Scheduling with Partial Orders and a Causal Model

Abstract

In an ongoing project at HTC, we are implementing a prototype scheduling system for a NASA domain using the “Time Map Manager” (TMM). TMM representations are flexible enough to permit the representation of precedence constraints, metric constraints between activities, and constraints relative to a variety of references (e.g. Mission Elapsed Time vs. Mission Day). There is also support for a simple form of causal reasoning (projection), dynamic database updates, and monitoring certain database properties as changes occur over time. The greatest apparent advantage to using the TMM is the flexibility added to the scheduling process: schedules are constructed by a process of “iterative refinement,” in which scheduling decisions correspond to constraining an activity either with respect to another activity or with respect to some timeline. The schedule gradually “hardens” as constraints are added. Undoing a decision means removing a constraint, not removing an activity from a specified place on the timeline. For example, we can move an activity around on the timeline by deleting constraints and adding new ones, and other activities constrained with respect to the one we move will move as well (assuming they can, given current constraints).

Assets

BibTeX