Novel fruit fly algorithm for global optimisation and its application to short-term wind forecasting. Issue 3 (3rd July 2019)

• Record Type: Journal Article
• Authors: Chen, Yang; Pi, DeChang
• Is Part Of: Connection science. Volume 31:Issue 3(2019)
• Page Start: 244
• Page End: 266
• Publication Date: 2019-07-03
• Subjects: Fruit fly optimisation algorithm -- evolutionary computation -- premature convergence -- function optimisation -- wind forecasting; Neural computers -- Periodicals; Artificial intelligence -- Periodicals; Cognitive science -- Periodicals; Connectionism -- Periodicals; 006.3
• DOI: 10.1080/09540091.2019.1573419
• Languages: English
• ISSNs: 0954-0091

Abstract

ABSTRACT: Fruit fly optimisation algorithm is a new swarm intelligence algorithm, which is simple and efficient. However, it is easy to get premature convergence in solving high-dimensional complex continuous functions. In order to overcome the shortcoming and improve the precision of solution, we propose a new fruit fly optimisation algorithm (SEDMFOA) based on spatial expansion and dynamic mutation. It is featured with changing the original constant step size to a focused search method, and embedding the dynamic mutation strategy in the evolution of the algorithm. Furthermore, we employed gauss mapping operation on the best individual to generate new individuals to substitute for those trans-boundary individuals. Finally, the inverse solution to expand the space was designed to develop the durative search ability in the later stage of the algorithm. According to the experimental results of eighteen well-known benchmark functions, the SEDMFOA is efficient and effective. The precision and stability of the approximate solution of SEDMFOA are superior the algorithms proposed in some related literatures. In wind energy research, the new algorithm is applied to optimise extreme learning machines for short-term wind forecasting. Simulation results show that SEDMFOA has better prediction effect than traditional algorithms.