Use of Machine Learning Models to Warmstart Column Generation for Unit Commitment

References

• Bard JF (1988) Short-term scheduling of thermal-electric generators using Lagrangian relaxation. Oper. Res. 36(5):756–766.Link, Google Scholar
• Bengio Y, Lodi A, Prouvost A (2021) Machine learning for combinatorial optimization: A methodological tour d’horizon. Eur. J. Oper. Res. 290(2):405–421.Crossref, Google Scholar
• Bertsekas DP (2009) Convex Optimization Theory (Athena Scientific, Belmont, MA).Google Scholar
• Bertsekas D, Lauer G, Sandell N, Posbergh T (1983) Optimal short-term scheduling of large-scale power systems. IEEE Trans. Automatic Control 28(1):1–11.Crossref, Google Scholar
• Borghetti A, Frangioni A, Lacalandra F, Nucci CA (2002) Lagrangian heuristics based on disaggregated bundle methods for hydrothermal unit commitment. IEEE Power Engrg. Rev. 22(12):60–60.Crossref, Google Scholar
• Briant O, Lemaréchal C, Meurdesoif P, Michel S, Perrot N, Vanderbeck F (2008) Comparison of bundle and classical column generation. Math. Programming 113(2):299–344.Crossref, Google Scholar
• Cobbe K, Klimov O, Hesse C, Kim T, Schulman J (2019) Quantifying generalization in reinforcement learning. Chaudhuri K, Salakhutdinov R, eds. Proc. 36th Internat. Conf. on Machine Learn., vol. 97 (PMLR, New York), 1282–1289.Google Scholar
• Dalal G, Gilboa E, Mannor S, Wehenkel L (2018) Unit commitment using nearest neighbor as a short-term proxy. Proc. Power Systems Comput. Conf. (IEEE, Piscataway, NJ), 1–7.Google Scholar
• De S, Smith S (2020) Batch normalization biases residual blocks toward the identity function in deep networks. Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H, eds. Advances in Neural Information Processing Systems, vol. 33 (Curran Associates, Red Hook, NY), 19964–19975.Google Scholar
• Gasse M, Chetelat D, Ferroni N, Charlin L, Lodi A (2019) Exact combinatorial optimization with graph convolutional neural networks. Wallach H, Larochelle H, Beygelzimer A, d’Alché-Buc F, Fox E, Garnett R, eds. Advances in Neural Information Processing Systems (Curran Associates, Red Hook, NY), 15580–15592.Google Scholar
• Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. J. Machine Learn. Res. 9:249–256.Google Scholar
• Guan X, Luh PB, Yan H, Amalfi JA (1992) An optimization-based method for unit commitment. Internat. J. Electrical Power Energy Systems 14(1):9–17.Crossref, Google Scholar
• Guha N, Wang Z, Wytock M, Majumdar A (2019) Machine learning for AC optimal power flow. Preprint, submitted October 19, https://arxiv.org/pdf/1910.08842.Google Scholar
• Hiriart-Urruty J, Lemaréchal C (1993) Convex Analysis and Minimization Algorithms II (Springer, Berlin).Crossref, Google Scholar
• Hutter F, Hoos HH, Leyton-Brown K (2011) Sequential model-based optimization for general algorithm configuration, Lecture Notes in Computer Science. Internat. Conf. Learn. Intelligent Optim., vol. 6683 (Springer, Berlin, Heidelberg).Google Scholar
• Jones DR (2001) A taxonomy of global optimization methods based on response surfaces. J. Global Optim. 21:345–383.Crossref, Google Scholar
• Khalil E, Bodic PL, Song L, Nemhauser G, Dilkina B (2016) Learning to branch in mixed integer programming. Proc. Conf. AAAI Artificial Intelligence (AAAI Press, Washington, DC).Crossref, Google Scholar
• Kingma DP, Ba J (2017) Adam: A method for stochastic optimization. Preprint, submitted January 30, https://arxiv.org/pdf/1412.6980.Google Scholar
• Lodi A, Zarpellon G (2017) On learning and branching: A survey. TOP 25(2):207–236.Crossref, Google Scholar
• Morabit M, Desaulniers G, Lodi A (2021) Machine-learning–based column selection for column generation. Transportation Sci. 55(4):815–831.Link, Google Scholar
• Nair V, Dvijotham K, Dunning I, Vinyals O (2018) Learning fast optimizers for contextual stochastic integer programs. Globerson A, Silva R, eds. Proc. 34th Conf. on Uncertainty in Artificial Intelligence (AUAI Press, Corvallis, OR), 591–600.Google Scholar
• Ostrowski J, Anjos MF, Vannelli A (2012) Tight mixed integer linear programming formulations for the unit commitment problem. IEEE Trans. Power Systems 27(1):39–46.Crossref, Google Scholar
• Owerko D, Gama F, Ribeiro A (2020) Optimal power flow using graph neural networks. Proc. IEEE Internat. Conf. on Acoustics, Speech and Signal Processing (IEEE, Piscataway, NJ), 5930–5934.Google Scholar
• Pineda S, Morales JM (2022) Is learning for the unit commitment problem a low-hanging fruit? Electric Power Systems Res. 207:107851.Crossref, Google Scholar
• Schulze T, Grothey A, McKinnon K (2017) A stabilised scenario decomposition algorithm applied to stochastic unit commitment problems. Eur. J. Oper. Res. 261(1):247–259.Crossref, Google Scholar
• Shen Y, Sun Y, Li X, Eberhard A, Ernst A (2022) Enhancing column generation by a machine-learning-based pricing heuristic for graph coloring. Proc. AAAI Conf. on Artificial Intelligence (AAAI Press, Washington, DC), 9926–9934.Google Scholar
• Takriti S, Birge JR, Long E (1996) A stochastic model for the unit commitment problem. IEEE Trans. Power Systems 11(3):1497–1508.Crossref, Google Scholar
• Václavík R, Novák A, Šůcha P, Hanzálek Z (2018) Accelerating the branch-and-price algorithm using machine learning. Eur. J. Oper. Res. 271(3):1055–1069.Crossref, Google Scholar
• van Ackooij W, Lopez ID, Frangioni A, Lacalandra F, Tahanan M (2018) Large-scale unit commitment under uncertainty: An updated literature survey. Annals Oper. Res. 271(1):11–85.Crossref, Google Scholar
• van Hoai T, Reinelt G, Bock HG (2005) Advanced column generation techniques for crew pairing problems. Bock HG, Phu HX, Kostina E, Rannacher R, eds. Modeling, Simulation and Optimization of Complex Processes (Springer, Berlin), 203–214.Crossref, Google Scholar
• Vanderbeck F (2005) Implementing mixed integer column generation. Column Generation (Springer, Berlin), 331–358.Crossref, Google Scholar
• Vanderbeck F, Savelsbergh MWP (2006) A generic view of Dantzig–Wolfe decomposition in mixed integer programming. Oper. Res. Lett. 34(3):296–306.Crossref, Google Scholar
• Xavier AS, Qiu F, Ahmed S (2020) Learning to solve large-scale security-constrained unit commitment problems. INFORMS J. Comput. 33(2):739–756.Link, Google Scholar
• Yang Y, Wu L (2021) Machine learning approaches to the unit commitment problem: Current trends, emerging challenges, and new strategies. Electricity J. 34(1):106889.Crossref, Google Scholar
• Zamzam AS, Baker K (2020) Learning optimal solutions for extremely fast AC optimal power flow. Proc. IEEE Internat. Conf. on Comm., Control, and Comput. Tech. for Smart Grids (IEEE, Piscataway, NJ), 1–6.Google Scholar