| Popis: |
In order to achieve carbon neutrality by 2045, it is estimated that California will need approximately eight million Electric Vehicles (EVs) and 1.5 million shared chargers by 2030. It is clear that innovative charging solutions will be needed to align EVs charging with renewable energy generation and local grid needs. We propose a carbon-based pricing strategy to charge EVs that considers CO2 emissions from the grid, local solar photovoltaics (PV) electricity generation, building power usage, Time-of-Use (TOU) rates, and Carbon Allowance Prices (CAP). Our model generates day-ahead and three-hour-ahead carbon-based pricing predictions by learning the patterns of the data to incentivize users to charge at favorable times. Our model was created by using data from the Center for Environmental Research & Technology (CE-CERT) at the University of California, Riverside (UCR) and from the California Independent System Operator (CAISO). We generate three separated predictions: CO 2 emissions rate from the grid, as well as solar PV power and building power usage from CE-CERT. Results show that the predicted cost per mile for an average EV (33 kWh to travel 100 miles) should be decreased from $0.0249 to $0 during abundant solar hours when considering our carbon-based pricing strategy instead of a pre-programmed Time-of-Use scheme. Further, the predicted cost per mile should also increase from $0.0249 to $0.027 during non-solar hours. |
