[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119023-en":3,"doc-seo-119023-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119023,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Use of Machine Learning Models to Warmstart Column Generation for Unit Commitment","The unit commitment problem is a key energy-industry optimization task for determining the most economical power-plant schedules over a fixed horizon. While machine learning has often been used to produce primal feasible solutions, this work applies ML to support Dantzig–Wolfe decomposition by generating initial dual values for column generation. Experiments compare ML warmstarting against column pre-population, the linear programming relaxation, and coldstart. Results show faster computation of tight lower bounds and accurate primal feasible solutions, with good scalability to large instances.","arXiv :2110 .06872v2 [math .OC] 15 Dec 2023  \nUse of Machine Learning Models to Warmstart Column Generation for Unit Commitment  \nNagisa Sugishita∗, Andreas Grothey∗, Ken McKinnon∗  \n2023-12-18  \nAbstract  \nThe unit commitment problem is an important optimization problem in the energy industry used to compute the most economical operating schedules of power plants. Typically, this problem has to be solved repeatedly with different data but with the same problem structure. Machine learning techniques have been applied in this context to find primal feasible solutions. On the other hand, Dantzig-Wolfe decomposition with a column generation procedure has been shown to be successful in solving the unit commitment problem to tight tolerance. We propose the use of machine learning models not to find primal feasible solutions directly but to generate initial dual values for the column generation procedure. Our numerical experiments compare machine learning based methods for warmstarting the column generation procedure with three baselines: column pre-population, the linear programming relaxation and coldstart. The experiments reveal that the machine learning approaches are able to find both tight lower bounds and accurate primal feasible solutions in a shorter time compared to the baselines. Furthermore, these approaches scale well to handle large instances.  \n1 Introduction  \nThe unit commitment (UC) problem is an important optimization problem in the energy industry. Its aim is to compute the optimal operating schedules of power plants for given demand over a fixed time period. This problem is solved by electricity generating companies on a daily basis to determine which generators are to be used. The timings of switching the generators on and off and the amount of power dispatched have to be optimized simultaneously. The decisions in successive time periods are coupled by ramping limits (the maximum rate of change in power output) and minimum up/downtime (the minimum number of time periods for a generator needs to stay on/off after startup/shutdown to prevent damage) constraints, and this gives rise to large-scale combinatorial problems. Due to their practical importance, they have been extensively studied over the last few decades. For a recent survey, see van Ackooij et al. (2018) .  \nThis work focuses on UC problems that are to be solved repeatedly with different data but with the same problem structure. This reflects practice: when a UC problem is solved as a day-ahead planning problem, the characterisations of generators such as generation costs and ramping rates remain the same across the days, but the problems are solved with different demand forecasts each day. This makes the problem a good candidate for the use of machine learning techniques to accelerate the solution.  \n∗ School of Mathematics, University of Edinburgh, James Clerk Maxwell Building, Edinburgh (UK), EH9 3FD,  \nEmail: [n.sugishita@sms.ed.ac.uk](n.sugishita@sms.ed.ac.uk) , [a.grothey@ed.ac.uk](a.grothey@ed.ac.uk), [k.mckinnon@ed.ac.uk](k.mckinnon@ed.ac.uk)  \n1.1 Literature Review  \nML for Optimization: In recent years, the use of machine learning techniques in optimization has been studied extensively, in particular for mixed-integer linear programming (MILP) problems. For a survey, see Bengio et al. (2021) . Hutter et al. (2011) study automatic configuration of an MILP solver using machine learning. They use a local search method to find a configuration with which the MILP solver performs well on a given set of problems. Another popular application is the acceleration of branch and bound. In branch and bound, the choice of branching variables has a significant impact on the overall solution time. Khalil et al. (2016) and Gasse et al. (2019) train machine learning models to predict the output of Strong Branching and use the trained model as a quick surrogate of Strong Branching to select the variable to branch on. Other applications of machine learning to br","cbCaiqJFqShVi7gz","https://ap.wps.com/l/cbCaiqJFqShVi7gz","pdf",686423,1,26,"English","en",105,"# Introduction\n## Literature Review","[{\"question\":\"What does the proposed method warmstart in column generation for unit commitment?\",\"answer\":\"It uses machine learning models to generate initial dual values, providing a warmstart for the column generation procedure rather than directly producing primal feasible solutions.\"},{\"question\":\"Which baseline methods are compared against the ML warmstarting approaches?\",\"answer\":\"The experiments compare against column pre-population, the linear programming relaxation, and a coldstart strategy.\"},{\"question\":\"What performance improvements are reported in the numerical experiments?\",\"answer\":\"The ML approaches are reported to achieve tight lower bounds and accurate primal feasible solutions in shorter time than the baselines, while scaling well to large problem instances.\"}]","Use of Machine Learning Models to Warmstart Column Generation for Unit Commitment | PDF",1785721971,66,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"use-of-machine-learning-models-to-warmstart-column-generation-for-unit-commitment","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/use-of-machine-learning-models-to-warmstart-column-generation-for-unit-commitment/119023/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What does the proposed method warmstart in column generation for unit commitment?","Question",{"text":75,"@type":76},"It uses machine learning models to generate initial dual values, providing a warmstart for the column generation procedure rather than directly producing primal feasible solutions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which baseline methods are compared against the ML warmstarting approaches?",{"text":80,"@type":76},"The experiments compare against column pre-population, the linear programming relaxation, and a coldstart strategy.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance improvements are reported in the numerical experiments?",{"text":84,"@type":76},"The ML approaches are reported to achieve tight lower bounds and accurate primal feasible solutions in shorter time than the baselines, while scaling well to large problem instances.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]