Dual-weight decay mechanism and Nelder-Mead simplex boosted RIME algorithm for optimal power flow DOI Creative Commons

Huangying Wu,

Yi Chen, Zhennao Cai

et al.

Journal Of Big Data, Journal Year: 2024, Volume and Issue: 11(1)

Published: Dec. 4, 2024

The increasing demand for electricity presents substantial challenges in power system planning, particularly optimizing the Optimal Power Flow (OPF) problem. OPF problem entails establishing best settings control variables a to reduce objectives such as generating cost and transmission losses while meeting operational restrictions. This research introduces an upgraded RIME optimization algorithm (WDNMRIME) address these challenges. WDNMRIME integrates dual-weight decay mechanism Nelder-Mead simplex (NMs), enhancing population diversity mitigating risk of local optima. Additionally, NMs expedites convergence by refining population's optimal solution set. Experimental validation on IEEE 30-bus test demonstrates that achieves generation $806.00298 per hour reduces total loss from 1.43 MW 1.39 MW. These results surpass performance original algorithm, showcasing 15% improvement speed. effectively optimizes multiple concurrent Flexible Alternating Current Transmission Systems (FACTS) devices, even under uncertain nature wind energy resources modeled using Weibull probability density function. findings highlight WDNMRIME's significant contribution improving dynamic systems.

Language: Английский

A new approach data processing: density-based spatial clustering of applications with noise (DBSCAN) clustering using game-theory DOI

Uranus Kazemi,

Seyfollah Soleimani

Soft Computing, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 15, 2025

Language: Английский

Citations

0
Clipper: An efficient cluster-based data pruning technique for biomedical data to increase the accuracy of machine learning model prediction DOI
Mahmut Burak Karadeniz, Ebru EFEOĞLU,

Burak Çelik

et al.

Egyptian Informatics Journal, Journal Year: 2025, Volume and Issue: 30, P. 100641 - 100641

Published: March 20, 2025

Language: Английский

Citations

0
A Dual-Stage Thermal Runaway Early Warning Strategy for Lithium-Ion Batteries Based on Multi-Domain Acoustic Signal Fusion DOI

Hankun Liu,

Yue Wang, Teng Wang

et al.

Energy, Journal Year: 2025, Volume and Issue: unknown, P. 135748 - 135748

Published: March 1, 2025

Language: Английский

Citations

0
Normalized mean difference (NMD): a novel filter-based feature selection method DOI
Mohammed Mehdi Bouchene, Maryam Fatima

International Journal of Machine Learning and Cybernetics, Journal Year: 2025, Volume and Issue: unknown

Published: April 23, 2025

Language: Английский

Citations

0
Feature Selection in High Dimension Datasets using Incremental Feature Clustering DOI Open Access

Damodar Patel,

Amit Saxena

Indian Journal of Science and Technology, Journal Year: 2024, Volume and Issue: 17(32), P. 3318 - 3326

Published: Aug. 24, 2024

Objectives: To develop a machine learning-based model to select the most important features from high-dimensional dataset classify patterns at high accuracy and reduce their dimensionality. Methods: The proposed feature selection method (FSIFC) forms combines clusters incrementally produces subsets each time. uses K-means clustering Mutual Information (MI) refine process iteratively. Initially, two of are formed using (K=2) by taking as basis instead (a traditional way). From these clusters, with highest MI value in cluster kept subset. Classification accuracies (CA) subset calculated three classifiers namely Support Vector Machines (SVM), Random Forest (RF), k-nearest Neighbor (knn). is repeated incrementing K i.e. number clusters; until maximum user-defined reached. best CA obtained trials recorded corresponding set finally accepted. Findings: demonstrated ten datasets results compared existing published determine method's performance. classified average CAs 92.72%, 93.13%, 91.5%, SVM, RF, K-NN respectively. selects thirty datasets. In terms selecting effective smallest sets, outperforms eight other methods considering CAs. Novelty: applies reduction combined filter an incremental way. This provides improved relevant while removing those which irrelevant different trials. Keywords: Feature selection, High-dimensional datasets, algorithm, information, Machine learning

Language: Английский

Citations

0
Dual-weight decay mechanism and Nelder-Mead simplex boosted RIME algorithm for optimal power flow DOI Creative Commons

Huangying Wu,

Yi Chen, Zhennao Cai

et al.

Journal Of Big Data, Journal Year: 2024, Volume and Issue: 11(1)

Published: Dec. 4, 2024

The increasing demand for electricity presents substantial challenges in power system planning, particularly optimizing the Optimal Power Flow (OPF) problem. OPF problem entails establishing best settings control variables a to reduce objectives such as generating cost and transmission losses while meeting operational restrictions. This research introduces an upgraded RIME optimization algorithm (WDNMRIME) address these challenges. WDNMRIME integrates dual-weight decay mechanism Nelder-Mead simplex (NMs), enhancing population diversity mitigating risk of local optima. Additionally, NMs expedites convergence by refining population's optimal solution set. Experimental validation on IEEE 30-bus test demonstrates that achieves generation $806.00298 per hour reduces total loss from 1.43 MW 1.39 MW. These results surpass performance original algorithm, showcasing 15% improvement speed. effectively optimizes multiple concurrent Flexible Alternating Current Transmission Systems (FACTS) devices, even under uncertain nature wind energy resources modeled using Weibull probability density function. findings highlight WDNMRIME's significant contribution improving dynamic systems.

Language: Английский

Citations

0