Data-Driven Trajectory Prediction of Grid Power Frequency Based on Neural Models
Frequency in power systems is a real-time information that shows the balance between generation and demand. Good system frequency observation is vital for system security and protection. This paper analyses the system frequency response following disturbances and proposes a data-driven approach for...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/2/151 |
| _version_ | 1797412774585827328 |
|---|---|
| author | Harold R. Chamorro Alvaro D. Orjuela-Cañón David Ganger Mattias Persson Francisco Gonzalez-Longatt Lazaro Alvarado-Barrios Vijay K. Sood Wilmar Martinez |
| author_facet | Harold R. Chamorro Alvaro D. Orjuela-Cañón David Ganger Mattias Persson Francisco Gonzalez-Longatt Lazaro Alvarado-Barrios Vijay K. Sood Wilmar Martinez |
| author_sort | Harold R. Chamorro |
| collection | DOAJ |
| description | Frequency in power systems is a real-time information that shows the balance between generation and demand. Good system frequency observation is vital for system security and protection. This paper analyses the system frequency response following disturbances and proposes a data-driven approach for predicting it by using machine learning techniques like Nonlinear Auto-regressive (NAR) Neural Networks (NN) and Long Short Term Memory (LSTM) networks from simulated and measured Phasor Measurement Unit (PMU) data. The proposed method uses a horizon-window that reconstructs the frequency input time-series data in order to predict the frequency features such as Nadir. Simulated scenarios are based on the gradual inertia reduction by including non-synchronous generation into the Nordic 32 test system, whereas the PMU collected data is taken from different locations in the Nordic Power System (NPS). Several horizon-windows are experimented in order to observe an adequate margin of prediction. Scenarios considering noisy signals are also evaluated in order to provide a robustness index of predictability. Results show the proper performance of the method and the adequate level of prediction based on the Root Mean Squared Error (RMSE) index. |
| first_indexed | 2024-03-09T05:08:08Z |
| format | Article |
| id | doaj.art-7b2c167bfadf4de9ad78bc4a1b25aec2 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T05:08:08Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-7b2c167bfadf4de9ad78bc4a1b25aec22023-12-03T12:52:48ZengMDPI AGElectronics2079-92922021-01-0110215110.3390/electronics10020151Data-Driven Trajectory Prediction of Grid Power Frequency Based on Neural ModelsHarold R. Chamorro0Alvaro D. Orjuela-Cañón1David Ganger2Mattias Persson3Francisco Gonzalez-Longatt4Lazaro Alvarado-Barrios5Vijay K. Sood6Wilmar Martinez7KU Leuven, Katholieke Universiteit Leuven, 3000 Leuven, BelgiumSchool of Medicine and Health Sciences, Universidad del Rosario, Bogota 111711, ColombiaEaton Corporation, Golden, CO 80401, USARISE, Research Institutes of Sweden, 41258 Gothenburg, SwedenDepartment of Electrical Engineering, Information Technology and Cybernetics, University of South-Eastern Norway, 3918 Porsgrunn, NorwayDepartamento de Ingeniería, Universidad Loyola Andalucía, 41704 Seville, SpainElectrical, Computer and Software Engineering, Ontario Tech University, Oshawa, ON L1H 7K4, CanadaKU Leuven, Katholieke Universiteit Leuven, 3000 Leuven, BelgiumFrequency in power systems is a real-time information that shows the balance between generation and demand. Good system frequency observation is vital for system security and protection. This paper analyses the system frequency response following disturbances and proposes a data-driven approach for predicting it by using machine learning techniques like Nonlinear Auto-regressive (NAR) Neural Networks (NN) and Long Short Term Memory (LSTM) networks from simulated and measured Phasor Measurement Unit (PMU) data. The proposed method uses a horizon-window that reconstructs the frequency input time-series data in order to predict the frequency features such as Nadir. Simulated scenarios are based on the gradual inertia reduction by including non-synchronous generation into the Nordic 32 test system, whereas the PMU collected data is taken from different locations in the Nordic Power System (NPS). Several horizon-windows are experimented in order to observe an adequate margin of prediction. Scenarios considering noisy signals are also evaluated in order to provide a robustness index of predictability. Results show the proper performance of the method and the adequate level of prediction based on the Root Mean Squared Error (RMSE) index.https://www.mdpi.com/2079-9292/10/2/151non-synchronous generationfrequency responselow-inertia power systemsprimary frequency controlwind powernadir estimation |
| spellingShingle | Harold R. Chamorro Alvaro D. Orjuela-Cañón David Ganger Mattias Persson Francisco Gonzalez-Longatt Lazaro Alvarado-Barrios Vijay K. Sood Wilmar Martinez Data-Driven Trajectory Prediction of Grid Power Frequency Based on Neural Models Electronics non-synchronous generation frequency response low-inertia power systems primary frequency control wind power nadir estimation |
| title | Data-Driven Trajectory Prediction of Grid Power Frequency Based on Neural Models |
| title_full | Data-Driven Trajectory Prediction of Grid Power Frequency Based on Neural Models |
| title_fullStr | Data-Driven Trajectory Prediction of Grid Power Frequency Based on Neural Models |
| title_full_unstemmed | Data-Driven Trajectory Prediction of Grid Power Frequency Based on Neural Models |
| title_short | Data-Driven Trajectory Prediction of Grid Power Frequency Based on Neural Models |
| title_sort | data driven trajectory prediction of grid power frequency based on neural models |
| topic | non-synchronous generation frequency response low-inertia power systems primary frequency control wind power nadir estimation |
| url | https://www.mdpi.com/2079-9292/10/2/151 |
| work_keys_str_mv | AT haroldrchamorro datadriventrajectorypredictionofgridpowerfrequencybasedonneuralmodels AT alvarodorjuelacanon datadriventrajectorypredictionofgridpowerfrequencybasedonneuralmodels AT davidganger datadriventrajectorypredictionofgridpowerfrequencybasedonneuralmodels AT mattiaspersson datadriventrajectorypredictionofgridpowerfrequencybasedonneuralmodels AT franciscogonzalezlongatt datadriventrajectorypredictionofgridpowerfrequencybasedonneuralmodels AT lazaroalvaradobarrios datadriventrajectorypredictionofgridpowerfrequencybasedonneuralmodels AT vijayksood datadriventrajectorypredictionofgridpowerfrequencybasedonneuralmodels AT wilmarmartinez datadriventrajectorypredictionofgridpowerfrequencybasedonneuralmodels |