A Task Offloading Method Based on Power Control and Resource Allocation

Abstract

The invention discloses a task offloading method based on power control and resource allocation, which relates to the field of industrial Internet of Things, establishes a cross-domain network model of an industrial site, constructs a calculation model of equipment tasks, and controls the communication power according to the model , Resource allocation and computing unloading problems are constructed as a mixed integer nonlinear programming model, the problem is decomposed into three sub-problems, and the optimal solution is obtained by using convex optimization knowledge, Lagrange multiplier method and KKT (Karush‑Kuhn‑Tucker) conditions The communication power and resource allocation strategy, after substituting the original objective function, uses the deep reinforcement learning algorithm to obtain the optimal decision of the task calculation position, and obtains the optimal strategy of the task offloading communication power, resource allocation and calculation position. The invention can obtain the optimal strategy in the unloading of industrial network tasks, and has the technical effects of reducing task delay, reducing equipment energy consumption and ensuring service quality.

Description

technical field [0001] The invention relates to the field of industrial internet of things, in particular to a task offloading method based on power control and resource allocation. Background technique [0002] Industrial Internet of Things is the application and promotion of Internet of Things technology in the industrial field. Compared with other application fields of the Internet of Things, such as smart medical care and intelligent transportation, the industrial field has higher requirements for real-time and reliability of data. Relevant research shows that most of the collected industrial data needs to be stored and processed in real time. Therefore, it is very necessary to study effective task processing strategies to meet the requirements of low latency and high reliability. [0003] The development of the Industrial Internet of Things puts forward higher requirements on the computing architecture. As a common computing architecture, cloud computing has abundant...

AI Technical Summary

Problems solved by technology

However, there are many devices in the industrial field environment, and the computing-intensive tasks generated on the devices have high requirements for processing delay. Uploading a large amount of data to the cloud server will not only cause network congestion, but also cause a large delay

Images