Data-Driven Chance Constrained AC-OPF using Hybrid Sparse Gaussian Processes

The alternating current (AC) chance-constrained optimal power flow (CC-OPF) problem addresses the economic efficiency of electricity generation and delivery under generation uncertainty. The latter is intrinsic to modern power grids because of the high amount of renewables. Despite its academic success, the AC CC-OPF problem is highly nonlinear and computationally demanding, which limits its practical impact. For improving the AC-OPF problem complexity/accuracy trade-off, the paper proposes a fast data-driven setup that uses the sparse and hybrid Gaussian processes (GP) framework to model the power flow equations with input uncertainty. We advocate the efficiency of the proposed approach by a numerical study over multiple IEEE test cases showing up to two times faster and more accurate solutions compared to the state-of-the-art methods.

[1]  Yury Maximov,et al.  Data-Driven Stochastic AC-OPF using Gaussian Processes , 2022, ArXiv.

[2]  Deepjyoti Deka,et al.  Importance Sampling Approach to Chance-Constrained DC Optimal Power Flow , 2021, IEEE Transactions on Control of Network Systems.

[3]  Yury Maximov,et al.  Power Grid Reliability Estimation via Adaptive Importance Sampling , 2021, IEEE Control Systems Letters.

[4]  Georgios B. Giannakis,et al.  Learning to Solve the AC-OPF Using Sensitivity-Informed Deep Neural Networks , 2021, IEEE Transactions on Power Systems.

[5]  Hung D. Nguyen,et al.  Gaussian Process Learning-Based Probabilistic Optimal Power Flow , 2020, IEEE Transactions on Power Systems.

[6]  Tianyu Zhao,et al.  DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flow , 2019, IEEE Transactions on Power Systems.

[7]  Ilyès Mezghani,et al.  Stochastic AC Optimal Power Flow: A Data-Driven Approach , 2019, Electric Power Systems Research.

[8]  Kyri Baker,et al.  Learning Optimal Solutions for Extremely Fast AC Optimal Power Flow , 2019, 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm).

[9]  Moritz Diehl,et al.  CasADi: a software framework for nonlinear optimization and optimal control , 2018, Mathematical Programming Computation.

[10]  Line A. Roald,et al.  Chance Constraints for Improving the Security of AC Optimal Power Flow , 2018, IEEE Transactions on Power Systems.

[11]  Felix Berkenkamp,et al.  Learning-Based Model Predictive Control for Safe Exploration , 2018, 2018 IEEE Conference on Decision and Control (CDC).

[12]  Afef Fekih,et al.  A probabilistic multi-objective approach for power flow optimization in hybrid wind-PV-PEV systems , 2018 .

[13]  Amber E. Budden,et al.  Environmental System Science Data Infrastructure for a Virtual Ecosystem (ESS-DIVE) - A New U.S. DOE Data Archive , 2017 .

[14]  Michael Chertkov,et al.  Importance sampling the union of rare events with an application to power systems analysis , 2017, Electronic Journal of Statistics.

[15]  Florian Schäfer,et al.  Pandapower—An Open-Source Python Tool for Convenient Modeling, Analysis, and Optimization of Electric Power Systems , 2017, IEEE Transactions on Power Systems.

[16]  Farzaneh Abbaspourtorbati,et al.  The swiss reserve market: Stochastic programming in practice , 2017, 2017 IEEE Power & Energy Society General Meeting.

[17]  Göran Andersson,et al.  Chance-Constrained AC Optimal Power Flow: Reformulations and Efficient Algorithms , 2017, IEEE Transactions on Power Systems.

[18]  Juraj Kabzan,et al.  Cautious Model Predictive Control Using Gaussian Process Regression , 2017, IEEE Transactions on Control Systems Technology.

[19]  Behnam Mohammadi-Ivatloo,et al.  Probabilistic multi-objective optimal power flow considering correlated wind power and load uncertainties , 2016 .

[20]  Line A. Roald,et al.  Stochastic AC optimal power flow with approximate chance-constraints , 2016, 2016 IEEE Power and Energy Society General Meeting (PESGM).

[21]  Demetris Koutsoyiannis.  The unavoidable uncertainty of renewable energy and its management , 2016 .

[22]  Santosh S. Vempala,et al.  A Cubic Algorithm for Computing Gaussian Volume , 2013, SODA.

[23]  Goran Andersson,et al.  Analytical reformulation of security constrained optimal power flow with probabilistic constraints , 2013, 2013 IEEE Grenoble Conference.

[24]  Michael Chertkov,et al.  Chance-Constrained Optimal Power Flow: Risk-Aware Network Control under Uncertainty , 2012, SIAM Rev..

[25]  Hui Zhang,et al.  Chance Constrained Programming for Optimal Power Flow Under Uncertainty , 2011, IEEE Transactions on Power Systems.

[26]  Marc Peter Deisenroth,et al.  Efficient reinforcement learning using Gaussian processes , 2010 .

[27]  Michalis K. Titsias,et al.  Variational Learning of Inducing Variables in Sparse Gaussian Processes , 2009, AISTATS.

[28]  Lorenz T. Biegler,et al.  On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming , 2006, Math. Program..

[29]  Junjie Tang,et al.  Chance-constrained optimal power flow based on a linearized network model , 2021 .

[30]  Stefanos Delikaraoglou,et al.  Chance-constrained optimal power flow with non-parametric probability distributions of dynamic line ratings , 2020 .

[31]  L. Hockstad,et al.  Inventory of U.S. Greenhouse Gas Emissions and Sinks , 2018 .

[32]  Tanja Hueber,et al.  Gaussian Processes For Machine Learning , 2016 .

[33]  Wilhelm Winter,et al.  Challenges, Experiences and Possible Solutions in Transmission System Operation with Large Wind Integration , 2012 .

[34]  C. Rasmussen,et al.  Gaussian Process Priors with Uncertain Inputs - Application to Multiple-Step Ahead Time Series Forecasting , 2002, NIPS.

[35]  L. Khachiyan.  Complexity of Polytope Volume Computation , 1993 .