Section: New Results

Greening Clouds

Participants : Maria Del Mar Callau Zori, Ismael Cuadrado Cordero, David Guyon, Sabbir Hasan Rochi, Yunbo Li, Christine Morin, Anne-Cécile Orgerie, Jean-Louis Pazat, Guillaume Pierre.

Energy-aware IaaS-PaaS co-design

Participants : Maria Del Mar Callau Zori, Anne-Cécile Orgerie, Guillaume Pierre.

The wide adoption of the cloud computing paradigm plays a crucial role in the ever-increasing demand for energy-efficient data centers. Driven by this requirement, cloud providers resort to a variety of techniques to improve energy usage at each level of the cloud computing stack. However, prior studies mostly consider resource-level energy optimizations in IaaS clouds, overlooking the workload-related information locked at higher levels, such as PaaS clouds. We conducted an extensive experimental evaluation of the effect of a range of Cloud infrastructure operations (start, stop, migrate VMs) on their computing throughput and energy consumption, and derived a model to help drive cloud reconfiguration operations according to performance/energy requirements. A publication on this topic is in preparation.

Energy-efficient cloud elasticity for data-driven applications

Participants : David Guyon, Anne-Cécile Orgerie, Christine Morin.

Distributed and parallel systems offer to users tremendous computing capacities. They rely on distributed computing resources linked by networks. They require algorithms and protocols to manage these resources in a transparent way for users. Recently, the maturity of virtualization techniques has allowed for the emergence of virtualized infrastructures (Clouds). These infrastructures provide resources to users dynamically, and adapted to their needs. By benefiting from economies of scale, Clouds can efficiently manage and offer virtually unlimited numbers of resources, reducing the costs for users.

However, the rapid growth for Cloud demands leads to a preoccupying and uncontrolled increase of their electric consumption. In this context, we will focus on data driven applications which require to process large amounts of data. These applications have elastic needs in terms of computing resources as their workload varies over time. While reducing energy consumption and improving performance are orthogonal goals, this internship aims at studying possible trade-offs for energy-efficient data processing without performance impact. As elasticity comes at a cost of reconfigurations, these trade-offs will consider the time and energy required by the infrastructure to dynamically adapt the resources to the application needs.

The master internship work of David Guyon on this topic has been presented at IEEE GreenCom 2015 [39] . This work will be continued during David's PhD thesis.

Energy-efficient and network-aware resource allocation in Cloud infrastructures

Participants : Ismael Cuadrado Cordero, Christine Morin, Anne-Cécile Orgerie.

Energy consumption is cloud computing has become a key environmental and economic concern. Our work aims at designing energy-efficient resource allocation for Cloud infrastructures. The ever-growing appetite of new applications for network resources leads to an unprecedented electricity bill, and for these bandwidth-hungry applications, networks can become a significant bottleneck. New algorithms have to be designed integrating the data locality dimension to optimize computing resource allocation while taking into account the fluctuating limits of network resources. Towards this end, we proposed GRaNADA, a semi-decentralized Platform-as-a-service (PaaS) architecture for real-time multiple-users applications. Our architecture geographically distributes the computation among the clients of the cloud, moving the computation away from the datacenter to save energy - by shutting down or downgrading non utilized resources such as routers and switches, servers, etc. - and provides lower latencies for users. GRaNADA implements the concept of micro-cloud, a fully autonomous energy-efficient subnetwork of clients of the same service, designed to keep the greenest path between its nodes. Along with GRaNADA, we proposed DEEPACC, a cloud-aware routing protocol which distributes the connection between the nodes. Our system GRaNADA targets services where the geographical distribution of clients working on the same data is limited - for example, a shared on-line document - or those services where, even if the geographical distribution of clients is high, the upload data communication to the cloud is small - for instance a light social network like Twitter. We compared our approach with two main existing solutions - replication of data in the edge and traditional centralized cloud computing. Our approach based on micro-clouds exhibits interesting properties in terms of QoS and especially latency. Simulations show that, using the proposed PaaS, one can save up to 75% of the spent network energy compared to traditional centralized cloud computing approaches. Our approach is also more energy-efficient than the most popular semi-decentralized solutions, like nano data centers. This work has been presented at IEEE GreenCom 2015 [18] .

