Performance optimization of annealing salp swarm algorithm: frameworks and applications for engineering design

Abstract

Swarm salp algorithm is a swarm intelligence optimization algorithm enlightened by the movement and foraging behaviors of the salp population. The salp swarm algorithm (SSA) has a simple structure and fast processing speed and can gain significant results on objective functions with fewer local optima. However, it has poor exploration ability and is easy to suffer from the local optimal solutions, so it performs poorly on multimodal objective functions. Besides, its unfair balance of exploration and exploitation is another notable shortcoming. To ameliorate these shortcomings and enhance the algorithm’s performance on multimodal functions, this research proposes simulated annealing (SA) improved salp swarm algorithm (SASSA). SASSA embeds the SA strategy into the followers’ position updating method of SSA, performs a certain number of iterations of the SA strategy, and uses Lévy flight to realize the random walk in the SA strategy. SASSA and 23 original and improved competitive algorithms are compared on 30 IEEE CEC2017 benchmark functions. SASSA ranked first in the Friedman test. Compared with SSA, SASSA can obtain better solutions on 27 benchmark functions. The balance and diversity experiment and analysis of SSA and SASSA are carried out. SASSA’s practicability is verified by solving five engineering problems and the fertilizer effect function problem. Experimental and statistical results reveal that the proposed SASSA has strong competitiveness and outperforms all the competitors. SASSA has excellent exploration ability, suitable for solving composition functions with multiple peaks. Meanwhile, SASSA brings about a good balance of exploration and exploitation and dramatically improves the quality of the solutions.