CCLBR: Congestion Control-Based Load Balanced Routing in Unstructured P2P Systems

Abstract

Given the growing popularity of the peer-to-peer (P2P) network systems in the recent years, efficient query routing under highly dynamic environments is still lacking in several P2P network systems. In response to this challenge, this paper proposes a new churn-resilient system to find alternative routing paths for the purpose of balancing the query loads under higher network churns and heavy workloads, ultimately to improve the search efficiency. Two novel methods are devised to balance the network query loads among both inter-and intragroup level peers. First, a resource grouping and a rewiring method is proposed to spontaneously organize and cluster the peers having same resources together. This strategy facilitates the peers to evolve the network into a cluster-like topology and balances the query loads among the intergroup peers. Second, a collaborative Q-learning method is proposed to balance the query loads among the intragroup peers in order to intelligently avoid queries being forwarded to the congested peers in the network. Experiments conducted under dynamic network scenarios demonstrate that our proposed method achieves better search performances with a more balanced network load than the existing methods, and further exhibits higher robustness and adaptability under higher network churns and heavy network loads.Index Terms-Collaborative Q-learning, congestion control, load balancing, query routing, unstructured peer-to-peer (P2P) systems.

Congestion Control Algorithm for Message Routing in Structured Peer-to-Peer Networks

“…Other approaches include the CCLBR [6], the methods in [8], [10] and [11]. The CCLBR [6] proposed a resource grouping and a rewiring method to spontaneously organize and cluster the peers having similar resources together.…”

“…Other approaches include the CCLBR [6], the methods in [8], [10] and [11]. The CCLBR [6] proposed a resource grouping and a rewiring method to spontaneously organize and cluster the peers having similar resources together. Then, a collaborative Q-learning method is proposed to balance the query loads among the intragroup peers in order to intelligently avoid queries being forwarded to the congested peers in the network.…”

“…Researches in congestion control in P2P networks are either to limit the sending speed of the query sending nodes or to change the message route to avoid congestion. There are a number of studies on congestion control in P2P such as the CSCC [5], the BPCC [5] and the CCLBR [6]. Those methods have a common characteristic: they use a fixed routing table and perform congestion control by reducing the sending speed of the query node or by using alternative message route in the routing table while ignoring the nodes that have high processing capacity in the network.…”

Reinforcement Learning Based Routing in Networks: Review and Classification of Approaches

“…CCLBR (Congestion Control-based Load Balanced Routing) - [94] proposed a routing protocol to efficiently forward query packets in peer-to-peer networks. CCLBR objective is load balancing between peers under dynamic loads.…”

“…Nodes on path forward (or not) the requests to locate the requested content. Then, when data packet containing the requested content are forwarded, relaying nodes receive feedback and adapt their paths to keep only paths that enable to return the maximum content at a minimum cost [87], [88], [94].…”