Abstract
Power dispatch is a core problem for smart grid operations. It aims to provide optimal operating points within a transmission network while power demands are changing over space and time. This function needs to be run every few minutes throughout the day; thus, a fast, accurate solution is of vital importance. However, due to the complexity of the problem, reliable and computationally efficient solutions are still under development. This issue will become more urgent and complicated as the integration of intermittent renewable energies increases and the severity of uncertain disasters gets worse. With the recent success of artificial intelligence in various industries, deep learning becomes a promising direction for power engineering as well, and the research community begins to rethink the problem of power dispatch. This paper reviews the recent progress in smart grid dispatch from a deep learning perspective. Through this paper, we hope to advance not only the development of smart grids but also the ecosystem of artificial intelligence.
摘要
电力调度是智能电网运行的一大核心问题, 其目的是在满足时空变化的电力负荷条件下提供电网的最优运行点。这一功能需要在一天内每隔几分钟运行一次, 因此快速、准确的调度决策方法至关重要。但是, 由于问题的复杂性, 可靠且高效的决策方法仍在不断探索的过程中。随着可再生能源的大规模并网以及灾害性气候的不断恶化, 智能电网对调度决策方法提出了更为严苛的要求。近年来, 以深度学习为代表的人工智能方法在不少领域取得巨大成功, 因此深度学习也被电气工程领域寄予厚望, 国内外研究者开始重新思考智能电网的调度决策问题。本文即从深度学习这一角度对智能电网调度决策相关研究进行综述, 旨在促进智能电网领域发展的同时促进人工智能生态的发展。
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ardakani AJ, Bouffard F, 2018. Prediction of umbrella constraints. Power Systems Computation Conf, p.1–7. https://doi.org/10.23919/PSCC.2018.8450586
Babaeinejadsarookolaee S, Birchfield A, Christie RD, et al., 2021. The power grid library for benchmarking AC optimal power flow algorithms. https://arxiv.org/abs/1908.02788
Baker K, 2019. Learning warm-start points for AC optimal power flow. IEEE 29th Int Workshop on Machine Learning for Signal Processing, p.1–6. https://doi.org/10.1109/MLSP.2019.8918690
Baker K, 2020. A learning-boosted quasi-Newton method for AC optimal power flow. Workshop on Machine Learning for Engineering Modeling, Simulation and Design, p.1–7.
Biagioni D, Graf P, Zhang XY, et al., 2020. Learning-accelerated ADMM for distributed DC optimal power flow. IEEE Contr Syst Lett, 6:1–6. https://doi.org/10.1109/LCSYS.2020.3044839
Blundell C, Cornebise J, Kavukcuoglu K, et al., 2015. Weight uncertainty in neural networks. Proc 32nd Int Conf on Machine Learning, p.1613–1622.
Bojarski M, Del Testa D, Dworakowski D, et al., 2016. End to end learning for self-driving cars. https://arxiv.org/abs/1604.07316v1
Bose BK, 2017. Artificial intelligence techniques in smart grid and renewable energy systems—some example applications. Proc IEEE, 105(11):2262–2273. https://doi.org/10.1109/JPROC.2017.2756596
Buchanan BG, 2005. A (very) brief history of artificial intelligence. AI Mag, 26(4):53–60.
