Mobile edge computing unloading method based on multi-agent reinforcement learning

Abstract

The invention discloses a mobile edge computing unloading method based on multi-agent reinforcement learning, belongs to the field of edge computing and wireless networks, and provides an intelligenttask unloading method for a multi-user multi-edge node complex scene. According to the method, a multi-agent reinforcement learning algorithm is adopted, each piece of user equipment establishes an Actor and Critic deep learning network locally, action selection and action scoring are carried out according to states and actions of the user equipment and other equipment, spectrum resources, computing resources and energy resources are comprehensively considered, and an unloading and resource allocation strategy is formulated by taking task delay optimization as a target. The method does not depend on a specific network model, each equipment can autonomously and intelligently make an optimal strategy through a learning process of exploring feedback, and the method can adapt to dynamic changeof a network environment.

Description

technical field [0001] The invention belongs to the field of edge computing and wireless network, and relates to a computing unloading method based on multi-agent deep reinforcement learning, in particular to computing task unloading strategies and multi-dimensional resource joint allocation problems. Background technique [0002] With the continuous development of mobile Internet technology, computing-intensive emerging applications such as virtual reality, online games, face recognition, and image processing are rapidly emerging. However, the popularity of these computing-intensive applications is limited due to the limited computing power of terminal devices. To solve this problem, cloud computing emerged as the times require, which uploads complex computing tasks on the terminal device side to cloud servers with more powerful computing capabilities for execution, so as to relieve the dependence of these emerging applications on device computing capabilities. However, tr...

AI Technical Summary

Problems solved by technology

However, this kind of decision-making optimization problem is usually NP-hard, especially when the network scale is large, even through the heuristic solution algorithm, it still takes a long calculation time to obtain the optimal strategy

In addition, the state of the network is usually changing dynamically, which requires the central node to continuously solve complex optimization problems, and it is difficult to adaptively track the dynamic environment of the network

Images