Soutenance de thèse : Guido LENA COTA
Addressing selfishness in the design of cooperative systems
Doctorant : Guido LENA COTA
Laboratoire INSA : LIRIS
Ecole doctorale : ED 152 : Informatique et Mathématiques de Lyon
Cooperative systems are at the basis of several mainstream Internet applications (ex.: peer-to- peer file-sharing and media streaming). Essential to their success is the voluntary contribution of resources (ex.: bandwidth, CPU, storage) from the participating nodes. However, as nodes are autonomous entities, they may be tempted to behave in a selfish manner by not contributing their fair share, potentially causing system performance degradation and instability. Addressing selfish nodes is, therefore, key to building efficient and reliable cooperative systems. Yet, it is a challenging task, as current techniques for analysing selfishness and designing effective countermeasures remain manual and time-consuming, requiring multi-domain expertise.
In this thesis, we aim to provide practical and conceptual tools to help system designers in dealing with selfish nodes. First, based on a comprehensive survey of existing work on selfishness, we develop a classification framework to identify and understand the most important selfish behaviours to focus on when designing a cooperative system.
Second, we propose RACOON, a unifying framework for the selfishness-aware design and configuration of cooperative systems. RACOON provides a semi-automatic methodology to integrate a given system with practical and finely tuned mechanisms to meet specified resilience and performance objectives, using game theory and simulations to predict the behaviour of the system when subjected to selfish nodes. An extension of the framework (RACOON++) is also proposed to improve the accuracy, flexibility, and usability of RACOON.
Finally, we propose SEINE, a framework for fast modelling and evaluation of various types of selfish behaviour in a given cooperative system. SEINE relies on a domain-specific language for describing the selfishness scenario to evaluate, and provides semi-automatic support for its implementation and study in a state-of-the-art simulator.
Salle Lauree, département des Sciences Informatiques, Université de Milan