Abstract
The use of data-driven ensemble approaches for the prediction of the solar Photovoltaic (PV) power production is promising due to their capability of handling the intermittent nature of the solar energy source. In this work, a comprehensive ensemble approach composed by optimized and diversified Artificial Neural Networks (ANNs) is proposed for improving the 24h-ahead solar PV power production predictions. The ANNs are optimized in terms of number of hidden neurons and diversified in terms of the diverse training datasets used to build the ANNs, by resorting to trial-and-error procedure and BAGGING techniques, respectively. In addition, the Bootstrap technique is embedded to the ensemble for quantifying the sources of uncertainty that affect the ensemble models' predictions in the form of Prediction Intervals (PIs). The effectiveness of the proposed ensemble approach is demonstrated by a real case study regarding a grid-connected solar PV system (231 kWac capacity) installed on the rooftop of the Faculty of Engineering at the Applied Science Private University (ASU), Amman, Jordan. The results show that the proposed approach outperforms three benchmark models, including smart persistence model and single optimized ANN model currently adopted by the PV system's owner for the prediction task, with a performance gain reaches up to 11%, 12%, and 9%, for RMSE, MAE, and WMAE standard performance metrics, respectively. Simultaneously, the proposed approach has shown superior in quantifying the uncertainty affecting the power predictions, by establishing slightly wider PIs that achieve the highest confidence level reaches up to 84% for a predefined confidence level of 80% compared to three other approaches of literature. These enhancements would, indeed, allow balancing power supplies and demands across centralized grid networks through economic dispatch decisions between the energy sources that contribute to the energy mix.
Highlights
The contribution of Renewable Energy (RE) sources to the energy production portfolio is boosting compared to other available productions obtained by alternative conventional energy sources, such as natural gas, oil, and coal [1]–[6]
The Artificial Neural Networks (ANNs) base models of the proposed ensemble are optimized in terms of number of hidden neurons in the hidden layer by a trial-and-error procedure and diversified by resorting to BAGGING technique
Standard performance metrics are considered to evaluate the effectiveness of the proposed approach with respect to the benchmark approaches, they are: i) the performance gains of the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Weighted Mean Absolute Error (WMAE) for the quantification of the predication accuracy gain, and ii) the Prediction Intervals (PIs) Coverage Probability (PICP) and PI Width (PIW) for the quantification of the goodness of the obtained PIs
Summary
The contribution of Renewable Energy (RE) sources to the energy production portfolio is boosting compared to other available productions obtained by alternative conventional energy sources, such as natural gas, oil, and coal [1]–[6]. From the adopted prediction model and of the scheme implemented to provide the final power predictions (i.e., individual model or ensemble of prediction models), various sources of uncertainty might affect the predictions, leading to non-accurate, possibly misleading, information for grid operation [35] In this context, the objective of this work is to develop a new comprehensive ensemble approach composed by several ANNs base models for i) 24h-ahead predicting the solar PV power production, as accurate as possible, and ii) quantifying the associated uncertainty. The major contributions of the present work are: The development of a new comprehensive ensemble approach for providing accurate 24h-ahead solar PV power production predictions and quantifying their associated uncertainty in the form of Prediction Intervals (PIs) by resorting to the BS technique;.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
