End-to-end (E2E) learning; Learning-to-optimize (L2O); Machine learning; Optimal power flow (OPF); Power systems; End to end; Machine-learning; Optimal power flow; Optimal power flow problem; Optimal power flows; Power; Power system; Technical constraints; Building and Construction; Renewable Energy, Sustainability and the Environment; Mechanical Engineering; Energy (all); Management, Monitoring, Policy and Law
Abstract :
[en] The Optimal Power Flow (OPF) problem is the cornerstone of power systems operations, providing generators’ most economical dispatch for power demands by fulfilling technical and physical constraints across the power network. To ensure safe and reliable operation of power systems, grid operators must steadily solve the nonconvex nonlinear OPF problem for immense power networks in (near) real-time, which poses tremendous computational challenges. The enormous amount of available data created by power systems digitalization and recent breakthroughs in machine learning have opened up new opportunities for grid operators to build shortcuts to predict or solve the OPF problem close to real-time. This survey overviews recent attempts at leveraging machine learning algorithms to solve the transmission-level OPF problem. On this basis, the groundwork is laid for commonly employed machine learning approaches leveraged to address the OPF problem. Subsequently, the frequently used performance evaluation metrics in learning-based OPFs are delineated to judge efficiency from diverse aspects (e.g., optimality in terms of the dispatched cost, feasibility concerning technical constraints, and computational efficiency) compared to conventional approaches. Next, the trend and progress of recently developed algorithms are discussed. Finally, the challenges and open problems at the interface of machine learning and OPF problems are highlighted.
Disciplines :
Electrical & electronics engineering Energy Computer science
Author, co-author :
Khaloie, Hooman ; Université de Mons - UMONS > Faculté Polytechnique > Service de Génie Electrique
Dolanyi, Mihaly ; Université de Mons - UMONS > Faculté Polytechnique > Service de Génie Electrique
Toubeau, Jean-François ; Université de Mons - UMONS > Faculté Polytechnique > Service de Génie Electrique
Vallée, François ; Université de Mons - UMONS > Faculté Polytechnique > Service de Génie Electrique
Language :
English
Title :
Review of machine learning techniques for optimal power flow
5513 - DISCRETE - FTE 2021 - Data driven optimization models for secure real-time operation of renewable dominated power systems - Sources fédérales
Funders :
FPS Economy - Federal Public Service Economy
Funding text :
This document is the results of the research project of the Energy Transition Fund, DISCRETE project, funded by the FPS Economy, S.M.E.s, Self-Employed and Energy, Belgium.
Dommel, HW, Tinney, WF, Optimal power flow solutions. IEEE Trans Power Appar Syst PAS 87:10 (1968), 1866–1876, 10.1109/TPAS.1968.292150.
Wang, S, Shahidehpour, S, Kirschen, D, Mokhtari, S, Irisarri, G, Short-term generation scheduling with transmission and environmental constraints using an augmented lagrangian relaxation. IEEE Trans Power Syst 10:3 (1995), 1294–1301.
Jabr, R, Coonick, A, Cory, B, A homogeneous linear programming algorithm for the security constrained economic dispatch problem. IEEE Trans Power Syst 15:3 (2000), 930–936, 10.1109/59.871715.
Bouffard, F, Galiana, F, Conejo, A, Market-clearing with stochastic security— part i: formulation. IEEE Trans Power Syst 20:4 (2005), 1818–1826, 10.1109/TPWRS.2005.857016.
Singh, H, Hao, S, Papalexopoulos, A, Transmission congestion management in competitive electricity markets. IEEE Trans Power Syst 13:2 (1998), 672–680, 10.1109/59.667399.
Yoshida, H, Kawata, K, Fukuyama, Y, Takayama, S, Nakanishi, Y, A particle swarm optimization for reactive power and voltage control considering voltage security assessment. IEEE Trans Power Syst 15:4 (2000), 1232–1239, 10.1109/59.898095.
Fisher, EB, O'Neill, RP, Ferris, MC, Optimal transmission switching. IEEE Trans Power Syst 23:3 (2008), 1346–1355.
Alguacil, N, Motto, A, Conejo, A, Transmission expansion planning: a mixed-integer lp approach. IEEE Trans Power Syst 18:3 (2003), 1070–1077, 10.1109/TPWRS.2003.814891.
Zamzam, AS, Baker, K, Learning optimal solutions for extremely fast ac optimal power flow., 2020 IEEE international conference on communications, control, and computing technologies for smart grids (SmartGridComm), 2020, IEEE, 1–6.
Capitanescu, F, Martinez Ramos, J, Panciatici, P, Kirschen, D, Marano Marcolini, A, Platbrood, L, et al. State-of-the-art, challenges, and future trends in security constrained optimal power flow. Electr Power Syst Res 81:8 (2011), 1731–1741, 10.1016/j.jpgr.2011.04.003.
