Laboratoire d’analyse et d’architecture des systèmes
S.REKIK, N.BACCOUR, M.JMAIEL, K.DRIRA, L.GRIECO
ReDCAD Laboratory, SARA, Politecnico Bari
Revue Scientifique : Computer Communications, Vol.135, pp.201-212, Avril 2018 , N° 18052
Wireless Sensor Networks (WSNs) have been recognized as a promising communication technology for smart grid monitoring and control applications. However, the deployment of WSNs in smart grid brought new challenges that pertain to the harsh electrical grid nature, and the different and often contradicting communication requirements of smart grid monitoring applications. MAC protocols play a crucial role to meet the reliability and latency requirements of WSN-based smart grid communications. In particular, the IEEE 802.15.4 TSCH (Time Slotted Channel Hopping), the latest generation of low-power and highly reliable MAC protocols, orchestrates the medium access according to a time-frequency communication schedule. However, TSCH specification does not provide any practical solution for the establishment of the schedule. Orchestra is a recent scheduling solution for TSCH that brings significant advantages such as, the use of simple scheduling rules, the low signaling overhead, and the high delivery ratio. Despite its unique features, Orchestra has the limitation of computing the TSCH schedule at each node independently from its traffic load, which can drastically affect the communication delay. This limitation makes Orchestra not sufficiently convenient for several delay-sensitive smart grid applications. Further, the current TSCH specification does not support traffic differentiation (i.e. handle all packets equally regardless of their criticality levels). In this paper, we propose an enhanced Orchestra-based TSCH protocol, called e-TSCH-Orch, that dynamically adjusts time slots assignment according to traffic load and criticality level. The performance analysis of e-TSCH-Orch shows that it significantly reduces the communication delay compared to the original Orchestra-based TSCH, while preserving the low signaling overhead and the high packet delivery ratio.
N.SEYDOUX, K.DRIRA, N.HERNANDEZ, T.MONTEIL
Rapport LAAS N°18086, Avril 2018, 6p.
The emergence of the IoT and the Semantic Web of Things is leading to intensive cloud processing executing reasoning rules over large volumes of enriched data. However, the role of the cloud in existing approaches as a central point for both data processing and provisioning reduces scalability and introduces latency. This paper sketches a new approach for rule-based reasoning, enabling distributed rule evaluation on edge nodes and reducing the latency for IoT applications while avoiding the total dependence on a central node. This approach is evaluated in a simulated smart building.
K.DRIRA, F.OQUENDO, A.LEGAY, T.BATISTA
SARA, Univ Bretagne Sud, INRIA Rennes, UFRN, Brésil
Manifestation avec acte : Annual ACM Symposium on Applied Computing ( ACM-SAC ) 2018 du 09 avril au 13 avril 2018, Pau (France), Avril 2018, 3p. , N° 17591
Pervasiveness of networks has made possible to interconnect systems that were independently developed, operated, managed, and evolved, yielding a new kind of complex system, i.e. a system that is itself composed of systems, the so-called System-of-Systems (SoS). Software-intensive SoS (SiSoS) has become a hotspot in the last years, from both the research and industry viewpoints. Indeed, various aspects of our lives and livelihoods have progressively become dependent on some sort of Software-intensive SoS. This is the case of SiSoS found in different areas as diverse as energy, healthcare, manufacturing, and transportation; and applications that address societal needs, e.g. environmental monitoring, distributed energy grids, emergency coordination, global traffic control, and smart cities. Moreover, ubiquitous platforms such as the Internet of Things and nascent kinds of SoS such as Cyber-Physical SoSs are accelerating the deployment of Software-intensive SoS in the near future. Definitely, the unique characteristics of Software-intensive SoS raise a grand research challenge for the future of software-reliant systems in our industry and society due to its intrinsic features, among which evolutionary development and emergent behavior. Statistics The SiSoS Track received 22 regular paper submissions and 3 SRC submissions. Each submission was reviewed by three members of the Track Program Committee. The Track Program Committee selected 5 full papers out of the 22, giving an acceptance rate of 23%. These papers were selected based on originality, quality, soundness, and relevance to this conference track. Moreover, 2 poster papers have been accepted for publications in the proceedings of the conference. Key Topics This track fosters (but is not limited to) submissions in the following topics:
U.AYESTA, T.BODAS, I.M.VERLOOP
Rapport LAAS N°18047, Mars 2018, 21p.
