core Language for Cloud Computing2016, 94--105URL: http://doi.acm.org/10.1145/2889443.2889452
  back to text
• 40 inproceedingsFranciscoF. Brasileiro, GiovanniG. Silva, FranciscoF. Araújo, MarcosM. Nóbrega, IgorI. Silva and GustavoG. Rocha. Fogbow: A Middleware for the Federation of IaaS CloudsThe 16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid)IEEE2016, 531--534
  back to text
• 41 inproceedingsHugoH. Bruneliere, ZakareaZ. Al-Shara, FredericoF. Alvares, JonathanJ. Lejeune and ThomasT. Ledoux. A Model-based Architecture for Autonomic and Heterogeneous Cloud SystemsCLOSER 2018 - 8h International Conference on Cloud Computing and Services Science1Best Paper AwardFunchal, PortugalMarch 2018, 201-212
  HALDOIback to text
• 42 inproceedingsEricE. Bruneton, ThierryT. Coupaye, MatthieuM. Leclercq, VivienV. Quema and Jean-BernardJ.-B. Stefani. An Open Component Model and Its Support in JavaComponent-Based Software EngineeringBerlin, HeidelbergSpringer Berlin Heidelberg2004, 7--22
  back to text
• 43 articleParisP. Carbone, AsteriosA. Katsifodimos, StephanS. Ewen, VolkerV. Markl, SeifS. Haridi and KostasK. Tzoumas. Apache Flink?: Stream and Batch Processing in a Single EngineIEEE Data Eng. Bull.382015, 28-38
  back to textback to text
• 44 inproceedingsValeriaV. Cardellini, Francesco LoF. Presti, MatteoM. Nardelli and Gabriele RussoG. Russo. Towards Hierarchical Autonomous Control for Elastic Data Stream Processing in the FogEuro-Par 2017: Parallel Processing Workshops: Euro-Par 2017 International Workshops, Santiago de Compostela, Spain, August 28-29, 2017, Revised Selected Papers10659Springer2018, 106-117
  back to text
• 45 inbookFeng-ChengF.-C. Chang, Hsiang-ChehH.-C. Huang and Hsueh-MingH.-M. Hang. Combined Encryption and Watermarking Approaches for Scalable Multimedia CodingAdvances in Multimedia Information Processing - PCM 2004: 5th Pacific Rim Conference on Multimedia, Tokyo, Japan, November 30 - December 3, 2004. Proceedings, Part IIIK. AizawaY. NakamuraS. SatohBerlin, HeidelbergSpringer Berlin Heidelberg2005, 356--363
  back to text
• 46 inproceedings Ronan-AlexandreR.-A. Cherrueau, RémiR. Douence and MarioM. Südholt. A Language for the Composition of Privacy-Enforcement Techniques IEEE RATSP 2015, The 2015 IEEE International Symposium on Recent Advances of Trust, Security and Privacy in Computing and Communications Helsinki, Finland August 2015
  HAL back to text
• 47 inproceedings Ronan-AlexandreR.-A. Cherrueau, AdrienA. Lebre, DimitriD. Pertin, FetahiF. Wuhib and JoãoJ. Soares. Edge Computing Resource Management System: a Critical Building Block! Initiating the debate via OpenStack The USENIX Workshop on Hot Topics in Edge Computing (HotEdge'18) july 2018
  back to text
• 48 inproceedingsH. E.H. Chihoub, S. Ibrahim, Y. Li, G. Antoniu, M. S.M. Perez and L. Bouge. Exploring Energy-Consistency Trade-Offs in Cassandra Cloud Storage System27th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)October 2015, 146-153
  back to text
• 49 inproceedings BastienB. Confais, AdrienA. Lebre and BenoîtB. Parrein. An Object Store Service for a Fog/Edge Computing Infrastructure based on IPFS and Scale-out NAS 1st IEEE International Conference on Fog and Edge Computing-ICFEC’2017 2017
  back to text
• 50 articleJames CJ. Corbett, JeffreyJ. Dean, MichaelM. Epstein, AndrewA. Fikes, ChristopherC. Frost, Jeffrey JohnJ. Furman, SanjayS. Ghemawat, AndreyA. Gubarev, ChristopherC. Heiser and PeterP. Hochschild. Spanner: Google’s globally distributed databaseACM Transactions on Computer Systems (TOCS)3132013, 8
  back to text
