Machine Learning and Data Analysis for Energy Efficiency in Buildings

Zhao Tianyi is the Deputy Dean and an Associate Professor of the School of Civil Engineering at Dalian University of Technology. He is the Group Lead of the On-line Automation Solutions Institute for Sustainability in Energy and Buildings (OASIS-EB). This group focuses on investigating intelligent regulation and control methods for building energy systems, incorporating advanced technologies such as the Internet of Things, big data, and artificial intelligence. He has published over 100 peer-reviewed articles in journals. Zhang Chengyu is a PhD student at the Institute for Building Energy and member of the Online Automation Solutions Institute for Sustainability in Energy and Buildings, both at the Dalian University of Technology, China. His main research focus is on energy application for sustainable intelligent buildings, with particular emphasis on energy consumption prediction and anomaly detection and repair of energy monitoring data. One of his most significant contributions in academia is the development of a novel model for building occupant energy-use behavior, which has been integrated into energy consumption prediction to enhance its effectiveness. Additionally, he has collaborated with colleagues to propose strategies for building energy conservation based on adjusting energy-use behaviors and has put forward a comprehensive approach for detecting and repairing anomalies in energy monitoring data.Ben Jiang is a PhD Candidate at the Dalian University of Technology and a member of the Online Automation Solutions Institute for Sustainability in Energy and Buildings, China, led by Professor Zhao. His research focuses on building intelligence applications, including the prediction and analysis of building energy consumption and related parameters.

• Part I: Data Basics1. Introduction2. Data Preparation3. Abnormal Data Identification and Repair4. Classification and Definition of Data Type5. Identification and Repair of Abnormal Energy Consumption Data6. Case Studies in Different BuildingsPart II: Data Mining7. Energy Consumption Forecasting8. Short-time-scale Energy Consumption Prediction (for O&M Regulation)9. Long-time-scale Energy Consumption Prediction (for Design Evaluation)10. Case Studies in Different ScenariosPart III: Data Application11. Review of Evaluation and Methods for Energy Supply and Demand Matching12. Energy Supply and Demand Matching Evaluation Methods: Power-load Matching Coefficient13. Optimization of Supply-side Energy Schemes14. Optimization of Demand-side Energy Use Solutions15. Conclusions