Parallelized Multiple Swarm Artificial Bee Colony Algorithm (MS-ABC) for Global Optimization

Abstract

Swarm intelligence metaheuristics have been successfully used for hard optimization problems. After the initial introduction phase such algorithms are further improved by modifications and hybridizations. Parallelization is usually introduced for performance improvement and better resources utilization. In this paper we present an improved parallelized artificial bee colony (ABC) algorithm with multiple swarm inter-communication and learning that not only significantly improves computational time, but also improves the results. Proposed algorithm was tested on large set of standard benchmark functions and it outperformed the state-of-art ABC algorithm.

Firefly algorithm for multi-objective RFID network planning problem

“…There are many swarm intelligence algorithms that have been successfully applied to different optimization tasks, such as ant colony optimization (ACO) [5], [6], [7], artificial bee colony (ABC) algorithm [8], [9], [10] etc. There are also many hybridized approaches [11], [12], [13], [14].…”

Gri Kurt Optimizasyon Algoritmasına Dayanan Çok Seviyeli İmge Eşik Seçimi

“…Meta-sezgisel algoritmaların orijinal versiyonları, çözüm kalitesini artırmak için modifiye edilir veya melezleştirilir. En yaygın doğadan esinlenen algoritmalar, parçacık sürü optimizasyonu (PSO) [18], diferansiyel evrim (DE) [19], ateşböceği algoritması (FA) [20], [21], guguk kuşu arama (CS) [22], karınca koloni optimizasyonu [23][24][25][26], yapay arı koloni algoritması [27][28][29][30], yarasa algoritması (BA) [31], ağaç tohum algoritması [32] …”

Upgraded Firefly Algorithm for Portfolio Optimization Problem

“…Artificial bee colony (ABC) was inspired by foraging behavior of honey bee swarm. This metaheuristic was successfully applied to portfolio optimization [8], [9] and other constrained problems [10], [11]. Social behavior of Antarctic krills was inspiration for emergence of krill herd (KH) algorithm [12] which was also applied to portfolio problem [13].…”