Time-based Dynamic Controllability of Disjunctive Temporal Networks with Uncertainty: A Tree Search Approach with Graph Neural Network Guidance

TL;DR

This paper introduces a new time-based controllability concept for disjunctive temporal networks with uncertainty, employing a tree search guided by graph neural networks to improve scheduling under uncertainty.

Contribution

It proposes a stronger form of controllability (TDC) for DTNUs and integrates a message passing neural network to enhance tree search efficiency and scalability.

Findings

Tree search outperforms state-of-the-art timed-game automata methods.

Using MPNN guidance significantly improves solving performance.

Method scales better to complex DTNU problems.

Abstract

Scheduling in the presence of uncertainty is an area of interest in artificial intelligence due to the large number of applications. We study the problem of dynamic controllability (DC) of disjunctive temporal networks with uncertainty (DTNU), which seeks a strategy to satisfy all constraints in response to uncontrollable action durations. We introduce a more restricted, stronger form of controllability than DC for DTNUs, time-based dynamic controllability (TDC), and present a tree search approach to determine whether or not a DTNU is TDC. Moreover, we leverage the learning capability of a message passing neural network (MPNN) as a heuristic for tree search guidance. Finally, we conduct experiments for which the tree search shows superior results to state-of-the-art timed-game automata (TGA) based approaches. We observe that using an MPNN for tree search guidance leads to a significant increase in solving performance and scalability to harder DTNU problems.