We also evaluated the suitability of using micro-clouds in the context of smart cities. We investigated the idea to build a local cloud on top of networking resources spread across a defined area and including the mobile devices of the users. This local cloud is managed by lightweight mechanisms in order to handle users who can appear/disappear and move. We used a scenario considering a platform for neighborhood services and showed that micro-clouds make better use of the network, reducing the amount of unnecessary data traveling through external networks. This work is currently under review for a conference.

Resource allocation in a Cloud partially powered by renewable energy sources

Participants : Yunbo Li, Anne-Cécile Orgerie.

We propose here to design a disruptive approach to Cloud resource management which takes advantage of renewable energy availability to perform opportunistic tasks. To begin with, the considered Cloud is mono-site (i.e. all resources are in the same physical location) and performs tasks (like web hosting or MapReduce tasks) running in virtual machines. This Cloud receives a fixed amount of power from the regular electric Grid. This power allows it to run usual tasks. In addition, this Cloud is also connected to renewable energy sources (such as windmills or solar cells) and when these sources produce electricity, the Cloud can use it to run more tasks.

The proposed resource management system needs to integrate a prediction model to be able to forecast these extra-power periods of time in order to schedule more work during these periods. Batteries will be used to guarantee that enough energy is available when switching on a new server working exclusively on renewable energy. Given a reliable prediction model, it is possible to design a scheduling algorithm that aims at optimizing resource utilization and energy usage, problem known to be NP-hard. The proposed heuristics will thus schedule tasks spatially (on the appropriate servers) and temporally (over time, with tasks that can be planed in the future).

This work is done in collaboration with Ascola team from LINA in Nantes. Two publications have been accepted this year on this topic for: SmartGreens 2015 [15] and IEEE GreenCom 2015 [21] .

SLA driven Cloud Auto-scaling for optimizing energy footprint

Participants : Sabbir Hasan Rochi, Jean-Louis Pazat.

As a direct consequence of the increasing popularity of Internet and Cloud Computing services, data centers are amazingly growing and hence have to urgently face energy consumption issues. At the Infrastructure-as-a-Service (IaaS) layer, Cloud Computing allows to dynamically adjust the provision of physical resources according to Platform-as-a-Service (PaaS) needs while optimizing energy efficiency of the data center.

The management of elastic resources in Clouds according to fluctuating workloads in the Software-as-a-Service (SaaS) applications and different Quality-of-Service (QoS) end-user’s expectations is a complex issue and cannot be done dynamically by a human intervention. We advocate the adoption of Autonomic Computing (AC) at each XaaS layer for responsiveness and autonomy in front of environment changes. At the SaaS layer, AC enables applications to react to a highly variable workload by dynamically adjusting the amount of resources in order to keep the QoS for the end users. Similarly, at the IaaS layer, AC enables the infrastructure to react to context changes by optimizing the allocation of resources and thereby reduce the costs related to energy consumption. However, problems may occur since those self-managed systems are related in some way (e.g. applications depend on services provided by a cloud infrastructure): decisions taken in isolation at given layer may interfere with other layers, leading whole system to undesired states.

We have defined a scheme for green energy management in the presence of explicit and implicit integration of renewable energy in datacenter [13] . More specifically we propose three contributions: i) we introduce the concept of virtualization of green energy to address the uncertainty of green energy availability, ii) we extend the Cloud Service Level Agreement (CSLA) language to support Green SLA introducing two new threshold parameters and iii) we introduce greenSLA algorithm which leverages the concept of virtualization of green energy to provide per interval specific Green SLA. Experiments were conducted with real workload profile from PlanetLab and server power model from SPECpower to demonstrate that, Green SLA can be successfully established and satisfied without incurring higher cost.

This work is done in collaboration with Ascola team from LINA in Nantes.