Industrial Internet-of-Things edge resource intelligent scheduling system and method based on deep learning

Abstract

The invention provides an industrial Internet-of-Things edge resource intelligent scheduling system based on deep learning. The system comprises a data collection module which monitors an intermediatelink of an industrial process, and schedules a data processing task to an edge server with surplus processing capability, a task scheduling module which is used for scheduling a task to a proper edgeserver according to the AoT and sending the task to a deep learning network layer for preliminary data processing, an edge data processing module which is used for processing and analyzing the monitoring data and uploading the output intermediate data to a cloud server, and a cloud deep learning network training module which is used for receiving the data and carrying out training by utilizing the preprocessed data so as to determine a DBN optimal network structure, and adjusting the weight to obtain a final model. According to the invention, the accuracy and timeliness of data acquisition ofthe deep learning model can be improved, and the number of deep learning tasks is maximized by using limited network bandwidth and the service capability of edge nodes.

Description

technical field [0001] The invention relates to a deep learning-based intelligent scheduling system and method for edge resources of the Industrial Internet of Things. Background technique [0002] With the introduction of the concept of "Industry 4.0", the development of strategic emerging industries such as the Internet of Things has attracted more and more attention from all countries in the world. At present, the integration and innovation of the Internet of Things and industry has become the general trend, and industrial big data technology and application have become the key elements to improve the productivity, competitiveness and innovation ability of the manufacturing industry. The Industrial Internet of Things is widely used in management such as healthcare, manufacturing, and smart grids, and it plays a very important role in promoting the implementation of smart manufacturing strategies. [0003] Deep learning is becoming an emerging technology for IoT applicati...

AI Technical Summary

Problems solved by technology

[0008] The technical problem to be solved by the present invention is to overcome the lack of large data processing capability of the industrial Internet of things existing in the prior art, and to provide a system and method for intelligently dispatching edge resources of the industrial Internet of things based on deep learning

Images