Capitanescu, F, Critical review of recent advances and further developments needed in ac optimal power flow. Electr Power Syst Res 136 (2016), 57–68, 10.1016/j.jpgr.2016.02.008.
Molzahn, DK, Hiskens, IA, A survey of relaxations and approximations of the power flow equations. Found Trends Electr Energy Syst 4 (2019), 1–2, 10.1561/3100000012.
Zhao, F, Litvinov, E, Zheng, T, A marginal equivalent decomposition method and its application to multi-area optimal power flow problems. IEEE Trans Power Syst 29:1 (2013), 53–61.
Molzahn, DK, Dörfler, F, Sandberg, H, Low, SH, Chakrabarti, S, Baldick, R, et al. A survey of distributed optimization and control algorithms for electric power systems. IEEE Trans Smart Grid 8:6 (2017), 2941–2962.
Mak, TW, Chatzos, M, Tanneau, M, Hentenryck, PV, Learning regionally decentralized ac optimal power flows with admm. IEEE Trans Smart Grid, 2023, 10.1109/TSG.2023.3251292 1–1.
Sun, K, Sun, XA, A two-level admm algorithm for ac opf with global convergence guarantees. IEEE Trans Power Syst 36:6 (2021), 5271–5281.
Ren, Y, Sun, Y, Peng, M, Deep reinforcement learning based computation offloading in fog enabled industrial internet of things. IEEE Trans Ind Inf 17:7 (2021), 4978–4987, 10.1109/TII.2020.3021024.
Xiang, X, Gui, J, Xiong, NN, An integral data gathering framework for supervisory control and data acquisition systems in green iot. IEEE Trans Green Commun Netw 5:2 (2021), 714–726, 10.1109/TGCN.2021.3068257.
Phadke, AG, Thorp, JS, Phadke, AG, Thorp, JS, Phasor measurement units and phasor data concentrators. Synchron Phasor Meas Appl, 2017, 83–109.
Zheng, J, Gao, DW, Lin, L, Smart meters in smart grid: An overview., 2013 IEEE green technologies conference (GreenTech), 2013, IEEE, 57–64.
Perez, J, A guide to digital fault recording event analysis., 2010 63rd Annual Conference for Protective Relay Engineers, 2010, IEEE, 1–17, 10.1109/CPRE.2010.5469501.
Yang, T, Zhao, L, Li, W, Zomaya, AY, Reinforcement learning in sustainable energy and electric systems: a survey. Annu Rev Control 49 (2020), 145–163, 10.1016/j.arcontrol.2020.03.001.
Ibrahim, MS, Dong, W, Yang, Q, Machine learning driven smart electric power systems: current trends and new perspectives. Appl Energy, 272, 2020, 115237, 10.1016/j.apenergy.2020.115237.
Huang, B, Wang, J, Applications of physics-informed neural networks in power systems - a review. IEEE Trans Power Syst 38:1 (2023), 572–588, 10.1109/TPWRS.2022.3162473.
Yu, L, Qin, S, Zhang, M, Shen, C, Jiang, T, Guan, X, A review of deep reinforcement learning for smart building energy management. IEEE Internet Things J 8:15 (2021), 12046–12063, 10.1109/JIOT.2021.3078462.
Zhu, Z, Hu, Z, Chan, KW, Bu, S, Zhou, B, Xia, S, Reinforcement learning in deregulated energy market: a comprehensive review. Appl Energy, 329, 2023, 120212, 10.1016/j.apenergy.2022.120212.
Van Hentenryck, P, Machine learning for optimal power flows. Tutor Oper Res Emerg Optim Methods Model Tech Appl, INFORMS, 2021, 62–82, 10.1287/educ.2021.0234.
Hasan, F, Kargarian, A, Mohammadi, A, A survey on applications of machine learning for optimal power flow., 2020 IEEE Texas Power and Energy Conference (TPEC), 2020, IEEE, 1–6, 10.1109/TPEC48276.2020.9042547.
Huang, G, Wu, F, Guo, C, Smart grid dispatch powered by deep learning: a survey. Front Inf Technol Electr Eng 23:5 (2022), 763–776, 10.1631/FITEE.2000719.
Ruan, G, Zhong, H, Zhang, G, He, Y, Wang, X, Pu, T, Review of learning-assisted power system optimization. CSEE J Power Energy Syst 7:2 (2020), 221–231.
Cunningham, P, Cord, M, Delany, SJ, Supervised learning. Machine learning techniques for multimedia: case studies on organization and retrieval, 2008, Springer, 21–49.
Hastie T, Tibshirani R, Friedman J, Hastie T, Tibshirani R, Friedman J. Unsupervised learning, the elements of statistical learning: data mining, inference, and prediction. 2009;485–585.
Sutton, RS, Barto, AG, Reinforcement learning: an introduction. 2018, MIT press.
Kotary, J, Fioretto, F, Van Hentenryck, P, Wilder, B, End-to-end constrained optimization learning: a survey, 2021 arXiv:2103.16378 arXiv preprint.
