Mobile edge computing task unloading method based on independent learning

Abstract

The invention relates to the technical field of wireless communication, in particular to a mobile edge computing task unloading method based on independent learning, which comprises the following steps: establishing a system model, and constructing a task queue model of an IoT equipment end according to the number of processed tasks; determining a task calculation mode and establishing a communication model; establishing a task local calculation model to obtain local task calculation total overhead; establishing a task unloading calculation model to obtain the total expenditure of unloading task calculation; introducing energy collection, and establishing a residual electric quantity queue model of the IoT equipment end; constructing an optimization problem aiming at minimizing the long-term average of the total overhead of the IoT equipment in the MEC system; establishing an independent learning task unloading model based on reinforcement learning, including a system state space, an action space and a reward function, and solving an optimal task unloading strategy; according to the invention, the total expenditure of time delay and energy consumption of IoT equipment is greatly reduced, and the service life of the MEC system is prolonged to a certain extent.

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