Search

The uncertain nature of renewable energy resources (RERs) and fast demand response lead to recurring voltage violations in the power systems, which causes frequent transformer tap shifting and capacitor switching. Therefore, this paper resorts to the static var compensators (SVCs) to manage the bus voltages based on the multi-agent deep reinforcement learning (MA-DRL) algorithm. The proposed scheme includes several system agents and SVC agents to collaboratively adjust the injected reactive power to restrict the bus voltages within the normal range. All the agents are trained centrally and executed separately, which requires minimum communication cost. The IEEE 14-bus system, IEEE 300-bus system, and China 157-node urban power grid are used to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The power industry in China has grown significantly over the past decade, spurring the adoption of system-wide automatic voltage control (AVC) technology to meet stricter requirements for security and economical power system operation. To cope with the rapidly developing and frequently changing Chinese power grid, an AVC scheme based on adaptive zone division is introduced in this paper. Logically, this type of system has a three-level hierarchical structure, but, here, both secondary voltage control (SVC) and tertiary voltage control (TVC) are implemented via software at the same control center. The control zones are no longer fixed but are reconfigured online and updated in accordance with variations in the grid structure. The technical details of these procedures are presented here. The implementation of TVC (which is based on an online reactive optimal power flow) and SVC are also discussed, together with some technical details on improvements to their reliability and robustness. Some results obtained from field-site applications based on similar-days testing rather than simulations are employed to evaluate the performance and improvements of the AVC system. This system has been installed at over 20 control centers in China. [ABSTRACT FROM PUBLISHER]