A reactive model based on neighborhood consensus for continuous optimization. (1st May 2019)

• Record Type: Journal Article
• Authors: Gálvez, Jorge; Cuevas, Erik; Hinojosa, Salvador; Avalos, Omar; Pérez-Cisneros, Marco
• Is Part Of: Expert systems with applications. Volume 121(2019)
• Page Start: 115
• Page End: 141
• Publication Date: 2019-05-01
• Subjects: Multi-agent systems -- Reactive response -- Meta-heuristic -- Optimization; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2018.12.018
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: The proposed algorithm considers a double pair of evolutionary operators. The proposed approach uses local consensus formulations with reactive responses. The proposed method guarantees leaderless movement decisions. The proposed algorithm outperforms several evolutionary methods. Abstract: Evolutionary Computation (EC) algorithms have been proposed as stochastic methods to solve complex optimization problems. The design of EC methods typically involves the construction of empirical operators based on abstractions of animal behaviors or physical and biological phenomena. Through its operators, every EC approach proposes a particular solution to the exploration-exploitation balance which is currently considered an unsolved problem within EC literature. On the other hand, multi-agent systems have been utilized as intelligent, cooperative and self-organized structures where the synergy of simple rules creates complex interactions among agents. In this paper, a novel EC algorithm called Neighborhood-based Consensus for Continuous Optimization (NCCO) is presented. NCCO is based on typical processes present in multi-agent systems, such as local consensus formulations and reactive responses. These operations are conducted by using appropriate operators that are applied in each evolutionary stage. A traditional EC algorithm considers in its operation the application of every operator without examining its final impact in the searching process. In contrast to other EC techniques, the proposed method uses additional operators to avoid the undesirable effects produced by the over-exploitation or suboptimal exploration of conventional operations. In order to illustrate the performance and accuracy of the proposed NCCO approach, it is compared to several well-known, state-of-the-art algorithms over a set of benchmark functions and real-world design applications. The experimental results demonstrate that NCCO's performance is superior to the test algorithms.