Satellite network resource arrangement method and system based on reinforcement learning

Abstract

The invention provides a reinforcement learning-based satellite network resource arrangement method and system, which are used for solving the technical problem of unreasonable satellite network resource allocation networking structure in the prior art. The method comprises the following steps: collecting resource states on LEO satellites in a system to form a resource state set; the LEO satellite formulates an on-satellite resource arrangement action set; a distributed decision module in the LEO satellite selects a resource arrangement action based on a local resource arrangement strategy in a current state, and reports a resource state to the GEO satellite; a business evaluation module of the GEO satellite sets a reward function of a resource arrangement strategy; and according to an evaluation result given by the service evaluation module, the LEO satellite adjusts and optimizes a resource arrangement strategy. The invention provides a reinforcement learning-based satellite network resource arrangement method and system, which can realize self-learning and self-evolution of a multi-satellite cooperative processing strategy, effectively improve the utilization rate of satellite communication resources and meet the development requirements of new services.

Description

technical field [0001] The present application relates to the field of satellite network communications, and in particular, to a method and system for scheduling satellite network resources based on reinforcement learning. Background technique [0002] As terrestrial mobile communication technology gradually enters the 5G / 6G era, the application scenarios for the deep integration of space-earth information networks will become very broad, and satellite networks will serve broadband Internet, Internet of Things, low-latency, high-reliability data transmission and other services in the future. Compared with traditional satellite services, these differentiated and dynamically changing new services will bring great challenges to the allocation of satellite network resources. [0003] At the same time, large-scale constellation networking based on inter-satellite link technology has become a research hotspot. Satellite communication systems are developing from "single satellite" ...

AI Technical Summary

Problems solved by technology

[0006] The embodiment of the present application provides a satellite network resource arrangement method and system based on reinforcement learning, which adopts a resource arrangement mechanism combining centralized evaluation and distributed decision-making, and combines the reinforcement learning method with the multi-layer satellite network topology structure. To solve the problems of excessive pressure on satellite nodes caused by centralized architecture, unstable satellite networking caused by distributed architecture and great waste of communication resources in the prior art

Images