A multi-objective Dyna-Q based routing in wireless mesh network

Abstract

Routing is an essential part for network deployment to maintain and improve the network performance. With the rapid demands of various wireless applications, delay and energy efficiency are two fundamentally important aspects in the next-generation communication. A multi-objective Dyna-Q based routing (MODQR) approach to improve both delay and energy performances is proposed in this paper. For delay, the interference, asymmetrical link condition and probability of transmission failure (PTF) are considered. When deriving the PTF, the gray physical interference model is used. For energy, the ratio of consumed energy to energy capacity is used to monitor energy condition. Reinforcement learning is an effective way to solve the routing problem in a network with uncertain conditions. A path can be chosen by iterative exploration and exploitation. Dyna-Q is an effective reinforcement learning algorithm which can increase the convergence speed. To the best of our knowledge, Dyna-Q is used to solve the multi-objective routing problem for the first time. The path with least end-to-end delay and largest energy efficiency will be selected. Simulation results show that MODQR can obtain up to 80.97%, 83.48% and 86.15% better network performance than three other state-of-the-art routing methods.