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 gridconnected solar PV system (231 kWac capacity) installed on the rooftop of the Faculty of Engineering at the Applied Science Private University (ASU), Amman, Jordan. 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.

The intermittent and stochastic nature of Renewable Energy Sources (RESs) necessitates accurate power production prediction for effective scheduling and grid management. This paper presents a comprehensive review conducted with reference to a pioneering, comprehensive, and data-driven framework proposed for solar Photovoltaic (PV) power generation prediction. The systematic and integrating framework comprises three main phases carried out by seven main comprehensive modules for addressing numerous practical difficulties of the prediction task: phase I handles the aspects related to data acquisition (module 1) and manipulation (module 2) in preparation for the development of the prediction scheme; phase II tackles the aspects associated with the development of the prediction model (module 3) and the assessment of its accuracy (module 4), including the quantification of the uncertainty (module 5); and phase III evolves towards enhancing the prediction accuracy by incorporating aspects of context change detection (module 6) and incremental learning when new data become available (module 7). This framework adeptly addresses all facets of solar PV power production prediction, bridging existing gaps and offering a comprehensive solution to inherent challenges. By seamlessly integrating these elements, our approach stands as a robust and versatile tool for enhancing the precision of solar PV power prediction in real-world applications.

We present a novel method for concept drift detection, based on: 1) the development and continuous updating of online sequential extreme learning machines (OS-ELMs) and 2) the quantification of how much the updated models are modified by the newly collected data. The proposed method is verified on two synthetic case studies regarding different types of concept drift and is applied to two public real-world data sets and a real problem of predicting energy production from a wind plant. The results show the superiority of the proposed method with respect to alternative state-of-the-art concept drift detection methods. Furthermore, updating the prediction model when the concept drift has been detected is shown to allow improving the overall accuracy of the energy prediction model and, at the same time, minimizing the number of model updatings.

The unpredictability of intermittent renewable energy (RE) sources (solar and wind) constitutes reliability challenges for utilities whose goal is to match electricity supply to consumer demands across centralized grid networks. Thus, balancing the variable and increasing power inputs from plants with intermittent energy sources becomes a fundamental issue for transmission system operators. As a result, forecasting techniques have obtained paramount importance. This work aims at exploiting the simplicity, fast computational and good generalization capability of Extreme Learning Machines (ELMs) in providing accurate 24 h-ahead solar photovoltaic (PV) power production predictions. The ELM architecture is firstly optimized, e.g., in terms of number of hidden neurons, and number of historical solar radiations and ambient temperatures (embedding dimension) required for training the ELM model, then it is used online to predict the solar PV power productions. The investigated ELM model is applied to a real case study of 264 kWp solar PV system installed on the roof of the Faculty of Engineering at the Applied Science Private University (ASU), Amman, Jordan. Results showed the capability of the ELM model in providing predictions that are slightly more accurate with negligible computational efforts compared to a Back Propagation Artificial Neural Network (BP-ANN) model, which is currently adopted by the PV system owners for the prediction task.