Comprehensive benefit-oriented resource intelligent collaborative scheduling method in space-ground-air integrated network

Abstract

The invention discloses a comprehensive benefit-oriented resource intelligent collaborative scheduling method in a space-ground-air integrated network, and the method comprises the steps: carrying out the analysis of the topological state of the space-ground-air integrated network, taking reinforcement learning as a research tool, carrying out the joint scheduling of the utilization rate of various resources, and taking the actual business service quality as an overall optimization target, and carrying out the comprehensive benefit-oriented resource intelligent collaborative scheduling of the space-ground-air integrated network. By means of the service analysis module, resource requirements of daily service requests are judged, reasonable allocation and scheduling of resources are carried out, and the method is oriented to comprehensive benefits instead of the utilization rate of a certain kind of resources. According to the method, a reinforcement learning strategy is adopted to carry out autonomous learning from historical scheduling experience, knowledge updating is carried out, weight distribution is carried out on evaluation criteria, the most reasonable planning decision based on the globality is selected from resource scheduling problems, and learning improvement is carried out according to feedback information completed at this time; the resource scheduling service quality is improved, the resource scheduling rationality is improved, the resource waste is reduced, and the resource scheduling method meeting the comprehensive benefit is realized.

Description

technical field [0001] The invention belongs to the field of space-ground-air integrated network resource scheduling, and in particular relates to a comprehensive benefit-oriented resource intelligent coordinated scheduling method in a space-ground-air integrated network. Background technique [0002] The satellite Internet and the ground network will form an integrated network of sky, earth and air. The coverage of this three-dimensional space is not limited by geographical areas. The interconnection under the integrated network can largely solve practical needs such as geographical location and post-disaster rescue. To meet the problems, and efficiently complete the communication needs of different users. [0003] However, due to the complex composition of the network and the dynamic nature of satellites, the network topology of the sky-earth-air integration network changes all the time, the number of nodes is large, and the connection relationship between nodes is also ve...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the above-mentioned deficiencies, and provide an intelligent resource collaborative scheduling method for comprehensive benefits in the space-ground-space integrated network, so as to solve the problem of not considering the space-ground integrated network in the resource scheduling process in the prior art. In the environment of heterogeneous network and dynamic topology, massive tasks with different requirements adopt the previous scheme for resource scheduling, resulting in problems such as inapplicability, low performance, serious errors, and large computing overhead.

Images