A flexible and scalable task planning system and method based on multi-agent

Abstract

The invention belongs to the technical field of program control except digital control, that is, sequence controller or logic controller, and discloses an elastic and scalable task planning system and method based on Multi-Agent. Satellites are divided into clustering algorithms firstly. After the K category, the satellites that have been grouped into one category are divided into a sub-Agent; the sub-Agent division in the comprehensive Agent can be dynamically divided according to different tasks, and the resource granularity and the resource granularity required by the task can be matched to the greatest extent. The present invention can effectively achieve a good match between task requirements and satellite resources, dynamically adjust the system structure according to the task, and effectively use the remaining resources to realize fast and efficient planning of multi-satellite and multi-task; the system method proposed by the present invention not only enables the system to be flexible and Scalable, can dynamically adjust the sub-agent structure and dynamically match the task resources, and can use the remaining resources of each agent to make resource utilization more efficient and task completion rate higher, and can be applied to different task scenarios.

Description

technical field [0001] The invention belongs to the technical field of program control other than digital control, that is, sequence controller or logic controller, and in particular relates to an elastic and scalable task planning system and method based on Multi-Agent. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: With the development of modern satellite technology, the number and types of satellite-ground systems continue to increase, and the functions of satellites continue to increase. The application of satellite systems in national defense and military affairs is gradually increasing, and they are also playing an increasingly important role in the development of the national economy. At the same time, the contradiction between the ever-increasing mission requirements and limited resources is also intensifying. Different missions may have various resource requirements for satellites, which may require ...

AI Technical Summary

Problems solved by technology

[0005] (1) In the current distributed system, each agent only manages and controls the resources of the isolated department, and it is difficult to cope with the complex and changeable requirements of the number and types of future user tasks

[0006] (2) In the general multi-agent planning system that has been proposed before, if the size of the resources required for the task assigned to the department does not match the satellite resources owned by the department, the task will be difficult to complete or the task can be completed but the resources will be wasted

[0007] (3) When the current distributed system changes with satellites and missions, the changes required are relatively large, and it is difficult to adjust quickly and dynamically, and it is difficult to adapt to changes in the satellite system and the development of mission requirements in the future

[0008] (4) After the planning of each subsystem of the existing multi-agent system, each agent lacks interaction, and the remaining resources of the satellite in the sub-agent are underutilized

Images