Xia, F, Sun, K, Yu, S, Aziz, A, Wan, L, Pan, S, et al. Graph learning: a survey. IEEE Trans Artif Intell 2:2 (2021), 109–127.
Goodfellow, I, Pouget-Abadie, J, Mirza, M, Xu, B, Warde-Farley, D, Ozair, S, et al. Generative adversarial nets. Adv Neural Inf Process Syst, 27, 2014.
Dener, A, Miller, MA, Churchill, RM, Munson, T, Chang, C-S, Training neural networks under physical constraints using a stochastic augmented lagrangian approach, 2020 arXiv:2009.07330 arXiv preprint.
Stooke, A, Achiam, J, Abbeel, P, Responsive safety in reinforcement learning by pid lagrangian methods., International Conference on Machine Learning, PMLR, 2020, 9133–9143.
Donti, PL, Rolnick, D, Kolter, JZ, Dc3: a learning method for optimization with hard constraints, 2021 arXiv:2104.12225 arXiv preprint.
Crozier, C, Baker, K, Data-driven probabilistic constraint elimination for accelerated optimal power flow., 2022 IEEE Power & Energy Society General Meeting (PESGM), 2022, IEEE, 1–5.
Sun, S, Cao, Z, Zhu, H, Zhao, J, A survey of optimization methods from a machine learning perspective. IEEE Trans Cybern 50:8 (2019), 3668–3681.
Panesar, A, Machine learning and AI for healthcare. 2021, Springer, 10.1007/978-1-4842-6537-6.
Saskia, How to normalize the rmse, 2019 https://www.marinedatascience.co/blog/2019/01/07/normalizing-the-rmse/.
Li, Y, Zhao, C, Liu, C, Solving non-linear optimization problem in engineering by model-informed generative adversarial network (mi-gan)., 2022 IEEE International Conference on Data Mining Workshops (ICDMW), 2022, 198–205, 10.1109/ICDMW58026.2022.00035.
Li, Y, Zhao, C, Liu, C, Model-informed generative adversarial network (mi-gan) for learning optimal power flow, 2022 arXiv:2206.01864 arXiv preprint.
Wang, J, Srikantha, P, Fast optimal power flow with guarantees via an unsupervised generative model. IEEE Trans Power Syst, 2022.
Canyasse, R, Dalal, G, Mannor, S, Supervised learning for optimal power flow as a real-time proxy., 2017 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2017, IEEE, 1–5.
Sun, Y, Fan, X, Huang, Q, Li, X, Huang, R, Yin, T, et al. Local feature sufficiency exploration for predicting security-constrained generation dispatch in multi-area power systems., 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), 2018, IEEE, 1283–1289, 10.1109/ICMLA.2018.00208.
Yang, K, Gao, W, Fan, R, Optimal power flow estimation using one-dimensional convolutional neural network., 2021 North American Power Symposium (NAPS), 2021, IEEE, 1–6, 10.1109/NAPS52732.2021.9654438.
Wu, H, Xu, Z, Fast dc optimal power flow based on deep convolutional neural network., 2022 IEEE 5th International Electrical and Energy Conference (CIEEC), 2022, IEEE, 2508–2512, 10.1109/CIEEC54735.2022.9846143.
Falconer, T, Mones, L, Leveraging power grid topology in machine learning assisted optimal power flow. IEEE Trans Power Syst, 2022, 1–13, 10.1109/TPWRS.2022.3187218.
Dong, Z, Hou, K, Liu, Z, Yu, X, Jia, H, Zhang, C, A sample-efficient opf learning method based on annealing knowledge distillation. IEEE Acces 10 (2022), 99724–99733, 10.1109/ACCESS.2022.3207146.
Lotfi, A, Pirnia, M, Constraint-guided deep neural network for solving optimal power flow. Electr Power Syst Res, 211, 2022, 108353, 10.1016/j.jpgr.2022.108353.
Chen, Y, Lakshminarayana, S, Maple, C, Poor, HV, A meta-learning approach to the optimal power flow problem under topology reconfigurations. IEEE Open Access J Power Energy 9 (2022), 109–120, 10.1109/OAJPE.2022.3140314.
Jia, Y, Bai, X, Zheng, L, Weng, Z, Li, Y, Convopf-dop: a data-driven method for solving ac-opf based on cnn considering different operation patterns. IEEE Trans Power Syst 38:1 (2022), 853–860.
Rahman, J, Feng, C, Zhang, J, A learning-augmented approach for ac optimal power flow. Int J Electr Power Energy Syst, 130, 2021, 106908.
Rahman, J, Feng, C, Zhang, J, Machine learning-aided security constrained optimal power flow., 2020 IEEE Power & Energy Society General Meeting (PESGM), 2020, IEEE, 1–5, 10.1109/PESGM41954.2020.9281941.
