Multi-population artificial bee colony algorithm for many-objective cascade reservoir scheduling

Abstract

Artificial bee colony (ABC) is a popular intelligent algorithm that is widely applied to many optimization problems. However, it is challenging for ABC to solve many-objective optimization problems (MaOPs). To tackle this issue, this article proposes a many-objective ABC based on multi-population (called MMaOABC) for MaOPs. In MMaOABC, the population is divided into multiple sub-populations, and each sub-population optimizes one objective. Three search strategies are constructed based on multiple sub-populations to improve convergence and diversity. In the employed bee stage, some excellent solutions in multiple sub-populations are used to guide the convergence. In the onlooker bee stage, new selection probabilities based on diversity metrics are designed to enhance the diversity. Dimensional learning is introduced in the scout bee stage to avoid falling into local minimum. In addition, environmental selection and external archives are utilized for communications among sub-populations. To validate the performance of MMaOABC, two benchmark sets (DTLZ and MaF) with 3, 5, 8, and 15 objectives are tested. Computational results show that MMaOABC is competitive when compared with seven other many-objective evolutionary algorithms (MaOEAs). Finally, MMaOABC is applied to many-objective cascade reservoir scheduling. Simulation results show that MMaOABC still obtains promising performance.