Machine Learning and Pattern Recognition for Smart Energy Systems
Description
Transitioning to carbon neutrality requires district integrated energy systems that coordinate electricity, heating, cooling, gas, water, energy storage, and renewable resources. However, the intermittency of solar, wind, and biomass energy, heterogeneous demand, and complex cross-energy dynamics create major challenges for forecasting, optimization, and secure operation. Advances in machine learning and pattern recognition offer powerful tools for data-driven modeling, multi-energy load and renewable-generation forecasting, anomaly and fault detection, digital twins, uncertainty quantification, adaptive control, and intelligent decision-making. This special session will bring together researchers and practitioners to exchange theories, algorithms, datasets, and real-world applications that support reliable, low-carbon, and efficient district energy transitions.
Session organizers
Assoc. Prof. Long Huang, Xi'an Jiaotong-Liverpool University, China
Associate Research Fellow Xiaojie Lin, Zhejiang University, China
The topics of interest include, but are not limited to:
▪ Multimodal energy-data analytics
▪ Load and renewable-generation forecasting
▪ Graph learning for coupled energy networks
▪ Reinforcement learning and decision intelligence
▪ Physics-informed and hybrid modeling
▪ Digital twins
▪ Intelligent optimization and energy management
▪ Anomaly, fault, and cyberattack detection
▪ Uncertainty-aware and trustworthy AI
▪ Federated and privacy-preserving learning
▪ Demand response and energy-storage coordination
▪ Building and industrial waste-heat recovery
▪ Data-center waste-heat integration
▪ Benchmark datasets and field demonstrations
Submission method
Submit your Full Paper (no less than 5 pages) or your paper abstract-without publication via Online Submission System, then choose Special Session 1 (Machine Learning and Pattern Recognition for Smart Energy Systems)
Introduction of Session organizers
Assoc. Prof. Long Huang
Xi'an Jiaotong-Liverpool University, China
Bio: Long Huang. Dr. Long Huang is an Associate Professor at Xi'an Jiaotong-Liverpool University. He received his Ph.D. in Mechanical Engineering from the University of Maryland, College Park, in 2014 and joined XJTLU in 2020 after industry roles at Navigant Consulting and Daikin Industries. His research covers thermo-fluid system modeling, heat and mass transfer, interpretable machine learning, data-driven prediction, and optimization. His work is supported by the National Natural Science Foundation of China, the Jiangsu Provincial Department of Education, and industry partners.
Associate Research Fellow Xiaojie Lin
Zhejiang University, China
Bio: Xiaojie Lin. Dr. Xiaojie Lin is a Distinguished Associate Research Fellow and doctoral supervisor at Zhejiang University's College of Energy Engineering. His research focuses on smart energy, integrated energy systems, energy-AI integration, multi-energy complementarity, intelligent control, and data-driven optimization. He has led an international collaboration project under the National Key R&D Program of China, an NSFC Young Scientists Fund project, and major industry projects. He has published more than 70 papers, including over 40 SCI/EI journal papers as first or corresponding author, and holds more than 30 granted invention patents.