These last times, we have conducted research on various aspects of P2P networks.
We have first studied hierarchical DHTs, in which peers are organized into groups, and each group has its autonomous intra-group overlay network and lookup service. The groups themselves are organized in a top-level overlay network. Our analysis shows that by designating the most reliable peers in the groups as super-peers, the hierarchical design can significantly improve the performance and resilience to failures over flat DHT designs. Hierarchical DHTs are the way to adapt DHT-based P2P networks to the reality of the Internet.
Further research in the domain of hierarchical DHTs and their suitability for the Internet drove us to TOPLUS: topology-centric lookup service (best paper award), a novel lookup service for structured peer-to-peer networks that is based on the hierarchical grouping of peers according to network IP prefixes, gathered from such sources as BGP tables and repositories of well-known prefixes. TOPLUS is fully distributed and symmetric, in the sense that all nodes have the same role. Packets are routed to their destination according to an efficient XOR metric along a path that mimics the router-level shortest-path, thereby providing a small stretch and very low latency. In addition, the TOPLUS design provides straightforward support for caching content within an IP sub-domain. Our premise, which we plan to substantiate in this project, is that topology-aware P2P networks like TOPLUS will allow us to build content delivery networks with near-optimal usage of network bandwidth.
In other fields of P2P systems, we have also studied semantics awareness in the context of unstructured P2P networks. P2P content sharing systems are usually designed as unstructured networks, because they impose few constraints on topology and data placement and support highly versatile search mechanisms. A major limitation of such networks lies, however, in the inefficiency of their search algorithms, which are usually based on simple flooding schemes. In this paper, we have proposed novel mechanisms for improving search efficiency in unstructured P2P networks. Unlike other approaches, we do not rely on specialized search algorithms; instead, the peers perform local dynamic topology adaptations, based on the query traffic patterns, in order to spontaneously create communities of peers that share similar interests. Requests have a high probability of being fulfilled within the semantic community they originate from, therefore increasing the search efficiency. We have also proposed extensions to balance the load among the peers and reduce the query traffic for increased scalability.
We have addressed the problem of content discovery in structured P2P networks (DHTs). Peer-to-peer DHT systems make it simple to discover specific data when their complete identifiers (or keys) are known in advance. In practice, however, users looking up content stored in peer-to-peer systems often have only partial information for identifying that content. We have developed novel techniques for indexing data stored in peer-to-peer networks, and discovering the content that matches a given user query. Our system creates multiple indexes, organized hierarchically, which permit users to access data in many different ways. The data itself is stored on only one (or few) of the nodes. Content can be subsequently retrieved using incomplete keys, at the price of a higher lookup cost. Such techniques can prove useful to index and discover content in P2P distribution networks.
We study a new approach to provide an efficient VoD service to a large client population in P2P networks. We show how to simplify the algorithm performed by the server in multicast approach and, at the same time, achieve an efficient use of the system resources. For this purpose, we present a new pull-based approach, called PBA. When a new client wishes to receive a video, the new client contacts first the server. If there is enough left over bandwidth along the path to the new client, the server transmits the video to the new client. Otherwise, the server provides to the new client a list of candidate servants chosen at random. These servants are clients that have received or are currently receiving the video. The new client then searches for an available servant to download the video from.
We have also analyzed BitTorrent, a new and already very popular peer-to-peer application that allows distribution of very large contents to a large set of hosts. Our analysis of BitTorrent is based on measurements collected on a five months long period that involved thousands of peers. We assess the performance of the algorithms used in BitTorrent through several metrics. Our conclusions indicate that BitTorrent is a realistic and inexpensive alternative to the classical server-based content distribution.
We have developed MULTI+, an application-level multicast protocol for content distribution over a peer-to-peer (P2P) TOPLUS-based network. We use the characteristics of TOPLUS to design a protocol that allows for every peer to connect to an available peer that is close. MULTI+ trees also reduce the amount of redundant flows leaving and entering each network, making more efficient bandwidth usage. We use different procedures to measure or calculate the distances among peers, in order to validate the algorithms in MULTI+.
Learn more about what we do.
Find here more resources and information about: