Deep Space Network Scheduling Using Evolutionary Computational Methods

The deep space network (DSN) is an international network of antennas that supports all of NASA's deep space missions. With the increasing demand of tracking time, DSN is highly over-subscribed. Therefore, the allocation of the DSN resources should be optimally scheduled to satisfy the requirements of as many missions as possible. Currently, the DSN schedules are manually and iteratively generated through several meetings to resolve conflicts. In an attempt to ease the burden of the DSN scheduling task, we have applied evolutionary computational techniques to the DSN scheduling problem. These methods provide a decision support system by automatically generating a population of optimized schedules under varying conflict conditions. These schedules are used to decide the simplest path to resolve conflicts as new scheduled items are added or changed along the scheduled 26 weeks. This paper presents the specific approach taken to formulate the problem in terms of gene encoding, fitness function, and genetic operations. The genome is encoded such that a subset of the scheduling constraints is automatically satisfied. Several fitness functions are formulated to emphasize different aspects of the scheduling problem. The optimal solutions of the different fitness functions demonstrate the trade-off of the scheduling problem and provide insight into a conflict resolution process.