X-BOT: A Protocol for Resilient Optimization of Unstructured Overlays

Abstract

Gossip, or epidemic, protocols have emerged as a highly scalable and resilient approach to implement several application level services such as reliable multicast, data aggregation, publish-subscribe, among others. All these protocols organize nodes in an unstructured random overlay network. In many cases, it is interesting to bias the random overlay in order to optimize some efficiency criteria, for instance, to reduce the stretch of the overlay routing. In this paper we propose X-BOT, a new protocol that allows to bias the topology of an unstructured gossip overlay network. X-BOT is completely decentralized and, unlike previous approaches, preserves several key properties of the original (non-biased) overlay (most notably, the node degree and consequently, the overlay connectivity). Experimental results show that X-BOT can generate more efficient overlays than previous approaches.

A Self-adaptive Algorithm for Topology Matching in Unstructured Peer-to-Peer Networks

“…To evaluate the performance of the proposed algorithm called LA_Match, it is compared with three algorithms: PROP-O [6,15], X-BOT [12,17], and THANCS [7]. It should be noted that, the proposed algorithm, like algorithms PROP-O, X-BOT, and THANCS (to which the proposed algorithm is compared) uses only the delays of links for solving the topology matching problem.…”

“…Reported algorithms can be classified into three classes of algorithms ( Fig. 4): algorithms in which each peer in the network uses some services such as GPS 1 or Oracle to gather information about the location of peers [23][24][25], algorithms in which each peer in the network uses information about landmark peers [26][27][28][29][30][31][32][33], and algorithms in which each peer in the network uses local information about its neighbors [6,7,9,11,12,16,17,[34][35][36][37][38][39]. In the rest of this section, we briefly review these classes of algorithms.…”

“…A main drawback of both PROP-O and PROP-G is that they have no self-adaptive mechanism to tune their parameters (such as parameter distance) of their local search algorithm. In [12,17], X-BOT is proposed. X-BOT is an algorithm for topology optimization in unstructured peer-to-peer networks that can be used to solve the topology mismatch problem.…”

“…Existing matching algorithms such as X-BOT (Bias the Overlay Topology according to criteria X) [12,17], Two-Hop-Away Neighbor Comparison and Selection (THANCS) [7], and Peer-exchange Routing Optimizing Protocol (PROP) [6,15] suffer from two problems. The first problem is that there is no adaptive mechanism for setting the neighborhood radius parameter.…”

“…In the proposed algorithm, we use learning automata to adapt the neighborhood radius and an adaptation mechanism inspired from the SSM to manage the execution of the exchange operator. To show the superiority of the proposed algorithm, computer experiments have been conducted and then the results are compared with the results obtained for algorithms PROP-O (an optimized version of PROP algorithm) [6,15], X-BOT [12,17], and THANCS [7]. The rest of this paper is organized as follows.…”