• 51 articleRoberto DiR. Cosmo, JacopoJ. Mauro, StefanoS. Zacchiroli and GianluigiG. Zavattaro. Aeolus: A component model for the cloudInformation and Computation239Supplement C2014, 100--121URL: http://www.sciencedirect.com/science/article/pii/S0890540114001424
  DOIback to text
• 52 articleHélèneH. Coullon, JulienJ. Bigot and ChristianC. Pérez. Extensibility and Composability of a Multi-Stencil Domain Specific FrameworkInternational Journal of Parallel ProgrammingNovember 2017, URL: https://doi.org/10.1007/s10766-017-0539-5
  DOIback to text
• 53 inproceedings HélèneH. Coullon, GuillaumeG. Le Louët and Jean-MarcJ.-M. Menaud. Virtual Machine Placement for Hybrid Cloud using Constraint Programming ICPADS 2017 2017
  back to text
• 54 inproceedings HélèneH. Coullon, DimitriD. Pertin and ChristianC. Pérez. Production Deployment Tools for IaaSes: an Overall Model and Survey IEEE International Conference on Future Internet of Things and Cloud (FiCloud) 2017 Prague, Czech Republic August 2017
  HAL back to text
• 55 inproceedings IsmaelI. Cuadrado-Cordero, Anne-CécileA.-C. Orgerie and Jean-MarcJ.-M. Menaud. Comparative Experimental Analysis of the Quality-of-Service and Energy-Efficiency of VMs and Containers' Consolidation for Cloud Applications SoftCOM: International Conference on Software, Telecommunications and Computer Networks 2017
  back to text
• 56 articlePierre-CharlesP.-C. David, ThomasT. Ledoux, MarcM. Léger and ThierryT. Coupaye. FPath and FScript: Language support for navigation and reliable reconfiguration of Fractal architecturesannals of telecommunications - annales des télécommunications641February 2009, 45--63URL: https://doi.org/10.1007/s12243-008-0073-y
  DOIback to text
• 57 inproceedingsFrederico AlvaresF. De Oliveira, ThomasT. Ledoux and RémiR. Sharrock. A framework for the coordination of multiple autonomic managers in cloud environmentsSelf-Adaptive and Self-Organizing Systems (SASO), 2013 IEEE 7th International Conference onIEEE2013, 179--188
  back to text
• 58 inproceedingsWesW. Felter, AlexandreA. Ferreira, RamR. Rajamony and JuanJ. Rubio. An updated performance comparison of virtual machines and linux containersPerformance Analysis of Systems and Software (ISPASS), 2015 IEEE International Symposium OnIEEE2015, 171--172
  back to text
• 59 inproceedingsAreskiA. Flissi, JérémyJ. Dubus, NicolasN. Dolet and PhilippeP. Merle. Deploying on the Grid with DeployWareEighth IEEE International Symposium on Cluster Computing and the GridFranceMay 2008, 177-184
  HALDOIback to text
• 60 miscThe OpenStackT. Foundation. Cloud Edge Computing: Beyond the Data Center (White Paper)(Accessed: 2020-02-08)January 2018, URL: https://www.openstack.org/assets/edge/OpenStack-EdgeWhitepaper-v3-online.pdf
  back to textback to text
• 61 miscThe OpenStackT. Foundation. Edge Computing: Next Steps in Architecture, Design and Testing)(Accessed: 2020-02-08)January 2020, URL: https://www.openstack.org/edge-computing/edge-computing-next-steps-in-architecture-design-and-testing
  back to textback to text
• 62 miscThe LinuxT. Foundation. Open Network Automation Platform(Accessed: 2018-03-08)2018, URL: https://www.onap.org/
  back to text
• 63 articlePedroP. Garcia Lopez, AlbertoA. Montresor, DickD. Epema, AnwitamanA. Datta, TeruoT. Higashino, AdrianaA. Iamnitchi, MarinhoM. Barcellos, PascalP. Felber and EtienneE. Riviere. Edge-centric Computing: Vision and ChallengesSIGCOMM Comput. Commun. Rev.455September 2015, 37--42URL: http://doi.acm.org/10.1145/2831347.2831354
  DOIback to text
