An Extensible Gradient-Based Optimization Method for Parameter Identification in Power Distribution Network
Accurate parameter identification of power distribution network (PDN) has attracted remarkable attention recently. However, power device parameters usually show an instability attributed to both the operating status and manual entry. Therefore, it is urgent to develop reliable algorithms for identif...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-01-01
|
| Series: | International Transactions on Electrical Energy Systems |
| Online Access: | http://dx.doi.org/10.1155/2023/4082305 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850229256921022464 |
|---|---|
| author | Chuanjun Wang Kehao Fei Xinle Xu Haoran Chen Ke Hu Shihe Xu Jiayang Ma |
| author_facet | Chuanjun Wang Kehao Fei Xinle Xu Haoran Chen Ke Hu Shihe Xu Jiayang Ma |
| author_sort | Chuanjun Wang |
| collection | DOAJ |
| description | Accurate parameter identification of power distribution network (PDN) has attracted remarkable attention recently. However, power device parameters usually show an instability attributed to both the operating status and manual entry. Therefore, it is urgent to develop reliable algorithms for identifying PDN parameters with both high accuracy and high efficiency. Most of the existing algorithms are gradient-free and based on the heuristic schemes, resulting in an unstable numerical calculation. Herein, based on our previous work about the adaptive gradient-based optimization (AGBO) method, we propose an extensive version, namely, AGBO-Pro model. In this method, both the numerical and categorical features of experimental observations are utilized and incorporated with each via a weighted average. By comparing the proposed method with several heuristic algorithms, it is found that the errors in RMSE, MAE, and MAPE criteria via AGBO-Pro are all about 2 times lower with a much faster and more stable convergence of the loss function. By further taking a linear transformation of the loss function, the AGBO-Pro model achieves a more robust performance with a much lower variance in repeat numerical calculations. This work shows great potential in possible extension of gradient-based optimization methods for parameter identification in PDN. |
| format | Article |
| id | doaj-art-28671dc2dfde40849b42c5c80f4a7284 |
| institution | OA Journals |
| issn | 2050-7038 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Transactions on Electrical Energy Systems |
| spelling | doaj-art-28671dc2dfde40849b42c5c80f4a72842025-08-20T02:04:18ZengWileyInternational Transactions on Electrical Energy Systems2050-70382023-01-01202310.1155/2023/4082305An Extensible Gradient-Based Optimization Method for Parameter Identification in Power Distribution NetworkChuanjun Wang0Kehao Fei1Xinle Xu2Haoran Chen3Ke Hu4Shihe Xu5Jiayang Ma6Nanjing Institute of TechnologyNanjing Institute of TechnologyUniversity of CaliforniaSchool of Information and CommunicationChongqing University of Posts and TelecommunicationsUniversity of Science and Technology of ChinaNanjing Institute of TechnologyAccurate parameter identification of power distribution network (PDN) has attracted remarkable attention recently. However, power device parameters usually show an instability attributed to both the operating status and manual entry. Therefore, it is urgent to develop reliable algorithms for identifying PDN parameters with both high accuracy and high efficiency. Most of the existing algorithms are gradient-free and based on the heuristic schemes, resulting in an unstable numerical calculation. Herein, based on our previous work about the adaptive gradient-based optimization (AGBO) method, we propose an extensive version, namely, AGBO-Pro model. In this method, both the numerical and categorical features of experimental observations are utilized and incorporated with each via a weighted average. By comparing the proposed method with several heuristic algorithms, it is found that the errors in RMSE, MAE, and MAPE criteria via AGBO-Pro are all about 2 times lower with a much faster and more stable convergence of the loss function. By further taking a linear transformation of the loss function, the AGBO-Pro model achieves a more robust performance with a much lower variance in repeat numerical calculations. This work shows great potential in possible extension of gradient-based optimization methods for parameter identification in PDN.http://dx.doi.org/10.1155/2023/4082305 |
| spellingShingle | Chuanjun Wang Kehao Fei Xinle Xu Haoran Chen Ke Hu Shihe Xu Jiayang Ma An Extensible Gradient-Based Optimization Method for Parameter Identification in Power Distribution Network International Transactions on Electrical Energy Systems |
| title | An Extensible Gradient-Based Optimization Method for Parameter Identification in Power Distribution Network |
| title_full | An Extensible Gradient-Based Optimization Method for Parameter Identification in Power Distribution Network |
| title_fullStr | An Extensible Gradient-Based Optimization Method for Parameter Identification in Power Distribution Network |
| title_full_unstemmed | An Extensible Gradient-Based Optimization Method for Parameter Identification in Power Distribution Network |
| title_short | An Extensible Gradient-Based Optimization Method for Parameter Identification in Power Distribution Network |
| title_sort | extensible gradient based optimization method for parameter identification in power distribution network |
| url | http://dx.doi.org/10.1155/2023/4082305 |
| work_keys_str_mv | AT chuanjunwang anextensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork AT kehaofei anextensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork AT xinlexu anextensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork AT haoranchen anextensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork AT kehu anextensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork AT shihexu anextensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork AT jiayangma anextensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork AT chuanjunwang extensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork AT kehaofei extensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork AT xinlexu extensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork AT haoranchen extensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork AT kehu extensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork AT shihexu extensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork AT jiayangma extensiblegradientbasedoptimizationmethodforparameteridentificationinpowerdistributionnetwork |