Adaptive Volt–Var Control in Smart PV Inverter for Mitigating Voltage Unbalance at PCC Using Multiagent Deep Reinforcement Learning
Modern distribution networks face an increasing number of challenges in maintaining balanced grid voltages because of the rapid increase in single-phase distributed generators. Because of the proliferation of inverter-based resources, such as photovoltaic (PV) resources, in distribution networks, a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/19/8979 |
| _version_ | 1797516829992681472 |
|---|---|
| author | Yoongun Jung Changhee Han Dongwon Lee Sungyoon Song Gilsoo Jang |
| author_facet | Yoongun Jung Changhee Han Dongwon Lee Sungyoon Song Gilsoo Jang |
| author_sort | Yoongun Jung |
| collection | DOAJ |
| description | Modern distribution networks face an increasing number of challenges in maintaining balanced grid voltages because of the rapid increase in single-phase distributed generators. Because of the proliferation of inverter-based resources, such as photovoltaic (PV) resources, in distribution networks, a novel method is proposed for mitigating voltage unbalance at the point of common coupling by tuning the volt–var curve of each PV inverter through a day-ahead deep reinforcement learning training platform with forecast data in a digital twin grid. The proposed strategy uses proximal policy optimization, which can effectively search for a global optimal solution. Deep reinforcement learning has a major advantage in that the calculation time required to derive an optimal action in the smart inverter can be significantly reduced. In the proposed framework, multiple agents with multiple inverters require information on the load consumption and active power output of each PV inverter. The results demonstrate the effectiveness of the proposed control strategy on the modified IEEE 13 standard bus systems with time-varying load and PV profiles. A comparison of the effect on voltage unbalance mitigation shows that the proposed inverter can address voltage unbalance issues more efficiently than a fixed droop inverter. |
| first_indexed | 2024-03-10T07:06:20Z |
| format | Article |
| id | doaj.art-080d848f2ecf44b1b58a5c24e1d9a047 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T07:06:20Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-080d848f2ecf44b1b58a5c24e1d9a0472023-11-22T15:45:56ZengMDPI AGApplied Sciences2076-34172021-09-011119897910.3390/app11198979Adaptive Volt–Var Control in Smart PV Inverter for Mitigating Voltage Unbalance at PCC Using Multiagent Deep Reinforcement LearningYoongun Jung0Changhee Han1Dongwon Lee2Sungyoon Song3Gilsoo Jang4School of Electrical Engineering, Korea University, Anam-ro, Sungbuk-gu, Seoul 02841, KoreaSchool of Electrical Engineering, Korea University, Anam-ro, Sungbuk-gu, Seoul 02841, KoreaSchool of Electrical Engineering, Korea University, Anam-ro, Sungbuk-gu, Seoul 02841, KoreaAdvanced Power Grid Research Center, Korea Electrotechnology Research Institute (KERI), 138, Naesonsunhwan-ro, Uiwang-si 16029, KoreaSchool of Electrical Engineering, Korea University, Anam-ro, Sungbuk-gu, Seoul 02841, KoreaModern distribution networks face an increasing number of challenges in maintaining balanced grid voltages because of the rapid increase in single-phase distributed generators. Because of the proliferation of inverter-based resources, such as photovoltaic (PV) resources, in distribution networks, a novel method is proposed for mitigating voltage unbalance at the point of common coupling by tuning the volt–var curve of each PV inverter through a day-ahead deep reinforcement learning training platform with forecast data in a digital twin grid. The proposed strategy uses proximal policy optimization, which can effectively search for a global optimal solution. Deep reinforcement learning has a major advantage in that the calculation time required to derive an optimal action in the smart inverter can be significantly reduced. In the proposed framework, multiple agents with multiple inverters require information on the load consumption and active power output of each PV inverter. The results demonstrate the effectiveness of the proposed control strategy on the modified IEEE 13 standard bus systems with time-varying load and PV profiles. A comparison of the effect on voltage unbalance mitigation shows that the proposed inverter can address voltage unbalance issues more efficiently than a fixed droop inverter.https://www.mdpi.com/2076-3417/11/19/8979voltage unbalancevolt–var curve controlsmart PV invertermultiagent proximal policy optimization |
| spellingShingle | Yoongun Jung Changhee Han Dongwon Lee Sungyoon Song Gilsoo Jang Adaptive Volt–Var Control in Smart PV Inverter for Mitigating Voltage Unbalance at PCC Using Multiagent Deep Reinforcement Learning Applied Sciences voltage unbalance volt–var curve control smart PV inverter multiagent proximal policy optimization |
| title | Adaptive Volt–Var Control in Smart PV Inverter for Mitigating Voltage Unbalance at PCC Using Multiagent Deep Reinforcement Learning |
| title_full | Adaptive Volt–Var Control in Smart PV Inverter for Mitigating Voltage Unbalance at PCC Using Multiagent Deep Reinforcement Learning |
| title_fullStr | Adaptive Volt–Var Control in Smart PV Inverter for Mitigating Voltage Unbalance at PCC Using Multiagent Deep Reinforcement Learning |
| title_full_unstemmed | Adaptive Volt–Var Control in Smart PV Inverter for Mitigating Voltage Unbalance at PCC Using Multiagent Deep Reinforcement Learning |
| title_short | Adaptive Volt–Var Control in Smart PV Inverter for Mitigating Voltage Unbalance at PCC Using Multiagent Deep Reinforcement Learning |
| title_sort | adaptive volt var control in smart pv inverter for mitigating voltage unbalance at pcc using multiagent deep reinforcement learning |
| topic | voltage unbalance volt–var curve control smart PV inverter multiagent proximal policy optimization |
| url | https://www.mdpi.com/2076-3417/11/19/8979 |
| work_keys_str_mv | AT yoongunjung adaptivevoltvarcontrolinsmartpvinverterformitigatingvoltageunbalanceatpccusingmultiagentdeepreinforcementlearning AT changheehan adaptivevoltvarcontrolinsmartpvinverterformitigatingvoltageunbalanceatpccusingmultiagentdeepreinforcementlearning AT dongwonlee adaptivevoltvarcontrolinsmartpvinverterformitigatingvoltageunbalanceatpccusingmultiagentdeepreinforcementlearning AT sungyoonsong adaptivevoltvarcontrolinsmartpvinverterformitigatingvoltageunbalanceatpccusingmultiagentdeepreinforcementlearning AT gilsoojang adaptivevoltvarcontrolinsmartpvinverterformitigatingvoltageunbalanceatpccusingmultiagentdeepreinforcementlearning |