We propose a forecasting technique based on multi-feature data fusion to enhance the accuracy of an electric vehicle (EV) charging station load forecasting deep-learning model. The proposed method uses multi-feature inputs based on observations of historical weather (wind speed, temperature, and humidity) data as multiple inputs to a Long Short-Term Memory (LSTM) model to achieve a robust prediction of charging loads. Weather conditions are significant influencers of the behavior of EV drivers and their driving patterns. These behavioral and driving patterns affect the charging patterns of the drivers. Rather than one prediction (step, model, or variables) made by conventional LSTM models, three charging load (energy demand) predictions of EVs were made depending on different multi-feature inputs. Data fusion was used to combine and optimize the different charging load prediction results. The performance of the final implemented model was evaluated by the mean absolute prediction error of the forecast. The implemented model had a prediction error of 3.29%. This prediction error was lower than initial prediction results by the LSTM model. The numerical results indicate an improvement in the performance of the EV load forecast, indicating that the proposed model could be used to optimize and improve EV load forecasts for electric vehicle charging stations to meet the energy requirements of EVs.

Recent motivation to cut greenhouse gas emissions to combat climate change has led to increasing transportation electrification. However, electric vehicle proliferation comes with a number of challenges such as battery capacities and the range anxiety of electric vehicles. In this paper, a review of the main components that affect electric vehicle adoption, which are charging infrastructure and energy resources, is presented. We discuss the categories of electric vehicle charging infrastructure, based on the location-of-charge and the charging technology. In addition, a review of the energy resources required for electric vehicles is also presented. The key features of these batteries are also discussed.

This paper presents a mathematical optimization framework for the strategic placement of quasi-dynamic wireless charging (QWC) stations within road networks to address the charging needs of battery electric buses (BEBs). This study evaluates two scenarios for powering the buses. In the first scenario, a grid-connected system is considered. The optimization aims to minimize annual costs related to capital, operation, and energy losses of the electric bus fleet. This involves determining the optimal locations for QWC stations, the length of power transmitters, and the corresponding battery capacities for the BEBs. Using MATLAB-based optimization tools Casadi and Yalmip, with solvers Bonmin and Fmincon, the optimal configuration includes a 13 kWh battery capacity and a 300 m power transmitter distributed across five bus stop areas. The second scenario employs a chance-constrained optimization approach for an isolated solar photovoltaic (PV) and battery energy storage system (BESS). This system is designed to reliably meet the BEBs' energy requirements throughout the day, considering different seasonal data (winter, summer, all seasons/year-round). The optimization results for the PV and BESS capacities vary with the seasons: 394.247 kW and 2012.6 kWh using summer data, 1762.1 kW and 2738.2 kWh using winter data, and 1610.8 kW and 2741.9 kWh using year-round data. Additionally, the paper examines the impact of varying bus fleet sizes on the optimal battery size and power transmitter combination using a real-world example of the bus route between Khalifa City and Abu Dhabi Downtown in the UAE. The findings suggest that larger batteries with fewer or no charging stations are more economical for smaller fleets. Conversely, as the fleet size increases, a combination of smaller battery sizes and a greater number (and length) of QWC (power transmitters) becomes more cost-effective. This research offers significant insights into the efficient deployment of QWC stations and the integration of renewable energy and energy storage for sustainable urban electric bus networks. The proposed optimization models provide a systematic approach to designing and operating charging infrastructure, contributing to sustainable urban transportation systems. Moreover, the study highlights the influence of seasonal data on PV system sizing and costs.