Accelerated Ants Routing in Dynamic Networks
Hiroshi Matsuo, Koichi Mori · 2001
Efficiently routing in a dynamic network is a important problem in ad hoc network according to development of personal data assistant (PDA) and wireless network equipment. However conventional routing algorithm is difficult to apply to dynamic topology network. Q-Routing, DRQ-Routing and Ants-Routing which are based on reinforcement learning technique are proposed. But convergence speed and routing result are still unsatisfied. In this paper, accelerated AntsRouting which increase convergence speed and obtain good routing path is discussed. Experiment on dynamic network showed that accelerated Ants-Routing learns the optimum routing in terms of convergence speed and average packet latency.