A method and a system for predicting resources based on edge computation

Abstract

The invention provides a method and a system for predicting resources based on edge computation. In the process of prediction object conversion and pretreatment, noise and other interference factors are effectively avoided, which improves the accuracy and robustness of the prediction. The middle layer design of the model incorporates as much a priori information as possible to ensure that the correction of prediction value and the update of the weight of the resource prediction model are carried out according to the facts. The forward propagation and backward propagation of the loop make the error of the predicted value decrease and converge gradually. At the same time, the corresponding judgment conditions are set up to ensure the effective process of the loop propagation and transmission.

Description

technical field [0001] The present invention relates to the field of edge computing, in particular to a resource prediction method and system based on edge computing. Background technique [0002] In the Internet era, cloud computing, the most popular application nowadays, centralizes services such as computing and storage, and uses shared data center infrastructure and economies of scale to reduce costs. However, during the service process, problems such as data transmission delays have gradually become prominent. At the same time, the number of smart terminals is growing exponentially, and cloud computing can no longer match the processing of massive data, which is manifested in limited bandwidth, high latency, security, and energy consumption. Therefore, the establishment of integrated computing at the edge of the network near the data source, the open platform of storage and application can provide services nearby, and its real-time, security and privacy protection, dat...

AI Technical Summary

Problems solved by technology

[0006] The embodiment of the present invention provides a resource prediction method and system based on edge computing, which aims to solve the problems of low accuracy and high complexity of the design process. After the corresponding preprocessing process, the prediction parameters are converted, so that the Avoid complexity, and at the same time, the change of prediction parameters also improves the accuracy of the model

Images