Data-driven Modeling and Analytics for Greening the Energy Ecosystem

The energy ecosystem is undergoing a major transition from primarily using carbon-intensive energy sources to greener and renewable sources of energy. For instance, electric vehicles (EVs) are rapidly increasing in popularity thereby eliminating gas-based carbon emissions. Similarly, the increased adoption of solar is injecting greener energy into the grid, thus reducing the grid’s overall carbon footprint. At the same time, the proliferation of networked devices and sensors in the grid is enabling energy usage analysis at fine granularity. In this thesis, I argue that data-driven modeling and analytics applied to energy usage data can facilitate optimal carbon reduction in the energy transition. I present four studies that use principles from machine learning, optimization, and statistical time series analysis to study, analyze and understand the carbon footprint of various energy sectors and devise carbon reduction strategies. First, I study the impact of residential EVs on the demand experienced by a city-wide distribution grid. Since the residential distribution grid was built in a pre-EVA era, it was not designed to account for EV loads, and challenges such as transformer overloading can arise with increased EV energy demand. I quantify and show how grid energy storage and smart charging technologies can mitigate this increased demand and increase transformer lifetime. Second, I examine the feasibility, costs, and carbon benefits of using electric bike sharing -- a low carbon form of ride sharing -- as a potential substitute for shorter ride sharing trips with the overall goal of greening the ride sharing ecosystem. I present a linear optimization framework that employs a hybrid mix of regular and electric bikes to perform substitution and quantify the carbon reduction achieved from such substitution. Third, I discuss the inequity that exists in the energy transition. I show that data driven approaches for building energy efficiency analysis may have inherent biases that prevent them from producing equitable results. I argue for design of equitable and fair analytic approaches to ensure that benefits of energy improvements and decarbonization brought about by the energy transition are distributed equitably across the whole society. Finally, I study the potential of electric heat pumps to reduce CO2 emission by replacing gas heating in buildings. I present a flexible multi-objective optimization framework that optimizes CO2 reduction while also maximizing other aspects of the energy transition such as carbon efficiency and minimizing energy inefficiency in buildings. I quantify the tradeoffs that exist in such multifaceted transition and present results that shed light into the expected load exerted on the electric grid by transitioning from natural gas to electric heat pumps