题目: Machine Learning for building energy efficiency
演讲人: Dr. Xiwang Li （李曦旺 博士）
Buildings consumes over 70% of electricity and 40% of primary energy in the United States. The penetration of distributed renewable energy systems and smart grid technologies creates the new opportunities and challenges for energy efficiency and reliability.
Building energy forecasting, as the basis of model based building control and design, has attracted more and more attention in both academia and industry. In the past decade, the increasingly development of computating, machine learning, and data mining, has been changing the fundamental approaches for energy forecasting.
This talk will start with the introduction of fundamental machine learning methods, such as regression and neural networks, and then the state-of-art machine learning tools and platforms, such as SKlearn, and TensorFlow, will be introduced. Besides the theoretical discussion, this talk will also share the hands-on experience and understanding of utilizing machine learning techniques in building energy efficiency as well as renewable energy integration.
Xiwang Li holds a Ph.D. degree in Civil Engineering from Drexel University in 2015. Dr. Li currently working in Lawrence Berkeley National Lab in USA. Before joining LBNL, Dr. Li was a Postdoc research fellow at Graduate school of design in Harvard University.
Dr. Li’s research focuses on building energy forecasting and modeling for energy efficiency and indoor environment quality, by utilizing various techniques in machine learning and data mining. Dr. Li has been working on several projects funded by U.S. Department of Energy, U.S. Department of Defense, U.S. National Science Foundation, etc., and have published over 20 scientific publications.