Predicting power and solar energy using neural networks and PCA with meteorological parameters from Diass and Taïba Ndiaye

The excessive reliance on conventional fossil fuel-based resources poses a significant threat to our environment. To mitigate this impact, it has become increasingly crucial to increase the integration of intermittent and non-polluting energy sources into our electrical grids. However, while this higher penetration rate brings benefits such as improved producer satisfaction and reduced fossil fuel consumption, it also presents challenges for traditional non-smart electrical networks. To promote intermittent energy sources effectively and maintain a balance between consumption and production, accurate forecasting of these energy outputs plays a vital role. This research paper focuses on studying the application of artificial neural networks for predicting the power and energy output of the Diass solar power plant in the short and medium term. The proposed approach utilizes not only the meteorological data from the city where the power plant is located but also data from a nearby city with a data acquisition station. Principal component analysis (PCA) is employed to select the relevant variables for the prediction model. Furthermore, the results obtained from our approach are compared to existing literature that solely uses meteorological data from the power plant's location. The comparison shows that our method achieves more satisfactory results, with mean absolute errors and root mean square errors of 0.0223 KWh and 0.003 KWh, respectively, and a prediction accuracy of 94.57% in terms of energy and power. It is worth noting that the computational resource requirements for our approach are higher, with simulation times ranging between 1788 seconds and 2201 seconds. By utilizing a broader range of data sources and employing advanced techniques like artificial neural networks, this research contributes to improving the accuracy of solar power generation forecasts. The findings highlight the potential of incorporating additional data inputs and advanced modeling techniques to enhance the performance of renewable energy systems, paving the way for a more sustainable and efficient energy future.