Date of Graduation


Document Type


Degree Type



Statler College of Engineering and Mineral Resources


Lane Department of Computer Science and Electrical Engineering

Committee Chair

Jignesh Solanki

Committee Member

Sarika K. Solanki

Committee Member

Muhammad Choudhry

Committee Member

Matthew Valenti

Committee Member

Hong-Jian Lai


Electrification of the transportation sector can play an essential role in curbing fossil fuel scarcity and oil shortages in the world. Electric vehicles (EVs) can significantly reduce CO2 emissions, improve urban pollution. Apart from these advantages of EVs, they may also pose challenges to the distribution grid. Increasing penetration of EVs puts an extra burden and leads to affect the grid severely. Load congestions, voltage drops/regulation, overloading are some of the issues that might incur in the grid because of improper charging of EVs. The uncertain nature of EV owners makes it very difficult to predict the charging pattern. So the grid operator may face a daunting task to avoid overloading if huge EVs are charged without following any smart charging management strategies. We propose a framework that allows EV users to follow a well-coordinated charging schedule and fulfill various objectives like load variance minimization and social welfare maximization for both electric utility and EV owners. A proof of concept of distributed resource allocation for EV charging is implemented using the output consensus approach. Microgrids are components of a smart power distribution grid that can operate as a decentralized/localized grid when disconnected from the main grid. A microgrid can enhance the grid resiliency and provide adequate power to a community or a region in case of grid failure caused by natural disasters or any other disruptions. We also propose the optimal scheduling model for Distributed Energy Resources (DERs) including an EV charging station and battery energy storage system (BESS) in a community microgrid. This model also minimizes the cost incurred in operating the DERs, charging station, BESS, and the grid load. Due to the two-way power flow in the smart grid because of the EVs and distributed energy resources (DERs) involvement, the distribution system operator (DSO) must provide control & protection to equipment and manage the reverse power flow without violating system constraints. Artificial Intelligence (AI) leads the path for a promising smart grid future and helps the DSO tackle such challenges. Given the large size of data flow in the smart grid due to phasor measurement units (PMUs) and smart sensors, AI-based techniques help the grid operator to manage and analyze such data effectively and improve grid resiliency. Machine learning can help the grid operator forecast the uncertainty in supply-demand because of the integration of renewable energy sources. For system planning and operation, the utility needs to perform the load flow analysis in regular intervals to check the different network quantities like bus voltages, line currents, real and reactive powers to plan for the future in case of hypothetical critical conditions like system failure or fault analysis. Such load flow analysis can be performed using different methods, including iterative power flow analysis like the backward forward sweep method. This dissertation develops an AI-based model for a three-phase unbalanced smart grid with a range of EV penetration, renewable energy sources like photovoltaic systems (PVs), and wind energy. We present a trained deep neural network that predicts the branch currents, node voltages, angles, power losses with very high accuracy. Our trained deep neural networks will replace the need for an iterative-based power flow. The proposed models are validated on American Electric Power utility feeder models and various IEEE benchmark distribution test feeders.