Angle Instability and Oscillations Control using SVC: A Deep Reinforcement Learning Enhanced Local Controller
نویسندگان
چکیده
An advanced control scheme to deal with transient angle instability and low-frequency oscillations in power systems is proposed this paper. The combines an existing controller (derived from the concept of Lyapunov energy functions) deep Q-network (a reinforcement learning algorithm) a static VAr compensator. This modified paper way directly thyristor reactor part compensator, offering easier implementation. aim improve performances through use while retaining its basic system stabilization characteristics. Advantages are illustrated by implementation model four-machine test (this considered as benchmark when studying phenomena dealt paper) MATLAB/Simulink environment using TensorFlow toolkit for usage.
منابع مشابه
Self-learning fuzzy SVC controller for oscillations damping
this paper investigates the use of self learning fuzzy PD controller applied to SVC device for improving damping inter-area modes of oscillations. The SLFLC utilizes sensitivity model for learning of SLFLC parameters. This has been enhanced by adding an integral term whose gain coefficient is also synthesized by learning that is actuated after completion of the main learning algorithm. The pape...
متن کاملDamping enhancement in the presence of load parameters uncertainty using reinforcement learning based SVC controller
This paper proposes a reinforcement learning based SVC controller to improve the damping of power systems in the presence of load model parameters uncertainty. The proposed method is trained over a wide range of typical load parameters in order to adapt the gains of the SVC stabilizer. The simulation results show that the tuned gains of the SVC stabilizer using Reinforcement Learning can provid...
متن کاملDesign of SVC controller for oscillations damping using Self-learning fuzzy approach
Application of fuzzy PD controller based on self learning algorithm for SVC device has been investigated in this paper. This approach used sensitivity model for learning Self Learning Fuzzy Logic parameters. This has been improved by adding up an integral term whose gain coefficient is also synthesized by learning that is actuated after completion of the main learning algorithm. The paper consi...
متن کاملUsing a Deep Reinforcement Learning Agent for Traffic Signal Control
Ensuring transportation systems are efficient is a priority for modern society. Technological advances have made it possible for transportation systems to collect large volumes of varied data on an unprecedented scale. We propose a traffic signal control system which takes advantage of this new, high quality data, with minimal abstraction compared to other proposed systems. We apply modern deep...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: European Journal of Electrical Engineering and Computer Science
سال: 2023
ISSN: ['2506-9853']
DOI: https://doi.org/10.24018/ejece.2023.7.1.490