• 64 articleÍñigoÍ. Goiri, WilliamW. Katsak, KienK. Le, Thu D.T. Nguyen and RicardoR. Bianchini. Parasol and GreenSwitch: Managing Datacenters Powered by Renewable EnergySIGARCH Comput. Archit. News411March 2013, 51--64
  back to text
• 65 inproceedingsÍñigoÍ. Goiri, KienK. Le, Thu D.T. Nguyen, JordiJ. Guitart, JordiJ. Torres and RicardoR. Bianchini. GreenHadoop: Leveraging Green Energy in Data-processing FrameworksProceedings of the 7th ACM European Conference on Computer SystemsEuroSys '12New York, NY, USABern, SwitzerlandACM2012, 57--70URL: http://doi.acm.org/10.1145/2168836.2168843
  DOIback to text
• 66 inproceedings HadiH. Goudarzi and MassoudM. Pedram. Geographical Load Balancing for Online Service Applications in Distributed Datacenters in IEEE international conference on cloud computing (CLOUD 2013 2013
  back to text
• 67 articleL. Gu, D. Zeng, A. Barnawi, S. Guo and I. Stojmenovic. Optimal Task Placement with QoS Constraints in Geo-Distributed Data Centers Using DVFSIEEE Transactions on Computers647July 2015, 2049-2059URL: http://dx.doi.org/10.1109/TC.2014.2349510
  DOIback to text
• 68 inproceedingsKiryongK. Ha, YoshihisaY. Abe, ThomasT. Eiszler, ZhuoZ. Chen, WenluW. Hu, BrandonB. Amos, RohitR. Upadhyaya, PadmanabhanP. Pillai and MahadevM. Satyanarayanan. You Can Teach Elephants to Dance: Agile VM Handoff for Edge ComputingProceedings of the Second ACM/IEEE Symposium on Edge ComputingSEC '17New York, NY, USASan Jose, CaliforniaACM2017, URL: http://doi.acm.org/10.1145/3132211.3134453
  DOIback to text
• 69 articleB. Han, V. Gopalakrishnan, L. Ji and S. Lee. Network function virtualization: Challenges and opportunities for innovationsIEEE Communications Magazine532February 2015, 90-97URL: http://dx.doi.org/10.1109/MCOM.2015.7045396
  DOIback to text
• 70 articleM. S.M. Hasan, F. Alvares, T. Ledoux and J. L.J. Pazat. Investigating Energy Consumption and Performance Trade-Off for Interactive Cloud ApplicationIEEE Transactions on Sustainable Computing22April 2017, 113-126URL: http://dx.doi.org/10.1109/TSUSC.2017.2714959
  DOIback to textback to text
• 71 articleFabienF. Hermenier, JuliaJ. Lawall and GillesG. Muller. Btrplace: A flexible consolidation manager for highly available applicationsIEEE Transactions on dependable and Secure Computing1052013, 273--286
  back to text
• 72 inproceedingsFabienF. Hermenier, AdrienA. Lebre and Jean-MarcJ.-M. Menaud. Cluster-wide Context Switch of Virtualized JobsProceedings of the Virtualization Technologies in Distributed Computing Workshop (co-locaed with ACM HPDC'10)HPDC '10New York, NY, USAChicago, IllinoisACM2010, 658--666URL: http://doi.acm.org/10.1145/1851476.1851574
  DOIback to text
• 73 inproceedingsFabienF. Hermenier, XavierX. Lorca, Jean-MarcJ.-M. Menaud, GillesG. Muller and JuliaJ. Lawall. Entropy: a consolidation manager for clustersProceedings of the 2009 ACM SIGPLAN/SIGOPS international conference on Virtual execution environmentsACM2009, 41--50
  back to textback to text
• 74 articleMartinM. Hirzel, ScottS. Schneider and BugraB. Gedik. SPL: An Extensible Language for Distributed Stream Processingtoplas391March 2017, URL: http://doi.acm.org/10.1145/3039207
  back to textback to text
• 75 inproceedingsS. Ibrahim, B. He and H. Jin. Towards Pay-As-You-Consume Cloud Computing2011 IEEE International Conference on Services ComputingJuly 2011, 370-377URL: http://dx.doi.org/10.1109/SCC.2011.38
  DOIback to text
• 76 articleSamanS. Iftikhar, SharifullahS. Khan, ZahidZ. Anwar and Others. GenInfoGuard: A Robust and Distortion-Free Watermarking Technique for Genetic DataPLOS ONE102February 2015, 1-22URL: https://doi.org/10.1371/journal.pone.0117717
