Two-Timescale Coordination of Discretely and Continuously Adjustable Devices in ADNs With DRL and Physical Convex Optimization
High penetration of electrical vehicles (EVs) and renewable distributed generators (DGs) into active distribution networks (ADNs) lead to frequent, rapid and fierce voltages magnitudes violations. A novel two-timescale coordination scheme for different types of adjustable devices in ADNs is put forw...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Access Journal of Power and Energy |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11016130/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850121458560270336 |
|---|---|
| author | Jian Zhang Yigang He |
| author_facet | Jian Zhang Yigang He |
| author_sort | Jian Zhang |
| collection | DOAJ |
| description | High penetration of electrical vehicles (EVs) and renewable distributed generators (DGs) into active distribution networks (ADNs) lead to frequent, rapid and fierce voltages magnitudes violations. A novel two-timescale coordination scheme for different types of adjustable devices in ADNs is put forward in this article by organically integrating data-driven deep reinforce-ment learning (DRL) into physical convex model. A Markov Decision Process (MDP) is formulated on slow timescale, in which ratios/statuses of on load transformer changers (OLTCs) and switchable capacitors reactors (SCRs) and ESSs charging/ discharging power are set hourly to optimize network losses while regulating voltages magnitudes. An improved DRL with relaxation-prediction-correction strategies is proposed for eradicating discrete action components dimension curses. Whereas, on fast timescale (e.g., several seconds or minutes), the optimal reactive power of DGs inverters and static VAR compensators (SVCs) in balanced and unbalanced ADNs are set with physical convex optimization to minimize network losses while respecting physical constraints. Five simulations cases with IEEE 33-node balanced and 123-node unbalanced feeders are carried out to verify capabilities of put forward method. |
| format | Article |
| id | doaj-art-06ffc145a3b54b48ab2c98839216dd2f |
| institution | OA Journals |
| issn | 2687-7910 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Access Journal of Power and Energy |
| spelling | doaj-art-06ffc145a3b54b48ab2c98839216dd2f2025-08-20T02:35:05ZengIEEEIEEE Open Access Journal of Power and Energy2687-79102025-01-011239140310.1109/OAJPE.2025.357396111016130Two-Timescale Coordination of Discretely and Continuously Adjustable Devices in ADNs With DRL and Physical Convex OptimizationJian Zhang0https://orcid.org/0000-0003-2955-0594Yigang He1https://orcid.org/0000-0002-6642-0740School of Electrical Engineering and Automation, Hefei University of Technology, Hefei, ChinaSchool of Electrical Engineering and Automation, Wuhan University, Wuhan, ChinaHigh penetration of electrical vehicles (EVs) and renewable distributed generators (DGs) into active distribution networks (ADNs) lead to frequent, rapid and fierce voltages magnitudes violations. A novel two-timescale coordination scheme for different types of adjustable devices in ADNs is put forward in this article by organically integrating data-driven deep reinforce-ment learning (DRL) into physical convex model. A Markov Decision Process (MDP) is formulated on slow timescale, in which ratios/statuses of on load transformer changers (OLTCs) and switchable capacitors reactors (SCRs) and ESSs charging/ discharging power are set hourly to optimize network losses while regulating voltages magnitudes. An improved DRL with relaxation-prediction-correction strategies is proposed for eradicating discrete action components dimension curses. Whereas, on fast timescale (e.g., several seconds or minutes), the optimal reactive power of DGs inverters and static VAR compensators (SVCs) in balanced and unbalanced ADNs are set with physical convex optimization to minimize network losses while respecting physical constraints. Five simulations cases with IEEE 33-node balanced and 123-node unbalanced feeders are carried out to verify capabilities of put forward method.https://ieeexplore.ieee.org/document/11016130/ADNsDGsdeep reinforcement learningconvex optimizationDDPG |
| spellingShingle | Jian Zhang Yigang He Two-Timescale Coordination of Discretely and Continuously Adjustable Devices in ADNs With DRL and Physical Convex Optimization IEEE Open Access Journal of Power and Energy ADNs DGs deep reinforcement learning convex optimization DDPG |
| title | Two-Timescale Coordination of Discretely and Continuously Adjustable Devices in ADNs With DRL and Physical Convex Optimization |
| title_full | Two-Timescale Coordination of Discretely and Continuously Adjustable Devices in ADNs With DRL and Physical Convex Optimization |
| title_fullStr | Two-Timescale Coordination of Discretely and Continuously Adjustable Devices in ADNs With DRL and Physical Convex Optimization |
| title_full_unstemmed | Two-Timescale Coordination of Discretely and Continuously Adjustable Devices in ADNs With DRL and Physical Convex Optimization |
| title_short | Two-Timescale Coordination of Discretely and Continuously Adjustable Devices in ADNs With DRL and Physical Convex Optimization |
| title_sort | two timescale coordination of discretely and continuously adjustable devices in adns with drl and physical convex optimization |
| topic | ADNs DGs deep reinforcement learning convex optimization DDPG |
| url | https://ieeexplore.ieee.org/document/11016130/ |
| work_keys_str_mv | AT jianzhang twotimescalecoordinationofdiscretelyandcontinuouslyadjustabledevicesinadnswithdrlandphysicalconvexoptimization AT yiganghe twotimescalecoordinationofdiscretelyandcontinuouslyadjustabledevicesinadnswithdrlandphysicalconvexoptimization |