It is now recognized that data centers are a significant consumer of energy resources and a substantial source of greenhouse gas emissions. Further, the energy usage of data centers is increasing dramatically, and will likely continue its growth over the coming decades as the transition toward cloud-based services continues. In this talk, I will introduce our work on utilizing the spatial and temporal demand flexibilities of data centers to reduce their energy cost and better utilize renewable generations. Specifically, I will cover geographical load balancing and integrated management of sustainable data center. Then I will continue to discuss the opportunities of using these flexibilities to provide demand response to the power grid, and therefore ease the integration of renewable energy.
Zhenhua Liu received B.E. degree in measurement and control, M.S. degree in computer science and technology from Tsinghua University, in 2006 and 2009, respectively. He also received a B.S. degree in economics from Peking University in 2009 and M.S. degree in computer science from California Institute of Technology in 2011. He is current working towards his PhD degree in Computer Science at California Institute of Technology. His current research interests include sustainable data center, demand response, smart grid, optimization and algorithm. He has interned with HP Labs, Palo Alto (twice), and Google, Mountain View. He has published two papers in ACM Sigmetrics and received the "Best Student Paper" award in ACM GreenMetrics 2011 and "Best Paper" award in IGCC 2012.