Physics-informed Machine Learning in Power Systems

The increasing deployment of sensors such as smart meters and phasor measurement units in power transmission and distribution systems around the world has generated an unprecedented amount of data. By the end of last year, the electric utility industry is swamped by more than two petabytes of smart meter data alone. The traditional software tools and computing platforms used by electric utilities are not capable of effectively utilizing the big and heterogeneous data sets. There is an urgent need to develop both innovative big data analytic use cases and advanced machine learning algorithms to improve the efficiency, reliability and resiliency of power systems. 

Off-the-shelf machine learning algorithms such as supervised machine learning methods, unsupervised machine learning methods, reinforcement learning algorithms, and generative models have been widely adopted by researchers and developers to solve a myriad of problems in power systems. These initial efforts have achieved some great results in areas such as load and renewable energy forecasting and equipment predictive maintenance. However, when it comes to power system monitoring, sequential decision-making, optimization and controls problems, pure data-driven algorithms often do not yield satisfactory results. Their accuracy, generalization capability, sample efficiency and interpretability are inadequate to handle real-world problems.

To fill this knowledge and technology gap, researchers started developing the so-called physics-informed, physics-inspired, and physics-based machine learning algorithms by synergistically combining power system models and advanced machine learning techniques. The unique power system domain knowledge, information and models that have been integrated into machine learning algorithms include high/low entropy of certain power system sensor data, low-rank property of streaming data matrix, physical model for generation resources, power flow models, optimality conditions, and power system dynamic and control models. If the output of the problem can be simply modeled as the sum of the machine learning model and the physics-based model, then one could iteratively fit the parameters of the two models until some convergence criteria is met. In the general case, the physical domain knowledge or model needs to be directly embedded into the data preprocessing technique, the loss function of the deep learning model, or the architecture of the deep neural network.

This IEEE PES Trending Tech email provides a list of relevant technical reports, papers, tutorials, workshops, panel sessions, and active committees/working groups for the IEEE members who are interested in this topic.

Active Committees/Task Forces of Interest

To learn more & get involved, please check out the PSOPE website.

