一种无线传感器网络数据包转发的博弈论算法

Game theoretical packet forwarding algorithm in wireless sensor networks

提出一种基于动态贝叶斯博弈的无线传感器网络数据包转发算法(PFDBG).该算法将数据包转发视作一种可观察行动的多阶段不完全信息博弈,相邻节点之间根据对方历史行为的评估,采取贝叶斯修正方法对其能量水平(私有类型)进行合理的计算和预测,并利用该预测值计算最大化期望收益函数的解,来作为双方在下个博弈阶段的最优发包策略;证明了数据包转发博弈中贝叶斯纳什均衡的存在性.理论和仿真结果表明,PFDBG算法在保证节点获得较高吞吐量的同时,能够很好地适应网络规模的变化,具有计算开销小、传输可靠性高和能量消耗低的特点,其性能优于现有的其他算法.

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.