Multi-Agent Deep Reinforcement Learning for Voltage Control With Coordinated Active and Reactive Power Optimization

The increasing penetration of distributed renewable energy resources causes voltage fluctuations in distribution networks. The controllable active and reactive power resources such as energy storage (ES) systems and electric vehicles (EVs) in active distribution networks play an important role in mi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on smart grid Ročník 13; číslo 6; s. 4873 - 4886
Hlavní autoři: Hu, Daner, Ye, Zhenhui, Gao, Yuanqi, Ye, Zuzhao, Peng, Yonggang, Yu, Nanpeng
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.11.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Active control
Algorithms
Capacitor banks
Controllability
Costs
Deep learning
Deep reinforcement learning
Electric potential
Electric vehicles
Energy policy
Energy sources
Energy storage
experience augmentation
Inverters
Machine learning
Mixed integer
multi-agent
Multiagent systems
Optimization
Quality control
Reactive power
Reinforcement learning
Robustness (mathematics)
soft actor-critic
Tap changers
Time
Voltage
Voltage control
Voltage fluctuations
ISSN:1949-3053, 1949-3061
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The increasing penetration of distributed renewable energy resources causes voltage fluctuations in distribution networks. The controllable active and reactive power resources such as energy storage (ES) systems and electric vehicles (EVs) in active distribution networks play an important role in mitigating the voltage excursions. This paper proposes a two-timescale hybrid voltage control strategy based on a mixed-integer optimization method and multi-agent reinforcement learning (MARL) to reduce power loss and mitigate voltage violations. In the slow-timescale, the active and reactive power optimization problem involving capacitor banks (CBs), on-load tap changers (OLTC), and ES systems is formulated as a mixed-integer second-order cone programming problem. In the fast-timescale, the reactive power of smart inverters connected to solar photovoltaic systems and active power of EVs are adjusted to mitigate short-term voltage fluctuations with a MARL algorithm. Specifically, we propose an experience augmented multi-agent actor-critic (EA-MAAC) algorithm with an attention mechanism to learn high-quality control policies. The control policies are executed online in a decentralized manner. The proposed hybrid voltage control strategy is validated on an IEEE testing distribution feeder. The numerical results show that our proposed control strategy is not only sample-efficient and robust but also effective in mitigating voltage fluctuations.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1949-3053
1949-3061
DOI:10.1109/TSG.2022.3185975