LAUSR

This paper studies the artificial intelligent (AI) task deployment problem of a multi-access edge intelligent system in a 6G network, in which the cloud server broadcasts the AI program to the edge computing nodes. In particular, task nodes can perform remote processing by offloading AI tasks to cloud servers or other edge computing nodes, or they can perform processing tasks locally. In order to minimize the total computing time and energy consumption of all task nodes and maximize the inference accuracy of AI tasks, we jointly optimize the resource allocation and computing offloading decision of each node by solving a mixed-integer non-linear programming (MINLP) problem. In order to efficiently solve this non-convex problem, we propose an alternating direction multiplier method (ADMM) based algorithm, which effectively decomposes the problem into easy-to-handle MINLP subproblems. Through the proposed ADMM-based algorithm, each task node can use local channel state information (CSI) to optimize its calculation mode and resource allocation, which is more suitable for large-scale networks. The simulation results show that this method is significantly better than other benchmarks in various network environments, and the computational complexity is relatively low.