Data-Driven Building Energy Systems: Applications, Platforms, and Benchmarking
Abstract: The traditional way to control building physical systems is by strategies based on principles of physics. Now there is a transformation where the decision-making is driven by information and data technologies. In this talk, we will briefly review some data-driven applications. With an increasing number of applications, a new challenge is to support such applications at scale. The main problem is how to handle various levels of heterogeneities in different buildings so that data and machine learning models can be used with minimal human involvement. We present our recent works to automatically translate data into standards and extract data under various local data conventions and organizations; as well as schemes to evaluate and select appropriate machine learning models for a target building. We are working with the Electrical and Mechanical Services Department (EMSD) of the Hong Kong government to benchmark machine learning models, in the hope to accelerate AI deployment in the campaign towards a smart city and a greener city.
Bio: Dan Wang is a professor in the Department of Computing, The Hong Kong Polytechnic University. His research interests lie in smart energy systems, in particular, smart building systems. He publishes in ACM eEnergy and ACM Buildsys, and he won best papers in both conferences. He is currently the steering committee chair of ACM eEnergy. He is an advisor of EMSD, the Hong Kong SAR government. He has extensive experiences in applied research and his research results have been adopted by industry, including Huawei, IBM, Henderson, etc.