Cambria E, White B, 2014. Jumping NLP curves: a review of natural language processing research. IEEE Comput Intell Mag, 9(2):48–57. https://doi.org/10.1109/MCI.2014.2307227
Capitanescu F, Wehenkel L, 2013. Experiments with the interior-point method for solving large scale optimal power flow problems. Electr Power Syst Res, 95:276–283. https://doi.org/10.1016/j.epsr.2012.10.001
Carpentier J, 1979. Optimal power flows. Int J Electr Power Energy Syst, 1(1):3–15. https://doi.org/10.1016/0142-0615(79)90026-7
Changpinyo S, Chao WL, Gong BQ, et al., 2016. Synthesized classifiers for zero-shot learning. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.5327–5336. https://doi.org/10.1109/CVPR.2016.575
Chatzimparmpas A, Martins RM, Jusufi I, et al., 2020. A survey of surveys on the use of visualization for interpreting machine learning models. Inform Visual, 19(3):207–233. https://doi.org/10.1177/1473871620904671
Chatzos M, Fioretto F, Mak TWK, et al., 2020. High-fidelity machine learning approximations of large-scale optimal power flow. https://arxiv.org/abs/2006.16356
Chen LJ, Tate JE, 2020. Hot-starting the AC power flow with convolutional neural networks. https://arxiv.org/abs/2004.09342
Chen YZ, Zhang BS, 2020. Learning to solve network flow problems via neural decoding. https://arxiv.org/abs/2002.04091
Chen YZ, Tan YS, Deka D, 2018. Is machine learning in power systems vulnerable? IEEE Int Conf on Communications, Control, and Computing Technologies for Smart Grids, p.1–6. https://doi.org/10.1109/SmartGridComm.2018.8587547
Coffrin C, Gordon D, Scott P, 2019. NESTA, the NICTA energy system test case archive. https://arxiv.org/abs/1411.0359
Deka D, Misra S, 2019. Learning for DC-OPF: classifying active sets using neural nets. IEEE Milan PowerTech, p.1–6. https://doi.org/10.1109/PTC.2019.8810819
Diehl F, 2019. Warm-starting AC optimal power flow with graph neural networks. Proc 33rd Conf on Neural Information Processing Systems, p.1–6.
Dror R, Baumer G, Bogomolov M, et al., 2017. Replicability analysis for natural language processing: testing significance with multiple datasets. Trans Assoc Comput Linguist, 5:471–486. https://doi.org/10.1162/tacl_a_00074
Duchesne L, Karangelos E, Sutera A, et al., 2020a. Machine learning for ranking day-ahead decisions in the context of short-term operation planning. Electr Power Syst Res, 189:106548. https://doi.org/10.1016/j.epsr.2020.106548
Duchesne L, Karangelos E, Wehenkel L, 2020b. Recent developments in machine learning for energy systems reliability management. Proc IEEE, 108(9):1656–1676. https://doi.org/10.1109/JPROC.2020.2988715
Eskandarpour R, Khodaei A, 2017. Machine learning based power grid outage prediction in response to extreme events. IEEE Trans Power Syst, 32(4):3315–3316. https://doi.org/10.1109/TPWRS.2016.2631895
Fioretto F, Mak TWK, van Hentenryck P, 2019. Predicting AC optimal power flows: combining deep learning and Lagrangian dual methods. https://arxiv.org/abs/1909.10461
Gandhi O, Rodríguez-Gallegos CD, Srinivasan D, 2016. Review of optimization of power dispatch in renewable energy system. IEEE Innovative Smart Grid Technologies-Asia, p.250–257. https://doi.org/10.1109/ISGT-Asia.2016.7796394
Gharavi H, Ghafurian R, 2011. Smart grid: the electric energy system of the future. Proc IEEE, 99(6):917–921. https://doi.org/10.1109/JPROC.2011.2124210
Glasmachers T, 2017. Limits of end-to-end learning. Proc Mach Learn Res, 77:17–32.
Goodfellow I, Bengio Y, Courville A, et al., 2016. Deep Learning. MIT Press, Cambridge, USA.
Guha N, Wang ZC, Wytock M, et al., 2019. Machine learning for AC optimal power flow. Climate Change Workshop at Int Conf on Machine Learning, p.1–4.
Gurobi Optimization, 2019. Gurobi optimizer reference manual. Available from https://www.gurobi.com/wp-content/plugins/hd_documentations/documentation/9.0/refman.pdf [Accessed on Dec. 24, 2020].
