Multi-swarm hybrid optimization algorithm with prediction strategy for dynamic optimization problems
- DOI
- 10.2991/ifmca-16.2017.68How to use a DOI?
- Keywords
- Dynamic optimization algorithm. Particle swarm optimization. Simulated Annealing. Prediction strategy
- Abstract
It is known that optimization in a changing environment is a challenging task, for which the basic goal is not only to obtain the optimal solution, but also strongly adapting to the environmental changes and tracking the optimal solution as closely as possible. In this paper, a novel multi-swarm optimization algorithm is proposed for solving dynamic optimization problems (DOPs) effectively, which is based on the hybrid of particle swarm optimization (PSO) and Simulated Annealing (SA) with an prediction strategy. Firstly, an multi-swarm strategy is adopted, which simultaneously employs PSO method to conduct global search for exploring promising optimal solutions and adopt SA to conduct local search. Secondly, a new forecasting model is developed by using the principle that the previous optimum locations can predict the optimum's location in the changing environment, which can improve the performance of the algorithm in dynamic environment. Then, a diversity preservation mechanism is incorporated into our method to obtain more robust results. Experiments are conducted on the set of benchmark functions used in CEC 2009 competition for DOPs, and the results show that the proposed algorithm achieves good performance and outperforms others in solving DOPs with the model changed by following some pattern.
- Copyright
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Wenbo Nie AU - Lihong Xu PY - 2017/03 DA - 2017/03 TI - Multi-swarm hybrid optimization algorithm with prediction strategy for dynamic optimization problems BT - Proceedings of the 2016 International Forum on Mechanical, Control and Automation (IFMCA 2016) PB - Atlantis Press SP - 437 EP - 446 SN - 2352-5401 UR - https://doi.org/10.2991/ifmca-16.2017.68 DO - 10.2991/ifmca-16.2017.68 ID - Nie2017/03 ER -