No abstract

A P2P system is composed by autonomous nodes interconnected to share resources. The interconnections between the nodes define the P2P topology that is traversed to lookup resources. As nodes are autonomous, they are free to decide when to arrive and leave and what resources to share and download. To cope with this dynamism, the Evolutionary P2P Networking approach performs a periodical P2P topology reconfiguration applying evolutionary computation and using the amount of successful lookups as the evaluation function that drives the process. We extended this approach to also consider, as a part of the evaluation function, the creation of redundant paths in the topology and, additionally, we introduced elitism to improve the evolutionary process. In this work we present an extensive evaluation of both approaches. The results show that our approach scales better and produces more connected topologies. The improved connectivity ensures a higher rate of successful lookups under static and dynamic scenarios.

This paper proposes a parallel MOEA/D which assigns the computational resources to generate solutions in the minimum overlapped update ranges of solutions. The search performance is verifie on DTLZ2 problem and a car design optimization using TORCS.

P2P systems can be used to provide a wide spectrum of traditional and novel applications. These systems are built around distributed hash tables (DHTs) that allow them to achieve efficient storage and retrieval of resources. A DHT is a data structure whose storage is distributed among network peers. Chord and Kademlia are two relevant examples of such DHTs. A limiting factor for the proper operation of P2P networks is the aggregate effect of peer arrivals and departures. This phenomenon is called churn and it negatively affects the quality of the services provided by DHTs. The lookup service, for instance, is a function that receives a resource ID as the input and determines the pointer to the holder of such resource. This service may fail if the nodes that store parts of a DHT leave the network. In this work we study the performance of the lookup service of Chord and Kademlia in simulation scenarios with different peer online times. We found that, by making use of long-lived peers in the network structure, Kademlia achieves better performance than Chord. Our results suggest that this benefit is obtained even with a low fraction of long-lived peers.

No abstract