As Electric Vehicles (EVs) become more common, the demand for electricity to power them is increasing day by day. As the number of EVs on the road continues to rise, there is growing concern about the potential imbalance between electricity production and consumption. To address this issue, the development of smart charging and charging strategies has become increasingly important in the development of EV charging stations today. With Smart Charging strategies, we can ensure that our energy systems remain balanced and sustainable. In this study, two different case studies for smart load management in EV charging stations are examined with two different data sets. The first case is about determining the appropriate charging speed in a system with two or more charging stations, and the second case is about evaluating the suitability of direct load management applications for a charging station in domestic use conditions. For both case studies, 2 different data sets consisting of 1000 data such as current charging capacity, next travel distance, instant consumption values, and departure time of the vehicle from the charging station will be used. In the study, the artificial neural network (ANN) method, which is known for high accuracy and flexibility in the classification field, was used to decide on the selection of the most appropriate charging rate and the suitability for demand-side management applications. The results obtained demonstrate that the proposed method can perform intelligent load management with high accuracy, achieving 97.6% for Case 1 and 96.4% for Case 2. (This study was produced from the master's thesis of the first-ranked author. ORCID NO: 0000-0002-8093-4078)
Keywords: EV Charging Station, Smart Grid, Demand Side Management, Artificial Neural Network, Intelligent Decision Maker, Direct Load Control
|
