Filters








3,296 Hits in 3.9 sec

Safe Reinforcement Learning for Grid Voltage Control [article]

Thanh Long Vu, Sayak Mukherjee, Renke Huang, Qiuhua Huang
2021 arXiv   pre-print
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.  ...  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  ...  the above three parts. 3 Safe Reinforcement Learning Approaches We discuss two of our recently proposed safe RL approaches for emergency voltage control.  ... 
arXiv:2112.01484v1 fatcat:qvhi44punndopfgod3jeiwju5u

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
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.  ...  Recently, deep reinforcement learning (RL) has been regarded and adopted as a promising approach that can significantly reduce the amount of load shedding.  ...  Section II introduces the RL-based grid emergency voltage control problem. The Barrier function based safe reinforcement learning methodology is described in Section III.  ... 
arXiv:2103.14186v2 fatcat:6l6x566fjjaxxeiqxmjdey4wii

Power Quality Enhancement in Microgrid With Dstatcom Using Modified Reinforcement Learning Algorithm

K Prabaakaran, Sri Krishnakumar, R Srividhya, R Ganesh Raw, R Gotham, R Tamilarasan
2019 Journal of Physics, Conference Series  
To enhance the power quality issue in grid system a new strategy with modification in algorithm is presented as reinforcement learning.  ...  A system as a current controller to enhance the current issue and the voltage controller to enhance the power quality issues in voltage.  ...  it has about 0.10 %, it shows that modified reinforced learning algorithm has effective control in THD elimination with adequate control of DSTATCOM for real time compensation.  ... 
doi:10.1088/1742-6596/1362/1/012080 fatcat:rlvnwnd5ond5zlbh4lwvvi75sm

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
Recently, deep reinforcement learning(RL) has been regarded and adopted as a promising approach leveraging massive data for fast and adaptive grid control.  ...  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.  ...  CONCLUSIONS In this paper, we presented a highly scalable and safe deep reinforcement learning algorithm for power system voltage stability control using load shedding.  ... 
arXiv:2011.09664v1 fatcat:pj3wk5i22velxgymlpnrjr6osu

OMG: A Scalable and Flexible Simulation and Testing Environment Toolbox for Intelligent Microgrid Control

Stefan Heid, Daniel Weber, Henrik Bode, Eyke Hüllermeier, Oliver Wallscheid
2020 Journal of Open Source Software  
Acknowledgements The authors kindly acknowledge the valuable contributions and advice regarding grid and controller design by Jarren Lange.  ...  The latter is particularly useful for the automatic training of data-driven control approaches such as reinforcement learning. • Large variety of predefined and parameterizable controllers (droop, voltage  ...  Interfaces for control and reinforcement learning The API is designed to provide a user-friendly interface to connect a modeled microgrid (the simulation environment) with a wide range of control methods  ... 
doi:10.21105/joss.02435 fatcat:zac5sosasvhy7fdqvjns2pzrxy

Towards a Scalable and Flexible Simulation and Testing Environment Toolbox for Intelligent Microgrid Control [article]

Henrik Bode, Stefan Heid, Daniel Weber, Eyke Hüllermeier, Oliver Wallscheid
2020 arXiv   pre-print
This applies in particular to data-driven control approaches from the field of reinforcement learning (RL), whose stability and operating behavior can hardly be evaluated a priori.  ...  Besides the presentation of the OMG toolbox, application examples are highlighted including safe Bayesian optimization for low-level controller tuning.  ...  Here, the integration of a priori expert knowledge for the evaluation of safe control methods appears to be especially promising, for example to monitor and guide the training of reinforcement learning-based  ... 
arXiv:2005.04869v2 fatcat:2nkbowyjz5hu7pnpa4smh2c654

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.  ...  Abstract-This paper presents a novel hierarchical deep reinforcement learning (DRL) based design for the voltage control of power grids.  ... 
arXiv:2102.00077v1 fatcat:lcme6ztwpne5vbn2za2hmremii

Table of contents

2020 IEEE Transactions on Smart Grid  
Wen 2303 Two-Timescale Voltage Control in Distribution Grids Using Deep Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Kong 2417 Constrained EV Charging Scheduling Based on Safe Deep Reinforcement Learning . . . . . . . . . . . . . . . . H. Li, Z.  ... 
doi:10.1109/tsg.2020.2983810 fatcat:j7djsxepozc4pgnpn7xwfsnhoi