In this paper, we present a unifying analysis for redundancy systems with cancel-on-start (c.o.s.) and cancel-on-complete (c.o.c.) with exponentially distributed service requirements. With c.o.s. (c.o.c.) all redundant copies are removed as soon as one of the copies starts (completes) service. As a consequence, c.o.s. does not waste any computing resources, as opposed to c.o.c.. We show that the c.o.s. model is equivalent to a queue-ing system with multi-type jobs and servers, which was analyzed in , and show that c.o.c. (under the assumption of i.i.d. copies) can be analyzed by a generalization of  where state-dependent departure rates are permitted. This allows us to show that the stationary distribution for both the c.o.c. and c.o.s. models have a product form. We give a detailed first-time analysis for c.o.s and derive a closed form expression for important metrics like mean number of jobs in the system, and probability of waiting. Comparing the performance of c.o.s. with that of c.o.c. gives the unexpected result (since c.o.s. does not waste any resources), that c.o.s. is worse in terms of mean number of jobs. The latter illustrates that the i.i.d. assumption (together with exponentially distributed requirements) might lead to conclusions that are qualitatively different from that observed in practice. We also show that the c.o.s. model is equivalent to Join-Shortest-Work queue with redundancy (JSW(d)). In the latter, an incoming job is dispatched to the server with smallest workload among d randomly chosen ones. Thus, all our results apply mutatis-mutandis to JSW(d).
T.SEREGINA, O.BRUN, B.PRABHU
Rapport LAAS N°18037, Mars 2018, 17p.
The technology of Delay Tolerant Networks (DTN) has been designed to support communication in environments where connectivity is intermittent and communication delays can be very long. We focus on game-theoretic model for DTNs. We consider the model where the source proposes a fixed reward to persuade selfish mobile nodes to participate in relaying messages. The mobile relays can decide to accept or not the packet and then to drop the packet in the future. This game can be modelled as a partially-observable stochastic game. For two relays, we have shown that the optimal policies for the relays relates to the threshold type.
Rapport LAAS N°18039, Mars 2018, 25p.
This paper studies optimal control subject to changing conditions. This is an area that recently received a lot of attention as it arises in numerous situations in practice. Some applications being cloud computing systems where the arrival rates of new jobs fluctuate over time, or the time-varying capacity as encountered in power-aware systems or wireless downlink channels. To study this, we focus on a restless bandit model, which has proved to be a powerful stochastic optimization framework to model scheduling of activities. In particular, it has been extensively applied in the context of optimal control of computing systems. This paper is a first step to its optimal control when restless bandits are subject to changing conditions, the latter being modeled by Markov-modulated environments. We consider the restless bandit problem in an asymptotic regime, which is obtained by letting the population of bandits grow large, and letting the environment change relatively fast. We present sufficient conditions for a policy to be asymptotically optimal and show that a set of priority policies satisfies these. Under an indexability assumption, an averaged version of Whittle's index policy is proved to be inside this set of asymptotic optimal policies. The performance of the averaged Whittle's index policy is numerically evaluated for a multi-class scheduling problem in a wireless downlink subject to changing conditions. While keeping the number of bandits constant, we observe that the average Whittle index policy becomes close to optimal as the speed of the modulated environment increases.
