Computing service dynamic pricing method and system oriented to large-scale edge computing system

Abstract

The invention discloses a computing service dynamic pricing method and system oriented to a large-scale edge computing system. The method comprises the steps that an edge computing server trains a dynamic pricing reinforcement learning agent; each edge computing server issues a new service price for task unloading at the beginning of each time slot according to the output of the dynamic pricing reinforcement learning agent, and feeds back the issued service price by a user mobile device connected to the edge computing server through a wireless network; the feedback comprises the task calculation amount unloaded to the edge calculation server by the user mobile equipment in the time slot; and at the end of the time slot, the load data of the edge computing server in the time slot, the service pricing and the income brought by the pricing are input into the dynamic pricing reinforcement learning agent for learning, and the dynamic pricing reinforcement learning agent is optimized by taking the maximization of the long-term income of each time slot as a learning target. According to the method, the dynamic pricing strategy can be continuously learned and improved only through interactive iteration with the user.

Description

technical field [0001] The invention relates to the field of edge computing, in particular to a method and system for dynamic pricing of computing services for large-scale edge computing systems. Background technique [0002] The rapid development of mobile computing devices (such as smartphones and smart cars) has brought about the prosperity of mobile computing, and a variety of new applications have emerged on mobile computing devices, such as image processing, augmented reality, cloud games, etc. Most of these new applications belong to the Computing-intensive and real-time applications have high demands on computing and communication resources, making mobile computing devices face huge challenges in terms of computing power, storage capacity and battery life. As the most popular network computing mode at present, cloud computing has the advantages of strong computing power and large coverage, and can solve the problems of poor computing power, small storage capacity and...

AI Technical Summary

Problems solved by technology

[0009] The present invention provides a large-scale edge computing system-oriented computing service dynamic pricing method and system, which are used to solve the problems of insufficient utilization of computing resources, unbalanced utilization, and insufficient profitability of computing resources caused by random changes in user behavior in the edge computing system. technical problem

Images