The transportation sector is one among the key sources of greenhouse gas emissions (GHGs) leading to climate change and global warming. Energy transition through electrified transportation is one of the solutions to tackle the issues. Electric vehicles (EVs) offer significant environmental and economic advantages against the conventional Internal Combustion Engine (ICE) vehicles. EVs are called mobility loads and their connectivity to the utility grid for charging is unpredictable. The large penetration of such unpredictable loads into the utility grid will lead to undesirable impacts on the utility service. This paper highlights the importance of managing and optimizing the charging schedules. The optimization of EV charging has diverse aspects, and the perspectives of EV charging differ among consumers, aggregators, and utility services. Proper planning and management of EV charging is essential to achieve harmony amongst these stakeholders. A comprehensive review on the objectives of electric vehicle charging optimization from various perspectives is presented and discussed in this paper. EV charging optimization techniques including mathematical programming, meta heuristics algorithms and machine learning techniques are explored. The main objectives, constraints, strength, and limitations of different charging optimization techniques are analyzed in detail. A brief discussion on the communication strategies for data exchange in EV charging framework is presented and the need for a communication security constrained EV charging scheduling is also emphasized.
Solar PV power generation is intermittent and results in various grid related issues when integrated to the utility grid. By having prior knowledge of the power generation capabilities of solar photovoltaic (PV) systems, it becomes possible to execute the operation of other power systems in a systematic manner, thereby mitigating grid-related issues arising from the intermittent nature of solar PV power generation. This paper discusses PV power forecasting using Artificial Neural Networks by two different approaches. The results obtained from the selected approaches are presented and discussed. The performance evaluation of the selected methods is carried out in terms of root mean square error (RMSE), mean absolute error (MAE) and R 2 values.
Plug-In Electric Vehicles (PEV) are developed as a sustainable substitute for Internal Combustion Engine (ICE) vehicles. However, the increasing penetration of
In recent years, there has been a rapid growth in the utilization of electricity generated from renewable energy sources. Solar energy stands out as a promising solution to the need for a sustainable and easily accessible power source. The integration of intermittent solar PV (photovoltaic) systems into the electricity grid can have a substantial impact on its stability. The implementation of dependable and accurate power forecasting is of utmost importance to enhance grid stability, optimize energy management, and maximize the economic advantages of photovoltaic (PV) power generation. To study the prediction capabilities, three distinct machine learning models, namely Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boost (XGBoost), were selected and subjected to refining and testing. The chosen models are briefly described. The photovoltaic (PV) power is computed by utilizing weather data for a span of one year, and subsequent generation forecasting is conducted based on the computed PV power. The evaluation of the performance of the chosen tools is conducted by assessing metrics such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Normalized Root Mean Squared Error (NRMSE), and R-squared (R2) values. The findings of this study not only contribute to the improvement of the integration of solar energy into the power grid, but also offer useful insights into the selection of machine learning techniques for accurate and efficient forecasting of solar photovoltaic (PV) generation.
Considering the sustainability and accessibility of solar power, a rapid growth of its integration into the energy mix has been observed recently. However, the power generation by solar photovoltaic (PV) systems have an intermittent nature, which poses some serious challenges to the stability of the grid. This highlights the need for a more accurate forecasting of solar power generation which helps in energy management optimization and for the enhancement of financial gains. This study analyzed the accuracy of solar PV power generation forecasting using deep learning models. A Long Short-Term Memory (LSTM) architecture is initially developed as a baseline model. To enhance predictive accuracy, a hybrid model is constructed by combining a Kernel-based Extreme Learning Machine (KELM) which helps in efficient nonlinear feature transformation. The output vector generated by KELM is then combined with the input weather features and passed to LSTM for final prediction. The experimental results obtained reveal that the hybrid KELM-LSTM model has superior forecasting accuracy over the standalone LSTM model by reducing RMSE by $10.9 \%$, MAE by $10.63 \%$, and SMAPE by $9.06 \%$ and improving the $\mathbf{R}^{\mathbf{2}}$ value by $0.33 \%$.