Currently, numerous machine learning (ML) techniques are being applied in the field of renewable energy (RE). These techniques may not perform well if they do not have enough training data. Additionally, the main assumption in most of the ML algorithms is that the training and testing data are from the same feature space and have similar distributions. However, in many practical applications, this assumption is false. Recently, transfer learning (TL) has been introduced as a promising machine-learning framework to mitigate these issues by preparing extra-domain data so that knowledge may be transferred across domains. This learning technique improves performance and avoids the resource expensive collection and labeling of domain-centric datasets; furthermore, it saves computing resources that are needed for re-training new ML models from scratch. Lately, TL has drawn the attention of researchers in the field of RE in terms of forecasting and fault diagnosis tasks. Owing to the rapid progress of this technique, a comprehensive survey of the related advances in RE is needed to show the critical issues that have been solved and the challenges that remain unsolved. To the best of our knowledge, few or no comprehensive surveys have reviewed the applications of TL in the RE field, especially those pertaining to forecasting solar and wind power, load forecasting, and predicting failures in power systems. This survey fills this gap in RE classification and forecasting problems, and helps researchers and practitioners better understand the state of the art technology in the field while identifying areas for more focused study. In addition, this survey identifies the main issues and challenges of using TL for REs, and concludes with a discussion of future perspectives.

The ability to predict solar radiation one-day-ahead is critical for the best management of renewable energy tied-grids. Several machine learning ensemble techniques have been proposed to enhance the short-term prediction of solar radiation strength. In general, finding an optimal ensemble model that consists of combining individual predictors is not trivial due to the need for tuning and other related issues. Few comparative studies have been presented to obtain optimal structures of machine learning ensemble that deal with predicting solar radiation. The contribution of the present research consists of a comparative study of various structures of stacking-based ensembles of data-driven machine learning predictors that are widely used nowadays to conclude the best stacking strategies in terms of performance to combine predictors of solar radiation. The base individual predictors are arranged to predict solar radiation intensity using historical weather and solar radiation records. Three stacking techniques, namely, feed-forward neural networks, support vector regressors, and k-nearest neighbor regressors, have been examined and compared to combine the prediction outputs of base learners. Most of the examined stacking models have been found capable to predict the solar radiation, but those related to combining heterogeneous models using neural meta-models have shown superior performance. Furthermore, we have compared the performance of combined models against recurrent models. The solar radiation predictions of the surveyed models have been evaluated and compared over an entire year. The performance enhancements provided by each alternative ensemble have been discussed.

The integration of solar energy in smart grids and other utilities is continuously increasing due to its economic and environmental benefits. However, the uncertainty of available solar energy creates challenges regarding the stability of the generated power the supply-demand balance’s consistency. An accurate global solar radiation (GSR) prediction model can ensure overall system reliability and power generation scheduling. This article describes a nonlinear hybrid model based on Long Short-Term Memory (LSTM) models and the Genetic Programming technique for short-term prediction of global solar radiation. The LSTMs are Recurrent Neural Network (RNN) models that are successfully used to predict time-series data. We use these models as base predictors of GSR using weather and solar radiation (SR) data. Genetic programming (GP) is an evolutionary heuristic computing technique that enables automatic search for complex solution formulas. We use the GP in a post-processing stage to combine the LSTM models’ outputs to find the best prediction of the GSR. We have examined two versions of the GP in the proposed model: a standard version and a boosted version that incorporates a local search technique. We have shown an improvement in terms of performance provided by the proposed hybrid model. We have compared its performance to stacking techniques based on machine learning for combination. The results show that the suggested method provides significant improvement in terms of performance and consistency.

Solar irradiance is one of the most important parameters that need to be estimated and modeled before engaging in any solar energy project. This article describes a non-linear regression model based on genetic programming technique for estimating solar irradiance in a specific region in the United Arab Emirates. The genetic programming is an evolutionary computing technique that enables automatic search for complex solutions. The best nonlinear modeling function that can estimate the global solar radiation on horizontal will be developed taking into account measured meteorological data. A reference approach to model the solar radiation is first presented. An enhanced approach is then presented which consists of multi nonlinear functions of regression in a parallel structure where each function is designed to estimate the global solar irradiance in a specific seasonal period of the year. Statistical analysis measures have been used to evaluate the performance of the proposed approaches. The obtained results are comparable with the outcomes of models developed by other researchers in the field

Short-term wind speed forecasting is essential for enhancing the efficiency and dependability of wind renewable energy installations. Although often used, conventional point predictions generated by machine learning techniques frequently fail to accurately capture the natural uncertainty associated with wind speed variation. Modeling this type of uncertainty is crucial for providing credible information as the level of uncertainty increases. Prediction intervals (PIs) offer a probabilistic framework for quantifying forecast uncertainty. This paper presents a hybrid forecasting methodology that combines support vector regression (SVR) with adaptive kernel density estimation (AKDE) to estimate wind speed prediction intervals over various short-term horizons (10, 30, 60, and 120 minutes). In contrast to standard kernel density estimation (KDE), which employs a uniform bandwidth and may overlook local data attributes, the adaptive KDE approach adjusts the bandwidth in accordance with the local distribution of forecast errors, thereby facilitating more precise and locally tuned uncertainty quantification. The efficacy of the proposed SVR-AKDE model is evaluated against conventional KDE-based interval estimation. Outcomes are assessed by recognized PI quality indicators, including prediction interval coverage probability (PICP), prediction interval normalized average width (PINAW), and coverage width-based criterion (CWC). Simulation findings confirm the efficacy of our approach and demonstrate that the SVR-AKDE-based PI forecasting consistently provides enhanced coverage and narrower widths compared to traditional KDE. This approach provides a comprehensive solution for short-term wind speed forecasting with quantifiable uncertainty, therefore enhancing its application in operational wind energy control.

The intermittent nature of renewable energy sources poses significant challenges for continuous power supply, necessitating the integration of robust energy storage and optimization systems. While hybrid renewable energy systems (HRES) offer a sustainable solution, achieving an optimal sizing that simultaneously minimizes economic costs and health-damaging carbon emissions remains a complex nonlinear challenge. This study proposes a comprehensive multi-objective optimization framework for a grid-connected HRES integrating photovoltaic (PV), wind turbine (WT), fuel cell (FC), electrolyzer, and hydrogen storage components. The Osprey Optimization Algorithm (OOA) is applied to optimize system sizing and power management. The primary objectives are to concurrently minimize the Cost of Energy (COE) and the Human Health Damage (HHD) due to lifecycle emissions, while ensuring strict system reliability (Loss of Power Supply Probability, LPSP = 0) using one-year meteorological data from Central Anatolia, Türkiye. Comparative analyses demonstrate that OOA exhibits superior performance in terms of solution quality and computational efficiency compared to PSO, TLBO, and GWO algorithms. Among the simulated scenarios (PV/WT/FC, PV/FC, and WT/FC), the PV/WT/FC configuration provides the most balanced Pareto-optimal solution. It achieves the lowest environmental impact with an HHD of 0.419 DALY and a highly competitive COE of 0.238 $/kWh. The integration of hydrogen production and storage effectively mitigates renewable intermittency, reducing grid dependency and emissions. The OOA is confirmed as a highly robust optimization tool, providing decision-makers with a cost-effective and environmentally sustainable framework for designing modern hybrid power systems.