交通信息采集传感器网络基于强化学习的路由

A routing approach based on reinforcement learning for sensor network used in traffic information collection

针对道路交通信息采集传感器网络网内数据的有效转发和汇聚问题,以节点剩余能量和通信链路的路径损耗作为路由选择的综合评价指标,基于Q学习算法实现了一种传感器网络自适应路由方法,通过Q表的查询实现了网内数据的路径选择和数据转发。仿真结果表明,各网络节点能够找到优化路径将数据转发至汇聚节点;同时能够有效的降低网络节点的平均能耗和减少数据包传输的平均跳数。在道路交通信息采集传感器网络中,基于Q学习的路由方法是可行的。

Traffic data collected by sensor network used in traffic information collection should be forwarded to the sink node efficiently.Using residual energy and path loss as comprehensive evaluation indexes,a routing approach based on Q-learning is proposed in this paper.Q table is established in each node to choose the optimal route to sink node and forward data through the route.Simulation results show that,with the proposed routing approach,each node could find an optimal path to sink node;average energy consumption of network nodes and average hop counts of data packets are also reduced.The routing approach based on Q-learning is feasible and effective for sensor network used in traffic information collection.