A multi-agent genetic algorithm with variable neighborhood search for resource investment project scheduling problems

In this paper, the multi-agent genetic algorithm (MAGA) is combined with the variable neighborhood search (VNS) to solve resource investment project scheduling problems (RIPSPs). An agent, coded by a valid activity list and a capacity list, represents a candidate solution to the RIPSPs. All agents live in a lattice-like environment, with each agent fixed on a lattice point. To increase energies, a series of operators, namely crossover, mutation, competition, self-learning and a VNS, are designed. The effectiveness of the algorithm is demonstrated through experiments on Möhring instances, synthetic instances and generated instances of J10, J14 and J20. The tests results are satisfactory.