Data-Driven Control of Electric Vehicle Aggregators for Voltage and Energy Stability in Smart Microgrids
TL;DR
Simulation results indicate that the data-based control framework is superior to traditional methods based on rule-setting due to improvements in voltage regulation performance, reductions in peak load demand and increased utilization of renewable energy resources than through the use of electric vehicles in intelligent microgrids.
Abstract
The exponential growth of electric vehicles (EVs) presents both positive and negative aspects to modern power systems, especially within intelligent microgrids containing many distributed energy resources (DER). Electric vehicle aggregator (EVA) companies work to coordinate the collective charging and discharging behaviour of large groups of EV fleets. As such, their function is critical to the successful maintenance of voltage and energy stability. The current study introduces a data-based control framework for EVAs that utilizes real-time measurement, historical operation data and machine learning-based predictions, which are designed to help the grid meet stability objectives. The proposed framework aims to adjust the EVAs’ charging and vehicle-to-grid (V2G) operations to account for local voltage deviation, load variation and renewable generation variability in order to provide real-time adjustment mechanisms. By combining predictive analytics with control decision-making, the data-based control framework is intended to increase microgrid reliability, decrease the occurrence of voltage violations and increase the energy balance of a microgrid without negatively impacting EV drivers’ mobility needs. Simulation results indicate that the data-based control framework is superior to traditional methods based on rule-setting due to improvements in voltage regulation performance, reductions in peak load demand and increased utilization of renewable energy resources than through the use of electric vehicles in intelligent microgrids