The installation of electric vehicle charging stations (EVCSs) that are powered by renewable energy sources has been growing rapidly. However, this has raised a crucial issue regarding the quality of power supplied to these stations. Due to the intermittent nature of renewable energy sources and the high-power requirements of EV charging, power quality disturbances (PQDs) occur more. This study proposes a new intelligent PQD classification method that considers feature extraction/selection based on pyramidal undecimated wavelet transform (p-UWT) and minimum redundancy maximum relevance (mRMR). The feature vector, derived through the application of mRMR, comprises a mere ten elements. The p-UWT-mRMR combination overcomes the problem of noise sensitivity inWTs. In addition, Bayesian optimization and UWT-mRMR have addressed hyperparameter selection difficulties and overfitting in support vector machine models. The proposed method demonstrated an impressive classification accuracy of 99.55% when faced with 30-dB noise. A prototype test platform is developed with EVCS-integrated PV systems in the laboratory to verify the performance of the proposed method in real-time cases. Dynamic analysis revealed that all PQDs have runtimes ranging from 5 to 10ms in experiments. The proposed method has been validated on a dataset of over 20 000 real-world signals with a test accuracy of 99.11%.

Forecasting solar power generation is essential for efficient energy management and grid stability. However, existing predictive models often rely on external datasets, such as meteorological and sensor data, to make accurate predictions. This dependency introduces complexities and limits their application in data-sparse scenarios. In this study, we propose a novel forecasting approach based on the NeuralProphet algorithm, a deep learning model that predicts solar power generation solely from its historical data, eliminating reliance on additional input data. To evaluate the proposed approach, we conducted two case studies. The first utilized a 10-month dataset from a 1.2 kW small-scale solar power unit at Bursa Technical University’s Smart Grids laboratory, recorded at 15-minute intervals. Despite the limited dataset, the model achieved an R-squared value exceeding 0.74, demonstrating promising predictive capability. The second case study applied the NeuralProphet-based model to a large-scale dataset of nationwide solar power generation in Germany, spanning five years and collected at 15-minute intervals. Models trained on this dataset achieved R-squared values exceeding 0.99, highlighting the algorithm’s capacity to effectively capture seasonal and temporal patterns at a national scale. Our results indicate that the NeuralProphet-based forecasting approach offers a viable and efficient alternative for solar power prediction, achieving high accuracy without external data dependencies.