Wind and Solar Power Generation Forecasting Using Hybrid Deep-Learning Models
DOI:
https://doi.org/10.47672/ajce.2862Keywords:
Wind Power Forecasting; Solar Power Forecasting; Hybrid Deep Learning; LSTM; CNN; ANFIS; EMD; Wavelet Transform; Renewable Energy ForecastingAbstract
Purpose: The extensive adoption of wind and solar energy into the contemporary power systems has enhanced the relevance of precise and dependable forecasting of the generation. Such variability, nonlinearity, and uncertainty of renewable resources are a major challenge to conventional forecasting methods, which encourages the use of the modern data-driven methods. The purpose of this review is to be a resource to those researchers and practitioners interested in advancing the renewable energy forecasting methods.
Materials and Methods: Deep-learning models have shown great potential in learning complex temporal and spatial patterns in renewable energy data in recent years, but independent deep-learning methods typically have drawbacks including noise sensitivity, overfitting, and lack of interpretability. In a bid to ensure these problems are solved, hybrid deep-learning forecasting models have come up as a promising solution to these problems because they combine deep learning with signal decomposition, machine learning, fuzzy systems, optimization algorithms, and physical knowledge. The review is a coherent and topical analysis of hybrid deep-learning models of the forecasting of wind and solar power generation. It talks about fundamental knowledge of forecasting, popular deep-learning designs and significant strategies of hybridization such as decomposition-based, machine learning, deep learning, fuzzy models and optimization models. Applications to wind and solar forecasting are examined in more detail, including deterministic, probabilistic and spatial forecasting applications. A comparative dialogue points out performance traits, computation concepts, and resource-specific modelling behaviour.
Findings: Lastly, the main issues, areas of research interest and the future research directions are established so as to assist in coming up with more vigorous, interpretable and operationally feasible hybrid forecasting models.
Unique Contribution to Theory, Practice and Policy: The review is a coherent and topical analysis of hybrid deep-learning models of the forecasting of wind and solar power generation.
Downloads
References
[1] T. Infield, D. Hill, and L. Freris, Renewable Energy in Power Systems. Hoboken, NJ, USA: John Wiley & Sons, 2020.
[2] P. Breviglieri, T. Erdem, and S. Eken, “Predicting smart grid stability with optimized deep models,” SN Computer Science, vol. 2, no. 2, Art. no. 73, 2021.
[3] K. Poplavskaya, J. Lago, and L. De Vries, “Effect of market design on strategic bidding behavior: Model-based analysis of European electricity balancing markets,” Applied Energy, vol. 270, Art. no. 115130, 2020.
[4] M. Lydia et al., “Linear and non-linear autoregressive models for short-term wind speed forecasting,” Energy Conversion and Management, vol. 112, pp. 115–124, 2016.
[5] E. B. Ssekulima et al., “Wind speed and solar irradiance forecasting techniques for enhanced renewable energy integration with the grid: A review,” IET Renewable Power Generation, vol. 10, no. 7, pp. 885–989, 2016.
[6] B. Wang et al., “Deep uncertainty quantification: A machine learning approach for weather forecasting,” in Proc. 25th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, 2019, pp. 2087–2095.
[7] R. J. Bessa, A. Trindade, and V. Miranda, “Spatial-temporal solar power forecasting for smart grids,” IEEE Trans. Industrial Informatics, vol. 11, no. 1, pp. 232–241, 2014.
[8] C. Sweeney et al., “The future of forecasting for renewable energy,” Wiley Interdisciplinary Reviews: Energy and Environment, vol. 9, no. 2, Art. no. e365, 2020.
[9] E. Beard et al., “Understanding and using time series analyses in addiction research,” Addiction, vol. 114, no. 10, pp. 1866–1884, 2019.
[10] S. Shamshirband, T. Rabczuk, and K.-W. Chau, “A survey of deep learning techniques: Application in wind and solar energy resources,” IEEE Access, vol. 7, pp. 164650–164666, 2019.
[11] R. Buizza and M. Leutbecher, “The forecast skill horizon,” Quarterly Journal of the Royal Meteorological Society, vol. 141, no. 693, pp. 3366–3382, 2015.
[12] D. C. Montgomery, C. L. Jennings, and M. Kulahci, Introduction to Time Series Analysis and Forecasting. Hoboken, NJ, USA: John Wiley & Sons, 2015.
[13] V. Prema et al., “Critical review of data, models and performance metrics for wind and solar power forecast,” IEEE Access, vol. 10, pp. 667–688, 2021.
[14] H. Sun et al., “Study of solar radiation prediction and modeling of relationships between solar radiation and meteorological variables,” Energy Conversion and Management, vol. 105, pp. 880–890, 2015.
[15] P. Piotrowski et al., “Analysis of forecasted meteorological data (NWP) for efficient spatial forecasting of wind power generation,” Electric Power Systems Research, vol. 175, Art. no. 105891, 2019.
[16] Y.-Y. Hong and C. L. P. P. Rioflorido, “A hybrid deep learning-based neural network for 24-h ahead wind power forecasting,” Applied Energy, vol. 250, pp. 530–539, 2019.
[17] H. Strobelt et al., “LSTMVis: A tool for visual analysis of hidden state dynamics in recurrent neural networks,” IEEE Trans. Visualization and Computer Graphics, vol. 24, no. 1, pp. 667–676, 2017.
[18] Y. Gao and D. Glowacka, “Deep gate recurrent neural network,” in Proc. Asian Conf. Machine Learning, PMLR, 2016, pp. 350–365.
[19] J. Devaraj et al., “A holistic review on energy forecasting using big data and deep learning models,” International Journal of Energy Research, vol. 45, no. 9, pp. 13489–13530, 2021.
[20] S. Hussain and A. AlAlili, “A hybrid solar radiation modeling approach using wavelet multiresolution analysis and artificial neural networks,” Applied Energy, vol. 208, pp. 540–550, 2017.
[21] A. F. Al-Anazi and I. D. Gates, “Support vector regression for porosity prediction in a heterogeneous reservoir: A comparative study,” Computers & Geosciences, vol. 36, no. 12, pp. 1494–1503, 2010.
[22] J. Wu et al., “Hyperparameter optimization for machine learning models based on Bayesian optimization,” Journal of Electronic Science and Technology, vol. 17, no. 1, pp. 26–40, 2019.
[23] B. Qolomany et al., “Parameters optimization of deep learning models using particle swarm optimization,” in Proc. 13th Int. Wireless Communications and Mobile Computing Conf. (IWCMC), IEEE, 2017, pp. 1285–1290.
[24] A. Lawal et al., “Wind speed prediction using hybrid 1D CNN and BLSTM network,” IEEE Access, vol. 9, pp. 156672–156679, 2021.
[25] W. Xie et al., “SegCloud: A novel cloud image segmentation model using a deep convolutional neural network for ground-based all-sky-view camera observation,” Atmospheric Measurement Techniques, vol. 13, no. 4, pp. 1953–1961, 2020.
[26] P. Ramsami and V. Oree, “A hybrid method for forecasting the energy output of photovoltaic systems,” Energy Conversion and Management, vol. 95, pp. 406–413, 2015.
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Krishna Gandhi, Pankaj Verma
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution (CC-BY) 4.0 License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