Haridas AV, Marimuthu R, Sivakumar VG, 2018. A critical review and analysis on techniques of speech recognition: the road ahead. Int J Knowl-Based Intell Eng Syst, 22(1):39–57. https://doi.org/10.3233/KES-180374
Hasan F, Kargarian A, Mohammadi A, 2020. A survey on applications of machine learning for optimal power flow. IEEE Texas Power and Energy Conf, p.1–6. https://doi.org/10.1109/TPEC48276.2020.9042547
He KM, Zhang XY, Ren SQ, et al., 2016. Deep residual learning for image recognition. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.770–778. https://doi.org/10.1109/CVPR.2016.90
Hey T, Tansley S, Tolle K, 2009. The Fourth Paradigm: Data-Intensive Scientific Discovery. Microsoft Research, Redmond, WA, USA.
Hossain E, Han Z, Poor HV, 2012. Smart Grid Communications and Networking. Cambridge University Press, Cambridge, UK.
Hu XY, Hu HJ, Verma S, et al., 2021. Physics-guided deep neural networks for power flow analysis. IEEE Trans Power Syst, 36(3):2082–2092. https://doi.org/10.1109/TPWRS.2020.3029557
Huang G, Wen YF, Bao YK, et al., 2015. Comprehensive decoupled risk-limiting dispatch. IEEE Power & Energy Society General Meeting, p.1–5. https://doi.org/10.1109/PESGM.2015.7286064
Huang G, Wang JH, Chen C, et al., 2017a. Integration of preventive and emergency responses for power grid resilience enhancement. IEEE Trans Power Syst, 32(6):4451–4463. https://doi.org/10.1109/Tpwrs.2017.2685640
Huang G, Wang JH, Chen C, et al., 2017b. System resilience enhancement: smart grid and beyond. Front Eng Manag, 4(3):271–282. https://doi.org/10.15302/J-FEM-2017030
Huang G, Wang JH, Chen C, et al., 2019. Cyber-constrained optimal power flow model for smart grid resilience enhancement. IEEE Trans Smart Grid, 10(5):5547–5555. https://doi.org/10.1109/TSG.2018.2885025
Huang G, Wu C, Hu YF, et al., 2021. Serverless distributed learning for smart grid analytics. Chinese Phys B, 30: 088802. https://doi.org/10.1088/1674-1056/abe232
Ibrahim MR, Haworth J, Cheng T, 2020. Understanding cities with machine eyes: a review of deep computer vision in urban analytics. Cities, 96:102481. https://doi.org/10.1016/j.cities.2019.102481
Jaller M, Otero-Palencia C, Pahwa A, 2020. Automation, electrification, and shared mobility in urban freight: opportunities and challenges. Transport Res Procedia, 46:13–20. https://doi.org/10.1016/j.trpro.2020.03.158
Jamei M, Mones L, Robson A, et al., 2019. Metaoptimization of optimal power flow. Climate Change Workshop at Int Conf on Machine Learning, p.1–3.
Kairouz P, McMahan HB, Avent B, et al., 2019. Advances and open problems in federated learning. https://arxiv.org/abs/1912.04977v3
King RTFA, Tu XP, Dessaint LA, et al., 2016. Multi-contingency transient stability-constrained optimal power flow using multilayer feedforward neural networks. IEEE Canadian Conf on Electrical and Computer Engineering, p.1–6. https://doi.org/10.1109/CCECE.2016.7726774
Kingma DP, Ba J, 2015. Adam: a method for stochastic optimization. Int Conf for Learning Representations, p.1–15.
Kundur P, 1994. Power System Stability and Control. McGraw-Hill, New York, USA.
Le QV, Ngiam J, Coates A, et al., 2011. On optimization methods for deep learning. Proc 28th Int Conf on Machine Learning, p.265–272.
LeCun Y, Bengio Y, Hinton G, 2015. Deep learning. Nature, 521(7553):436–444. https://doi.org/10.1038/nature14539
Li T, Sahu AK, Talwalkar A, et al., 2020. Federated learning: challenges, methods, and future directions. IEEE Signal Process Mag, 37(3):50–60. https://doi.org/10.1109/MSP.2020.2975749
Liu TJ, Liu YB, Liu JY, et al., 2020. A Bayesian learning based scheme for online dynamic security assessment and preventive control. IEEE Trans Power Syst, 35(5):4088–4099. https://doi.org/10.1109/TPWRS.2020.2983477
Liu ZF, 2020. Research on emergency response processing model of thermal power enterprise based on epidemic situation. Int Conf on Wireless Communications and Smart Grid, p.171–174. https://doi.org/10.1109/ICWCSG50807.2020.00045
Mai TT, Jadun P, Logan JS, et al., 2018. Electrification Futures Study: Scenarios of Electric Technology Adoption and Power Consumption for the United States. NREL/TP-6A20-71500, National Renewable Energy Laboratory, United States.
