The Research of Improved Wolf Pack Algorithm Based on Differential Evolution

Aiming at the problems of traditional wolf pack algorithm (WPA): easy to fall into local optimal, large computational resource cost and low robustness, an improved wolf pack algorithm based on differential evolution (DIWPA) is proposed. By introducing the search factor for search wolves, maximum number of raid wolves, adaptive siege step size and differential evolution strategy, the proposed algorithm can not only reduce the computational cost but also improve the global search ability. The DIWPA is used to conduct optimization test on 12 benchmark functions and compare to 3 typical optimization algorithms. The test results show that DIWPA has great robustness and global search ability, especially has excellent performance in multi-peak, high-dimension, indivisible functions.