An Incomplete Constraint-Based System for Scheduling with Renewable Resources

In this paper, we introduce a new framework for managing several kinds of renewable resources, including disjunctive resources, cumulative resources, and resources with setup times. In this framework, we use a list scheduling approach in which a priority order between activities must be determined to solve resource usage conflicts. In this context, we define a new differentiable constraint-based local search invariant which transforms a priority order into a full schedule and which incrementally maintains this schedule in case of change in the order. On top of that, we use multiple neighborhoods and search strategies, and we get new best upper bounds on several scheduling benchmarks.