Stability improvement of multimachine power system using DRL based wind-PV-controller

• Published in: Sustainable computing informatics and systems Vol. 47; p. 101168
• Main Authors: Narwal, Deshveer, Sharma, Deepesh
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.09.2025
• Subjects: DQN; DRL; PV STATCOM; Reactive power; Stability; Wind power; DQN; Reactive power; Stability; Wind power; PV STATCOM; DRL
• ISSN: 2210-5379
• DOI: 10.1016/j.suscom.2025.101168

A significant challenge in modern electric power grids is the stability of power systems, particularly under extreme events such as demand surges and disruptions. Integrating renewable energy into the current system present a viable approach for meeting the growing demand. Furthermore, apart from efficiently meeting the increasing need, these renewable energy systems, with their supplementary circuitry, can substantially improve the stability of the power system. This research suggests a new method that combines deep reinforcement learning (DRL) with a Fractional Order deep Q network (FO-DQN) to address stability problems in multimachine power systems. Incorporating wind and PV systems, which function as STATCOM when necessary, introduces intricacy to the system's dynamics. The proposed DRL based controller facilitates dynamic real-time control of power flow, guaranteeing voltage stability throughout the system. The controller based on DRL is able to autonomously modify the settings of the PV Static Synchronous Compensator (STATCOM) and unified inter-phase power controller (UIPC) operated wind turbine (WT) system. This adjustment helps to provide reactive power compensation and stabilize the system during extreme conditions. This results in a high level of resilience and flexibility. The efficacy of the suggested approach for enhancing stability of multimachine power systems is proven through thorough simulations and comparative analysis. The results demonstrate higher system performance, reduced voltage drop, and optimal reactive power compensation in the presence of diverse operating circumstances and disturbances (fault). •This paper deals with the challenges of reactive power fluctuations in case of unexpected demand surges and disruptions in multimachine power systems.•This study introduces an innovative method using deep reinforcement learning (DRL) combined with a Fractional Order Deep Q Network (FO-DQN).•The approach leverages wind and PV systems as STATCOMs, providing real-time voltage stability and reactive power control.•Extensive simulations confirm the method’s effectiveness, showing improved voltage stability, enhanced reactive power support, and heightened resilience.