Zhou, M, Chen, M, Low, SH, Deepopf-ft: one deep neural network for multiple ac-opf problems with flexible topology. IEEE Trans Power Syst 38:1 (2022), 964–967.
Huang, W, Pan, X, Chen, M, Low, SH, Deepopf-v: Solving ac-opf problems efficiently. IEEE Trans Power Syst 37:1 (2022), 800–803, 10.1109/TPWRS.2021.3114092.
Pan, X, Huang, W, Chen, M, Low, SH, Deepopf-al: augmented learning for solving ac-opf problems with a multi-valued load-solution mapping., Proceedings of the 14th ACM International Conference on Future Energy Systems, 2023, 42–47.
Vyakaranam, B, Mahapatra, K, Li, X, Wang, H, Etingov, P, Hou, Z, et al. Novel data-driven distributed learning framework for solving ac power flow for large interconnected systems. IEEE Open Access J Power Energy 8 (2021), 281–292.
Park, S, Chen, W, Mak, TW, Van Hentenryck, P, Compact optimization learning for ac optimal power flow. IEEE Trans Power Syst, 2023.
Klamkin, M, Tanneau, M, Mak, TWK, Van Hentenryck, P, Active bucketized learning for acopf optimization proxies, 2022 arXiv:2208.07497 arXiv preprint.
Zhai, Y, Ye, H, Zhang, L, Ge, Y, Model information-aided deep learning for corrective ac power flow., 2022 IEEE Power & Energy Society General Meeting (PESGM), 2022, IEEE, 1–5, 10.1109/PESGM48719.2022.9916916.
Zhao, T, Pan, X, Chen, M, Venzke, A, Low, SH, Deepopf+: a deep neural network approach for dc optimal power flow for ensuring feasibility., 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), 2020, IEEE, 1–6.
Pan, X, Zhao, T, Chen, M, Zhang, S, Deepopf: a deep neural network approach for security-constrained dc optimal power flow. IEEE Trans Power Syst 36:3 (2020), 1725–1735.
Pan, X, Deepopf: deep neural networks for optimal power flow., Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, 2021, 250–251.
Zhao, T, Pan, X, Chen, M, Low, SH, Ensuring dnn solution feasibility for optimization problems with convex constraints and its application to dc optimal power flow problems, 2021 arXiv:2112.08091 arXiv preprint.
Wang, Z, Menke, J-H, Schäfer, F, Braun, M, Scheidler, A, Approximating multi-purpose ac optimal power flow with reinforcement trained artificial neural network. Energy AI, 7, 2022, 100133.
Guha, N, Wang, Z, Wytock, M, Majumdar, A, Machine learning for ac optimal power flow, 2019 arXiv:1910.08842 arXiv preprint.
Hu, Z, Zhang, H, Optimal power flow based on physical-model-integrated neural network with worth-learning data generation, 2023 arXiv:2301.03766 arXiv preprint.
Nellikkath, R, Chatzivasileiadis, S, Physics-informed neural networks for minimising worst-case violations in dc optimal power flow., 2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), 2021, 419–424, 10.1109/SmartGridComm51999.2021.9632308.
Nellikkath, R, Chatzivasileiadis, S, Physics-informed neural networks for ac optimal power flow. Electr Power Syst Res, 212, 2022, 108412.
Venzke, A, Qu, G, Low, S, Chatzivasileiadis, S, Learning optimal power flow: worst-case guarantees for neural networks., 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), 2020, IEEE, 1–7.
Chen, K, Bose, S, Zhang, Y, Unsupervised deep learning for ac optimal power flow via lagrangian duality., GLOBECOM 2022-2022 IEEE Global Communications Conference, 2022, IEEE, 5305–5310.
Fioretto, F, Mak, TWK, Van Hentenryck, P, Predicting ac optimal power flows: combining deep learning and lagrangian dual methods., Proceedings of the AAAI conference on artificial intelligence, 2020, 630–637.
Fioretto, F, Van Hentenryck, P, Mak, TW, Tran, C, Baldo, F, Lombardi, M, Lagrangian duality for constrained deep learning., Machine Learning and Knowledge Discovery in Databases. Applied Data Science and Demo Track: European Conference, ECML PKDD 2020, 2021, Springer, 118–135.
Chatzos, M, Fioretto, F, Mak, TWK, Van Hentenryck, P, High-fidelity machine learning approximations of large-scale optimal power flow, 2020 arXiv:2006.16356 arXiv preprint.
Mak, TW, Fioretto, F, Van Hentenryck, P, Load embeddings for scalable{AC-OPF} learning, ArXivorg, 2023.
Chatzos, M, Mak, TWK, Hentenryck, PV, Spatial network decomposition for fast and scalable ac-opf learning. IEEE Trans Power Syst 37:4 (2022), 2601–2612, 10.1109/TPWRS.2021.3124726.
Dinh, MH, Fioretto, F, Mohammadian, M, Baker, K, Towards understanding the unreasonable effectiveness of learning ac-opf solutions, 2021 arXiv:2111.11168 arXiv preprint.
