Game theoretical packet forwarding algorithm in wireless sensor networks

A packet forwarding algorithm based on the dynamic Bayesian game named PFDBG is presented for wireless sensor networks. Packet forwarding is regarded as a multi-stage game with incomplete information and observable actions, the adjacent nodes take the Bayesian amendment method to reasonably calculate and predict the opponent's energy level (private type) based on evaluation of its historical actions, and use the predicted value to obtain the solution which maximizes the expected utility function. The solution is also the optimal forwarding strategy that the nodes will adopt in the next stage of the game; the existence of the Bayesian Nash Equilibrium in the game is proved. Theoretical analysis and experimental results show that the PFDBG algorithm not only ensures the higher throughput of nodes, but also adapts well to the network size, and that it has a small computational overhead, high transmission reliability and low energy consumption, with its performance superior to that of other existing algorithms.