Deep Reinforcement Leaming for Short-term Voltage Control by Dynamic Load Shedding in China Southem Power Grid
作者： Jingyi Zhang , Chao Lu , Jennie Si , Jie Song , Yinsheng Su
DOI: 10.1109/IJCNN.2018.8489041
关键词:
摘要: We propose a novel load shedding (LS) scheme against voltage instability using deep reinforcement learning (DRL). Both spatial and temporal information of large power grid are used in the DRL control scheme. Specifically, both dynamic state variables topology inputs to controller. Within scheme, neural network is designed implemented automatically extract translation-invariance about instability. The controller interacts with system dynamics through sequence observations, actions rewards determine amounts manner that maximizes cumulative future reward, accomplishing coordination within region rapidly meet online application requirements. based distributed LS performed China Southern Power Grid (CSG) system. Our results show improved recovery performance by proposed under different unknown test scenarios.
elsevier.com
sci-hub.se 参考文章(15)
Dit-Yan Yeung, Hao Wang, Xingjian Shi, Zhourong Chen, Wang-chun Woo, Wai-kin Wong, Convolutional LSTM Network: a machine learning approach for precipitation nowcasting neural information processing systems. ,vol. 28, pp. 802- 810 ,(2015)
Z. Feng, V. Ajjarapu, D.J. Maratukulam, A practical minimum load shedding strategy to mitigate voltage collapse IEEE Transactions on Power Systems. ,vol. 13, pp. 1285- 1290 ,(1998) , 10.1109/59.736266
Sambarta Dasgupta, Magesh Paramasivam, Umesh Vaidya, Venkataramana Ajjarapu, Entropy-Based Metric for Characterization of Delayed Voltage Recovery IEEE Transactions on Power Systems. ,vol. 30, pp. 2460- 2468 ,(2015) , 10.1109/TPWRS.2014.2361649
Ramtin Hadidi, Benjamin Jeyasurya, Reinforcement Learning Based Real-Time Wide-Area Stabilizing Control Agents to Enhance Power System Stability IEEE Transactions on Smart Grid. ,vol. 4, pp. 489- 497 ,(2013) , 10.1109/TSG.2012.2235864
Tao Yu, Bin Zhou, Ka Wing Chan, Liang Chen, Bo Yang, Stochastic Optimal Relaxed Automatic Generation Control in Non-Markov Environment Based on Multi-Step $Q(\lambda)$ Learning IEEE Transactions on Power Systems. ,vol. 26, pp. 1272- 1282 ,(2011) , 10.1109/TPWRS.2010.2102372
Hua Bai, Venkataramana Ajjarapu, A Novel Online Load Shedding Strategy for Mitigating Fault-Induced Delayed Voltage Recovery IEEE Transactions on Power Systems. ,vol. 26, pp. 294- 304 ,(2011) , 10.1109/TPWRS.2010.2047279
Felix A. Gers, Jürgen Schmidhuber, Fred Cummins, Learning to Forget: Continual Prediction with LSTM Neural Computation. ,vol. 12, pp. 2451- 2471 ,(2000) , 10.1162/089976600300015015
Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, Demis Hassabis, None, Human-level control through deep reinforcement learning Nature. ,vol. 518, pp. 529- 533 ,(2015) , 10.1038/NATURE14236
B. Otomega, T. Van Cutsem, A load shedding scheme against both short- and long-term voltage instabilities in the presence of induction motors ieee powertech conference. pp. 1- 7 ,(2011) , 10.1109/PTC.2011.6019184
C.M. Affonso, L.C.P. daSilva, F.G.M. Lima, S. Soares, MW and MVar management on supply and demand side for meeting voltage stability margin criteria IEEE Transactions on Power Systems. ,vol. 19, pp. 1538- 1545 ,(2004) , 10.1109/TPWRS.2004.831659