Data-driven Analytics for Sustainable Buildings and Cities

Xingxing Zhang is an Associate Professor in energy technology at Dalarna University, Sweden. He has multidisciplinary research experience, especially in energy systems, energy data analytics, adaption to future climate and urban building energy modelling for sustainable transition. He is leading the City Information Modelling (CIM) group at the university, which includes technical, economic, and environmental analyses by interdisciplinary research methods from building physics, energy engineering, informatics, machine learning and artificial intelligence. He is active in EU, UK and China research networks, by working in Swedish national projects, Sweden-China joint project, Nordic research project, EU H2020/FP7 projects, EU cost action and IEA tasks. He has won the second place of “EU-China Dragon-star Innovation Prize” in 2015. He serves as Editor Board Member of two journals and the regular reviewer for many international journals. He has an Accredited Professional Certificate of Leadership in Energy and Environmental Design (LEED AP) and he is UK Chartered Engineer (CEng), Member of Chartered Institution of Building Services Engineers (CIBSE) and CIB Commission Member of W098 Intelligent and Responsive Buildings.

• The evolving of data-driven analytics for buildings and cities towards sustainability.-   Data-driven approaches for prediction and classification of building energy consumption.-   Prediction of occupancy level and energy consumption in office building using blind system identification and neural networks.-   Cluster Analysis for Occupant-behaviour based Electricity Load Patterns in Buildings: A Case Study in Shanghai Residences.-   A data-driven model predictive control for lighting system based on historical occupancy in an office building: Methodology development.-  Tailoring future climate data for building energy simulation.-   A solar photovoltaic/thermal (PV/T) concentrator for building application in Sweden using Monte Carlo method.-   Influencing factors for occupants' window-opening behaviour in an office building through logistic regression and Pearson correlation approaches.-   Reinforcement learning methodologies for controlling occupant comfort in buildings.-   A novel Reinforcement learning method for improving occupant comfort via window opening and closing.  2942492291991671341156161