The energy management problem in the context of smart grids is inherently complex due to the interdependencies among diverse system components. Although Reinforcement Learning (RL) has been proposed for solving Optimal Power Flow (OPF) problems, the requirement for iterative interaction with an environment often necessitates computationally expensive simulators, leading to significant sample inefficiency. In this study, these challenges are addressed through the use of Physics-Informed Neural Networks (PINNs), which can replace conventional and costly smart grid simulators. The RL policy learning process is enhanced so that convergence can be achieved in a fraction of the time required by the original environment. The PINN-based surrogate is compared with other benchmark data-driven surrogate models. By incorporating knowledge of the underlying physical laws, the results show that the PINN surrogate is the only approach considered in this context that can obtain a strong RL policy even without access to samples from the true simulator. The results demonstrate that using PINN surrogates can accelerate training by 50% compared to RL training without a surrogate. This approach enables the rapid generation of performance scores similar to those produced by the original simulator.
PINN-DT: Optimizing Energy Consumption in Smart Building Using Hybrid Physics-Informed Neural Networks and Digital Twin Framework with Blockchain Security
Department of Civil Engineering, University of Texas at Arlington（德克萨斯大学阿灵顿分校土木工程系）；Department of Information Systems, Statistics and Management Science, The University of Alabama（阿拉巴马大学信息系统、统计与管理科学系）；College of Arts and Letters, School of Art, Florida Atlantic University（佛罗里达国际大学艺术与文学学院、艺术学院）；Department of Environment and Energy, Science and Research Branch, Islamic Azad University（伊斯兰阿扎德大学环境与能源系、科学与研究分支）；Department of Quantity Surveying, University of Malaya（马来大学工程量系）；Department of Computer Engineering, Islamic Azad University of Hamadan（伊斯兰阿扎德大学哈马丹分校计算机工程系）；Department of Civil, Construction, and Environmental Engineering, University of Alabama（阿拉巴马大学土木、建筑与环境工程系）
Distributed Deep Reinforcement Learning for Intelligent Load Scheduling in Residential Smart Grids
University of Oslo（奥斯陆大学）；Simula Metropolitan Center for Digital Engineering（Simula大都会数字工程中心）
家庭用电量多年来一直在不断增长。为了应对这种增长，有必要对家庭的消费情况进行智能管理，以便家庭可以节省电费，并可以减少高峰时段对电网的压力。然而，实现这样的方法是具有挑战性的，由于存在随机性的电价和消费的电器。为了应对这一挑战，我们采用了一种无模型的方法，该方法适用于有关不确定因素的有限信息的家庭。更具体地说，家庭和电网之间的相互作用可以被建模为一个非合作的随机对策，其中的电价被视为一个随机变量。为了寻找博弈的纳什均衡（NE），我们采用了一种基于分布式深度强化学习的方法。此外，所提出的方法可以保护家庭的隐私。然后，我们利用Pecan Street Inc.的真实数据，其包含超过1000个家庭的电力消耗概况，以评估所提出的方法的性能。平均而言，结果表明，我们可以实现约12%的峰均比（PAR）和11%的负载方差减少。通过这种方法，可以降低电网的运行成本和家庭的用电成本。
Federated Learning for Water Consumption Forecasting in Smart Cities
Mohammed V University in Rabat（拉巴特穆罕默德五世大学）；ENSIAS（国家高等信息与系统分析学院（拉巴特穆罕默德五世大学下属，按独立机构提取为ENSIAS，中文暂译：国家高等信息与系统分析学院））；Al Akhawayn University in Ifrane（伊夫兰阿卡韦恩大学）；School of Science and Engineering（科学与工程学院）
Spatiotemporal Graph Neural Networks in short term load forecasting: Does adding Graph Structure in Consumption Data Improve Predictions?
Interdisciplinary Centre for Security, Reliability and Trust - SnT, University of Luxembourg（卢森堡大学安全、可靠性与信任跨学科中心 - SnT）；University of Luxembourg（卢森堡大学）
EnsembleNTLDetect: An Intelligent Framework for Electricity Theft Detection in Smart Grid
Pune Institute of Computer Technology（浦那计算机技术学院）；College of Engineering, Guindy, Anna University（安娜大学金底工程学院）；Robert Bosch Centre for Data Science & Artificial Intelligence, IIT Madras（罗伯特博世数据科学与人工智能中心，马德拉斯印度理工学院）；Department of Electrical Engineering, IIT Bombay（印度理工学院孟买分校电气工程系）
Hyperdimensional Computing for Sustainable Manufacturing: An Initial Assessment
School of Mechanical, Aerospace, and Manufacturing Engineering University of Connecticut Storrs, Connecticut, USA（机械、航空航天与制造工程学院 美国康涅狄格大学 斯托尔斯分校）；Department of Mechanical and Aerospace Engineering Rutgers University New Brunswick, NJ, USA（机械与航空航天工程系 罗格斯大学 新泽西州新布朗斯维爾分校）
Prediction of Energy Consumption for Variable Customer Portfolios Including Aleatoric Uncertainty Estimation
Fraunhofer IIS/EAS, Fraunhofer Institute for Integrated Circuits, Division Engineering of Adaptive Systems（弗劳恩霍夫集成电路研究所自适应系统工程部）；R&D Department Bettergy S.L.（贝特吉有限公司研发部）
Investigating Underlying Drivers of Variability in Residential Energy Usage Patterns with Daily Load Shape Clustering of Smart Meter Data
Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；Convergence Data Analytics, LLC（Convergence Data Analytics有限责任公司）；Youngstown State University（扬斯敦州立大学）；University of Vermont（佛蒙特大学）
INRIA（法国国家信息与自动化研究所）；Ecole Polytechnique（巴黎综合理工学院）；Technische Universität Wien（维也纳工业大学）；CentraleSupélec（中央理工-高等电力学院）；CNRS（法国国家科学研究中心）；Universite Paris-Saclay（巴黎萨克雷大学）
Machine Learning for Smart and Energy-Efficient Buildings
University of California, Berkeley（加州大学伯克利分校）；Xi’an Jiaotong University（西安交通大学）；Pacific Northwest National Laboratory（太平洋西北国家实验室）；National University of Singapore（新加坡国立大学）
