An intensified sparrow search algorithm for solving optimization problems

• Published in: Journal of ambient intelligence and humanized computing Vol. 14; no. 7; pp. 9173 - 9189
• Main Authors: Xue, Jiankai, Shen, Bo, Pan, Anqi
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.07.2023; Springer Nature B.V
• Subjects: Artificial Intelligence; Basic converters; Computational Intelligence; Design engineering; Engineering; Iterative methods; Neural networks; Optimization; Optimization algorithms; Original Research; Pressure vessel design; Pressure vessels; Robotics and Automation; Root-mean-square errors; Search algorithms; Search methods; Solution space; Swarm intelligence; User Interfaces and Human Computer Interaction; Long short-term memory network; Swarm intelligence; Sparrow search algorithm; Short-term load forecasting; Neighbor search strategy
• ISSN: 1868-5137; 1868-5145
• DOI: 10.1007/s12652-022-04420-9

In this paper, a novel swarm intelligence optimization algorithm is presented based on the sparrow search algorithm, namely, an intensified sparrow search algorithm (ISSA). Specifically, the newly proposed neighbor search strategy takes into account both exploring the entire feasible solution space as much as possible in the iterative process and effectively preventing the weakening of exploration ability in the late iteration. In addition, a new foraging method called the saltation learning strategy is put forward to improve the search capability of the scrounger. Firstly, the effectiveness of the ISSA is comprehensively evaluated by competition functions, known as CEC-BC-2017. The simulation results show that the ISSA substantially improves the convergence accuracy of the basic SSA and also outperforms three SSA-based variants and six state-of-art optimization algorithms. Then, to further demonstrate the real-world application potential, the ISSA is successfully used in two engineering design problems (including the pressure vessel and the welded beam designs). Finally, the proposed ISSA is employed to optimize the hyper-parameters of the long short-term memory (LSTM) network, which leads to a novel ISSA-LSTM model. The developed ISSA-LSTM model is applied to the short-term load forecasting of the power system. The experimental results show that the mean absolute percentile error (MAPE), root mean square error (RMSE) and mean absolute error (MAE) values of the proposed ISSA-LSTM model are 1.2778%, 1.2171 and 0.9267 respectively, which is superior to several LSTM-based variants.