An adaptive algorithm for super-peer selection considering peer’s capacity in mobile peer-to-peer networks based on learning automata

Abstract

Mobile peer-to-peer (MP2P) networks refer to the peer-to-peer overlay networks superimposing above the mobile ad-hoc networks. Heterogeneity of capacity and mobility of the peers as well as inherent limitation of resources along with the wireless networks characteristics are challenges on MP2P networks. In some MP2P networks, in order to improve network performances, special peers, are called super-peers, undertake to perform network managerial tasks. Selection of super-peers, due to their influential position, requires a protocol which considers the capacity of peers. Lack of general information about the capacity of other peers, as well as peers mobility along with dynamic nature of MP2P networks are the major challenges that impose uncertainty in decision making of the super-peer management algorithms. This paper proposes an adaptive super-peer selection algorithm considering peers capacity based on learning automata in MP2P networks, called SSBLA. In the proposed algorithm, each peer is equipped with a learning automaton which is used locally in the operation of super-peer selection by that peer. It has been shown that the suggested algorithm is superior to the existing algorithms. The results of the simulation show that the proposed algorithm can maximize capacity utilization by minimum number of super-peer and improve robustness against failures of super-peers while minimizing selection communication overhead.