Unloading strategy method of wireless power supply system based on deep reinforcement learning

Abstract

The invention discloses an unloading strategy method of a wireless power supply system based on deep reinforcement learning, which can optimally adapt to task unloading decision and wireless resource allocation, and maximize the calculation rate and task success rate of the system on the basis of ensuring the service life of a battery. The method comprises the steps: decomposing an optimization problem by constructing an online unloading framework based on deep reinforcement learning; solving the unloading sub-problem by using a method of dynamically and adaptively adjusting DROO algorithm parameters; combining a double-segment search algorithm and a Lagrangian multiplier method to solve an optimal value; estimating the transmitting power of the equipment and the computing power of the user equipment in advance by setting the threshold value of the electric quantity of the battery, converting a four-variable optimization problem into a two-variable optimization problem, and obtaining an optimal value by combining a double-segment search algorithm and a Lagrange multiplier method, so the computing complexity is reduced.

Description

technical field [0001] The invention relates to the technical field of computer wireless communication, in particular to an unloading strategy method of a wireless power supply system based on deep reinforcement learning. Background technique [0002] IoT devices, such as sensors, cameras, and wearable devices, have computational bottlenecks in supporting advanced applications such as interactive online games and face recognition due to limitations in computing power, power, and memory. This challenge can be addressed by Mobile Edge Computing (MEC) technology. In MEC technology, mobile devices offload computing tasks to MEC devices in the wireless access of IoT devices, such as base stations, access points (Access Point, AP), laptops and smartphones. Computing offload can reduce computing latency, save battery life, and even improve the security of computing-intensive IoT applications by utilizing the computing, cache, and power resources of MEC devices. Energy harvesting ...

AI Technical Summary

Problems solved by technology

Most of these documents minimize energy consumption or maximize computing efficiency by optimizing task allocation or resource allocation, such as Dynamic Task Offloading and Scheduling for Low-Latency IoT Services in Multi-Access Edge Computing; Dynamic Resource and TaskAllocation for Energy Minimization in Mobile CloudSystems; Mobile Edge Computing: A survey), does not consider balancing the calculation amount of the user equipment, which will cause the user equipment with poor channel resources to be unable to complete the calculation task, resulting in a decrease in the success rate of the task, and does not consider the issue of battery loss. In a large-scale system, frequent deep charging and discharging will cause great damage to the battery, making the battery life extremely low

Images