Mathis A, Mamidanna P, Cury KM, et al., 2018. DeepLab-Cut: markerless pose estimation of user-defined body parts with deep learning. Nat Neurosci, 21(9):1281–1289. https://doi.org/10.1038/s41593-018-0209-y
McMahan HB, Ramage D, 2017. Federated learning: collaborative machine learning without centralized training data. Google Research Blog. Available from https://ai.googleblog.com/2017/04/federated-learning-collaborative.html [Accessed on Dec. 24, 2020].
Misra S, Roald L, Ng Y, 2019. Learning for constrained optimization: identifying optimal active constraint sets. https://arxiv.org/abs/1802.09639
Mohamed MA, Eltamaly AM, 2018. Modeling and Simulation of Smart Grid Integrated with Hybrid Renewable Energy Systems. Springer, Switzerland.
Oughton EJ, Skelton A, Horne RB, et al., 2017. Quantifying the daily economic impact of extreme space weather due to failure in electricity transmission infrastructure. Space Wea, 15(1):65–83. https://doi.org/10.1002/2016SW001491
Owerko D, Gama F, Ribeiro A, 2020. Optimal power flow using graph neural networks. IEEE Int Conf on Acoustics, Speech and Signal Processing, p.5930–5934. https://doi.org/10.1109/ICASSP40776.2020.9053140
Padhy NP, 2004. Unit commitment—a bibliographical survey. IEEE Trans Power Syst, 19(2):1196–1205. https://doi.org/10.1109/TPWRS.2003.821611
Pan X, Zhao TY, Chen MH, 2019. DeepOPF: deep neural network for DC optimal power flow. IEEE Int Conf on Communications, Control, and Computing Technologies for Smart Grids, p.1–6. https://doi.org/10.1109/SmartGridComm.2019.8909795
Pan X, Zhao TY, Chen MH, et al., 2021a. DeepOPF: a deep neural network approach for security-constrained DC optimal power flow. IEEE Trans Power Syst, 36(3):1725–1735. https://doi.org/10.1109/TPWRS.2020.3026379
Pan X, Chen MH, Zhao TY, et al., 2021b. DeepOPF: a feasibility-optimized deep neural network approach for AC optimal power flow problems. https://arxiv.org/abs/2007.01002
Papernot N, McDaniel P, Jha S, et al., 2016. The limitations of deep learning in adversarial settings. IEEE European Symp on Security and Privacy, p.372–387. https://doi.org/10.1109/EuroSP.2016.36
Prabhu VU, Birhane A, 2020. Large image datasets: a pyrrhic win for computer vision? https://arxiv.org/abs/2006.16923
Rahman J, Feng C, Zhang J, 2020. Machine learning-aided security constrained optimal power flow. IEEE Power & Energy Society General Meeting, p.1–5. https://doi.org/10.1109/PESGM41954.2020.9281941
Ravi S, Larochelle H, 2016. Optimization as a model for few-shot learning. Int Conf for Learning Representations, p.1–11.
