[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122345-en":3,"doc-seo-122345-105":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},122345,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","COMPARISON OF ENERGY STORAGE MARKET RETURN VALUE THROUGH RULE-BASED SYSTEM AND MACHINE LEARNING BASED METHODS IN CALIFORNIA","Hypothesis: Optimizing charge schedules using machine learning enhances wholesale market returns for energy storage over traditional methods. The research guides shareholders and researchers in targeting energy storage market value and benchmarking approaches for wholesale electricity market operation planning. Methods transform price guidance from demand, past price, or predicted price, then optimize charging schedules. Machine learning predicted-price methods achieve MAE roughly 10.63–17.40 $/MWh versus 26.47–90.46 $/MWh. Quantile regression captures over 95% of theoretical maximum return, confirming the hypothesis that machine learning optimization improves market returns.","COMPARISON OF ENERGY STORAGE MARKET RETURN VALUE THROUGH  \nRULE-BASED SYSTEM AND MACHINE LEARNING BASED METHODS IN  \nCALIFORNIA NP-15 HUB  \nby  \nJiaqun Wang  \nA thesis submitted to Johns Hopkins University in conformity with the requirements for the  \ndegree of Master of Science  \nBaltimore, Maryland  \nMay, 2025  \n© 2025 Jiaqun Wang  \nAll Rights Reserved  \nAbstract  \nHypothesis: Optimizing charge schedules using machine learning enhances wholesale market returns for energy storage over traditional methods.  \nThis research aims to provide guidance for shareholders and researchers in targeting the market value of energy storage and benchmarking various methods for planning storage operation schedules in the wholesale electricity market. Methods are critical to improving the economic performance of energy storage, as the study found that energy storage optimized using the specific methods can boost market revenue by nearly 50% compared to industry common practices. The study examined different methods, including ordinary (rule-based) and machine learning-based methods, to produce the price guidance, which was either transformed from the demand, past price, or predicted price, and then optimized energy storage charge schedules in the wholesale electricity market. For the predicted price methods, machine learning base methods have a mean absolute error (MAE) range from 10.63$/MWh to 17.40 $/MWh while the Common Statistics methods have an MAE range from  \n26.47$/MWh to 90.46 $/MWh. It reveals the advantage of Machine learning based methods in predicting the wholesale electricity market price change. However, analysis has shown that more accurate market price prediction does not inherently correlate to higher market returns for energy storage. The results show that Quantile Regression-Based methods can capture over 95% of the theoretical maximum market return, which is slightly lower than the best machine learning based approach-Lightgbm. So, some common statistics maintain competitiveness in the energy storage charging schedule optimization, even though it lacks accuracy in predicting the market price change. In conclusion, the research results confirm the hypothesis that machine learning-based energy storage charge optimization enhances wholesale market returns over traditional methods.  \nExecutive Summary  \n“Sustainability, in its true form, is about balancing the triple bottom line: people,  \nplanet, and profit.” -John Elkington  \nEnergy storage is crucial for integrating renewable energy sources like solar and wind into the electricity grid, as these resources are non-dispatchable, meaning their output is uncertain. Efficient energy storage charging schedules can convert renewable energy into dispatchable resources, yet the complexities of electricity market mechanisms present challenges in developing optimal charging strategies to maximize profit. This research explores various approaches, including rule-based and machine learning methods, to improve energy storage operations within market frameworks.  \nThe Energy Policy and Climate (EPC) Program gave me insights into electricity markets, renewable project finance, and energy policy. The program also exposed me to cutting-edge machine learning techniques. Thus, I was able to deliver this little “out of spectrum” research paper that combines energy storage and machine learning technology.  \nIn conclusion, this research suggests that implementing optimized methods could boost market returns by 50% . It demonstrates the importance of the operation optimization method selection for the energy storage market value. Additionally, machine learning shows potential for delivering more accurate predictions of wholesale electricity market prices. The paper also summarizes various interconnection policy models for energy storage in California, highlighting the importance of policy frameworks in supporting the transition to clean energy.  \nDedication  \nThis paper is about mathematical calcu","cbCair5RenXgIgsa","https://ap.wps.com/l/cbCair5RenXgIgsa","pdf",1571393,1,54,"English","en",105,"# Abstract\n## Executive Summary\n## Dedication","[{\"question\":\"What hypothesis does the thesis test regarding energy storage charge scheduling?\",\"answer\":\"The study hypothesizes that machine learning-based optimization of charge schedules increases wholesale market returns compared with traditional methods.\"},{\"question\":\"How are different methods compared in producing price guidance for optimization?\",\"answer\":\"The research evaluates ordinary rule-based and machine learning-based approaches, generating price guidance from demand, past price, or predicted price, and then optimizing charging schedules in the wholesale electricity market.\"},{\"question\":\"Do more accurate wholesale price predictions always lead to higher market returns?\",\"answer\":\"No. The analysis shows that higher prediction accuracy does not inherently correlate with higher energy storage market returns.\"}]","COMPARISON OF ENERGY STORAGE MARKET RETURN VALUE THROUGH RULE-BASED SYSTEM AND MACHINE LEARNING BASED METHODS IN CALIFORNIA | PDF",1785810156,136,{"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},"comparison-of-energy-storage-market-return-value-through-rule-based-system-and-machine-learning-based-methods-in-california","",{"@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/comparison-of-energy-storage-market-return-value-through-rule-based-system-and-machine-learning-based-methods-in-california/122345/",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","2026-08-04",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 hypothesis does the thesis test regarding energy storage charge scheduling?","Question",{"text":75,"@type":76},"The study hypothesizes that machine learning-based optimization of charge schedules increases wholesale market returns compared with traditional methods.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are different methods compared in producing price guidance for optimization?",{"text":80,"@type":76},"The research evaluates ordinary rule-based and machine learning-based approaches, generating price guidance from demand, past price, or predicted price, and then optimizing charging schedules in the wholesale electricity market.",{"name":82,"@type":73,"acceptedAnswer":83},"Do more accurate wholesale price predictions always lead to higher market returns?",{"text":84,"@type":76},"No. The analysis shows that higher prediction accuracy does not inherently correlate with higher energy storage market returns.","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"]