空天地一体化网络性能优化的最新进展、挑战以及研究前景OA

Space-air-ground integrated networks(SAGIN)have emerged as a pivotal technology in propelling the development of sixth-generation(6G)mobile communications.This is achieved through the seamless integration of space-based,air-based,and ground wireless networks.SAGIN offers distinct advantages,enabling the extension of high-speed broadband services to remote and inaccessible regions.Nonetheless,SAGIN encounters several critical challenges during its practical operation.These challenges stem from the intricate nature of its architecture,along with the limited availability of resources such as power and storage.Specific challenges include multi-layer dynamic optimization,topological structure variations,and resource constraints.artificial intelligence(AI)-driven solutions,encompassing deep reinforcement learning(DRL)as well as supervised and unsupervised learning approaches,present promising avenues for addressing these challenges.By incorporating AI techniques,it becomes possible to collaboratively optimize core aspects of SAGIN,including network topology,scheduling strategies,resource allocation,routing mechanisms,and mobility management.This optimization process enhances SAGIN's decision-making and predictive capabilities,thereby improving its resilience in complex external environments.Maximizing the potential of SAGIN and ensuring its optimal implementation in terms of deployment,configuration,and design is of paramount importance.To this end,this paper provides a comprehensive overview of the latest advancements in optimizing key performance factors within SAGIN.It also conducts an in-depth analysis of the existing technical bottlenecks and offers insights into potential future research directions.