Anil Aswani Wins Siebel Energy Institute Grant
May 6, 2016 The Siebel Energy Institute has just announced its 2016 research grant recipients which include IEOR Assistant Professor Anil Aswani. Recipients will receive $50,000 seed grants to develop energy science research. Anil will join Emmanuel Gobet and Philippe Drobinski from École Polytechnique in researching “Data Analytics and Stochastic Control for Optimal Management of Microgrid Generation and Storage Resources.” More information can be found at the Siebel Energy Institute. The full abstract can be found below:
Project Abstract:
Microgrids are a localized and small-scale group of interconnected loads and distributed energy generation that operate either isolated from, or connected to, the main grid. Given the inherent intermittency of local production from renewable energy sources, coupled with the unpredictability of building energy loads, optimal management and device-level coordination of the generation and energy storage elements of a microgrid is difficult yet crucial for reliability and efficiency. One recent trend is the emergence of novel Internet of Things (IoT) sensor modalities, which provide previously unachievable measurement and communication capabilities.
Use of IoT devices in microgrids holds great promise, and it is an active research question as to how to best utilize these devices to improve the operation of microgrids. This research will study how to use data from novel IoT sensors to model the impacts of behavioral, economic, and other consumption activity on electricity demand, and study how to use such models to predict future electricity demand and optimize distributed management of microgrid generation and storage resources. The research team includes industry collaborations with eLum and the Electricity of France (EDF) Public Utility. The anticipated outcomes include (i) data analytics algorithms for forecasting electricity demand based on models and measurements of behavioral, economic, and other consumption activity; (ii) stochastic control algorithms to optimize scheduling and operation of microgrid resources; and (iii) deployment of a microgrid testbed in an office building. The microgrid testbed will generate a real-world dataset for validation of developed algorithms.