Fabrice Saffre

A survey of autonomic communications

Autonomic communications seek to improve the ability of network and services to cope with unpredicted change, including changes in topology, load, task, the physical and logical characteristics of the networks that can be accessed, and so forth. Broad-ranging autonomic solutions require designers to account for a range of end-to-end issues affecting programming models, network and contextual modeling and reasoning, decentralised algorithms, trust acquisition and maintenance---issues whose solutions may draw on approaches and results from a surprisingly broad range of disciplines. We survey the current state of autonomic communications research and identify significant emerging trends and techniques.

Aggregation Dynamics in Overlay Networks and Their Implications for Self-Organized Distributed Applications

In this paper, we investigate the global self-aggregation dynamics arising from local decision-based rewiring of an overlay network, used as an abstraction for an autonomic service-oriented architecture. We measure the ability of a selected set of local rules to foster self-organization of what is originally a random graph into a structured network. Scalability issues with respect to the key parameters of system size and diversity are extensively discussed. Conflicting goals are introduced, in the form of a population of nodes actively seeking to acquire neighbours of a type different from their own, resulting in decreased local homogeneity. We show that a ‘secondary’ self-organization process ensues, whereby nodes spontaneously cluster according to their implicit objective. Finally, we introduce dynamic goals by making the preferred neighbour type a function of the local characteristics of a simulated workload. We demonstrate that in this context, an overlay rewiring process based purely on local decisions and interactions can result in efficient load-balancing without central planning. We conclude by discussing the implications of our findings for the design of future distributed applications, the likely influence of other factors and of extreme parameter values on the ability of the system to self-organize and the potential improvements to our framework.

Applying self-aggregation to load balancing: experimental results

One of the today issues in software engineering is to find new effective ways to deal intelligently with the increasing complexity of distributed computing systems. In this context a crucial role is played by the balancing of the work load among all nodes in the system. So far load balancing approaches have been designed for networks with fixed or dynamic topologies. These approaches work well in the case each node knows its similes and is able to contact them to delegate tasks. However, they do not address the needs of more dynamic systems where nodes are able to process different types of jobs and have limited knowledge about their neighbors and the whole system. To address these issue, we are experimenting with the usage of autonomic self-aggregation techniques that rewire such highly dynamic systems in groups of homogeneous nodes that are then able to balance the load among each others. We present our approach and show through simulation that it provides significant advantages under the circumstances described before.

The Intelligent Campus (iCampus): End-to-End Learning Lifecycle of a Knowledge Ecosystem

A new paradigm of thinking pertaining to a novel holistic intelligent campus (iCampus) environment is proposed, in this paper, in order to enrich and enhance, as well as to transform, the end-to-end learning lifecycle of a knowledge ecosystem. Analogous to the different functions of a biological brain, the central digital nervous system of the campus is comprised of various different interconnected functional intelligences. Each of these intelligent areas is set to perform its specified functional role in a dynamic and coherent inter- and intra-integrative manner within the environment itself. A generalized roadmap has also been devised to encapsulate the concept from within an existing or a new campus setting. Note that the nature of the iCampus proposition is inherently multi-disciplinary and has multi-applicability to other forms of intelligent environment. To capture part of the essence of the concept, some of the key challenges pertinent to the iCampus ecosystem have also been highlighted within the campus value proposition framework.

Reliable sensor networks using decentralised channel selection

In this paper, we present a fully decentralised algorithm for channel selection in wireless ad-hoc sensor networks. The objective is to generate reliable, interference-free links between first neighbours so as to ensure the emergence of a single network including the majority of all devices, in a context where spatial distribution is unpredictable. The algorithm combines random channel selection with variable signal intensity to minimise the probability of collisions at the receivers end, yet relies exclusively on locally available information. Proof of concept is provided by Monte Carlo simulation results. We demonstrate military relevance by showing how our system could be used to retrieve information from a network of vibration-monitoring devices designed to track vehicle movement. Advantages in terms of power saving and increased sensor stealth are briefly discussed.

Self-Aggregation Techniques for Load Balancing in Distributed Systems

One of the today issues in software engineering is to find new effective ways to deal intelligently with the increasing complexity of distributed computing systems. In this context a crucial role is played by the balancing of the work load among all nodes in a system composed of interconnected nodes that enter and exit the system without following any rule. To address this issue, we are experimenting with the usage of autonomic self-aggregation techniques that rewire the system in groups of homogeneous nodes that are then able to balance the load among each others using classical techniques. We present our approach together with some simulation experiments that show how the application of self- aggregation algorithms makes it possible to balance the load also in these extreme situations. Besides, our experiments show that the introduction of self-aggregation does not introduce a significant overhead in terms of execution time, even if it requires the exchange of a higher number of messages between nodes.

Aggregation Dynamics in Service Overlay Networks

In this work we analyze the characteristics of service overlay networks generated by uncoordinated service providers that deploy different service replicas on overlay nodes across the Internet. Our approach differs from previous works, that generally rely on application-level routing, in that we allow nodes to autonomously re-wire the service overlay to make it capable of absorbing a heterogeneously distributed workload that would otherwise result in some nodes with a specific service being overloaded and others remaining idle. We provide a game theoretic model of the overlay creation process and propose several optimization methods to achieve Nash equilibrium topologies. Equilibrium overlays are characterized by interconnected clusters of nodes that instantiate the same service replicas. Hindered by the computational complexity of finding stable wirings, we propose a simple distributed heuristic that allows the study of overlay networks with a realistic size and with several service instances. We show the ability of our re-wiring strategy to promote the emergence of a clustered global topology whilst running locally. We also argue that the lack of incentives for nodes to participate in the overlay creation might lead to several types of misbehavior, of which some representative cases are analyzed. Finally, both scalability and diversity (in terms of service instances) issues that might affect our distributed heuristic are evaluated in detail.

SelfService: a theoretical protocol for autonomic distribution of services in P2P communities

In this paper, we present a theoretical protocol for autonomic distribution of services in a P2P environment, as well as the results of its simulated implementation. Our objective is to demonstrate that it is possible to obtain a distribution of the corresponding software modules that meets the requirement of the community in the absence of any centralized resource management. Instead, an acceptable balance between offer and demand is achieved via a simple trial-and-error mechanism, involving a simple, locally applied reasoning loop running independently on every peer.

Understanding the environmental costs of fixed line networking

bit associated with real-world communication networking. We highlight the key real-world network deployment issues, particularly legacy systems and utilization, which can have a strong bearing on the level of energy efficiency. We show how and why the real-world metric values differ from prior models of network energy use. We show how including embodied energy leads to the overall environmental impact being minimized only when legacy systems are maintained. We capture the full end to end impact of networking including an understanding of the data centre and home equipment. An accurate understanding is needed if claims around the potential carbon benefit of communications technologies are to be substantiated.

Panel report: “grand challenges of network and service composition”

This brief report intends to summarize some of the things we learned during WAC2004 sessions “Network Composition” and “Negotiation and Deployment”, and that were highlighted during the subsequent panel discussion. We try to focus especially on the following aspects: traits and trends of convergence emerging from the rather diverse findings presented in those sessions; controversial or divergent opinions on some of those findings; open issues that should be addressed by the autonomic communication community and how to tackle them; and major research directions that seem likely to emerge and shape a significant part of the autonomic communication landscape.