Filters








1,230 Hits in 4.7 sec

Accelerated Deep Reinforcement Learning Based Load Shedding for Emergency Voltage Control [article]

Renke Huang, Yujiao Chen, Tianzhixi Yin, Xinya Li, Ang Li, Jie Tan, Wenhao Yu, Yuan Liu, Qiuhua Huang
2020 arXiv   pre-print
Load shedding has been one of the most widely used and effective emergency control approaches against voltage instability.  ...  To overcome these issues, an accelerated DRL algorithm named PARS was developed and tailored for power system voltage stability control via load shedding.  ...  This paper focuses on developing an accelerated deep reinforcement learning (DRL)-based control method to make load shedding for emergency voltage control fast, adaptive, and scalable.  ... 
arXiv:2006.12667v2 fatcat:vhhl5ipzwvbfthk4regiolu63y

Barrier Function-based Safe Reinforcement Learning for Emergency Control of Power Systems [article]

Thanh Long Vu and Sayak Mukherjee and Renke Huang and Qiuhua Hung
2021 arXiv   pre-print
Recently, deep reinforcement learning (RL) has been regarded and adopted as a promising approach that can significantly reduce the amount of load shedding.  ...  In this paper, we introduce a novel safe RL method for emergency load shedding of power systems, that can enhance the safe voltage recovery of the electric power grid after experiencing faults.  ...  In [6] , we have designed a deep Q learning based RL control for emergency load shedding in response to voltage stability issues of the electric power grid.  ... 
arXiv:2103.14186v2 fatcat:6l6x566fjjaxxeiqxmjdey4wii

Safe Reinforcement Learning for Emergency LoadShedding of Power Systems [article]

Thanh Long Vu and Sayak Mukherjee and Tim Yin and Renke Huang and and Jie Tan and Qiuhua Huang
2020 arXiv   pre-print
In this paper, we introduce a novel method for safe RL-based load shedding of power systems that can enhance the safe voltage recovery of the electric power grid after experiencing faults.  ...  Recently, deep reinforcement learning(RL) has been regarded and adopted as a promising approach leveraging massive data for fast and adaptive grid control.  ...  In our previous work, we have designed a deep Q learning based RL control [9] for emergency load shedding to address this problem.  ... 
arXiv:2011.09664v1 fatcat:pj3wk5i22velxgymlpnrjr6osu

Adaptive Power System Emergency Control using Deep Reinforcement Learning [article]

Qiuhua Huang, Renke Huang, Weituo Hao, Jie Tan, Rui Fan, Zhenyu Huang
2019 arXiv   pre-print
Details of the platform and DRL-based emergency control schemes for generator dynamic braking and under-voltage load shedding are presented.  ...  To address these challenges, for the first time, this paper developed novel adaptive emergency control schemes using deep reinforcement learning (DRL), by leveraging the high-dimensional feature extraction  ...  Guanji Hou for his valuable suggestions and assistance in developing the MPC-based emergency control method in this paper.  ... 
arXiv:1903.03712v2 fatcat:tlnl7if7uvb25ir3oijhihysti

Safe Reinforcement Learning for Grid Voltage Control [article]

Thanh Long Vu, Sayak Mukherjee, Renke Huang, Qiuhua Huang
2021 arXiv   pre-print
Under voltage load shedding has been considered as a standard approach to recover the voltage stability of the electric power grid under emergency conditions, yet this scheme usually trips a massive amount  ...  Reinforcement learning (RL) has been adopted as a promising approach to circumvent the issues; however, RL approach usually cannot guarantee the safety of the systems under control.  ...  Conclusions In this paper, we discussed two safe deep reinforcement learning approaches for power system voltage stability control using load shedding.  ... 
arXiv:2112.01484v1 fatcat:qvhi44punndopfgod3jeiwju5u

Scalable Voltage Control using Structure-Driven Hierarchical Deep Reinforcement Learning [article]

Sayak Mukherjee, Renke Huang, Qiuhua Huang, Thanh Long Vu, Tianzhixi Yin
2021 arXiv   pre-print
This paper presents a novel hierarchical deep reinforcement learning (DRL) based design for the voltage control of power grids.  ...  We employ an enhanced augmented random search algorithm that is tailored for the voltage control problem in a two-level architecture.  ...  Index Terms-Emergency voltage control, deep reinforcement learning, hierarchical learning control, scalable learning. I.  ... 
arXiv:2102.00077v1 fatcat:lcme6ztwpne5vbn2za2hmremii

Learning and Fast Adaptation for Grid Emergency Control via Deep Meta Reinforcement Learning [article]

Renke Huang, Yujiao Chen, Tianzhixi Yin, Qiuhua Huang, Jie Tan, Wenhao Yu, Xinya Li, Ang Li, Yan Du
2022 arXiv   pre-print
Towards this end, great progress has been made in developing deep reinforcement learning (DRL) based grid control solutions in recent years.  ...  In this paper, we mitigate these limitations by developing a novel deep meta reinforcement learning (DMRL) algorithm.  ...  The objective of emergency control for FIDVR problem is to shed as little load as possible to recover voltages to meet the voltage recovery criterion.  ... 
arXiv:2101.05317v2 fatcat:55lmzubo5fhrfjsderg3csbfae

(Deep) Reinforcement learning for electric power system control and related problems: A short review and perspectives

