This paper proposes a reinforcement learning-based framework for optimizing the operation of electric arc furnaces (EAFs) under volatile electricity prices. We formulate the deterministic version of the EAF scheduling problem into a mixed-integer linear programming (MILP) formulation, and then develop a Q-learning algorithm to perform real-time control of multiple EAF units under real-time price volatility and shared feeding capacity constraints. We design a custom reward function for the Q-learning algorithm to smooth the start-up penalties of the EAFs. Using real data from EAF designs and electricity prices in New York State, we benchmark our algorithm against a baseline rule-based controller and a MILP benchmark, assuming perfect price forecasts. The results show that our reinforcement learning algorithm achieves around 90% of the profit compared to the perfect MILP benchmark in various single-unit and multi-unit cases under a non-anticipatory control setting.
Enhancing Profit and CO2 Mitigation: Commercial Direct Air Capture Design and Operation with Power Market Volatility
Columbia University（哥伦比亚大学）；Princeton University（普林斯顿大学）；Energy Systems Modelling Analytics Limited（能源系统建模分析有限公司）；Lamont-Doherty Earth Observatory, Columbia University（哥伦比亚大学拉蒙特-多尔蒂地球观测站）；Carbon Direct（碳直接）
Optimal sizing of a hydrogen-based direct reduced iron-electric arc furnace system integrated with methanol synthesis toward zero-carbon steel production
Tsinghua University（清华大学）；Ningxia Institute of Applied Technology（宁夏应用技术研究院）；State Key Laboratory of Power System Operation and Control（电力系统运行与控制国家重点实验室）；State Grid Jibei Electric Power Company Limited（国网冀北电力有限公司）
Machine Learning and Deep Learning Models for Short Term Electricity Price Forecasting in Australia's National Electricity Market
School of Engineering, Computer & Mathematical Sciences, Auckland University of Technology (AUT)（奥克兰技术大学工程、计算机与数学科学学院）；Department of Thermal Energy and Power Engineering, Yantai University（烟台大学热能与动力工程系）；Department of Building Environment and Equipment, School of Civil Engineering, Hefei University of Technology（合肥工业大学土木工程学院建筑环境与设备系）；Green Gold Energy Pty Ltd
Towards the Interactive Effects of Demand Response Participation on Electricity Spot Market Price
Energy Production and Infrastructure Center (EPIC)（能源生产与基础设施中心）；Belk College of Business（贝尔克商学院）；University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
A Robust Optimization Framework for Flexible Industrial Energy Scheduling: Application to a Cement Plant with Market Participation
CARTIF Technology Centre（CARTIF技术中心）；Instituto de las Tecnologías Avanzadas de la Producción, Valladolid University（瓦拉多利德大学先进生产技术研究所）；Departamento de Ingeniería Eléctrica, Valladolid University（瓦拉多利德大学电气工程系）
