Measurement and control resource scheduling distribution method based on Multi-Agent and DNN

Abstract

The invention discloses a measurement and control resource scheduling distribution method based on Multi-Agent and a DNN, and the method comprises the steps: designing three big types of intelligent agents of a measurement and control resource dynamic scheduling problem; carrying out the initial arrangement of the measurement and control tasks and measurement and control resources based on a Multi-Agent negotiation distribution mechanism of the game theory; creating a measurement and control task knowledge base, carrying out the repeated training of the measurement and control task knowledge base through a DNN (depth neural network) algorithm with a deep learning structure, and eliminating a problem of mutual conflict between the measurement and control tasks; generating a measurement andcontrol task dynamic factbase after deep learning, and distributing tasks to each measurement and control station for accurate execution according to a generated optimal measurement and control task execution sequence. The method optimizes the measurement and control resource planning and scheduling through the Multi-Agent cooperation technology based on the game theory and the DNN technology. Through the deep learning process of the DNN algorithm, the measurement and control task knowledge base is continuously improved, thereby improving the dynamic adjustment and intelligent execution of themeasurement and control resource scheduling management.

Description

technical field [0001] The invention belongs to the field of intelligent body technology, and relates to a method for scheduling and allocating measurement and control resources based on Multi-Agent and DNN. Background technique [0002] With the continuous growth of the space industry of various countries in the world, different types of satellites and corresponding payloads have played a vital role in the cultural, economic and military aspects of the world. Due to the increasing number and types of satellites, related research on multi-satellite measurement and control resource scheduling has been introduced. At present, the number of TT&C resources is certain. The multi-satellite TT&C resource scheduling problem refers to the study of how to meet the TT&C requirements and mission problems of various satellites under the condition of limited TT&C resources, and through reasonable scheduling and allocation of TT&C resources, All kinds of satellites can be used to maximize...

AI Technical Summary

Problems solved by technology

On the issue of measurement and control, if the measurement and control requirements and tasks are few and there is no conflict, the existing algorithm combining artificial intelligence and intelligence can meet the needs. And then become more and more, so that the pressure of measurement and control becomes more and more

The conflict between a certain amount of measurement and control resources and more and more measurement and control requirements continues to increase, making it increasingly difficult to solve measurement and control problems

Images