Continuous estimation of power system inertia using convolutional neural networks
Abstract Inertia is a measure of a power system’s capability to counteract frequency disturbances: in conventional power networks, inertia is approximately constant over time, which contributes to network stability. However, as the share of renewable energy sources increases, the inertia associated...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-07-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-023-40192-2 |
| _version_ | 1827890351440920576 |
|---|---|
| author | Daniele Linaro Federico Bizzarri Davide del Giudice Cosimo Pisani Giorgio M. Giannuzzi Samuele Grillo Angelo M. Brambilla |
| author_facet | Daniele Linaro Federico Bizzarri Davide del Giudice Cosimo Pisani Giorgio M. Giannuzzi Samuele Grillo Angelo M. Brambilla |
| author_sort | Daniele Linaro |
| collection | DOAJ |
| description | Abstract Inertia is a measure of a power system’s capability to counteract frequency disturbances: in conventional power networks, inertia is approximately constant over time, which contributes to network stability. However, as the share of renewable energy sources increases, the inertia associated to synchronous generators declines, which may pose a threat to the overall stability. Reliably estimating the inertia of power systems dominated by inverted-connected sources has therefore become of paramount importance. We develop a framework for the continuous estimation of the inertia in an electric power system, exploiting state-of-the-art artificial intelligence techniques. We perform an in-depth investigation based on power spectra analysis and input-output correlations to explain how the artificial neural network operates in this specific realm, thus shedding light on the input features necessary for proper neural-network training. We validate our approach on a heterogeneous power network comprising synchronous generators, static compensators and converter-interfaced generation: our results highlight how different devices are characterized by distinct spectral footprints - a feature that must be taken into account by transmission system operators when performing online network stability analyses. |
| first_indexed | 2024-03-12T21:09:25Z |
| format | Article |
| id | doaj.art-d8f07928897b4554b38546d6a0ac0e94 |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-03-12T21:09:25Z |
| publishDate | 2023-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-d8f07928897b4554b38546d6a0ac0e942023-07-30T11:18:55ZengNature PortfolioNature Communications2041-17232023-07-0114111410.1038/s41467-023-40192-2Continuous estimation of power system inertia using convolutional neural networksDaniele Linaro0Federico Bizzarri1Davide del Giudice2Cosimo Pisani3Giorgio M. Giannuzzi4Samuele Grillo5Angelo M. Brambilla6DEIB, Politecnico di MilanoDEIB, Politecnico di MilanoDEIB, Politecnico di MilanoTerna Rete Italia S.p.A.Terna Rete Italia S.p.A.DEIB, Politecnico di MilanoDEIB, Politecnico di MilanoAbstract Inertia is a measure of a power system’s capability to counteract frequency disturbances: in conventional power networks, inertia is approximately constant over time, which contributes to network stability. However, as the share of renewable energy sources increases, the inertia associated to synchronous generators declines, which may pose a threat to the overall stability. Reliably estimating the inertia of power systems dominated by inverted-connected sources has therefore become of paramount importance. We develop a framework for the continuous estimation of the inertia in an electric power system, exploiting state-of-the-art artificial intelligence techniques. We perform an in-depth investigation based on power spectra analysis and input-output correlations to explain how the artificial neural network operates in this specific realm, thus shedding light on the input features necessary for proper neural-network training. We validate our approach on a heterogeneous power network comprising synchronous generators, static compensators and converter-interfaced generation: our results highlight how different devices are characterized by distinct spectral footprints - a feature that must be taken into account by transmission system operators when performing online network stability analyses.https://doi.org/10.1038/s41467-023-40192-2 |
| spellingShingle | Daniele Linaro Federico Bizzarri Davide del Giudice Cosimo Pisani Giorgio M. Giannuzzi Samuele Grillo Angelo M. Brambilla Continuous estimation of power system inertia using convolutional neural networks Nature Communications |
| title | Continuous estimation of power system inertia using convolutional neural networks |
| title_full | Continuous estimation of power system inertia using convolutional neural networks |
| title_fullStr | Continuous estimation of power system inertia using convolutional neural networks |
| title_full_unstemmed | Continuous estimation of power system inertia using convolutional neural networks |
| title_short | Continuous estimation of power system inertia using convolutional neural networks |
| title_sort | continuous estimation of power system inertia using convolutional neural networks |
| url | https://doi.org/10.1038/s41467-023-40192-2 |
| work_keys_str_mv | AT danielelinaro continuousestimationofpowersysteminertiausingconvolutionalneuralnetworks AT federicobizzarri continuousestimationofpowersysteminertiausingconvolutionalneuralnetworks AT davidedelgiudice continuousestimationofpowersysteminertiausingconvolutionalneuralnetworks AT cosimopisani continuousestimationofpowersysteminertiausingconvolutionalneuralnetworks AT giorgiomgiannuzzi continuousestimationofpowersysteminertiausingconvolutionalneuralnetworks AT samuelegrillo continuousestimationofpowersysteminertiausingconvolutionalneuralnetworks AT angelombrambilla continuousestimationofpowersysteminertiausingconvolutionalneuralnetworks |