IEEE Transactions on Evolutionary Computation · 2002 · 93 citations · 25 references
ManagementIndustrial EngineeringProject ManagementOptimizationProject SchedulingSchedulingCombinatorial OptimizationGenetic AlgorithmsHeuristic OptimizationHeuristic SearchMetaheuristic OptimizationResource-constrained SchedulingAnt Colony OptimizationHeuristic AlgorithmsHeuristicsMetaheuristic SchedulingResource-constrained Project SchedulingScheduling HeuristicsTabu Search
The study introduces an ant colony optimization method for the resource‑constrained project scheduling problem. The algorithm combines two pheromone evaluation strategies, adapts heuristic influence during runs, and allows an elitist ant to forget the best solution, and is evaluated on large Project Scheduling Library benchmarks. It outperforms genetic algorithms, simulated annealing, tabu search, and sampling methods on average and discovers new best solutions for about a third of the benchmark problems.
An ant colony optimization (ACO) approach for the resource-constrained project scheduling problem (RCPSP) is presented. Several new features that are interesting for ACO in general are proposed and evaluated. In particular, the use of a combination of two pheromone evaluation methods by the ants to find new solutions, a change of the influence of the heuristic on the decisions of the ants during the run of the algorithm, and the option that an elitist ant forgets the best-found solution are studied. We tested the ACO algorithm on a set of large benchmark problems from the Project Scheduling Library. Compared to several other heuristics for the RCPSP, including genetic algorithms, simulated annealing, tabu search, and different sampling methods, our algorithm performed best on average. For nearly one-third of all benchmark problems, which were not known to be solved optimally before, the algorithm was able to find new best solutions.
25