A Backbone Whale Optimization Algorithm Based on Cross-stage Evolution

The swarm intelligent algorithms (SIs) are effective and widely used, while the balance between exploitation and exploration directly affects the accuracy and efficiency of algorithms. To cope with this issue, a backbone whale optimization algorithm based on cross-stage evolution (BWOACS) is proposed. BWOACS is mainly composed of three parts: (1) adopts the density peak clustering (DPC) method to actively divide the population into several sub-populations, generates the backbone representatives (BR) during backbone construction stage; (2) determines the deviation placement (DP) by constructing the co-evolution operators (CE), the search space expansion operators (SE) and the guided transfer operators (GT) during bionic evolution strategy stage; (3) realises the bionic optimisation through DP during backbone representatives guiding co-evolution stage. To verify the accuracy and performance of BWOACS, we compare BWOACS with other variants on 9 IEEE CEC 2017 benchmark problems. Experimental results indicate that BWOACS has better accuracy and convergence speed than other algorithms.