Mohammadian, M, Baker, K, Dinh, MH, Fioretto, F, Learning solutions for intertemporal power systems optimization with recurrent neural networks., 2022 17th International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), 2022, IEEE, 1–6, 10.1109/PMAPS53380.2022.9810638.
Kotary, J, Fioretto, F, Van Hentenryck, P, Learning hard optimization problems: a data generation perspective. Adv Neural Inf Process Syst 34 (2021), 24981–24992.
Park, S, Van Hentenryck, P, Self-supervised primal-dual learning for constrained optimization., Proceedings of the AAAI Conference on Artificial Intelligence, 2023, 4052–4060.
Chen, G, Qin, J, On the choice of loss function in learning-based optimal power flow, 2024 arXiv:2402.00773 arXiv preprint.
Kim, M, Kim, H, Projection-aware deep neural network for dc optimal power flow without constraint violations., 2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), 2022, IEEE, 116–121, 10.1109/SmartGridComm52983.2022.9961047.
Li, M, Kolouri, S, Mohammadi, J, Learning to solve optimization problems with hard linear constraints. IEEE Acces 11 (2023), 59995–60004.
Zhang, L, Tabas, D, Zhang, B, An efficient learning-based solver for two-stage dc optimal power flow with feasibility guarantees, 2023.
Kolter, MZ, Duvenaud, D, Johnson, M, Deep implicit layers-neural odes, deep equilibirum models, and beyond, 2020, NeurIPS tutorial, 2020.
Amos, B, Kolter, JZ, Optnet: differentiable optimization as a layer in neural networks., International Conference on Machine Learning, PMLR, 2017, 136–145.
Chen, B, Donti, PL, Baker, K, Kolter, JZ, Bergés, M, Enforcing policy feasibility constraints through differentiable projection for energy optimization., Proceedings of the Twelfth ACM International Conference on Future Energy Systems, 2021, 199–210.
Xia, F, Sun, K, Yu, S, Aziz, A, Wan, L, Pan, S, et al. Graph learning: a survey. IEEE Trans Artif Intell 2:2 (2021), 109–127.
Hansen, JB, Anfinsen, SN, Bianchi, FM, Power flow balancing with decentralized graph neural networks., IEEE Transactions on Power Systems, 2022.
Liu, S, Wu, C, Zhu, H, Topology-aware graph neural networks for learning feasible and adaptive ac-opf solutions., IEEE Transactions on Power Systems, 2022.
Liu, S, Wu, C, Zhu, H, Graph neural networks for learning real-time prices in electricity market, 2021 arXiv:2106.10529 arXiv preprint.
Gao, M, Yu, J, Yang, Z, Zhao, J, A physics-guided graph convolution neural network for optimal power flow., IEEE Transactions on Power Systems, 2023.
Yang, M, Liu, J, Qiu, G, Liu, T, Tang, Z, Ac optimal power flows: combining lagrangian dual and physics-guided graph neutral networks, Authorea Preprints, 2023.
Wolgast, T, Nieße, A, Learning the optimal power flow: environment design matters, 2024 arXiv:2403.17831 arXiv preprint.
Nie H, Chen Y, Song Y, Huang S. A general real-time opf algorithm using ddpg with multiple simulation platforms. 2019 IEEE innovative smart grid technologies-asia (ISGT asia). IEEE; 2019. p. 3713–18.
Yan, Z, Xu, Y, Real-time optimal power flow: a Lagrangian based deep reinforcement learning approach. IEEE Trans Power Syst 35:4 (2020), 3270–3273.
Xiao, T, Chen, Y, Diao, H, Huang, S, Shen, C, On fast-converged reinforcement learning for optimal dispatch of large-scale power systems under transient security constraints, 2023 arXiv:2304.08320 arXiv preprint.
Zhen, H, Zhai, H, Ma, W, Zhao, L, Weng, Y, Xu, Y, et al. Design and tests of reinforcement-learning-based optimal power flow solution generator. Energy Rep 8 (2022), 43–50.
Woo, JH, Wu, L, Park, J-B, Roh, JH, Real-time optimal power flow using twin delayed deep deterministic policy gradient algorithm. IEEE Acces 8 (2020), 213611–213618, 10.1109/ACCESS.2020.3041007.
Wu, T, Scaglione, A, Arnold, D, Constrained reinforcement learning for stochastic dynamic optimal power flow control., 2023 IEEE Power & Energy Society General Meeting (PESGM), 2023, IEEE, 1–5.
Han, X, Mu, C, Yan, J, Niu, Z, An autonomous control technology based on deep reinforcement learning for optimal active power dispatch. Int J Electr Power Energy Syst, 145, 2023, 108686.
Sayed, AR, Wang, C, Anis, H, Bi, T, Feasibility constrained online calculation for real-time optimal power flow: a convex constrained deep reinforcement learning approach., IEEE Transactions on Power Systems, 2022.
