Self-Organizing Migrating Algorithm Team To Team Adaptive - SOMA T3A

Swarm intelligence algorithm and its variants are constantly evolving over the years, the SOMA algorithm is also not out of that trend. In this paper, we propose a novel strategy of SOMA, called SOMA T3A. The proposed algorithm is divided into three main processes, namely Organization, Migration, an...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2019 IEEE Congress on Evolutionary Computation (CEC) s. 1182 - 1187
Hlavní autor: Diep, Quoc Bao
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2019
Témata:
Approximation algorithms
Benchmark testing
Optimization
Organizations
Particle swarm optimization
Self-organizing migrating algorithm
single objective optimization
Sociology
Statistics
swarm intelligence
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Swarm intelligence algorithm and its variants are constantly evolving over the years, the SOMA algorithm is also not out of that trend. In this paper, we propose a novel strategy of SOMA, called SOMA T3A. The proposed algorithm is divided into three main processes, namely Organization, Migration, and Update. Migrants are selected from the initial population and migrate towards the selected Leader according to the organization process. The Step and PRT parameters are no longer fixed like in the original version; instead, they are adapted through each migration loop. The performance of the algorithm is proven on the 58 well-known benchmark problems from the CEC2013 as well as CEC2017 benchmark suites. The results are compared with the SOMA family and compared with the state-of-the-art algorithms to show its promising performance.
DOI:10.1109/CEC.2019.8790202