ERI: Vehicle-to-Grid applied to Demand Response

University Of South Alabama, Mobile AL

Investigators

Abstract

The use of electric vehicles (EVs) as well as renewable energy as power sources for consumers will reduce greenhouse gas emissions. Moreover, power utility companies encourage consumers to reduce their consumption during peak-hours (when most consumers use most power). Vehicle-to-Grid (V2G) is a new technology that allows EV owners to use their EV batteries to power their homes while connected to the grid. Thus, EVs with V2G technology will become attractive for consumers because their EV batteries can help to reduce their power demand from the utility company at peak-hours. Artificial Intelligence algorithms are powerful tools for forecasting complex properties and have been extensively researched for applications in several areas of Power Systems. The proposed research will answer important questions regarding the influence of V2G on consumer power demand, using the Mobile, Alabama area as an example market so that realistic financial and environmental considerations are used in the simulations. The outcomes of this research will boost the motivation for consumers to use V2G to reduce peak power demands, and will provide information on making V2G more attractive, advancing national prosperity. The results from this award will be disseminated to academic, community and industry stakeholders through newspapers, technical peer-reviewed journal articles and conference articles and reports, participation in conferences, and presentations in webinars. The goal of the project is to investigate the advantages and challenges of V2G to support Demand Response (DR), by creating short-term Artificial Intelligence (AI) algorithms to predict EV load demand statuses for a few minutes and hours ahead, and a Simulation system to verify the best way to utilize EVs for DR and evaluate the means to overcome challenges. An initial investigation of existing EVs in the Mobile, Alabama region and their usage and power characteristics will be used to verify the pros and cons of V2G and to supply data to AI algorithms that will be designed to predict the EV characteristics needed to support DR. The project will be developed in two phases: in Phase I, data about existing EVs in the region will be collected and analyzed and a simulation will be developed; in Phase II, the AI algorithms will be developed along with a workshop involving ten high-school students to be selected from underrepresenting groups. This workshop will support the dissemination of the project results, and will clarify to the general public some common misconceptions related to EVs, V2G and DR. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.