Reactive Power Optimization Configuration Strategy for Power Systems based on the Fusion Algorithm of Deep Learning and Particle Swarm Optimization
Abstract
optimization (PSO) is proposed. Extracting key features of the power system through deep neural networks and combining them with PSO algorithm for global optimization can effectively solve the problem of traditional methods easily falling into local optima in large-scale complex
power grids. The experimental results show that the proposed method can significantly reduce system power loss in IEEE 30 node systems,
with better optimization performance than traditional algorithms and higher convergence speed. This strategy provides new ideas and methods
for reactive power optimization in power systems.
Keywords
Full Text:
PDFReferences
[1] Yang Jing, Zhao Jinman, Meng Runquan, etc Power system operation state identification based on particle swarm optimization and convolutional neural network [J]. Power grid technology, 2024, 48(1):315-324.
[2] Xia Peng, Zhang Qian, Wang Qunjing, etc Reactive power optimization based on random matrix theory and improved particle swarm
optimization deep belief network [J]. Science, Technology and Engineering, 2021, 21(33):8.
[3] Zhao Jingjing, Jia Ran, Chen Linghan, etc Research on Fast Zoning of Reactive Power and Voltage in Power Grid Based on Deep Learning and Improved K-means Clustering Algorithm [J]. Power System Protection and Control, 2021, 49(14):7.
[4] Martin, Shen Chen, Chen Ying, etc Feasibility study on the application of deep learning in power flow calculation and convergence
problem [J]. Southern Power Grid Technology, 2020, 14(2):9.
[5] Pan Sirong, Liu Youbo, Tang Zhiyuan, etc Evolutionary Algorithm for Voltage and Reactive Power Control in Active Distribution Networks with Deep Learning Agent Model [J]. Power System Protection and Control, 2022, 50(17):97-106.
[6] Liu Haifeng, Lu Yilei, Dai Ximing Research on Particle Swarm Optimization Algorithm and Sensitivity Analysis in Reactive Power Optimization of Power System [J]. Hebei Electric Power Technology, 2020, 39(2):4.
[7] Wu Xiaofeng, Zhong Weikun, Zhang Cheng, etc Research on Reactive Power Optimization of Power System Based on Adaptive Fuzzy
Particle Swarm Optimization Algorithm [J]. Shaanxi Electric Power, 2022(8).
[8] Ma Fanfan Research on Reactive Power Optimization of Power Systems Based on Intelligent Algorithms [C]//Proceedings of the National Green Digital Intelligent Power Equipment Technology Innovation Achievement Exhibition (VI). 2024
[9] Zhao Didi, Wang Mengdi Application of Particle Swarm Optimization Algorithm in Reactive Power Optimization of Power System [J].
Information Technology and Informatization, 2021, 000(009):246-248.
[10] Wang Lin, Ma Cheng Reactive Power Optimization of Power Systems Based on Improved Attraction Exclusion Particle Swarm Optimization Algorithm with Disturbance [J]. Journal of Heilongjiang University of Engineering, 2020, 34 (2): 5
DOI: http://dx.doi.org/10.70711/aitr.v2i8.6641
Refbacks
- There are currently no refbacks.
