Evolutionary Scheduler for the Deep Space Network

A computer program assists human schedulers in satisfying, to the maximum extent possible, competing demands from multiple spacecraft missions for utilization of the transmitting/receiving Earth stations of NASA’s Deep Space Network. The program embodies a concept of optimal scheduling to attain multiple objectives in the presence of multiple constraints. Optimization of schedules is performed through a selection-and-reproduction process inspired by a biological evolution process. A genome (a representation of design parameters in a genetic algorithm) is encoded such that a subset of the scheduling constraints (e.g., the times when a given spacecraft lies within the field of view of a given antenna) are automatically satisfied. Several fitness functions are formulated to emphasize different aspects of the scheduling problem, and multi-fitness functions are optimized simultaneously by use of multi-objective optimization algorithms.

The output of the program consists of a population of Pareto-optimal schedules that demonstrate the compromises made in solving the scheduling problem and provide insight into a conflict resolution process. These schedules are used by human schedulers to choose the simplest paths to resolution of conflicts as items on schedules are changed and as new items are added to schedules.

This program was written by Alexandre Guillaume, Seungwon Lee, Yeou-Fang Wang, Hua Zheng, Savio Chau, Yu-Wen Tung, Richard J. Terrile, and Robert Hovden of Caltech for NASA’s Jet Propulsion Laboratory. For more information, contact This e-mail address is being protected from spambots. You need JavaScript enabled to view it .

This software is available for commercial licensing. Please contact Daniel Broderick of the California Institute of Technology at This e-mail address is being protected from spambots. You need JavaScript enabled to view it . Refer to NPO-44821.