  DOIback to text
• 77 articleBrendanB. Jennings and RolfR. Stadler. Resource Management in Clouds: Survey and Research ChallengesJournal of Network and Systems Management233July 2015, 567--619URL: https://doi.org/10.1007/s10922-014-9307-7
  DOIback to text
• 78 inproceedingsE. Jonardi, M. A.M. Oxley, S. Pasricha, A. A.A. Maciejewski and H. J.H. Siegel. Energy cost optimization for geographically distributed heterogeneous data centers2015 Sixth International Green and Sustainable Computing Conference (IGSC)December 2015, 1-6URL: http://dx.doi.org/10.1109/IGCC.2015.7393677
  DOIback to text
• 79 book HoldenH. Karau, AndyA. Konwinski, PatrickP. Wendell and MateiM. Zaharia. Learning Spark O'Reilly Media February 2015
  back to text
• 80 articleJ. Kramer and J. Magee. The evolving philosophers problem: dynamic change managementIEEE Transactions on Software Engineering1611November 1990, 1293-1306URL: http://dx.doi.org/10.1109/32.60317
  DOIback to text
• 81 inproceedingsA. Lebre, J. Pastor, A. Simonet and F. Desprez. Revising OpenStack to Operate Fog/Edge Computing InfrastructuresThe IEEE International Conference on Cloud Engineering (IC2E)April 2017, 138-148URL: http://dx.doi.org/10.1109/IC2E.2017.35
  DOIback to text
• 82 inproceedingsGrzegorzG. Malewicz, Matthew H.M. Austern, Aart J.CA. Bik, James C.J. Dehnert, IlanI. Horn, NatyN. Leiser and GrzegorzG. Czajkowski. Pregel: A System for Large-scale Graph ProcessingProceedings of the 2010 ACM SIGMOD International Conference on Management of DataSIGMOD '10New York, NY, USAIndianapolis, Indiana, USAACM2010, 135--146URL: http://doi.acm.org/10.1145/1807167.1807184
  back to text
• 83 inproceedingsThuy LinhT. Nguyen and AdrienA. Lebre. Virtual Machine Boot Time ModelParallel, Distributed and Network-based Processing (PDP), 2017 25th Euromicro International Conference onIEEE2017, 430--437
  back to textback to text
• 84 inproceedingsKeisukeK. Okamura and YoshihiroY. Oyama. Load-based covert channels between Xen virtual machinesProceedings of the 2010 ACM Symposium on Applied ComputingACM2010, 173--180
  back to text
• 85 inproceedingsPeymanP. Oreizy, NenadN. Medvidovic and Richard N.R. Taylor. Runtime Software Adaptation: Framework, Approaches, and StylesCompanion of the 30th International Conference on Software EngineeringICSE Companion '08New York, NY, USALeipzig, GermanyACM2008, 899--910URL: http://doi.acm.org/10.1145/1370175.1370181
  DOIback to text
• 86 inproceedingsT. D.T. Phan, S. Ibrahim, G. Antoniu and L. Bouge. On Understanding the Energy Impact of Speculative Execution in Hadoop2015 IEEE International Conference on Data Science and Data Intensive SystemsDecember 2015, 396-403
  back to text
• 87 articleFlavienF. Quesnel, AdrienA. Lebre and MarioM. Südholt. Cooperative and reactive scheduling in large-scale virtualized platforms with DVMSConcurrency and Computation: Practice and Experience25122013, 1643--1655
  back to text
• 88 articleD. Sabella, A. Vaillant, P. Kuure, U. Rauschenbach and F. Giust. Mobile-Edge Computing Architecture: The role of MEC in the Internet of ThingsIEEE Consumer Electronics Magazine54October 2016, 84-91URL: http://dx.doi.org/10.1109/MCE.2016.2590118
  DOIback to textback to text
• 89 articleDamianD. Serrano, SaraS. Bouchenak, YousriY. Kouki, Frederico AlvaresF. de Oliveira Jr., ThomasT. Ledoux, JonathanJ. Lejeune, JulienJ. Sopena, LucianaL. Arantes and PierreP. Sens. SLA guarantees for cloud servicesFuture Generation Computer Systems54Supplement C2016, 233--246URL: http://www.sciencedirect.com/science/article/pii/S0167739X15000801
