An Improved Artificial Bee Colony Algorithm Based on k-means Clustering

The Artificial Bee Colony (ABC) algorithm is a simple and efficient optimization method with few control parameters and robust global search capabilities. It performs well in solving complex optimization problems but has weak local search abilities and a tendency to fall into local optima. To address these issues, we propose an improved Artificial Bee Colony algorithm based on k-means clustering (IKABC). The IKABC algorithm enhances local search and convergence abilities by utilizing k-means clustering to divide the population and optimize the search process. Additionally, a search strategy that balances global optimization and local search is introduced, alongside an improved roulette wheel selection strategy, to make nectar source searches more directional and to balance the algorithm's exploration and exploitation capabilities. Finally, the IKABC algorithm is compared through simulations with other enhanced ABC algorithms using 12 benchmark test functions, demonstrating its superior performance in solving complex optimization problems.