Robson A, Jamei M, Ududec C, et al., 2020. Learning an optimally reduced formulation of OPF through metaoptimization. https://arxiv.org/abs/1911.06784
Ruan GC, Zhong HW, Zhang GL, et al., 2021. Review of learning-assisted power system optimization. CSEE J Power Energy Syst, 7(2):221–231. https://doi.org/10.17775/CSEEJPES.2020.03070
Rudin C, Waltz D, Anderson RN, et al., 2012. Machine learning for the New York City power grid. IEEE Trans Patt Anal Mach Intell, 34(2):328–345. https://doi.org/10.1109/TPAMI.2011.108
Sheble GB, Fahd GN, 1994. Unit commitment literature synopsis. IEEE Trans Power Syst, 9(1):128–135. https://doi.org/10.1109/59.317549
Shorten C, Khoshgoftaar TM, 2019. A survey on image data augmentation for deep learning. J Big Data, 6(1):60. https://doi.org/10.1186/s40537-019-0197-0
Silver D, Schrittwieser J, Simonyan K, et al., 2017. Mastering the game of go without human knowledge. Nature, 550(7676):354–359. https://doi.org/10.1038/nature24270
Sun DI, Ashley B, Brewer B, et al., 1984. Optimal power flow by Newton approach. IEEE Power Eng Rev, PER-4(10):39. https://doi.org/10.1109/MPER.1984.5526285
Tejada-Arango DA, Lumbreras S, Sánchez-Martín P, et al., 2020. Which unit-commitment formulation is best? A comparison framework. IEEE Trans Power Syst, 35(4):2926–2936. https://doi.org/10.1109/TPWRS.2019.2962024
Venzke A, Chatzivasileiadis S, 2021. Verification of neural network behaviour: formal guarantees for power system applications. IEEE Trans Smart Grid, 12(1):383–397. https://doi.org/10.1109/TSG.2020.3009401
Venzke A, Qu GN, Low S, et al., 2020a. Learning optimal power flow: worst-case guarantees for neural networks. IEEE Int Conf on Communications, Control, and Computing Technologies for Smart Grids, p.1–7. https://doi.org/10.1109/SmartGridComm47815.2020.9302963
Venzke A, Viola DT, Mermet-Guyennet J, et al., 2020b. Neural networks for encoding dynamic security-constrained optimal power flow to mixed-integer linear programs. https://arxiv.org/abs/2003.07939
Venzke A, Molzahn DK, Chatzivasileiadis S, 2021. Efficient creation of datasets for data-driven power system applications. Electr Power Syst Res, 190:106614. https://doi.org/10.1016/j.epsr.2020.106614
Wächter A, Biegler LT, 2006. On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming. Math Program, 106(1):25–57. https://doi.org/10.1007/s10107-004-0559-y
Walsh B, 2013. The surprisingly large energy footprint of the digital economy. Time Magazine. Available from https://science.time.com/2013/08/14/power-drain-the-digital-cloud-is-using-more-energy-than-you-think/ [Accessed on Dec. 24, 2020].
Wen GH, Yu XH, Liu ZW, 2021. Recent progress on the study of distributed economic dispatch in smart grid: an overview. Front Inform Technol Electron Eng, 22(1):25–39. https://doi.org/10.1631/FITEE.2000205
Wen YF, Li WY, Huang G, et al., 2016. Frequency dynamics constrained unit commitment with battery energy storage. IEEE Trans Power Syst, 31(6):5115–5125. https://doi.org/10.1109/TPWRS.2016.2521882
Wood AJ, Wollenberg BF, Sheblé GB, 2013. Power Generation, Operation, and Control (3rd Ed.). John Wiley & Sons, New York, USA.
