A multi-modal feature combination mechanism for identification of harmonic load in distribution networks based on artificial intelligence models
The challenge of harmonic pollution in active distribution networks is inherently complex, a data-driven approach being necessitated to comprehensively capture the nonlinear and non-stationary characteristics of harmonic power sequence signals, thereby enhancing recognition accuracy. To achieve inte...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-05-01
|
| Series: | International Journal of Electrical Power & Energy Systems |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0142061525000705 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850219777385037824 |
|---|---|
| author | Renzeng Yang Shuang Peng Gang Yao |
| author_facet | Renzeng Yang Shuang Peng Gang Yao |
| author_sort | Renzeng Yang |
| collection | DOAJ |
| description | The challenge of harmonic pollution in active distribution networks is inherently complex, a data-driven approach being necessitated to comprehensively capture the nonlinear and non-stationary characteristics of harmonic power sequence signals, thereby enhancing recognition accuracy. To achieve intelligent identification of harmonic loads within distribution networks, an innovative methodology that integrates parameter-optimized variational mode decomposition with sequential neural networks is proposed. Firstly, based on IEEE Std. 1459-2010 power theory, the harmonic apparent power distortion caused by nonlinear loads is calculated. Secondly, using an optimization algorithm, the penalty parameter and the number of intrinsic mode functions in variational mode decomposition are fine-tuned to decompose the harmonic power sequence and extract intrinsic mode functions. The most suitable intrinsic mode sequences are selected as input features for sequential neural networks training. Finally, a multi-modal feature tensor combination mechanism that integrates reshaped vector layers into the sequential neural networks architecture is introduced, enabling adaptive extraction of spatial–temporal characteristics and significantly improving the accuracy of harmonic load identification without prior knowledge of their spectral features. |
| format | Article |
| id | doaj-art-8bd8d22d45254302817f91d0e4e759a6 |
| institution | OA Journals |
| issn | 0142-0615 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Electrical Power & Energy Systems |
| spelling | doaj-art-8bd8d22d45254302817f91d0e4e759a62025-08-20T02:07:16ZengElsevierInternational Journal of Electrical Power & Energy Systems0142-06152025-05-0116611051910.1016/j.ijepes.2025.110519A multi-modal feature combination mechanism for identification of harmonic load in distribution networks based on artificial intelligence modelsRenzeng Yang0Shuang Peng1Gang Yao2School of Data Science, Guizhou Institute of Technology, Boshi Road, Gui’an New District, 550025, Guizhou, China; Key Laboratory of Electric Power Big Data of Guizhou Province, Guizhou Institute of Technology, Boshi Road, Gui’an New District, 550025, Guizhou, China; Corresponding author.Key Laboratory of Electric Power Big Data of Guizhou Province, Guizhou Institute of Technology, Boshi Road, Gui’an New District, 550025, Guizhou, China; Electrical Engineering College, Guizhou University, Jiaxiu South Road, Guiyang, 550025, Guizhou, ChinaPower Dispatch Control Center of Guizhou Power Grid Co., Ltd., Jiefang Road, Guiyang, 550002, Guizhou, ChinaThe challenge of harmonic pollution in active distribution networks is inherently complex, a data-driven approach being necessitated to comprehensively capture the nonlinear and non-stationary characteristics of harmonic power sequence signals, thereby enhancing recognition accuracy. To achieve intelligent identification of harmonic loads within distribution networks, an innovative methodology that integrates parameter-optimized variational mode decomposition with sequential neural networks is proposed. Firstly, based on IEEE Std. 1459-2010 power theory, the harmonic apparent power distortion caused by nonlinear loads is calculated. Secondly, using an optimization algorithm, the penalty parameter and the number of intrinsic mode functions in variational mode decomposition are fine-tuned to decompose the harmonic power sequence and extract intrinsic mode functions. The most suitable intrinsic mode sequences are selected as input features for sequential neural networks training. Finally, a multi-modal feature tensor combination mechanism that integrates reshaped vector layers into the sequential neural networks architecture is introduced, enabling adaptive extraction of spatial–temporal characteristics and significantly improving the accuracy of harmonic load identification without prior knowledge of their spectral features.http://www.sciencedirect.com/science/article/pii/S0142061525000705Active distribution networkHarmonic power loadVariational mode decomposition (VMD)Arithmetic optimization algorithm (AOA)Bidirectional long short-term memory (bi-LSTM) |
| spellingShingle | Renzeng Yang Shuang Peng Gang Yao A multi-modal feature combination mechanism for identification of harmonic load in distribution networks based on artificial intelligence models International Journal of Electrical Power & Energy Systems Active distribution network Harmonic power load Variational mode decomposition (VMD) Arithmetic optimization algorithm (AOA) Bidirectional long short-term memory (bi-LSTM) |
| title | A multi-modal feature combination mechanism for identification of harmonic load in distribution networks based on artificial intelligence models |
| title_full | A multi-modal feature combination mechanism for identification of harmonic load in distribution networks based on artificial intelligence models |
| title_fullStr | A multi-modal feature combination mechanism for identification of harmonic load in distribution networks based on artificial intelligence models |
| title_full_unstemmed | A multi-modal feature combination mechanism for identification of harmonic load in distribution networks based on artificial intelligence models |
| title_short | A multi-modal feature combination mechanism for identification of harmonic load in distribution networks based on artificial intelligence models |
| title_sort | multi modal feature combination mechanism for identification of harmonic load in distribution networks based on artificial intelligence models |
| topic | Active distribution network Harmonic power load Variational mode decomposition (VMD) Arithmetic optimization algorithm (AOA) Bidirectional long short-term memory (bi-LSTM) |
| url | http://www.sciencedirect.com/science/article/pii/S0142061525000705 |
| work_keys_str_mv | AT renzengyang amultimodalfeaturecombinationmechanismforidentificationofharmonicloadindistributionnetworksbasedonartificialintelligencemodels AT shuangpeng amultimodalfeaturecombinationmechanismforidentificationofharmonicloadindistributionnetworksbasedonartificialintelligencemodels AT gangyao amultimodalfeaturecombinationmechanismforidentificationofharmonicloadindistributionnetworksbasedonartificialintelligencemodels AT renzengyang multimodalfeaturecombinationmechanismforidentificationofharmonicloadindistributionnetworksbasedonartificialintelligencemodels AT shuangpeng multimodalfeaturecombinationmechanismforidentificationofharmonicloadindistributionnetworksbasedonartificialintelligencemodels AT gangyao multimodalfeaturecombinationmechanismforidentificationofharmonicloadindistributionnetworksbasedonartificialintelligencemodels |