  • Technologies and Innovations (T&I) Subcommittee of IEEE PES PSOPE
    Working Group (WG) on Machine Learning for Power Systems
  • Distribution System Operation and Planning (DSOP) Subcommittee of IEEE PES PSOPE
  • Big Data and Analytics Subcommittee of IEEE PES AMPS
    Working Group on Data-Driven Modeling, Monitoring and Control in Power Distribution Networks.
  • Intelligent Systems Subcommittee (ISS) of IEEE PES AMPS
Technical Reports & Applicable Papers or Presentations
  • W. Wang, N. Yu, Y. Gao and J. Shi, “Safe Off-Policy Deep Reinforcement Learning Algorithm for Volt-VAR Control in Power Distribution Systems,” in IEEE Transactions on Smart Grid, vol. 11, no. 4, pp. 3008-3018, July 2020
    Read More >
  • X. Lei, Z. Yang, J. Yu, J. Zhao, Q. Gao and H. Yu, “Data-Driven Optimal Power Flow: A Physics-Informed Machine Learning Approach,” in IEEE Transactions on Power Systems, vol. 36, no. 1, pp. 346-354, Jan. 2021.
    Read More >
  • Y. Liu, N. Zhang, Y. Wang, J. Yang and C. Kang, “Data-Driven Power Flow Linearization: A Regression Approach,” in IEEE Transactions on Smart Grid, vol. 10, no. 3, pp. 2569-2580, May 2019.
    Read More >
  • F. Li and Y. Du, “From AlphaGo to Power System AI: What Engineers Can Learn from Solving the Most Complex Board Game,” in IEEE Power and Energy Magazine, vol. 16, no. 2, pp. 76-84, March-April 2018.
    Read More >
  • X. Kong, B. Foggo, K. Yamashita and N. Yu, “Online Voltage Event Detection Using Synchrophasor Data With Structured Sparsity-Inducing Norms,” in IEEE Transactions on Power Systems, vol. 37, no. 5, pp. 3506-3515, Sept. 2022.
    Read More >
  • Y. Susuki and I. Mezić, “Nonlinear Koopman Modes and Power System Stability Assessment Without Models,” in IEEE Transactions on Power Systems, vol. 29, no. 2, pp. 899-907, March 2014.
    Read More >
  • S. K. Azman, Y. J. Isbeih, M. S. E. Moursi and K. Elbassioni, “A Unified Online Deep Learning Prediction Model for Small Signal and Transient Stability,” in IEEE Transactions on Power Systems, vol. 35, no. 6, pp. 4585-4598, Nov. 2020.
    Read More >
  • K. Chen, J. Hu, Y. Zhang, Z. Yu and J. He, “Fault Location in Power Distribution Systems via Deep Graph Convolutional Networks,” in IEEE Journal on Selected Areas in Communications, vol. 38, no. 1, pp. 119-131, Jan. 2020.
    Read More >
  • K. Chen, J. Hu, Y. Zhang, Z. Yu and J. He, “Fault Location in Power Distribution Systems via Deep Graph Convolutional Networks,” in IEEE Journal on Selected Areas in Communications, vol. 38, no. 1, pp. 119-131, Jan. 2020.
    Read More >
  • Z. Yan and Y. Xu, “Real-Time Optimal Power Flow: A Lagrangian Based Deep Reinforcement Learning Approach,” in IEEE Transactions on Power Systems, vol. 35, no. 4, pp. 3270-3273, July 2020.
    Read More >
  • S. Gupta, V. Kekatos and M. Jin, “Deep Learning for Reactive Power Control of Smart Inverters under Communication Constraints,” 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), Tempe, AZ, USA, 2020, pp. 1-6.
    Read More >
  • J. Shi, B. Foggo and N. Yu, “Power System Event Identification Based on Deep Neural Network With Information Loading,” in IEEE Transactions on Power Systems, vol. 36, no. 6, pp. 5622-5632, Nov. 2021.
    Read More >
  • L. Zhang, Y. Chen and B. Zhang, “A Convex Neural Network Solver for DCOPF With Generalization Guarantees,” in IEEE Transactions on Control of Network Systems, vol. 9, no. 2, pp. 719-730, June 2022.
    Read More >
  • X. Hu, H. Hu, S. Verma and Z. -L. Zhang, “Physics-Guided Deep Neural Networks for Power Flow Analysis,” in IEEE Transactions on Power Systems, vol. 36, no. 3, pp. 2082-2092, May 2021.
    Read More >
  • Y. Gao, B. Foggo and N. Yu, “A Physically Inspired Data-Driven Model for Electricity Theft Detection With Smart Meter Data,” in IEEE Transactions on Industrial Informatics, vol. 15, no. 9, pp. 5076-5088, Sept. 2019.
    Read More >
  • R. Yousefian and S. Kamalasadan, “Energy Function Inspired Value Priority Based Global Wide-Area Control of Power Grid,” in IEEE Transactions on Smart Grid, vol. 9, no. 2, pp. 552-563, March 2018.
    Read More >
  • J. Stiasny, G. S. Misyris and S. Chatzivasileiadis, “Physics-Informed Neural Networks for Non-linear System Identification for Power System Dynamics,” 2021 IEEE Madrid PowerTech, Madrid, Spain, 2021, pp. 1-6.
    Read More >
  • W. Wang and N. Yu, “Estimate Three-Phase Distribution Line Parameters With Physics-Informed Graphical Learning Method,” in IEEE Transactions on Power Systems, vol. 37, no. 5, pp. 3577-3591, Sept. 2022.
    Read More >
  • A. S. Zamzam and N. D. Sidiropoulos, “Physics-Aware Neural Networks for Distribution System State Estimation,” in IEEE Transactions on Power Systems, vol. 35, no. 6, pp. 4347-4356, Nov. 2020.
    Read More >
  • L. Zhang, G. Wang and G. B. Giannakis, “Real-Time Power System State Estimation and Forecasting via Deep Unrolled Neural Networks,” in IEEE Transactions on Signal Processing, vol. 67, no. 15, pp. 4069-4077, 1 Aug.1, 2019.
    Read More >
  • Y. Gao, W. Wang, J. Shi and N. Yu, “Batch-Constrained Reinforcement Learning for Dynamic Distribution Network Reconfiguration,” in IEEE Transactions on Smart Grid, vol. 11, no. 6, pp. 5357-5369, Nov. 2020.
    Read More >
  • G. S. Misyris, A. Venzke and S. Chatzivasileiadis, “Physics-Informed Neural Networks for Power Systems,” 2020 IEEE Power & Energy Society General Meeting (PESGM), Montreal, QC, Canada, 2020, pp. 1-5.
    Read More >
  • B. Huang and J. Wang, “Applications of Physics-Informed Neural Networks in Power Systems – A Review,” in IEEE Transactions on Power Systems, vol. 38, no. 1, pp. 572-588, Jan. 2023.
    Read More >
  • F. Li, “Successful Applications and Future Challenges of Machine Learning for Power Systems: A Summary of Recent Activities by the IEEE WG on Machine Learning for Power Systems,” in IEEE Electrification Magazine, vol. 10, no. 4, pp. 90-96, Dec. 2022.
    Read More >
Publications
IEEE Power & Energy Magazine
  • S. Chatzivasileiadis, A. Venzke, J. Stiasny and G. Misyris, “Machine Learning in Power Systems: Is It Time to Trust It?,” in IEEE Power and Energy Magazine, vol. 20, no. 3, pp. 32-41, May-June 2022 Read More >
IEEE Electrification Magazine
  • Y. Y. C. Zhang and M. Spieler, “Bringing Artificial Intelligence to the Grid Edge [Technology Leaders],” in IEEE Electrification Magazine, vol. 10, no. 4, pp. 6-9, Dec. 2022. Read More >
  • N. Yu, W. Wang and R. Johnson, “Behind-the-Meter Resources: Data-driven modeling, monitoring, and control,” in IEEE Electrification Magazine, vol. 10, no. 4, pp. 20-28, Dec. 2022. Read More >
  • A. d. Castro, A. Mui and G. Frere, “Turning Data into Knowledge: Big data analytics with behind-the-meter distributed energy resources in the digital utility,” in IEEE Electrification Magazine, vol. 10, no. 4, pp. 50-57, Dec. 2022. Read More >

