Deep learning has experienced significant growth in recent years, resulting in increased energy consumption and carbon emission from the use of GPUs for training deep neural networks (DNNs). Answering the call for sustainability, conventional solutions have attempted to move training jobs to locations or time frames with lower carbon intensity. However, moving jobs to other locations may not always be feasible due to large dataset sizes or data regulations. Moreover, postponing training can negatively impact application service quality because the DNNs backing the service are not updated in a timely fashion. In this work, we present a practical solution that reduces the carbon footprint of DNN training without migrating or postponing jobs. Specifically, our solution observes real-time carbon intensity shifts during training and controls the energy consumption of GPUs, thereby reducing carbon footprint while maintaining training performance. Furthermore, in order to proactively adapt to shifting carbon intensity, we propose a lightweight machine learning algorithm that predicts the carbon intensity of the upcoming time frame. Our solution, Chase, reduces the total carbon footprint of training ResNet-50 on ImageNet by 13.6% while only increasing training time by 2.5%.
A Market-Rule-Informed Neural Network for Efficient Imbalance Electricity Price Forecasting
Delft University of Technology（代尔夫特理工大学）；Austrian Institute of Technology（奥地利技术研究院）；London Business School（伦敦商学院）；University of Technology Sydney（悉尼大学）；The Chinese University of Hongkong (Shenzhen)（香港中文大学（深圳））
Safe and Sustainable Electric Bus Charging Scheduling with Constrained Hierarchical DRL
College of Engineering, University of Guelph（圭尔夫大学工程学院）；EthicalAI；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）
Green Energy Management for Sustainable Data Centers Using Deep Reinforcement Learning
Computer Science and Applied Mathematics Laboratory (LIMA), Faculty of Science and Technology, Chadli Bendjedid University（计算机科学与应用数学实验室（LIMA），科学与技术学院，查德利·本杰迪德大学）；Mathematical Modeling and Numerical Simulation Laboratory (LAM2SIN), Faculty of Technology, Badji Mokhtar University（数学建模与数值模拟实验室（LAM2SIN），技术学院，Badji Mokhtar大学）；School of Business, Istanbul Medipol University（商业学院，伊斯坦布尔Medipol大学）；Department of Economics and Management, Khazar University（经济学与管理学院，Khazar大学）；University College, Korea University（大学学院，韩国大学）；Clinic of Economics, Azerbaijan State University of Economics (UNEC)（经济学诊所，阿塞拜疆国家经济大学（UNEC））；Department of Computer Science, Faculty of Technology, LRI Laboratory, Badji Mokhtar University（计算机科学系，技术学院，LRI实验室，Badji Mokhtar大学）
Wavelet-Enhanced Neural ODE and Graph Attention for Interpretable Energy Forecasting
organization= School of Science, Engineering \& Technology, East Delta University , addressline = Abdullah Al Noman Road, Noman Society , city= Chattagram , postcode= 4209 , country= Bangladesh
An Extensive and Methodical Review of Smart Grids for Sustainable Energy Management-Addressing Challenges with AI, Renewable Energy Integration and Leading-edge Technologies
Westcliff University（韦斯特克利夫大学）；Pioneer Alpha（先锋阿尔法）；Clark Atlanta University（克拉克亚特兰大大学）；Bangladesh University of Engineering and Technology（孟加拉工程技术大学）
Real-time scheduling of renewable power systems through planning-based reinforcement learning
Tsinghua University（清华大学）；State Grid Corporation of China（国家电网有限公司）；National Power Dispatching and Control Center（国家电力调度控制中心）；China Electric Power Research Institute（中国电力科学研究院）
