Active Distribution Network Reconfiguration Method Based on Photovoltaic Generation Prediction

He Ming; Ma Chunyan; Duan Qing; Ni Shan; Deng Wenwen; Liu Xinyan; Li Zhenyi; Chen Yin; Shi Yong

doi:10.1109/EEBDA53927.2022.9744887

Active Distribution Network Reconfiguration Method Based on Photovoltaic Generation Prediction

He Ming, Ma Chunyan, Duan Qing, Ni Shan, Deng Wenwen, Liu Xinyan, Li Zhenyi, Chen Yin, Shi Yong

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Network reconfiguration is an important method to optimize the operation of the active distribution system. It can achieve the goal of reducing network loss and improving power quality by changing the state of network switch without requiring additional equipment investment. The randomness of photovoltaic power generation makes the network reconfiguration of the distribution network need to consider the characteristics of photovoltaic power generation for dynamic optimization. In this paper, a photovoltaic power generation prediction method based on the combination of similar day BP neural network is proposed. The dynamic reconfiguration of distribution network is carried out with the minimum network loss and minimum voltage offset as the objective function, which is optimized by genetic algorithm. Finally, the effectiveness of the proposed model is verified by taking the improved IEEE 33 bus system as an example.

Original language	English
Title of host publication	2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	82-87
Number of pages	6
ISBN (Electronic)	9781665416061
DOIs	https://doi.org/10.1109/EEBDA53927.2022.9744887
State	Published - 2022
Externally published	Yes
Event	2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022 - Changchun, China Duration: 25 Feb 2022 → 27 Feb 2022

Publication series

Name	2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022

Conference

Conference	2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022
Country/Territory	China
City	Changchun
Period	25/02/22 → 27/02/22

Keywords

Active distribution network
Genetic algorithm
Network reconfiguration
Photovoltaic power generation forecast

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/EEBDA53927.2022.9744887

Cite this

Ming, H., Chunyan, M., Qing, D., Shan, N., Wenwen, D., Xinyan, L., Zhenyi, L., Yin, C., & Yong, S. (2022). Active Distribution Network Reconfiguration Method Based on Photovoltaic Generation Prediction. In 2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022 (pp. 82-87). (2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EEBDA53927.2022.9744887

Ming, He ; Chunyan, Ma ; Qing, Duan et al. / Active Distribution Network Reconfiguration Method Based on Photovoltaic Generation Prediction. 2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 82-87 (2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022).

@inproceedings{626b181fbe244a07aee448ea3fbc0f01,

title = "Active Distribution Network Reconfiguration Method Based on Photovoltaic Generation Prediction",

abstract = "Network reconfiguration is an important method to optimize the operation of the active distribution system. It can achieve the goal of reducing network loss and improving power quality by changing the state of network switch without requiring additional equipment investment. The randomness of photovoltaic power generation makes the network reconfiguration of the distribution network need to consider the characteristics of photovoltaic power generation for dynamic optimization. In this paper, a photovoltaic power generation prediction method based on the combination of similar day BP neural network is proposed. The dynamic reconfiguration of distribution network is carried out with the minimum network loss and minimum voltage offset as the objective function, which is optimized by genetic algorithm. Finally, the effectiveness of the proposed model is verified by taking the improved IEEE 33 bus system as an example.",

keywords = "Active distribution network, Genetic algorithm, Network reconfiguration, Photovoltaic power generation forecast",

author = "He Ming and Ma Chunyan and Duan Qing and Ni Shan and Deng Wenwen and Liu Xinyan and Li Zhenyi and Chen Yin and Shi Yong",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022 ; Conference date: 25-02-2022 Through 27-02-2022",

year = "2022",

doi = "10.1109/EEBDA53927.2022.9744887",

language = "英语",

series = "2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "82--87",

booktitle = "2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022",

}

Ming, H, Chunyan, M, Qing, D, Shan, N, Wenwen, D, Xinyan, L, Zhenyi, L, Yin, C & Yong, S 2022, Active Distribution Network Reconfiguration Method Based on Photovoltaic Generation Prediction. in 2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022. 2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022, Institute of Electrical and Electronics Engineers Inc., pp. 82-87, 2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022, Changchun, China, 25/02/22. https://doi.org/10.1109/EEBDA53927.2022.9744887

Active Distribution Network Reconfiguration Method Based on Photovoltaic Generation Prediction. / Ming, He; Chunyan, Ma; Qing, Duan et al.
2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 82-87 (2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Active Distribution Network Reconfiguration Method Based on Photovoltaic Generation Prediction

AU - Ming, He

AU - Chunyan, Ma

AU - Qing, Duan

AU - Shan, Ni

AU - Wenwen, Deng

AU - Xinyan, Liu

AU - Zhenyi, Li

AU - Yin, Chen

AU - Yong, Shi

PY - 2022

Y1 - 2022

N2 - Network reconfiguration is an important method to optimize the operation of the active distribution system. It can achieve the goal of reducing network loss and improving power quality by changing the state of network switch without requiring additional equipment investment. The randomness of photovoltaic power generation makes the network reconfiguration of the distribution network need to consider the characteristics of photovoltaic power generation for dynamic optimization. In this paper, a photovoltaic power generation prediction method based on the combination of similar day BP neural network is proposed. The dynamic reconfiguration of distribution network is carried out with the minimum network loss and minimum voltage offset as the objective function, which is optimized by genetic algorithm. Finally, the effectiveness of the proposed model is verified by taking the improved IEEE 33 bus system as an example.

AB - Network reconfiguration is an important method to optimize the operation of the active distribution system. It can achieve the goal of reducing network loss and improving power quality by changing the state of network switch without requiring additional equipment investment. The randomness of photovoltaic power generation makes the network reconfiguration of the distribution network need to consider the characteristics of photovoltaic power generation for dynamic optimization. In this paper, a photovoltaic power generation prediction method based on the combination of similar day BP neural network is proposed. The dynamic reconfiguration of distribution network is carried out with the minimum network loss and minimum voltage offset as the objective function, which is optimized by genetic algorithm. Finally, the effectiveness of the proposed model is verified by taking the improved IEEE 33 bus system as an example.

KW - Active distribution network

KW - Genetic algorithm

KW - Network reconfiguration

KW - Photovoltaic power generation forecast

UR - http://www.scopus.com/inward/record.url?scp=85128664766&partnerID=8YFLogxK

U2 - 10.1109/EEBDA53927.2022.9744887

DO - 10.1109/EEBDA53927.2022.9744887

M3 - 会议稿件

AN - SCOPUS:85128664766

T3 - 2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022

SP - 82

EP - 87

BT - 2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022

Y2 - 25 February 2022 through 27 February 2022

ER -

Ming H, Chunyan M, Qing D, Shan N, Wenwen D, Xinyan L et al. Active Distribution Network Reconfiguration Method Based on Photovoltaic Generation Prediction. In 2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 82-87. (2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2022). doi: 10.1109/EEBDA53927.2022.9744887

Active Distribution Network Reconfiguration Method Based on Photovoltaic Generation Prediction

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this