  DOIback to text
• 90 articleQ. Shen, X. Liang, X. S.X. Shen, X. Lin and H. Y.H. Luo. Exploiting Geo-Distributed Clouds for a E-Health Monitoring System With Minimum Service Delay and Privacy PreservationIEEE Journal of Biomedical and Health Informatics182March 2014, 430-439URL: http://dx.doi.org/10.1109/JBHI.2013.2292829
  DOIback to text
• 91 articleW. Shi and T. F.T. Wenisch. Energy-Efficient Data CentersIEEE Internet Computing2142017, 6-7URL: http://dx.doi.org/10.1109/MIC.2017.2911429
  DOIback to text
• 92 inproceedingsJean-BernardJ.-B. Stefani. Components as Location GraphsFormal Aspects of Component Software - 11th International Symposium, FACS 2014, Bertinoro, Italy, September 10-12, 2014, Revised Selected Papers2014, 3--23URL: https://doi.org/10.1007/978-3-319-15317-9_1
  back to text
• 93 book ClemensC. Szyperski. Component Software: Beyond Object-Oriented Programming Boston, MA, USA Addison-Wesley Longman Publishing Co., Inc. 2002
  back to text back to text
• 94 inproceedingsY. Taleb, S. Ibrahim, G. Antoniu and T. Cortes. Characterizing Performance and Energy-Efficiency of the RAMCloud Storage System2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS)June 2017, 1488-1498URL: http://dx.doi.org/10.1109/ICDCS.2017.51
  DOIback to textback to text
• 95 inproceedingsAshishA. Thusoo, ZhengZ. Shao, SureshS. Anthony, DhrubaD. Borthakur, NamitN. Jain, JoydeepJ. Sen Sarma, RaghothamR. Murthy and HaoH. Liu. Data Warehousing and Analytics Infrastructure at FacebookProceedings of the 2010 ACM SIGMOD International Conference on Management of DataSIGMOD '10Indianapolis, Indiana, USAACM Press2010, 1013--1020URL: http://doi.acm.org/10.1145/1807167.1807278
  back to text
• 96 book TomT. White. Hadoop: The Definitive Guide O'Reilly Media April 2015
  back to text
• 97 inproceedingsA. Wierman, Z. Liu, I. Liu and H. Mohsenian-Rad. Opportunities and challenges for data center demand responseInternational Green Computing ConferenceNovember 2014, 1-10URL: http://dx.doi.org/10.1109/IGCC.2014.7039172
  DOIback to text
• 98 inproceedingsJidongJ. Xiao, ZhangZ. Xu, HaiH. Huang and HainingH. Wang. Security implications of memory deduplication in a virtualized environment2013 43rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)IEEE2013, 1--12
  back to text
• 99 articleFeiF. Xu, FangmingF. Liu, HaiH. Jin and Athanasios VA. Vasilakos. Managing performance overhead of virtual machines in cloud computing: A survey, state of the art, and future directionsProceedings of the IEEE10212014, 11--31
  back to textback to textback to text
• 100 inproceedingsO. Yildiz, M. Dorier, S. Ibrahim, R. Ross and G. Antoniu. On the Root Causes of Cross-Application I/O Interference in HPC Storage Systems2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS)May 2016, 750-759URL: http://dx.doi.org/10.1109/IPDPS.2016.50
  DOIback to text
• 101 inproceedingsO. Yildiz, A. C.A. Zhou and S. Ibrahim. Eley: On the Effectiveness of Burst Buffers for Big Data Processing in HPC Systems2017 IEEE International Conference on Cluster Computing (CLUSTER)September 2017, 87-91URL: http://dx.doi.org/10.1109/CLUSTER.2017.73
  DOIback to text
• 102 inproceedingsMateiM. Zaharia, TathagataT. Das, HaoyuanH. Li, TimothyT. Hunter, ScottS. Shenker and IonI. Stoica. Discretized Streams: Fault-tolerant Streaming Computation at ScaleProceedings of the Twenty-Fourth ACM Symposium on Operating Systems PrinciplesSOSP '13New York, NY, USAFarminton, PennsylvaniaACM2013, 423--438URL: http://doi.acm.org/10.1145/2517349.2522737
  DOIback to text