Noise-Immune Machine Learning and Autonomous Grid Control
Most recently, stochastic control methods such as deep reinforcement learning (DRL) have proven to be efficient and quick converging methods in providing localized grid voltage control. Because of the random dynamical characteristics of grid reactive loads and bus voltages, such stochastic control m...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Open Access Journal of Power and Energy |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10024373/ |
| _version_ | 1797352872229208064 |
|---|---|
| author | James Obert Rodrigo D. Trevizan Adrian Chavez |
| author_facet | James Obert Rodrigo D. Trevizan Adrian Chavez |
| author_sort | James Obert |
| collection | DOAJ |
| description | Most recently, stochastic control methods such as deep reinforcement learning (DRL) have proven to be efficient and quick converging methods in providing localized grid voltage control. Because of the random dynamical characteristics of grid reactive loads and bus voltages, such stochastic control methods are particularly useful in accurately predicting future voltage levels and in minimizing associated cost functions. Although DRL is capable of quickly inferring future voltage levels given specific voltage control actions, it is prone to high variance when the learning rate or discount factors are set for rapid convergence in the presence of bus noise. Evolutionary learning is also capable of minimizing cost function and can be leveraged for localized grid control, but it does not infer future voltage levels given specific control inputs and instead simply selects those control actions that result in the best voltage control. For this reason, evolutionary learning is better suited than DRL for voltage control in noisy grid environments. To illustrate this, using a cyber adversary to inject random noise, we compare the use of evolutionary learning and DRL in autonomous voltage control (AVC) under noisy control conditions and show that it is possible to achieve a high mean voltage control using a genetic algorithm (GA). We show that the GA additionally can provide superior AVC to DRL with comparable computational efficiency. We illustrate that the superior noise immunity properties of evolutionary learning make it a good choice for implementing AVC in noisy environments or in the presence of random cyber-attacks. |
| first_indexed | 2024-03-08T13:22:01Z |
| format | Article |
| id | doaj.art-d01b5b79c4c24d859d71dc3ef732cbe0 |
| institution | Directory Open Access Journal |
| issn | 2687-7910 |
| language | English |
| last_indexed | 2024-03-08T13:22:01Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Access Journal of Power and Energy |
| spelling | doaj.art-d01b5b79c4c24d859d71dc3ef732cbe02024-01-18T00:02:47ZengIEEEIEEE Open Access Journal of Power and Energy2687-79102023-01-011017618610.1109/OAJPE.2023.323888610024373Noise-Immune Machine Learning and Autonomous Grid ControlJames Obert0https://orcid.org/0000-0001-5066-1745Rodrigo D. Trevizan1https://orcid.org/0000-0003-2885-1213Adrian Chavez2https://orcid.org/0000-0003-3779-2462Sandia National Laboratories, Albuquerque, NM, USASandia National Laboratories, Albuquerque, NM, USASandia National Laboratories, Albuquerque, NM, USAMost recently, stochastic control methods such as deep reinforcement learning (DRL) have proven to be efficient and quick converging methods in providing localized grid voltage control. Because of the random dynamical characteristics of grid reactive loads and bus voltages, such stochastic control methods are particularly useful in accurately predicting future voltage levels and in minimizing associated cost functions. Although DRL is capable of quickly inferring future voltage levels given specific voltage control actions, it is prone to high variance when the learning rate or discount factors are set for rapid convergence in the presence of bus noise. Evolutionary learning is also capable of minimizing cost function and can be leveraged for localized grid control, but it does not infer future voltage levels given specific control inputs and instead simply selects those control actions that result in the best voltage control. For this reason, evolutionary learning is better suited than DRL for voltage control in noisy grid environments. To illustrate this, using a cyber adversary to inject random noise, we compare the use of evolutionary learning and DRL in autonomous voltage control (AVC) under noisy control conditions and show that it is possible to achieve a high mean voltage control using a genetic algorithm (GA). We show that the GA additionally can provide superior AVC to DRL with comparable computational efficiency. We illustrate that the superior noise immunity properties of evolutionary learning make it a good choice for implementing AVC in noisy environments or in the presence of random cyber-attacks.https://ieeexplore.ieee.org/document/10024373/Autonomous voltage controldeep reinforcement learningpower distribution systemsvoltage control |
| spellingShingle | James Obert Rodrigo D. Trevizan Adrian Chavez Noise-Immune Machine Learning and Autonomous Grid Control IEEE Open Access Journal of Power and Energy Autonomous voltage control deep reinforcement learning power distribution systems voltage control |
| title | Noise-Immune Machine Learning and Autonomous Grid Control |
| title_full | Noise-Immune Machine Learning and Autonomous Grid Control |
| title_fullStr | Noise-Immune Machine Learning and Autonomous Grid Control |
| title_full_unstemmed | Noise-Immune Machine Learning and Autonomous Grid Control |
| title_short | Noise-Immune Machine Learning and Autonomous Grid Control |
| title_sort | noise immune machine learning and autonomous grid control |
| topic | Autonomous voltage control deep reinforcement learning power distribution systems voltage control |
| url | https://ieeexplore.ieee.org/document/10024373/ |
| work_keys_str_mv | AT jamesobert noiseimmunemachinelearningandautonomousgridcontrol AT rodrigodtrevizan noiseimmunemachinelearningandautonomousgridcontrol AT adrianchavez noiseimmunemachinelearningandautonomousgridcontrol |