基于竞争双深度Q学习的边缘计算服务部署优化方法OA

To address the issues of uneven deployment and limited resource coverage of edge computing server for vehicle-to-everything(V2X)network,an intelligent deployment method for edge computing servers based on a residual graph attention network and dueling double deep Q-learning was proposed.Firstly,the roadside unit(RSU)network was transformed into structured graph data through a V2X environment modeling method that utilized a dual adjacency ma-trix and multi-dimensional feature encoding.Secondly,a graph neural network integrating residual connection and atten-tion mechanism was constructed to extract complex spatial dependencies among nodes.Thirdly,a sequential decision-making framework based on dueling double deep Q-network was designed,which improved the accuracy of Q-value esti-mation through value function decomposition and a dual-network update mechanism,while guiding policy convergence using a multi-objective reward function.Experimental results show that compared to existing methods,the proposed method improves service coverage by 5.1％and load balancing by 1.4％,and reduces transmission latency by 17％.