Section: New Results
Performance analysis and networks protocols
Participants : Mohammed Amer, Thomas Begin, Anthony Busson, Éric Fleury, Paulo Gonçalves Andrade, Yannick Léo, Isabelle Guérin Lassous, Philippe Nain, Huu Nghi Nguyen, Laurent Reynaud.
Use of large scale CDR for protocol performance evaluation and modelling
In [11] we use large scale CDR (Call Data Records) coming from a nationwide cellular telecommunication operator during a two month period to validate several DTN approaches for conveying SMS traffic in dense urban areas taking benefits of the density of users and the mobility of the users. We study a mobile dataset including 8 Million users living in large urban area. This gives us a precise estimation of the average transmission time and the global performance of our approach. Our analysis shows that after 30 min, half of the SMS are delivered successfully to destination. In [10], we study the temporal activity of a user and the user movements. At the user scale, the usage is not only defined by the amount of calls but also by the userâs mobility. At a higher level, the base stations have a key role on the quality of service. From a very large Call Detail Records (CDR) we first study call duration and inter-arrival time parameters. Then, we assess user movements between consecutive calls (switching from a station to another one). Our study suggests that user mobility is pretty dependent on user activity. Furthermore, we show properties of the inter-call mobility by making an analysis of the call distribution.
End-to-end delay
Because of the growing complexity of computer networks, a new paradigm has been introduced to ease their design and management, namely, the SDN (Software-defined Networking). In particular, SDN defines a new entity, the controller that is in charge of controlling the devices belonging to the data plane In order to let the controller take its decisions, it must have a global view on the network. This includes the topology of the network and its links capacity, along with other possible performance metrics such delays, loss rates, and available bandwidths. This knowledge can enable a multi-class routing, or help guarantee levels of Quality of Service. In [33], [20], [42], we proposed new algorithms that allow a centralised entity, such as the controller in an SDN network, to accurately estimate the end-to-end delay for a given flow in its network. The proposed methods are passive in the sense that they do not require any additional traffic to be run. Through extensive simulations, we show that these methods are able to accurately estimate the expectation and the standard deviation of end-to-end delays.
In [14] we investigated the traversal time of a file across N communication links subject to stochastic changes in the sending rate of each link. Each link's sending rate is modelled by a finite-state Markov process. Two cases, one where links evolve independently of one another (N mutually independent Markov processes), and the second where their behaviours are dependent (these N Markov processes are not mutually independent) were considered. A particular instance where the above is
Circumventing the complexity of multi-server queues
Many real-life systems can be viewed as instances of multi-server queues. However, when the number of servers is high (say more than 16) and the arrival or/and service process exhibit high variability, current state-of-the-art solutions often become intractable due to the combinatorial growth of the underlying state space of the Markov chain. We proposed two efficient, fast and easy-to-implement approximate solutions to deal with G/G/c-like queues in [4], [2]. Our solutions rely the use of an original, though incomplete, state description that heavily breaks the complexity of multi-server queues. We have extensively validated our approximations against discrete-event simulation for several QoS performance metrics such as mean sojourn time and blocking probability with excellent results.
Wi-Fi networks optimization
Densification of Wi-Fi networks has led to the possibility for a station to choose between several access points (APs). On the other hand, the densification of APs generates interference, contention and decreases the global throughput as APs have to share a limited number of channels. Optimizing the association step between APs and stations can alleviate this problem and increase the overall throughput and fairness between stations. We proposed original solutions [23], [22] to this optimization problem based on two contributions. First, we modeled the association optimization problem assuming a realistic share of the medium between APs and stations and among APs when using the 802.11 DCF (Distributed Coordination Function) mode. Then, we introduced a local search algorithm to solve this problem through a suitable neighborhood structure. We show that the classical approaches in the literature, based on a time based fairness scheme, is less efficient than our solution when the number of orthogonal channels is limited. Also, we show through a large set of simulations and scenarios that our models are able to capture the real throughputs of Wi-Fi networks.
Controlled mobility in wireless networks
In this work, we have investigated the application of an adapted controlled mobility strategy on self-propelling nodes, which could efficiently provide network resource to users scattered on a designated area. In [7], we describe an adapted controlled mobility strategy and detail the design of our Virtual Force Protocol (VFP) which allows a swarm of vehicles to track and follow hornets to their nests, while maintaining connectivity through a wireless multi-hop communication route with a remote ground station used to store applicative data such as hornet trajectory and vehicle telemetry. In [43], we design a physics-based controlled mobility strategy, which we name the extended Virtual Force Protocol (VFPe), allowing self-propelled nodes, and in particular here unmanned aerial vehicles, to fly autonomously and cooperatively. In this way, ground devices scattered on the operation site may establish communications through the wireless multi-hop communication routes formed by the network of aerial nodes. In [28], we design a virtual force-based controlled mobility scheme, named VFPc, and evaluate its ability to be jointly used with a dual packet-forwarding and epidemic routing protocol. In particular, we study the possibility for end-users to achieve synchronous communications at given times of the considered scenarios.