Learning Optimal Solutions for Extremely Fast AC Optimal Power Flow

We develop, in this paper, a machine learning approach to optimize the real-time operation of electric power grids. In particular, we learn feasible solutions to the AC optimal power flow (OPF) problem with negligible optimality gaps. The AC OPF problem aims at identifying optimal operational conditions of the power grids that minimize power losses and/or generation costs. Due to the computational challenges with solving this nonconvex problem, many efforts have focused on linearizing or approximating the problem in order to solve the AC OPF on faster timescales. However, many of these approximations can be fairly poor representations of the actual system state and still require solving an optimization problem, which can be time consuming for large networks. In this work, we learn a mapping between the system loading and optimal generation values, enabling us to find near-optimal and feasible AC OPF solutions. This allows us to bypass solving the traditionally nonconvex AC OPF problem, resulting in a significant decrease in computational burden for grid operators.

[1]  Tianyu Zhao,et al.  DeepOPF: Deep Neural Network for DC Optimal Power Flow , 2019, 2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm).

[2]  Line Roald,et al.  Learning for Convex Optimization , 2018 .

[3]  Nikos D. Sidiropoulos,et al.  Physics-Aware Neural Networks for Distribution System State Estimation , 2019, IEEE Transactions on Power Systems.

[4]  Yibing Liu,et al.  A Fully Distributed Reactive Power Optimization and Control Method for Active Distribution Networks , 2014, IEEE Transactions on Smart Grid.

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

[6]  Petar M. Djuric,et al.  Gibbs sampling approach for generation of truncated multivariate Gaussian random variables , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[7]  Florian Dörfler,et al.  Fast power system analysis via implicit linearization of the power flow manifold , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

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

[9]  Dimitris Bertsimas,et al.  Online Mixed-Integer Optimization in Milliseconds , 2019, INFORMS J. Comput..

[10]  Gabriela Hug,et al.  Distributed MPC for Efficient Coordination of Storage and Renewable Energy Sources Across Control Areas , 2016, IEEE Transactions on Smart Grid.

[11]  Yi Wang,et al.  Review of Smart Meter Data Analytics: Applications, Methodologies, and Challenges , 2018, IEEE Transactions on Smart Grid.

[12]  Emiliano Dall'Anese,et al.  Optimal power flow pursuit , 2016, 2016 American Control Conference (ACC).

[13]  R D Zimmerman,et al.  MATPOWER: Steady-State Operations, Planning, and Analysis Tools for Power Systems Research and Education , 2011, IEEE Transactions on Power Systems.

[14]  Helmut Bölcskei,et al.  Deep Neural Network Approximation Theory , 2019, IEEE Transactions on Information Theory.

[15]  G. Hug,et al.  Online optimization in closed loop on the power flow manifold , 2017, 2017 IEEE Manchester PowerTech.

[16]  Sairaj V. Dhople,et al.  Scalable Optimization Methods for Distribution Networks With High PV Integration , 2016, IEEE Transactions on Smart Grid.

[17]  Andrey Bernstein,et al.  Real-Time Feedback-Based Optimization of Distribution Grids: A Unified Approach , 2017, IEEE Transactions on Control of Network Systems.

[18]  Javad Lavaei,et al.  Convexification of optimal power flow problem , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[19]  S. Sastry,et al.  Analysis of power-flow equation , 1981 .

[20]  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).

[21]  Tomaso Erseghe,et al.  Distributed Optimal Power Flow Using ADMM , 2014, IEEE Transactions on Power Systems.

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

[23]  J. Le Boudec,et al.  Load Flow in Multiphase Distribution Networks: Existence, Uniqueness, Non-Singularity and Linear Models , 2017, IEEE Transactions on Power Systems.

[24]  Andrey Bernstein,et al.  Linear power-flow models in multiphase distribution networks , 2017, 2017 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe).

[25]  Steven H. Low,et al.  The Optimal Power Flow Operator: Theory and Computation , 2019, IEEE Transactions on Control of Network Systems.

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

[27]  Hamed Mohsenian-Rad,et al.  Power systems big data analytics: An assessment of paradigm shift barriers and prospects , 2018, Energy Reports.

[28]  Matt Wytock,et al.  Machine Learning for AC Optimal Power Flow , 2019, ArXiv.

[29]  Krishnamurthy Dvijotham,et al.  Real-Time Optimal Power Flow , 2017, IEEE Transactions on Smart Grid.

[30]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[31]  Yoshua Bengio,et al.  Tackling Climate Change with Machine Learning , 2019, ACM Comput. Surv..

[32]  Ian A. Hiskens,et al.  Semidefinite relaxations of equivalent optimal power flow problems: An illustrative example , 2015, 2015 IEEE International Symposium on Circuits and Systems (ISCAS).

[33]  Mihaela van der Schaar,et al.  Machine Learning in the Air , 2019, IEEE Journal on Selected Areas in Communications.