Incentives for P2P Fair Resource Sharing

We consider the problem of fair resource sharing to optimize the performance of resource sharing in peer to peer systems. Resource sharing systems currently face rational peers which may exhibit a variety of strategies including: no participation, also referred as free-riding, and greedy behavior. The first aspect has been extensively studied in the late years, while the second one has not received much attention. The broad class of proposed solutions focuses on designing incentives to reward cooperative peers. The side effect of these incentives is twofold: the system load is not balanced and the resource potential of the system is not fully exploited. The P2P fair resource sharing aims at both balancing the load and maximizing the use of system resources. The contribution of our work is twofold. First, we specify the P2P fair resource sharing problem and propose a mechanism to solve it in large scale dynamic networks with rational users. Our mechanism is composed of a novel incentive (i.e. fair cooperation) and an algorithmic part encapsulated in a middleware layer. Second, we propose an architecture for our mechanism middleware layer including four distributed services that bring together several research area: aggregation, semantic group membership and tracking. Finally, we implement our mechanism using a peer-to-peer unstructured model and evaluate it through simulations

I. Introduction

In peer-to-peer (P2P) systems resources are highly distributed and stored by individual peers. In such environments where each peer may present a different self-interested entity, designing algorithms for sharing resources becomes a difficult task. Traditional distributed algorithms design faces only two types of behaviors: obedient (i.e. to follow the algorithm) or malicious (i.e. to “play” against the others). In contrast, in P2P systems users may have a strategic behavior which may be neither obedient nor malicious, just rational. It was established in [1] for example that in the absence of incentives a large fraction of peers have a priori no motivation to share while they are naturally incited to use system resources. The effects of “free-riding” (consuming resources without contributing) was extensively studied in the last years [1], [13]. This behavior can cause severe degradation of the system performances or even may lead to the system collapse [14]. As emphasized by Shneidman and al. [14], different approaches may be adopted to face rationality: i) to ignore it and to expect that system will do its best despite self-interested peers, ii) to limit the effect that a rational peer can have on the system by using trusted mechanisms, or iii) to adopt the fault tolerance techniques. However, none of these approaches benefits from resources that may be potentially offered by these rational and self-interested peers. Thus the system must motivate each peer to behave rationally in a system efficient way. Solutions come from economics and more precisely from the mechanism design theory that always stressed for algorithms that work correctly in the presence of predictable selfish behavior.