A Mobile Edge Computing Task Offloading Method Based on Independent Learning

Abstract

The present invention relates to the technical field of wireless communication, in particular to a mobile edge computing task offloading method based on independent learning, including: establishing a system model, and constructing a task queue model of an IoT device according to the number of processed tasks; determining the task calculation method and establishing communication Model; establish a task local computing model to obtain the total overhead of local task computing; establish a task offloading computing model to obtain the total overhead of offloading task computing; introduce energy harvesting and establish a queue model for remaining power at the IoT device side; build to minimize IoT devices in the MEC system The long-term average of the total cost is an optimization problem; an independent learning task offloading model based on reinforcement learning is established, including system state space, action space and reward function, and the optimal task offloading strategy is solved; the invention not only greatly reduces IoT device The total overhead of time delay and energy consumption, and to a certain extent prolong the service life of the MEC system.

Description

technical field [0001] The present invention relates to the technical field of wireless communication, in particular to a mobile edge computing task offloading method based on independent learning. Background technique [0002] With the continuous improvement of mobile communication rate, the continuous emergence of Internet of Things (IoT) business applications, and the increasing variety of mobile terminals, the number of IoT devices (such as smart phones, sensors, etc.) has shown an exponential growth. However, most IoT devices have limited volume and battery capacity. When dealing with computing-intensive applications, there will be problems such as slow computing speed and rapid drop points, which cannot meet the processing power and battery life requirements of computing-intensive applications. , which makes the conflict between computing-intensive applications and resource-constrained IoT devices increasing. Mobile Edge Computing (Mobile Edge Computing, MEC) provides...

AI Technical Summary

Problems solved by technology

[0003] The limited energy of IoT devices is a key problem hindering the development of MEC, which can usually be solved by equipping large batteries or recharging the batteries frequently, but due to the limited size of IoT devices, it is difficult to equip large battery devices

Images