Wang, T, Tang, Y, Transfer-reinforcement-learning-based rescheduling of differential power grids considering security constraints. Appl Energy, 306, 2022, 118121.
Sayed, AR, Zhang, X, Wang, G, Wang, C, Qiu, J, Optimal operable power flow: sample-efficient holomorphic embedding-based reinforcement learning., IEEE Transactions on Power Systems, 2023, 1–13, 10.1109/TPWRS.2023.3266773.
Huang, Z, Yu, T, Pan, Z, Deng, B, Zhang, X, Wu, Y, et al. Stochastic dynamic power dispatch with high generalization and few-shot adaption via contextual meta graph reinforcement learning. Int J Electr Power Energy Syst, 162, 2024, 110272.
Zhou, Y, Zhang, B, Xu, C, Lan, T, Diao, R, Shi, D, et al. Lee, a data-driven method for fast ac optimal power flow solutions via deep reinforcement learning. J Modern Power Syst Clean Energy 8:6 (2020), 1128–1139.
Zhou, Y, Lee, W, Diao, R, Shi, D, Deep reinforcement learning based real-time ac optimal power flow considering uncertainties. J Modern Power Syst Clean Energy 10:5 (2021), 1098–1109.
López-Cardona, Á, Bernárdez, G, Barlet-Ros, P, Cabellos-Aparicio, A, Proximal policy optimization with graph neural networks for optimal power flow, 2022 arXiv:2212.12470 arXiv preprint.
Zhao, Y, Liu, J, Liu, X, Yuan, K, Ren, K, Yang, M, A graph-based deep reinforcement learning framework for autonomous power dispatch on power systems with changing topologies., 2022 IEEE Sustainable Power and Energy Conference (iSPEC), 2022, IEEE, 1–5, 10.1109/iSPEC54162.2022.10033001.
Donnot, B, Grid2op- a testbed platform to model sequential decision making in power systems, GitHub repository, 2020.
Misra, S, Roald, L, Ng, Y, Learning for constrained optimization: identifying optimal active constraint sets. INFORMS J Comput 34:1 (2022), 463–480, 10.1287/ijoc.2020.1037.
Robson, A, Jamei, M, Ududec, C, Mones, L, Learning an optimally reduced formulation of opf through meta-optimization, 2019 arXiv:1911.06784 arXiv preprint.
Deka, D, Misra, S, Learning for dc-opf: classifying active sets using neural nets., 2019 IEEE Milan PowerTech, 2019, IEEE, 1–6.
Wu, H, Wang, M, Xu, Z, Jia, Y, Active constraint identification assisted dc optimal power flow., 2022 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia), 2022, IEEE, 185–189, 10.1109/ICPSAsia55496.2022.9949655.
Phamh, T, Li, X, Constraints and variables reduction for optimal power flow using hierarchical graph neural networks with virtual node-splitting, 2024 arXiv:2411.06268 arXiv preprint.
Khazaei, H, Zhao, Y, Physics-aware fast learning and inference for predicting active set of dc-opf., 2022 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2022, IEEE, 1–5.
Liu, S, Guo, Y, Tang, W, Sun, H, Huang, W, Hou, J, Varying condition scopf optimization based on deep learning and knowledge graph., IEEE Transactions on Power Systems, 2022.
Liu, S, Guo, Y, Tang, W, Sun, H, Huang, W, Predicting active constraints set in security-constrained optimal power flow via deep neural network., 2021 IEEE Power & Energy Society General Meeting (PESGM), 2021, IEEE, 01–05, 10.1109/PESGM46819.2021.9637964.
Hasan, F, Kargarian, A, Mohammadi, J, Hybrid learning aided inactive constraints filtering algorithm to enhance ac opf solution time. IEEE Trans Ind Appl 57:2 (2021), 1325–1334.
Chen, Y, Zhang, L, Zhang, B, Learning to solve dcopf: a duality approach. Electr Power Syst Res, 213, 2022, 108595.
Bose, S, Chen, K, Zhang, Y, A mixture-of-gradient-experts framework for accelerating ac optimal power flow, 2024 https://arxiv.org/abs/2312.07276.
Ferrando, R, Pagnier, L, Mieth, R, Liang, Z, Dvorkin, Y, Bienstock, D, et al. Physics-informed machine learning for electricity markets: a nyiso case study., IEEE Transactions on Energy Markets, Policy and Regulation, 2023.
He, X, Wen, H, Zhang, Y, Chen, Y, Enabling fast unit commitment constraint screening via learning cost model, 2022 https://arxiv.org/abs/2212.00483.
Jiménez-Cordero, A, Morales, JM, Pineda, S, Warm-starting constraint generation for mixed-integer optimization: a machine learning approach. Knowl-Based Syst, 253, 2022, 109570, 10.1016/j.knosys.2022.109570 https://www.sciencedirect.com/science/article/pii/S0950705122007894.
