Prof. Dr. K. Selçuk CANDAN
Professor of Computer Science and Engineering
Director of School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, USA,
Securing Building Energy Systems Through Cyber Defense And Resilient System Design
41% of the primary energy and represents about 40% of the carbon emission, yet buildings very often fail to deliver an indoor environment that satisfies occupants’ comfort, health, and productivity needs. Malfunctioning building envelope, equipment, sensor, and control system, are considered as the top causes for “deficient” building systems. Faults (malfunctioning components) in a building are analogous to illnesses in a human body. Field studies have repeatedly shown that energy savings of 5-30% and improved indoor environmental quality can be achieved by applying fault detection and diagnosis (a core component of commissioning), followed by corrections, even if not done in real time. Especially, in grid enabled buildings, faulty sensor inputs due to cyber attacks may lead to the violation of indoor environment requirements (e.g., temperature, humidity, etc.) and the increase of energy consumption. While many model based approaches have been proposed in the literature for building HVAC control, it is costly to develop accurate physical models for ensuring their performance and even more challenging to address the impact of sensor faults. Building systems are highly complex and dynamic, requiring data and model driven situational awareness and decision making at different scales. This involves real-time and online machine learning to support inferences and predictions, at multiple scales. Models need to be constructed in the presence of sensed data, along with applicable physical models, from multiple sources, characterized by varying levels of accuracies. In this talk, we will discuss new research avenues in (a) big building and IoT data integration and causal analytics, (b) data driven whole building fault and attack detection and diagnosis, and (c) data-driven prognosis, fault impact analysis and energy modeling
K. Selçuk Candan is a professor of computer science and engineering at Arizona State University and the director of ASU’s Center for Assured and Scalable Data Engineering (CASCADE). He joined ASU in August 1997, after receiving his doctorate from the Computer Science Department at the University of Maryland at College Park. He has worked extensively on the integration and presentation of heterogeneous and distributed information and information sources. His research interests include multimedia and web data management. His current research projects include quality adaptive data processing and indexing for sensory data, distributed data management and Internet technologies for efficient dynamic content delivery, and adaptive information management for creating technologies helping blind individuals. His research projects are funded by the National Science Foundation, Department of Defense, and Department of Education (Rehabilitation Services Administration). He has published over 170 journal and peer-reviewed conference articles, one book, and 16 book chapters. He has 9 patents. He served in the organization and program committees of various international conferences. Most recently, Prof. Candan served as an associate editor of for the Very Large Databases (VLDB) journal and IEEE Transactions on Multimedia.