S.TOUFGA, P.OWEZARSKI, S.ABDELLATIF, T.VILLEMUR
Manifestation avec acte : Embedded Real Time Software and Systems ( ERTS² ) 2018 du 31 janvier au 02 février 2018, Toulouse (France), Février 2018, 8p. , N° 17464
Vehicular networks are one of the cornerstone of an Intelligent Transportation System (ITS). They are expected to provide ubiquitous network connectivity to moving vehicles while supporting various ITS services, some with very stringent requirements in terms of latency and reliability. Two vehicular networking technologies are envisioned to jointly support the full range of ITS services : DSRC (Dedicated Short Range Communication) for direct vehicle to vehicle/Road Side Units (RSU) communications and cellular technologies. To the best of our knowledge, approaches from the literature usually divide ITS services on each of these networks according to their requirements and one single network is in charge of supporting the each service. Those that consider both network technologies to offer multi-path routing, load balancing or path splitting for a better quality of experience of ITS services assume obviously separately controlled networks. Under the umbrella of SDN (Software Defined Networking), we propose in this paper a hybrid network architecture that enables the joint control of the networks providing connectivity to multi-homed vehicles and, also, explore the opportunities brought by such an architecture. We show through some use cases, that in addition to the flexibility and fine-grained programmability brought by SDN, it opens the way towards the development of effective network control algorithms that are the key towards the successful support of ITS services and especially those with stringent QoS. We also show how these algorithms could also benefit from information related to the environment or context in which vehicles evolve (traffic density, planned trajectory, ..), which could be easily collected by data providers and made available via the cloud.
M.MEDDEB, A.DHRAIEF, A.BELGHITH, T.MONTEIL, K.DRIRA, S.ALAHMADI
SARA, HANA Research Group, King Saud University
Revue Scientifique : The Computer Journal, Janvier 2018, https://doi.org/10.1093/comjnl/bxy005 , N° 18011
The Information-Centric Networking (ICN) paradigm is shaping the foreseen future Internet architecture by focusing on the data itself rather than its hosting location. It is a shift from a host-centric communication model to a content-centric model supporting among others unique and location-independent content names, in-network caching and name-based routing. By leveraging the easy data access, and reducing both the retrieval delay and the load on the data producer, the ICN can be a viable framework to support the Internet of Things (IoT), interconnecting billions of heterogeneous constrained objects. Among several ICN architectures, the Named Data Networking (NDN) is considered as a suitable ICN architecture for IoT systems. However, its default caching approach lacks a data freshness mechanism, while IoT data are transient and frequently updated by the producer which imposes stringent requirements in terms of information freshness. Furthermore, IoT devices are usually resource-constrained with harsh limitations on energy, memory and processing power. We propose in this paper a caching strategy and a novel cache freshness mechanism to monitor the validity of cached contents in an IoT environment while minimizing the caching process cost. We compared our solution to several relevant schemes using the ccnSim simulator. Our solution exhibits the best system performances in terms of hop reduction ratio, server hit reduction ratio and response latency, yet it provides the lowest cache cost and significantly improves the content validity.
I.MAHJRI, S.MEDJIAH, A.DHRAIEF, K.DRIRA, A.BELGHITH
SARA, HANA Research Group
Revue Scientifique : Internet Technology Letters, Vol.1, N°1, e12p., Janvier 2018 , N° 17388
Localization of wireless devices is a crucial requirement for many emerging applications such as environmental monitoring, intelligent transportation, home automation, health-care monitoring and social networking. In this letter, we propose AWL a new Aggregate Weighted Localization algorithm for mobile wireless networks. The proposed algorithm is distributed and requires low computational and communication overheads enabling its use in resource-limited devices.
G.BOETTGER, R.LAPEYRADE, E.FERNANDES, T.N.DENG, R.CLAUBERG, P.OWEZARSKI, G.ANTICHI, M.GUSAT, I.CASTRO
Univ Quenn Mary, Londres, SARA, IBM Zurich, CAMBRIDGE, DE-CIX
Rapport de Contrat : ENDEAVOUR. H2020-ICT-2014-1 Project N° 644960, Décembre 2017, 20p. , N° 17493