We are thrilled to share with you the exciting lineup for our session "Exploring the Intersection of Machine Learning and Discrete Optimization: Techniques and Applications" at the INFORMS Annual Meeting 2023 #INFORMS2023. This session will take place on October 16, from 10:45 AM to 12:00 PM in Phoenix, Arizona (CC-North 231B). Co-chairs: Dr. Bing Yan and Anbang Liu abstractsonline.com/pp8/#!/1… The first speaker, Anbang Liu from @Tsinghua_Uni, will discuss the innovative methods of integrating Machine Learning within the price-based decomposition-and-coordination framework for solving large-scale job shop scheduling problems. Co-authors: Prof. Peter Luh, Kailai Sun, Dr. Mikhail Bragin (@prof_Bragin) and Dr. Bing Yan In the second presentation, Meng Li from @UCBerkeley will present the softplus penalty function's application in constrained convex optimization. The talk will highlight the development of upper bounds on the violation of constraints for the solutions to the penalty reformulations by analyzing the solution path with respect to the smoothness parameter and applying gradient methods, with demonstrated advantages when the number of constraints is large. Co-authors: Dr. Paul Grigas (@paulgrigas), and Prof. Alper Atamturk (@AlperAtamturk). The third presentation is based on the work by Dr. Jianghua Wu (@UConn) who recently defended his PhD. The presentation’s focus is on the integration of machine learning and mathematical optimization for sub-hourly Unit Commitment (UC). The discussion will shed light on the potential of machine learning to predict subproblem solutions quickly on pathways to efficiently resolve UC problems. Speaker: Dr. Mikhail Bragin (@prof_Bragin); Co-authors: Dr. Bing Yan, Dr. Yonghong Chen, Prof. Peter Luh, and Dr. Zongjie Wang Lastly, Dr. Bing Yan from the Rochester Institute of Technology will delve into the power systems field, specifically on the topic of Unit Commitment. Her talk will focus on a deep learning approach for transmission line screening to ensure faster and high-quality solutions. Co-authors: Farhan Hyder, Sriparvathi Bhattathiri, and Prof. Michael Kuhl We warmly invite you to join us in this session. Whether you are a data scientist, a machine learning engineer, a power systems engineer, a manufacturing scheduling expert, an optimization expert, or simply interested in machine learning and optimization, this session will offer valuable insights and discussions that you won't want to miss! We hope to see you there! #INFORMS2023 #INFORMS #INFORMS23 #INFORMS2023 #informsannualmeeting #machinelearning #discreteoptimization #computingsociety #INFORMSComputingSociety #AI #ML #manufacturing #scheduling #jobshop #powersystems #unitcommitment

Quick Summary of Recent Achievements - Last 30 Days: Thrilled to announce that three research papers I have been involved in have been accepted: J. Qin, Y. Gao, M. A. Bragin, and N. Yu. “An Optimization Method-Assisted Ensemble Deep Reinforcement Learning Algorithm to Solve Unit Commitment Problems.” Accepted to IEEE Access. S. Zhou, M. A. Bragin, L. Pepin, D. Gurevin, C. Ding, and F. Miao. “Surrogate Lagrangian Relaxation: A Path To Retrain-free Deep Neural Network Pruning.” Accepted to Transactions on Design Automation of Electronic Systems. X. Wang, S. Sahoo, J. Gascon, M. A. Bragin, F. Liu, J. Olchowski, S. Rothfarb, Y. Huang, W. Xiang, P. Gao, P. Alpay, and B. Li. “Deciphering Electrochemical Interactions in Metal-Polymer Catalysts for CO2 Reduction.” Accepted to Energy and Environmental Science. #ResearchUpdate #RecentPublications #DeepReinforcementLearning #UnitCommitment #NeuralNetworkPruning #CO2Reduction #AcademicAchievements #EnergyResearch #PowerAndEnergy #OptimizationMethods #Optimization #IEEEAccess #EnergyAndEnvironmentalScience #LatestPapers

#OpenAccess #Paper by Andrés Ramos, researcher at @IIT_Comillas @Comillas_ICAI @UCOMILLAS , et al. #Generationandtransmissionexpansionplanning #Twostagestochasticprogramming #MulticutBendersdecomposition #Largescalepowersystems #Unitcommitment link.springer.com/article/10…

Excited to share our recent work with Ming, Chung-Lun, and Feng on a #PolyhedralStudy on Fuel-Constrained #UnitCommitment! It is finally published in INFORMS Journal on Computing, online at pubsonline.informs.org/doi/f…

N.Zhakiyev, Z.Sotsial, A.Salkenov, R.Omirgaliyev (2022) Set of Data for Modeling Large-scale Coal-Fired Combined Heat and Power Plant in Kazakhstan, #DatainBrief, 108547, doi.org/10.1016/j.dib.2022.1… advanced #unitcommitment problems coupled with CHP #maintenance #scheduling

Synergistic Integration of Machine Learning and Mathematical Optimization for Unit Commitment #TechRxiv #DeepNeuralNetwork #MachineLearning #SLR #UnitCommitment techrxiv.org/articles/prepri…

#Openaccess #paper by Luis M. Montero, Antonio Bello & Javier Reneses, researchers at @IIT_Comillas @Comillas_ICAI @UCOMILLAS, et al. mdpi.com/1996-1073/15/4/1296 #unitcommitment #optimalthermalgeneration #numericaloptimization #evolutionaryoptimization #optimizationtechniques

Then, @alvaroporras15 (from @GroupOasys) will tell us how to improve the performance of the #UnitCommitment problem via #MachineLearning tools in the talk "Cost-aware Constraint Screening for the Unit Commitment Problem" ⚙

In this letter I wrote with @juanmi82mg we would like to open a debate on how to benchmark #learning methods for #powersystem problems. We found out that learning for the #unitcommitment problem is, in some cases, a low-hanging fruit 🍓🍑 arxiv.org/abs/2106.11687

Using #MachineLearning to solve the #UnitCommitment problem more efficiently is definitely a hot research topic nowadays. I really enjoyed reading this clear and concise review about it. sciencedirect.com/science/ar…

#mdpienergies #particularinterest Article Assessing the Impact of #Cybersecurity Attacks on Power Systems 👉mdpi.com/1996-1073/12/4/725 #cybersecuritythreats #unitcommitment #uncertainty #powersystem

#mdpienergies #particularinterest Article An Improved Mixed Integer Linear Programming Approach Based on Symmetry Diminishing for Unit Commitment of Hybrid Power System 👉mdpi.com/1996-1073/12/5/833 #unitcommitment #MILP #symmetrydiminishing #renewableenergy @HBUT_China @HuazhongUST