A Survey on Applications of Machine Learning for Optimal Power Flow

Optimal power flow (OPF) is at the heart of many power system operation tools and market clearing processes. Several mathematical and heuristic approaches have been presented in literature to solve OPF. The recent flourish of machine learning (ML) algorithms and advancement of computational resources, with unforeseen data availability, has motivated the power system community to embrace ML. Although many papers are published on the applications of ML for solving various power system problems, in case of OPF, the same research orientation is still in its early days. This paper presents a survey of recent studies that have applied ML to solve OPF-related problems and provides readers with visions on potential research directions in this field. The surveyed literature is categorized according to the type of studied OPF problems.

[1]  David Fridovich-Keil,et al.  Data-Driven Decentralized Optimal Power Flow , 2018, ArXiv.

[2]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[3]  Joe H. Chow,et al.  Power System Dynamics and Stability: With Synchrophasor Measurement and Power System Toolbox 2e: With Synchrophasor Measurement and Power System Toolbox , 2017 .

[4]  Nikolaos Gatsis,et al.  KERNEL-BASED LEARNING FOR SMART INVERTER CONTROL , 2018, 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[5]  Sidhant Misra,et al.  Statistical Learning for DC Optimal Power Flow , 2018, 2018 Power Systems Computation Conference (PSCC).

[6]  Deepjyoti Deka,et al.  Is Machine Learning in Power Systems Vulnerable? , 2018, 2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm).

[7]  Yi Guo,et al.  Data-Based Distributionally Robust Stochastic Optimal Power Flow—Part I: Methodologies , 2018, IEEE Transactions on Power Systems.

[8]  Robert Eriksson,et al.  Data-Driven Security-Constrained OPF , 2017 .

[9]  Michael I. Jordan,et al.  Machine learning: Trends, perspectives, and prospects , 2015, Science.

[10]  Renke Huang,et al.  Local Feature Sufficiency Exploration for Predicting Security-Constrained Generation Dispatch in Multi-area Power Systems , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[11]  François Bouffard,et al.  Prediction of Umbrella Constraints , 2018, 2018 Power Systems Computation Conference (PSCC).

[12]  Gabriela Hug,et al.  Toward Distributed/Decentralized DC Optimal Power Flow Implementation in Future Electric Power Systems , 2018, IEEE Transactions on Smart Grid.

[13]  Xiyu Wang,et al.  An Unsupervised Deep Learning Approach for Scenario Forecasts , 2018, 2018 Power Systems Computation Conference (PSCC).

[14]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[15]  H. L. Happ,et al.  OPTIMAL POWER DISPATCH -A COMPREHENSIVE SURVEY , 1977 .

[16]  J. L. Carpentier,et al.  Optimal Power Flows: Uses, Methods and Developments , 1985 .

[17]  Gabriela Hug,et al.  Data-Driven Local Control Design for Active Distribution Grids Using Off-Line Optimal Power Flow and Machine Learning Techniques , 2019, IEEE Transactions on Smart Grid.

[18]  Michael Chertkov,et al.  Machine Learning for the Grid , 2016 .

[19]  Yi Guo,et al.  Data-Based Distributionally Robust Stochastic Optimal Power Flow—Part II: Case Studies , 2018, IEEE Transactions on Power Systems.

[20]  Andrey Bernstein,et al.  JOINT CHANCE CONSTRAINTS REDUCTION THROUGH LEARNING IN ACTIVE DISTRIBUTION NETWORKS , 2018, 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[21]  Andrey Bernstein,et al.  Joint Chance Constraints in AC Optimal Power Flow: Improving Bounds Through Learning , 2018, IEEE Transactions on Smart Grid.

[22]  Pierre Pinson,et al.  Data-driven Security-Constrained AC-OPF for Operations and Markets , 2018, 2018 Power Systems Computation Conference (PSCC).

[23]  Daniel Kirschen,et al.  Model-Free Renewable Scenario Generation Using Generative Adversarial Networks , 2017, IEEE Transactions on Power Systems.

[24]  Claire J. Tomlin,et al.  Regression-based Inverter Control for Decentralized Optimal Power Flow and Voltage Regulation , 2019, ArXiv.

