Minimization of Energy Consumption in TDMA-Based Wireless-Powered Multi-Access Edge Computing Networks

Many nodes in Internet of Things (IoT) rely on batteries for power. Additionally, the demand executing compute-intensive and latency-sensitive tasks is increasing IoT nodes. In some practical scenarios, computation WDs have non-separable characteristic, that is, binary offloading strategies should be used. this paper, we focus design an efficient algorithm minimizes system energy consumption (EC) TDMA-based wireless-powered multi-access edge computing networks, where either compute locally or offload them to hybrid access points (H-APs). We formulate EC minimization problem which a non-convex decompose it into master optimizing decision subproblem WPT duration task transmission durations. For problem, DRL based method applied obtain near-optimal decision. subproblem, firstly consider scenario do not completion time constraints optimal analytical solution. Then with constraints. By jointly using Golden Section Method bisection method, solution can obtained due convexity constraint function. Simulation results show proposed achieve near-minimal EC.