An Evolvable Real-time System of Integrated Satellite Scheduling based on Cooperative Neuro Evolution of Augmenting Topologies

Satellite Imaging Scheduling, Satellite Downlinking Scheduling and Ground Resources Scheduling are important components in satellites daily management. Considering the highly interlinking of these three types of scheduling, an Integrated Satellite Scheduling model is formulated and proved NP-complete in this paper. To address the large scale and oversubscription of the Integrated Satellite Scheduling in an actual background, an evolvable real-time system of Integrated Satellite Scheduling is constructed based on Cooperative Neuro Evolution of Augmenting Topologies (C-NEAT). With the help of the C-NEAT, the system learns from historical scheduling data and adaptively assigns each request to the satellite or the ground antenna which is most likely to fulfill this request. Moreover, the real-time scheduling function of the system is actualized by the windowed scheduling framework. Experimental results indicate that the system greatly reduces the problem size of Integrated Satellite Scheduling and improves the scheduling efficiency, where daily and emergent requests are arranged over time.