Using Statistical Network Link Model for Routing in Ad Hoc Networks with multi-agent Reinforcement Learning
Existing mobile ad-hoc routing protocols are based on a discrete, bimodal model for links between nodes: a link either exists or is broken. This model cannot distinguish transmissions which fail due to interference or congestion from those which fail due to their target being out of transmission range. A statistrical network link model is introduced to represent the quality of the link by a statistical measure of link performance. Because of dynamic topologies properties of ad hoc network, each node cant achieve the global information about other nodes in the whole nerwork. In order to define optimal routes in a network with links of variable quality, ad-hoc routing is modeled as a sequential decision making problem with incomplete information. More precisely, ad hoc routing is mapped into a multi-agent reinforcement karning problem involving a parhally observable Markov decision processes (POMDPs). A new routing protocol called SNL-Q is proposed based on a combination of continuous (rather than discrete) model for links and the POMDP modd within the ad hoc network Different scenario-based performance evalua tions of the protocol in NS-2 are presented. In comparisons with AODV and DSR, SNL-Q routing exhibits improved per formance in congested wireless networks.
POMDPs Reinforcement Learning, Mobile Ad hoc network Q-routing
Zhang Binbin Liu Quan Zhao Shouling
Institute of Computer Science and Technology,Soochow University, Soochow ,215006, China
国际会议
The 2nd IEEE International Conference on Advanced Computer Control(第二届先进计算机控制国际会议 ICACC 2010)
沈阳
英文
462-466
2010-03-27（万方平台首次上网日期，不代表论文的发表时间）