Improved solar photovoltaic energy generation forecast using deep learning-based ensemble stacking approach. (1st February 2022)

• Record Type: Journal Article
• Authors: Khan, Waqas; Walker, Shalika; Zeiler, Wim
• Is Part Of: Energy. Volume 240(2022)
• Publication Date: 2022-02-01
• Subjects: Solar energy forecasting -- Uncertainty -- Machine learning -- Deep learning -- Stacking -- Ensemble learning; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2021.122812
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: An accurate solar energy forecast is of utmost importance to allow a higher level of integration of renewable energy into the controls of the existing electricity grid. With the availability of data in unprecedented granularities, there is an opportunity to use data-driven algorithms for improved prediction of solar generation. In this paper, an improved generally applicable stacked ensemble algorithm (DSE-XGB) is proposed utilizing two deep learning algorithms namely artificial neural network (ANN) and long short-term memory (LSTM) as base models for solar energy forecast. The predictions from the base models are integrated using an extreme gradient boosting algorithm to enhance the accuracy of the solar PV generation forecast. The proposed model was evaluated on four different solar generation datasets to provide a comprehensive assessment. Additionally, the shapely additive explanation framework was utilized in this study to provide a deeper insight into the learning mechanism of the algorithm. The performance of the proposed model was evaluated by comparing the prediction results with individual ANN, LSTM, and Bagging. The proposed DSE-XGB method exhibits the best combination of consistency and stability on different case studies irrespective of the weather variations and demonstrates an improvement in R 2 value of 10%–12% to other models. Graphical abstract: Image 1 Highlights: A deep learning-based ensemble stacking (DSE-XGB) approach is proposed for Solar PV energy generation forecast. A detailed comparison between individual deep learning models, bagging and the proposed model is presented. The models are evaluated on two case studies (5 dataset) from different locations with 15-min and 1-h data resolution. The proposed DSE-XGB model outperform individual deep learning models and bagging for all case studies.