OAJPE Task Force on Promotion and Outreach

  • Y. Chen, S. Lakshminarayana, C. Maple and H. V. Poor, “A Meta-Learning Approach to the Optimal Power Flow Problem Under Topology Reconfigurations,” in IEEE Open Access Journal of Power and Energy, vol. 9, pp. 109-120, 2022 Read More >
  • P. Hart et al., “Application of Big Data Analytics and Machine Learning to Large-Scale Synchrophasor Datasets: Evaluation of Dataset ‘Machine Learning-Readiness’,” in IEEE Open Access Journal of Power and Energy, vol. 9, pp. 386-397, 2022 Read More >
  • J. Appiah-Kubi and C. C. Liu, “Cyberattack Correlation and Mitigation for Distribution Systems via Machine Learning,” in IEEE Open Access Journal of Power and Energy, vol. 10, pp. 128-140, 2023 Read More >
Other Available Material
  • 2020 PES General Meeting Tutorial Series: Machine Learning and Big Data Analytics in Smart Grid, Session 1: Data-driven Analytics for Power System Dynamics. Authors: Dr. Ning Zhou and Dr. Hao Zhu. Chair: Dr. Nanpeng Yu
    Read More >
  • 2020 PES General Meeting Tutorial Series: Machine Learning and Big Data Analytics in Smart Grid, Session 2: Overview & Reinforcement learning-based Control in Power Distribution Systems. Author: Dr. Nanpeng Yu. Chair: Dr. Nanpeng Yu.
    Read More >
  • 2020 PES General Meeting Tutorial Series: Machine Learning and Big Data Analytics in Smart Grid, Session 3: Estimation of System State and Behind-the-Meter Solar Generation. Authors: Dr. Lang Tong and Dr. Yingchen Zhang. Chair: Dr. Nanpeng Yu.
    Read More >
  • 2020 PES General Meeting Tutorial Series: Machine Learning and Big Data Analytics in Smart Grid, Session 4: Streaming Analytics and Machine Learning Design for Smart Grid and Power Systems. Authors: Dr. Le Xie and Dr. Yang Weng. Chair: Dr. Nanpeng Yu.
    Read More >
  • 2021 IEEE Workshop on Machine Learning for Power Systems. Authors: Dr. Fangxing Fran Li, Dr. Jin Zhao, Dr. Junbo Zhao, Dr. Pengwei Du, Dr. Spyros Chatzivasileiadis, Dr. C.Y. Chung, and Dr. Anurag K. Srivastava. Chair: Dr. Fangxing Fran Li.
    Read More >
  • 2021 IEEE PES GM Panel Session. Physics-informed Machine Learning for Power Systems. Authors: Dr. Le Xie, Dr. Vassilis Kekatos, Dr. Johanna Mathieu, Dr. Nanpeng Yu, and Dr. Ahmed Zamzam. Chair: Dr. Hao Zhu.
    Read More >
  • 2022 IEEE PES GM Panel Session. Data-Driven State and Parameter Estimation in Power Distribution Systems. Authors: Dr. Yuzhang Lin, Dr. Balasubramaniam Natarajan, Dr. Yang Weng, and Dr. Nanpeng Yu. Chair: Dr. Yuzhang Lin and Dr. Nanpeng Yu.
    Read More >