DRSC-MOAGDE

版本 1.0.2 (24.7 KB) 作者: Mustafa AKBEL
A Clustering-Based Archive Handling Method and Multi-objective Optimization of the Optimal Power Flow Problem
0.0
(0)
24.0 次下载
更新时间 2024/8/18

查看许可证

A Clustering-Based Archive Handling Method and Multi-objective Optimization of the Optimal Power Flow Problem
Abstract
The main challenge in finding the optimal Pareto Front (PF) and Pareto Set (PS) sets for multimodal multi-objective optimization problems (MMOPs) with conflicting objective functions is to exhibit a balanced and sustainable diversity and exploitation capability in both the objective and decision spaces. This paper introduces dynamic reference spaces based clustering (DRSC) as a new archive handling method to overcome this challenge. DRSC incorporates a niche method called dynamically switched reference spaces and adapts the K-means-based method for clustering non-dominant vectors and handling the archive. The performance of the proposed DRSC is tested on twenty-four benchmark problems. According to the results of non-parametric statistical analysis using data from four different performance metrics, DRSC-MOAGDE designed using the proposed archiving mechanism managed to achieve the best Friedman rank among thirty different competitors. According to the stability analysis results, the average success rates and average computation times of the three best performing algorithms DRSC-MOAGDE, MMODE-ICD and SSMOPSO are (88.69%, 3.01 s), (66.87%, 9.47 s) and (64.29%, 1372.49 s), respectively. It is also observed that the proposed DRSC-MOAGDE outperforms the best cost optimization values in the literature with a minimum of 0.1838 $/h and a maximum of 30.9157 $/h for the multi-objective OPF real-world problem.

引用格式

Akbel, M., Kahraman, H. T., Duman, S., Temel, S. (2024). A clustering‑based archive handling method and multi‑objective optimization of the optimal power flow problem. Applied Intelligence, https://doi.org/10.1007/s10489-024-05714-5.

MATLAB 版本兼容性
创建方式 R2024a
兼容任何版本
平台兼容性
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

版本 已发布 发行说明
1.0.2

Abstract added
1.0.1

Description changed
1.0.0