A Method of Scheduling and Allocation of Measurement and Control Resources Based on Multi-agent and DNN
A resource scheduling and resource allocation technology, applied in the field of agents, can solve problems such as increased difficulty in solving measurement and control problems, high measurement and control pressure, and increased conflicts in measurement and control requirements, achieving high strength, high difficulty, good modularity and scalability Effect
Active Publication Date: 2022-02-08
SPACE STAR TECH CO LTD
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
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
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0026] Hereinafter, the present invention will be described in detail based on the drawings.
[0027] Below in conjunction with accompanying drawing, the mode of invention is described in further detail:
[0028] 1. The technical route adopted is as follows: figure 1 shown. Based on the scheduling method of multi-agent cooperation technology, the dynamic scheduling problem of measurement and control resources includes three types of agents. The specific content is as follows:
[0029] (1) Manager Agent. The core of measurement and control resource allocation and scheduling is responsible for the management of the entire measurement and control resource scheduling and allocation, including task allocation, management, scheduling, and measurement and control resource management.
[0030] (2) Task Agent. Contains a collection of all tasks to be assigned and scheduled, and the relationship with the actual tasks is corresponding and mapped. Under normal circumstances, the tas...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for dispatching and allocating measurement and control resources based on Multi-Agent and DNN. The steps are: designing three types of intelligent agents for the dynamic scheduling of measurement and control resources; using the Multi-Agent negotiation and allocation mechanism based on game theory, for the measurement and control tasks and Preliminary arrangement of measurement and control resources; create measurement and control task knowledge base, use DNN deep neural network algorithm with deep learning structure to repeatedly train the measurement and control task knowledge base, and then eliminate conflicts between measurement and control tasks; generate dynamic facts of measurement and control tasks after deep learning Then, according to the generated optimal measurement and control task execution sequence, the tasks are distributed to each measurement and control station for accurate execution. The present invention optimizes the planning and dispatching of measurement and control resources by adopting Multi-Agent collaboration technology based on game theory and deep neural network technology. Utilize the deep learning process of the DNN deep neural network algorithm to continuously improve the measurement and control task knowledge base, thereby improving the dynamic adjustment and intelligent execution of measurement 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...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06N5/04G06N3/04G06Q10/04G06Q10/06
CPCG06N5/043G06Q10/04G06Q10/0631G06N3/042
Inventor 李长德徐梁陈洁王兆俊
Owner SPACE STAR TECH CO LTD