Pineda, S, Morales, JM, Jiménez-Cordero, A, Data-driven screening of network constraints for unit commitment. IEEE Trans Power Syst 35:5 (2020), 3695–3705, 10.1109/TPWRS.2020.2980212.
Diehl, F, Warm-starting ac optimal power flow with graph neural networks., 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), 2019, 1–6.
Baker, K, Learning warm-start points for ac optimal power flow., 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP), 2019, IEEE, 1–6.
Sadat, SA, Sahraei-Ardakani, M, Initializing successive linear programming solver for acopf using machine learning., 2020 52nd North American Power Symposium (NAPS), 2021, IEEE, 1–6, 10.1109/NAPS50074.2021.9449706.
Dong, W, Xie, Z, Kestor, G, Li, D, Smart-pgsim: using neural network to accelerate ac-opf power grid simulation., SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, 2020, IEEE, 1–15, 10.1109/SC41405.2020.00067.
Zhang, L, Zhang, B, Learning to solve the ac optimal power flow via a lagrangian approach., 2022 North American Power Symposium (NAPS), 2022, IEEE, 1–6, 10.1109/NAPS56150.2022.10012237.
Zeng, S, Kody, A, Kim, Y, Kim, K, Molzahn, DK, A reinforcement learning approach to parameter selection for distributed optimal power flow. Electr Power Syst Res, 212, 2022, 108546.
Biagioni, D, Graf, P, Zhang, X, Zamzam, AS, Baker, K, King, J, Learning-accelerated admm for distributed dc optimal power flow. IEEE Control Syst Lett 6 (2020), 1–6.
Cengil, F, Nagarajan, H, Bent, R, Eksioglu, S, Eksioglu, B, Learning to accelerate globally optimal solutions to the ac optimal power flow problem. Electr Power Syst Res, 212, 2022, 108275.
Murzakhanov, I, Venzke, A, Misyris, GS, Chatzivasileiadis, S, Neural networks for encoding dynamic security-constrained optimal power flow, 2020 arXiv:2003.07939 arXiv preprint.
Liu, Y, Wang, Y, Zhang, N, Lu, D, Kang, C, A data-driven approach to linearize power flow equations considering measurement noise. IEEE Trans Smart Grid 11:3 (2020), 2576–2587, 10.1109/TSG.2019.2957799.
Hu, R, Li, Q, Lei, S, Ensemble learning based linear power flow., 2020 IEEE Power & Energy Society General Meeting (PESGM), 2020, IEEE, 1–5, 10.1109/PESGM41954.2020.9281793.
Hu, R, Li, Q, Qiu, F, Ensemble learning based convex approximation of three-phase power flow. IEEE Trans Power Syst 36:5 (2021), 4042–4051, 10.1109/TPWRS.2021.3055481.
Taheri, B, Molzahn, DK, Ac power flow feasibility restoration via a state estimation-based post-processing algorithm. Electr Power Syst Res, 235, 2024, 110642.
Taheri, B, Molzahn, DK, Restoring ac power flow feasibility from relaxed and approximated optimal power flow models., 2023 American Control Conference (ACC), 2023, IEEE, 4463–4470.
Han, J, Wang, W, Yang, C, Niu, M, Yang, C, Yan, L, et al. Frmnet: a feasibility restoration mapping deep neural network for ac optimal power flow., IEEE Transactions on Power Systems, 2024.
Stratigakos, A, Pineda, S, Morales, JM, Kariniotakis, G, Interpretable machine learning for dc optimal power flow with feasibility guarantees., IEEE Transactions on Power Systems, 2023.
Dinh, MH, Fioretto, F, Mohammadian, M, Baker, K, An analysis of the reliability of ac optimal power flow deep learning proxies., 2023 IEEE PES Innovative Smart Grid Technologies Latin America (ISGT-LA), 2023, IEEE, 170–174.
Pineda, S, Fernández-Blanco, R, Morales, JM, Time-adaptive unit commitment. IEEE Trans Power Syst 34:5 (2019), 3869–3878, 10.1109/TPWRS.2019.2903486.
Khaloie, H, Faraji, J, Vallée, F, Lai, CS, Toubeau, J-F, Lai, LL, Risk-aware battery bidding with a novel benchmark selection under second-order stochastic dominance. IEEE Trans Ind Appl 59:3 (2023), 3009–3018, 10.1109/TIA.2023.3245047.
Nick, M, Alizadeh-Mousavi, O, Cherkaoui, R, Paolone, M, Security constrained unit commitment with dynamic thermal line rating. IEEE Trans Power Syst 31:3 (2016), 2014–2025, 10.1109/TPWRS.2015.2445826.
Zhao, C, Wang, J, Watson, J-P, Guan, Y, Multi-stage robust unit commitment considering wind and demand response uncertainties. IEEE Trans Power Syst 28:3 (2013), 2708–2717.
Constante-Flores, GE, Conejo, AJ, Qiu, F, Daily scheduling of generating units with natural-gas market constraints. Eur J Oper Res 313:1 (2024), 387–399.
