Deep neural network based distribution system state estimation using hyperparameter optimization
In the past decade, distribution system state estimation has become a crucial topic in power system research due to the increasing importance of distribution networks amidst the decline of centralized energy production. This paper addresses a gap in the literature regarding the application of modern...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123024011630 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850112394892673024 |
|---|---|
| author | Gergő Békési Lilla Barancsuk Bálint Hartmann |
| author_facet | Gergő Békési Lilla Barancsuk Bálint Hartmann |
| author_sort | Gergő Békési |
| collection | DOAJ |
| description | In the past decade, distribution system state estimation has become a crucial topic in power system research due to the increasing importance of distribution networks amidst the decline of centralized energy production. This paper addresses a gap in the literature regarding the application of modern hyperparameter optimization techniques in low-voltage distribution system state estimation using deep neural networks. In particular, it demonstrates the use of the Tree-structured Parzen Estimator algorithm, which is a Bayesian hyperparameter optimization method, for distribution system state estimation on real Hungarian low-voltage networks. The study uses data from four real-life low-voltage supply areas in Hungary, which were modeled to address the challenges in obtaining network information. Compared to traditional methods like the weighted least squares method, the Tree-structured Parzen Estimator algorithm significantly improves the accuracy of the voltage amplitude and angle estimations, reducing the relative error by 14–73%. Additionally, it is shown that TPE outperforms simpler methods like Random Search in hyperparameter optimization. The results also reveal connections between the distribution system size and optimal hyperparameters, such as batch size, learning rate, and hidden layer configuration. The proposed non-iterative algorithm, combined with the parallel computation capabilities of deep neural networks utilizing GPU, resulted in four orders of magnitude improvement in runtime. These advancements make the proposed approach a valuable tool for renewable energy integration planning and real-time monitoring, highlighting its potential for practical applications in the power industry. |
| format | Article |
| id | doaj-art-de8176f83f4b4029a3066058bc6c8fc1 |
| institution | OA Journals |
| issn | 2590-1230 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-de8176f83f4b4029a3066058bc6c8fc12025-08-20T02:37:24ZengElsevierResults in Engineering2590-12302024-12-012410290810.1016/j.rineng.2024.102908Deep neural network based distribution system state estimation using hyperparameter optimizationGergő Békési0Lilla Barancsuk1Bálint Hartmann2Department of Automation and Applied Informatics, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Műegyetem rkp. 3., Budapest, H-1111, Hungary; Corresponding author.Department of Electric Power Engineering, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Műegyetem rkp. 3., Budapest, H-1111, HungaryDepartment of Electric Power Engineering, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Műegyetem rkp. 3., Budapest, H-1111, HungaryIn the past decade, distribution system state estimation has become a crucial topic in power system research due to the increasing importance of distribution networks amidst the decline of centralized energy production. This paper addresses a gap in the literature regarding the application of modern hyperparameter optimization techniques in low-voltage distribution system state estimation using deep neural networks. In particular, it demonstrates the use of the Tree-structured Parzen Estimator algorithm, which is a Bayesian hyperparameter optimization method, for distribution system state estimation on real Hungarian low-voltage networks. The study uses data from four real-life low-voltage supply areas in Hungary, which were modeled to address the challenges in obtaining network information. Compared to traditional methods like the weighted least squares method, the Tree-structured Parzen Estimator algorithm significantly improves the accuracy of the voltage amplitude and angle estimations, reducing the relative error by 14–73%. Additionally, it is shown that TPE outperforms simpler methods like Random Search in hyperparameter optimization. The results also reveal connections between the distribution system size and optimal hyperparameters, such as batch size, learning rate, and hidden layer configuration. The proposed non-iterative algorithm, combined with the parallel computation capabilities of deep neural networks utilizing GPU, resulted in four orders of magnitude improvement in runtime. These advancements make the proposed approach a valuable tool for renewable energy integration planning and real-time monitoring, highlighting its potential for practical applications in the power industry.http://www.sciencedirect.com/science/article/pii/S2590123024011630Deep neural networkDistribution system state estimationHyperparameter optimizationLow-voltageTree-structured Parzen Estimator |
| spellingShingle | Gergő Békési Lilla Barancsuk Bálint Hartmann Deep neural network based distribution system state estimation using hyperparameter optimization Results in Engineering Deep neural network Distribution system state estimation Hyperparameter optimization Low-voltage Tree-structured Parzen Estimator |
| title | Deep neural network based distribution system state estimation using hyperparameter optimization |
| title_full | Deep neural network based distribution system state estimation using hyperparameter optimization |
| title_fullStr | Deep neural network based distribution system state estimation using hyperparameter optimization |
| title_full_unstemmed | Deep neural network based distribution system state estimation using hyperparameter optimization |
| title_short | Deep neural network based distribution system state estimation using hyperparameter optimization |
| title_sort | deep neural network based distribution system state estimation using hyperparameter optimization |
| topic | Deep neural network Distribution system state estimation Hyperparameter optimization Low-voltage Tree-structured Parzen Estimator |
| url | http://www.sciencedirect.com/science/article/pii/S2590123024011630 |
| work_keys_str_mv | AT gergobekesi deepneuralnetworkbaseddistributionsystemstateestimationusinghyperparameteroptimization AT lillabarancsuk deepneuralnetworkbaseddistributionsystemstateestimationusinghyperparameteroptimization AT balinthartmann deepneuralnetworkbaseddistributionsystemstateestimationusinghyperparameteroptimization |