Wu C, Xiao J, Huang G, et al., 2019. Galaxy learning—a position paper. https://arxiv.org/abs/1905.00753
Wu F, Lu CW, Zhu MJ, et al., 2020. Towards a new generation of artificial intelligence in China. Nat Mach Intell, 2(6):312–316. https://doi.org/10.1038/s42256-020-0183-4
Wu ZH, Pan SR, Chen FW, et al., 2021. A comprehensive survey on graph neural networks. IEEE Trans Neur Netw Learn Syst, 32(1):4–24. https://doi.org/10.1109/TNNLS.2020.2978386
Xiang YM, Wang LF, Liu N, 2018. A robustness-oriented power grid operation strategy considering attacks. IEEE Trans Smart Grid, 9(5):4248–4261. https://doi.org/10.1109/TSG.2017.2653219
Xu Y, Dong ZY, Zhang R, et al., 2014. Solving preventive-corrective SCOPF by a hybrid computational strategy. IEEE Trans Power Syst, 29(3):1345–1355. https://doi.org/10.1109/TPWRS.2013.2293150
Yan ZM, Xu Y, 2020. Real-time optimal power flow: a Lagrangian based deep reinforcement learning approach. IEEE Trans Power Syst, 35(4):3270–3273. https://doi.org/10.1109/TPWRS.2020.2987292
Yang Y, Yang ZF, Yu J, et al., 2020a. Fast calculation of probabilistic power flow: a model-based deep learning approach. IEEE Trans Smart Grid, 11(3):2235–2244. https://doi.org/10.1109/TSG.2019.2950115
Yang Y, Yang ZF, Yu J, et al., 2020b. Fast economic dispatch in smart grids using deep learning: an active constraint screening approach. IEEE Int Things J, 7(11):11030–11040. https://doi.org/10.1109/JIOT.2020.2993567
Yin LF, Yu T, Zhang XS, et al., 2018. Relaxed deep learning for real-time economic generation dispatch and control with unified time scale. Energy, 149:11–23. https://doi.org/10.1016/j.energy.2018.01.165
Yin LF, Gao Q, Zhao LL, et al., 2020. Expandable deep learning for real-time economic generation dispatch and control of three-state energies based future smart grids. Energy, 191:116561. https://doi.org/10.1016/j.energy.2019.116561
Zamzam AS, Baker K, 2020. Learning optimal solutions for extremely fast AC optimal power flow. IEEE Int Conf on Communications, Control, and Computing Technologies for Smart Grids, p.1–6. https://doi.org/10.1109/SmartGridComm47815.2020.9303008
Zeng B, Ge SY, Kong XY, et al., 2014. Study for economic dispatch considering network loss in power pool market. Int Conf on Power System Technology, p.1754–1759. https://doi.org/10.1109/POWERCON.2014.6993569
Zhang DX, Han XQ, Deng CY, 2018. Review on the research and practice of deep learning and reinforcement learning in smart grids. CSEE J Power Energy Syst, 4(3):362–370. https://doi.org/10.17775/cseejpes.2018.00520
Zhao TY, Pan X, Chen MH, et al., 2020. DeepOPF+: a deep neural network approach for DC optimal power flow for ensuring feasibility. IEEE Int Conf on Communications, Control, and Computing Technologies for Smart Grids, p.1–6. https://doi.org/10.1109/SmartGridComm47815.2020.9303017
Zhou Y, Tuzel O, 2018. VoxelNet: end-to-end learning for point cloud based 3D object detection. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.4490–4499.
Zhou YH, Zhang B, Xu CL, et al., 2020. Deriving fast AC OPF solutions via proximal policy optimization for secure and economic grid operation. https://arxiv.org/abs/2003.12584v1
Zimmerman R, Zhu QY, Dimitri C, 2016. Promoting resilience for food, energy, and water interdependencies. J Environ Stud Sci, 6(1):50–61. https://doi.org/10.1007/s13412-016-0362-0
Zimmerman RD, Murillo-Sánchez CE, Thomas RJ, 2011. MATPOWER: steady-state operations, planning, and analysis tools for power systems research and education. IEEE Trans Power Syst, 26(1):12–19. https://doi.org/10.1109/TPWRS.2010.2051168
Author information
Authors and Affiliations
Corresponding author
Additional information
Project supported by the National Natural Science Foundation of China (Nos. 52007173 and U19B2042), the Zhejiang Provincial Natural Science Foundation of China (No. LQ20E070002), and Zhejiang Lab’s Talent Fund for Young Professionals (No. 2020KB0AA01)
Contributors
Gang HUANG drafted the paper. Gang HUANG, Fei WU, and Chuangxin GUO revised and finalized the paper.
Compliance with ethics guidelines
Gang HUANG, Fei WU, and Chuangxin GUO declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Huang, G., Wu, F. & Guo, C. Smart grid dispatch powered by deep learning: a survey. Front Inform Technol Electron Eng 23, 763–776 (2022). https://doi.org/10.1631/FITEE.2000719
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/FITEE.2000719