Mevludin Glavic
2019 Annual Reviews in Control  
This paper reviews existing works on (deep) reinforcement learning considerations in electric power system control.  ...  Due attention is paid to the control-related problems considerations (cyber-security, big data analysis, short-term load forecast, and composite load modelling).  ...  load shedding as emergency control realized using T D(λ) RL method.  ... 
doi:10.1016/j.arcontrol.2019.09.008 fatcat:2sldrcrykzd7bectmvrn3nisky

Scalable Learning for Optimal Load Shedding Under Power Grid Emergency Operations [article]

Yuqi Zhou, Jeehyun Park, Hao Zhu
2022 arXiv   pre-print
This work puts forth an innovative learning-for-OLS approach by constructing the optimal decision rules of load shedding under a variety of potential contingency scenarios through offline neural network  ...  Numerical studies on the IEEE 14-bus system have demonstrated the effectiveness of our scalable OLS design for real-time responses to severe grid emergency events.  ...  Similarly, to accelerate the AC-OLS solution, [9] has proposed to learn the percentage ratio of load shedding from the system-wide contingency information.  ... 
arXiv:2111.11980v2 fatcat:jbkyma7bibfklgyhudusjo4pya

Emergency Load Shedding Strategy for Microgrids Based on Dueling Deep Q-Learning

Can Wang, Hongliang Yu, Lin Chai, Huikang Liu, Binxin Zhu
2021 IEEE Access  
At present, deep Q learning is widely used in the MG operation control. A power management method based on adaptive reinforcement learning is proposed in [25] .  ...  MG EMERGENCY LOAD SHEDDING STRATEGY BASED ON A DUELING DEEP Q-LEARNING This section introduces an islanded MG load shedding strategy based on the dueling deep Q-learning in detail.  ... 
doi:10.1109/access.2021.3055401 fatcat:3vinwizfprglpcn7ifgn6dev64

2020 Index IEEE Transactions on Power Systems Vol. 35

2020 IEEE Transactions on Power Systems  
., +, TPWRS July 2020 2670-2682 Deep-Reinforcement-Learning-Based Autonomous Voltage Control for Power Grid Operations.  ...  ., +, TPWRS March 2020 1048-1060 Deep-Reinforcement-Learning-Based Autonomous Voltage Control for Power Grid Operations.  ... 
doi:10.1109/tpwrs.2020.3040894 fatcat:jjw2rnzr2re6fejvariekzr5uy

Understanding the Safety Requirements for Learning-based Power Systems Operations [article]

Yize Chen, Daniel Arnold, Yuanyuan Shi, Sean Peisert
2021 arXiv   pre-print
Case studies performed on both voltage regulation and topology control tasks demonstrated the potential vulnerabilities of the standard reinforcement learning algorithms, and possible measures of machine  ...  short-term emergency control, Volt/VAr control, long-term residential demand response and battery energy management.  ...  Shedding Voltage Failure ... ...  ... 
arXiv:2110.04983v2 fatcat:niwatsbuzvahnf3rsukmofwwpm

Massively Digitized Power Grid: Opportunities and Challenges of Use-inspired AI [article]

Le Xie, Xiangtian Zheng, Yannan Sun, Tong Huang, Tony Bruton
2022 arXiv   pre-print
Open challenges and research opportunities for data, computing, and AI algorithms are articulated within the context of the power industry's tremendous decarbonization efforts.  ...  ACKNOWLEDGEMENTS The authors sincerely thank Jimmy Liu, Steven Dennis, and Thomas Wilson for their help on the Oncor use cases presented in this paper.  ...  [166] 140-NPCC (N) i5-5200U CPU, 8GB RAM ELM Emergency control [196] 39-IEEE (N) AMD Opteron CPU, 64GB RAM Deep reinforcement learning Under-voltage load shedding [167] 77-Nordic (N) [178] 30  ... 
arXiv:2205.05180v1 fatcat:ecmq2wqy2nhk7e2zcabwdkhltq

Review of Learning-Assisted Power System Optimization [article]

Guangchun Ruan, Haiwang Zhong, Guanglun Zhang, Yiliu He, Xuan Wang, Tianjiao Pu
2020 arXiv   pre-print
With dramatic breakthroughs in recent years, machine learning is showing great potential to upgrade the toolbox for power system optimization.  ...  Deep integration between machine learning approaches and optimization models is expected to become the most promising technical trend.  ...  For current and voltage control, [58] integrate the consensus method and deep reinforcement learning to coordinate distributed generators in an island microgrid.  ... 
arXiv:2007.00210v2 fatcat:sh54n6fdk5c4pdouq6u4ois53q

Optimizing the post-disaster control of islanded microgrid: A multi-agent deep reinforcement learning approach

Huanhuan Nie, Ying Chen, Yue Xia, Shaowei Huang, Bingqian Liu
2020 IEEE Access  
Since AlphaGo was proposed in 2016 and defeated a world champion in the game of Go [16] , deep reinforcement learning (DRL) has set off a new research boom again.  ...  On the load side, the load shedding control is discrete control.  ...  His research interests include reinforcement learning and cyber-physical system modeling.  ... 
doi:10.1109/access.2020.3018142 fatcat:uf4j2ickwvck7e7jfjzah3avha
« Previous Showing results 1 — 15 out of 1,230 results