Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise Deep Residual model for short-term multi-step solar radiation prediction
Article
Article Title | Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise Deep Residual model for short-term multi-step solar radiation prediction |
---|---|
ERA Journal ID | 4067 |
Article Category | Article |
Authors | Ghimire, Sujan (Author), Deo, Ravinesh C (Author), Casillas-Perez, David (Author) and Salcedo-sanz, Sancho |
Journal Title | Renewable Energy |
Journal Citation | 190, pp. 408-424 |
Number of Pages | 17 |
Year | 2022 |
Publisher | Elsevier |
Place of Publication | United Kingdom |
ISSN | 0960-1481 |
1879-0682 | |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.renene.2022.03.120 |
Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S0960148122004049 |
Abstract | Global Solar Radiation (GSR) prediction models are critical to improve the dispatch, control, and stabilization of solar renewable power, and to integrate the solar energy into the electrical grid system. GSR, especially on a short-term scale, can have important fluctuations, which may affect the total energy expected to be supplied to the grid. To overcome this issue, prediction models with a high forecasting performance are needed. In this paper a novel framework based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and Deep Residual Network with Bidirectional long short-term memory, i.e., DRESNET model, is proposed for obtaining accurate multi-step ahead GSR predictions. To train the proposed ICEEMDAN-DRESNET hybrid model, minute-level daylight data from Energy Sector Management Assistance Program in Nepalgunj (mid-western Nepal) are used. The results demonstrate ICEEMDAN-DRESNET model is an excellent tool for short-term solar energy monitoring, yielding excellent predictions, in all metrics such as MAE 9.769 W/m2, MAPE 5.657%, TIC 1.143, CPI 4.739, and TIC 0.023 for 5-min time-horizon predictions, improving the results from the benchmark models. As the forecasting time-horizon is increased, the ICEEMDAN-DRESNET model accuracy drops, with MAE 33.672 W/m2; MAPE 31.749% for 1-hr, MAE 22.625 W/m2; MAPE 18.312% (30-min) and MAE 14.897 W/m2; MAPE 10.358% (15-min), also better than the benchmark models. The results confirm the competitive merit of ICEEMDAN and DRESNET integration to improve deep learning and the potential of proposed model for the monitoring of solar or other renewable (e.g., wind or solar) energies. |
Keywords | Short-term solar predictions; Deep residual network; Bidirectional long short-term memory; Solar renewable energy; Solar energy monitoring system |
ANZSRC Field of Research 2020 | 460207. Modelling and simulation |
400803. Electrical energy generation (incl. renewables, excl. photovoltaics) | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Institution of Origin | University of Southern Queensland |
Byline Affiliations | School of Mathematics, Physics and Computing |
School of Mathematics, Physics and Computing | |
Rey Juan Carlos University, Spain |
https://research.usq.edu.au/item/q759q/improved-complete-ensemble-empirical-mode-decomposition-with-adaptive-noise-deep-residual-model-for-short-term-multi-step-solar-radiation-prediction
115
total views3
total downloads1
views this month0
downloads this month