2020 Index IEEE Transactions on Smart Grid Vol. 11

2020 IEEE Transactions on Smart Grid  
Algorithm for Volt-VAR Control in Power Distribution Systems; TSG July 2020 3008-3018 Wang, W., see Gao, Y., TSG Nov. 2020 5357-5369 Wang, X., see Sheng, H., TSG Jan. 2020 95-105 Wang, X., Zhang,  ...  Sept. 2020 4331-4344 Wang, J., see Zhang, Y., TSG Sept. 2020 4321-4330 Wang, M., see Li, J., TSG Nov. 2020 4760-4772 Wang, M., see Dong, C., TSG Nov. 2020 5084-5098 Wang, M., see Chang, F., Learning  ...  ., +, TSG May 2020 2014-2022 Safe Off-Policy Deep Reinforcement Learning Algorithm for Volt-VAR Control in Power Distribution Systems.  ... 
doi:10.1109/tsg.2020.3044227 fatcat:qp5iogfnrnambc3qzuwvj4aega

Safe Bayesian Optimization for Data-Driven Power Electronics Control Design in Microgrids: From Simulations to Real-World Experiments

Daniel Weber, Stefan Heid, Henrik Bode, Jarren H. Lange, Eyke Hullermeier, Oliver Wallscheid
2021 IEEE Access  
Both the current and voltage control loops of a voltage source inverter operating in standalone, grid-forming mode for a remote MSG are automatically tuned given an uncertain application environment.  ...  This applies, in particular, to data-driven control approaches such as reinforcement learning, of which the stability and operating behavior can hardly be evaluated on an analytical basis.  ...  ACKNOWLEDGMENT The authors would like to thank Andreas Heuermann from Linköping University for support on OpenModelica and FMU integration issues.  ... 
doi:10.1109/access.2021.3062144 fatcat:zwxqgaoeondkfili5xu54okceq

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
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  ...  Power system emergency control is generally regarded as the last safety net for grid security and resiliency.  ...  Guanji Hou for his valuable suggestions and assistance in developing the MPC-based emergency control method in this paper.  ... 
arXiv:1903.03712v2 fatcat:tlnl7if7uvb25ir3oijhihysti

Optimal control and learning for cyber‐physical systems

Yan Wan, Tao Yang, Ye Yuan, Frank L. Lewis
2021 International Journal of Robust and Nonlinear Control  
This special issue focuses on the optimal control theory and learning for CPSs.  ...  and power grids.  ...  In the paper titled "Safe reinforcement learning: A control barrier function optimization approach," the authors Marvi and Kiumarsi design a safe reinforcement learning scheme that achieves both safety  ... 
doi:10.1002/rnc.5442 fatcat:2sqn5j3urrgcrbjxfx6vsgvnci

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  ...  learning robustness and security are discussed for power systems operation tasks.  ...  Learning-based control paradigms have been proposed for a variety of operation tasks in power grids, including control of voltage and frequency [11] - [14] , capacity scheduling of PV and energy storage  ... 
arXiv:2110.04983v2 fatcat:niwatsbuzvahnf3rsukmofwwpm

Optimization Method of Power Equipment Maintenance Plan Decision-Making Based on Deep Reinforcement Learning

Yanhua Yang, Ligang Yao, Pietro Bia
2021 Mathematical Problems in Engineering  
The safe and reliable operation of power grid equipment is the basis for ensuring the safe operation of the power system.  ...  Based on a multiagent deep reinforcement learning decision-making optimization algorithm, a method for decision-making and optimization of power grid equipment maintenance plans is proposed.  ...  in intelligent power generation control, power grid intelligent control, and other fields [1, 22, 23] .  ... 
doi:10.1155/2021/9372803 fatcat:p6ylsy2pxnhlxmdcuaqervylaq

Deep Reinforcement Learning for DER Cyber-Attack Mitigation

Ciaran Roberts, Sy-Toan Ngo, Alexandre Milesi, Sean Peisert, Daniel Arnold, Shammya Saha, Anna Scaglione, Nathan Johnson, Anton Kocheturov, Dmitriy Fradkin
2020 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)  
Within this work we consider deep reinforcement learning as a tool to learn the optimal parameters for the control logic of a set of uncompromised DER units to actively mitigate the effects of a cyber-attack  ...  The name stands for Python based Cybersecurity via Inverter-Grid Automatic Reconfiguration.  ...  PyCIGAR is a Python library for distributed reinforcement learning for electric power distribution grids on quasi-static time scales.  ... 
doi:10.1109/smartgridcomm47815.2020.9302997 fatcat:uizxprnhljhsdps4abimjujkcy
« Previous Showing results 1 — 15 out of 3,296 results