Khaloie, H, Vallée, F, Day-ahead dispatch of liquid air energy storage coupled with lng regasification in electricity and lng markets. IEEE Trans Power Syst, 2023, 1–14, 10.1109/TPWRS.2023.3324150.
Khaloie, H, Toubeau, J-F, Vallée, F, Lai, CS, Lai, LL, An innovative coalitional trading model for a biomass power plant paired with green energy resources. IEEE Trans Sustain Energy 13:2 (2022), 892–904, 10.1109/TSTE.2021.3138777.
Oikonomou, K, Parvania, M, Optimal coordination of water distribution energy flexibility with power systems operation. IEEE Trans Smart Grid 10:1 (2019), 1101–1110, 10.1109/TSG.2018.2824308.
Farahani, A, Voghoei, S, Rasheed, K, Arabnia, HR, A brief review of domain adaptation., Advances in data science and information engineering: proceedings from ICDATA 2020 and IKE 2020, 2021, 877–894.
Zhuang, F, Qi, Z, Duan, K, Xi, D, Zhu, Y, Zhu, H, et al. A comprehensive survey on transfer learning., Proceedings of the IEEE, 2020, 43–76.
Ganaie, MA, Hu, M, Malik, A, Tanveer, M, Suganthan, P, Ensemble deep learning: A review. Eng Appl Artif Intel, 115, 2022, 105151.
Zöller, M-A, Huber, MF, Benchmark and survey of automated machine learning frameworks. J Artif Intell Res 70 (2021), 409–472.
Jia, W, Sun, M, Lian, J, Hou, S, Feature dimensionality reduction: a review, complex & intelligent Systems, 2022.
Castro, FM, Marín-Jiménez, MJ, Guil, N, Schmid, C, Alahari, K, End-to-end incremental learning., Proceedings of the European conference on computer vision (ECCV), 2018, 233–248.
Mumuni, A, Mumuni, F, Data augmentation: a comprehensive survey of modern approaches, array, 2022.
Deng, L, Li, G, Han, S, Shi, L, Xie, Y, Model compression and hardware acceleration for neural networks: a comprehensive survey., Proceedings of the IEEE, 2020, 485–532.
Verbraeken, J, Wolting, M, Katzy, J, Kloppenburg, J, Verbelen, T, Rellermeyer, JS, A survey on distributed machine learning. ACM Comput Surv (CSUR) 53:2 (2020), 1–33.
Bugaje, A-AB, Cremer, JL, Strbac, G, Generating quality datasets for real-time security assessment: balancing historically relevant and rare feasible operating conditions. Int J Electr Power Energy Syst, 154, 2023, 109427.
Gao, M, Yu, J, Yang, Z, Improving the robustness of data-driven opf by nonlinearity-focused sampling., IEEE Transactions on Power Systems, 2024.
Klamkin, M, Tanneau, M, Mak, TW, Van Hentenryck, P, Bucketized active sampling for learning acopf. Electr Power Syst Res, 235, 2024, 110697.
Joswig-Jones, T, Baker, K, Zamzam, AS, Opf-learn: an open-source framework for creating representative ac optimal power flow datasets., 2022 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2022, IEEE, 1–5.
Nadal, IV, Chevalier, S, Scalable bilevel optimization for generating maximally representative opf datasets., 2023 IEEE PES Innovative Smart Grid Technologies Europe (ISGT EUROPE), 2023, IEEE, 1–6.
Lovett, S, Zgubic, M, Liguori, S, Madjiheurem, S, Tomlinson, H, Elster, S, et al. Opfdata: large-scale datasets for ac optimal power flow with topological perturbations, 2024 arXiv:2406.07234 arXiv preprint.
S&p 500® | s&p dow jones indices. https://www.spglobal.com/spdji/en/indices/equity/sp-500/#overview.
Imagenet. https://www.image-net.org/.
Babaeinejadsarookolaee, S, Birchfield, A, Christie, RD, Coffrin, C, DeMarco, C, Diao, R, et al. The power grid library for benchmarking ac optimal power flow algorithms, 2019 arXiv:1908.02788 arXiv preprint.
Li, L, Fan, Y, Tse, M, Lin, K-Y, A review of applications in federated learning. Comput Ind Eng, 149, 2020, 106854.
Arora, S, Doshi, P, A survey of inverse reinforcement learning: challenges, methods and progress. Artif Intell, 297, 2021, 103500.
Van Moffaert, K, Nowé, A, Multi-objective reinforcement learning using sets of pareto dominating policies. J Mach Learn Res 15:1 (2014), 3483–3512.
Ergun, H, Dave, J, Van Hertem, D, Geth, F, Optimal power flow for ac–dc grids: formulation, convex relaxation, linear approximation, and implementation. IEEE Trans Power Syst 34:4 (2019), 2980–2990, 10.1109/TPWRS.2019.2897835.
