Coordinated volt/VAR control for photovoltaic inverters: A soft actor-critic enhanced droop control approach. (July 2023)

• Record Type: Journal Article
• Authors: Xiong, Kang; Cao, Di; Zhang, Guozhou; Chen, Zhe; Hu, Weihao
• Is Part Of: International journal of electrical power & energy systems. Volume 149(2023)
• Publication Date: 2023-07
• Subjects: Active distribution network -- Photovoltaic -- Droop control -- Minimise power loss -- Voltage regulating; Electrical engineering -- Periodicals; Electric power systems -- Periodicals; Électrotechnique -- Périodiques; Réseaux électriques (Énergie) -- Périodiques; Electric power systems; Electrical engineering; Periodicals; 621.3
• DOI: 10.1016/j.ijepes.2023.109019
• Languages: English
• ISSNs: 0142-0615

Abstract

Highlights: A novel coordinated volt/VAR control structure is proposed to minimize power loss. The mutual impacts between central hierarchy and local hierarchy can be fully considered. The soft actor-critic algorithm is utilized to deal with the uncertainties of PV generation. Abstract: The reactive power capacity of photovoltaic inverters can be utilised to minimise power loss and mitigate rapid voltage fluctuations in an active distribution network. This paper proposes a coordinated volt/VAR control framework that simultaneously optimises the base reactive power output of photovoltaic inverters and the voltage intercept of each droop control function in the central hierarchy based on whole-system information to minimise the power loss. The photovoltaic inverters use the optimised droop function to eliminate the voltage violation based on the real-time local information in the local hierarchy. Subsequently, the optimisation problem is formed as a Markov decision process and solved using an improved deep reinforcement learning algorithm called a soft actor-critic to achieve fast control with full consideration of uncertainties. Thus, the proposed method can simultaneously guarantee the cooperation and rapidity of the control performance to minimise power loss and quickly respond to real-time voltage fluctuations. Case studies were implemented using IEEE 33-bus and 123-bus distribution networks. The comparison results demonstrate that the proposed method can reduce the power loss and voltage violation rate by up to 12.3% and 2.71%, respectively, compared with other benchmark methods, which demonstrates the superiority of the proposed method in terms of power loss minimisation and voltage fluctuation mitigation.