[25]  Ian A. Hiskens,et al.  A Survey of Relaxations and Approximations of the Power Flow Equations , 2019, Foundations and Trends® in Electric Energy Systems.

[26]  Xiaojin Zhu,et al.  Semi-Supervised Learning , 2010, Encyclopedia of Machine Learning.

[27]  Manfred Morari,et al.  Stochastic optimal power flow based on convex approximations of chance constraints , 2014, 2014 Power Systems Computation Conference.

[28]  Thomas Navidi,et al.  Predicting Solutions to the Optimal Power Flow Problem , 2016 .

[29]  Yoshua Bengio,et al.  Unsupervised and Transfer Learning Challenge: a Deep Learning Approach , 2011, ICML Unsupervised and Transfer Learning.

[30]  Eduardo F. Morales,et al.  An Introduction to Reinforcement Learning , 2011 .

[31]  Desheng Dash Wu,et al.  Power load forecasting using support vector machine and ant colony optimization , 2010, Expert Syst. Appl..

[32]  M. Milligan,et al.  Integrating Variable Renewable Energy: Challenges and Solutions , 2013 .

[33]  Soteris A. Kalogirou,et al.  Machine learning methods for solar radiation forecasting: A review , 2017 .

[34]  Steven H. Low,et al.  Convex Relaxation of Optimal Power Flow—Part II: Exactness , 2014, IEEE Transactions on Control of Network Systems.

[35]  Jaime Lloret,et al.  An Integrated IoT Architecture for Smart Metering , 2016, IEEE Communications Magazine.

[36]  Deepjyoti Deka,et al.  Learning for DC-OPF: Classifying active sets using neural nets , 2019, 2019 IEEE Milan PowerTech.

[37]  M. Kubát.  An Introduction to Machine Learning , 2017, Springer International Publishing.

[38]  Xinghuo Yu,et al.  Smart Electricity Meter Data Intelligence for Future Energy Systems: A Survey , 2016, IEEE Transactions on Industrial Informatics.

[39]  Sotiris B. Kotsiantis,et al.  Supervised Machine Learning: A Review of Classification Techniques , 2007, Informatica.

[40]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[41]  Yasin Kabalci,et al.  A survey on smart metering and smart grid communication , 2016 .

[42]  Shie Mannor,et al.  Supervised learning for optimal power flow as a real-time proxy , 2016, 2017 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT).

[43]  Gabriela Hug,et al.  Optimized Local Control for Active Distribution Grids using Machine Learning Techniques , 2018, 2018 IEEE Power & Energy Society General Meeting (PESGM).

[44]  Mohammad Farajollahi,et al.  A data-driven analysis of lightning-initiated contingencies at a distribution grid with a PV farm using Micro-PMU data , 2017, 2017 North American Power Symposium (NAPS).

[45]  Feng Qiu,et al.  Learning to Solve Large-Scale Security-Constrained Unit Commitment Problems , 2019, INFORMS J. Comput..

[46]  Steven H. Low,et al.  Convex Relaxation of Optimal Power Flow—Part I: Formulations and Equivalence , 2014, IEEE Transactions on Control of Network Systems.

[47]  Innocent Kamwa,et al.  Multi-contingency transient stability-constrained optimal power flow using multilayer feedforward neural networks , 2016, 2016 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE).

[48]  Henrik Sandberg,et al.  A Survey of Distributed Optimization and Control Algorithms for Electric Power Systems , 2017, IEEE Transactions on Smart Grid.

[49]  Line Roald,et al.  Learning for Constrained Optimization: Identifying Optimal Active Constraint Sets , 2018, INFORMS J. Comput..

[50]  Kyri Baker,et al.  Learning Warm-Start Points For Ac Optimal Power Flow , 2019, 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP).

[51]  Francisco D. Galiana,et al.  A survey of the optimal power flow literature , 1991 .

[52]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[53]  Shie Mannor,et al.  Unit Commitment Using Nearest Neighbor as a Short-Term Proxy , 2016, 2018 Power Systems Computation Conference (PSCC).

[54]  M. B. Cain,et al.  History of Optimal Power Flow and Formulations , 2012 .