User Preference Optimization for Oversubscribed Scheduling of NASA's Deep Space Network

User Preference Optimization for Oversubscribed Scheduling of NASA's Deep Space Network. Johnston, M. D. In 11th International Workshop on Planning and Scheduling for Space (IWPSS), pages 86–92, Berkeley, California, USA, July, 2019.

Paper abstract bibtex 19 downloads

NASA's Deep Space Network (DSN) is the primary resource for communications and navigation for interplanetary space missions, for both NASA and partner agencies. With three complexes spread roughly evenly around the globe, the DSN provides services to dozens of active missions. Growth in mission demand, both in number of spacecraft and in data return, has led to increased loading levels on the network, and projected demand has exceeded network capacity for quite some time. The DSN scheduling process involves peer-to-peer collaborative negotiation, which consumes significant time and resources in order to reach a baseline version of the schedule, and then to manage and agree to changes. The delays inherent in this process are exacerbated by the high level of oversubscription experienced by the DSN: it is not unusual for the scheduling process to start with 20-40% more requested time can be accommodated on the available antennas. The other NASA networks make use of a static priority list to address a similar problem: missions are ranked in priority order, and the schedule is populated by priority from highest to lowest. Such a mechanism would not work for DSN due to the heterogeneity of the mission set, and to the time-varying mission requirements with mission phase. This paper reports on a new paradigm for DSN scheduling that addresses the key problems inherent in the current process. The main characteristics of the new approach are to use loading-based limits on requested time, and user preferences as the basis for optimization criteria.

@inproceedings{johnston_iwpss2019_userprefopt,
	title        = {User Preference Optimization for Oversubscribed Scheduling of NASA's Deep Space Network},
	author       = {Mark D. Johnston},
	year         = 2019,
	month        = {July},
	booktitle    = {11th International Workshop on Planning and Scheduling for Space (IWPSS)},
	address      = {Berkeley, California, USA},
	pages        = {86--92},
	url          = {https://ai.jpl.nasa.gov/public/papers/johnston-iwpss2019-userprefopt.pdf},
	abstract     = {NASA's Deep Space Network (DSN) is the primary resource for communications and navigation for interplanetary space missions, for both NASA and partner agencies. With three complexes spread roughly evenly around the globe, the DSN provides services to dozens of active missions. Growth in mission demand, both in number of spacecraft and in data return, has led to increased loading levels on the network, and projected demand has exceeded network capacity for quite some time. The DSN scheduling process involves peer-to-peer collaborative negotiation, which consumes significant time and resources in order to reach a baseline version of the schedule, and then to manage and agree to changes. The delays inherent in this process are exacerbated by the high level of oversubscription experienced by the DSN: it is not unusual for the scheduling process to start with 20-40\% more requested time can be accommodated on the available antennas. The other NASA networks make use of a static priority list to address a similar problem: missions are ranked in priority order, and the schedule is populated by priority from highest to lowest. Such a mechanism would not work for DSN due to the heterogeneity of the mission set, and to the time-varying mission requirements with mission phase. This paper reports on a new paradigm for DSN scheduling that addresses the key problems inherent in the current process. The main characteristics of the new approach are to use loading-based limits on requested time, and user preferences as the basis for optimization criteria.},
	clearance    = {CL\#19-3416},
	project      = {SSS}
}

Downloads: 19