Solar Irradiance Forecasting Research Articles

Potential assessment of the TVF-EMD algorithm in forecasting hourly global solar radiation: Review and case studies

Accurate and effective forecasting of short-term global solar radiation is critical for the development of photovoltaic systems, particularly for integration into existing grid systems. However, its non-stationary characteristics caused by climatic factors make its estimation extremely challenging. In this regard, a newly designed learning technique for multi-hour global solar radiation forecasting is proposed based on a time-varying filter-empirical mode decomposition (TVF-EMD), feature selection, and extreme learning machine (ELM) as an essence regression. The proposed hybridization strategy consists of three main steps for understanding the fundamental behavioral aspects of hourly global solar radiation data. The first phase employs the TVF-EMD algorithm to deal with the variability of global solar radiation data by separating it into a series of more stable and constant subseries. Then, the feature selection step is employed to evaluate and identify distinctive features set from the whole decomposed subseries by means of the RReliefF algorithm. The selected feature sets are used to train and optimize our forecasting extreme learning machine model, then the tuned ELM model is used to assess the forecasting accuracy. The proposed TVF-EMD-RF-ELM model is evaluated and validated in different regions in Algeria with various climate conditions. The forecasting findings of the TVF-EMD algorithm demonstrate high accuracy compared to the recent version of empirical mode decomposition CEEMDAN. Overall forecasting periods, the TVF-EMD-RF-ELM model produces an error less than 8.3% in terms of normalized root mean square error nRMSE in all studied regions.

Machine learning-based thermo-electrical performance improvement of nanofluid-cooled photovoltaic–thermal system

Hybrid photovoltaic–thermal (hPVT) collectors are devices that allow the conversion of sun energy into useful thermal and electrical energy simultaneously. The power obtained from the photovoltaic (PV) module introduces random fluctuations into the system. While obtaining the data for PV power output in advance and for reducing the impact of random fluctuations, exact day-ahead PV power prediction is crucial. Machine learning algorithms have been proven an effective tool in PV technology for day-ahead prediction of PV-power output. This research employs the Gaussian process regression method using the Matlab environment for forecasting the hPVT collector's performance operating with pure water and Fe/water nanofluid. A one-year historical data pertaining to solar irradiance as well as ambient temperature for Roorkee (29.8543 °N, 77.8880 °E), India location has been used to validate the proposed model. This data is utilized for day-ahead forecasting of solar irradiance and ambient temperature. The outcome elucidates that as the mass-flow rate increases, the thermo-electric performance of the hPVT collector enhances. Raising the mass-flow rate of Fe/water nanofluid from 0.01 to 0.1 kg/s, the cell temperature decreases by 9.35 °C and 9.47 °C, respectively, for the actual and predicted data. The thermal, electrical, as well as overall efficiency of the hPVT collector, improves by 2.73%, 7.11%, and 9.84%, respectively, using Fe/water nanofluid ( ϕ = 2%) in contrast to the water-cooled PVT system. Finally, results demonstrate that the outcomes obtained using the forecasted data closely follow the results obtained using the actual data. In conclusion, this analysis provides a comprehensive solution for utilizing nanofluids as a coolant in the most cost-effective ways.

One-hour-ahead solar radiation forecasting by MLP, LSTM, and ANFIS approaches

One-hour-ahead solar radiation forecasting by MLP, LSTM, and ANFIS approaches

Solar and Wind Energy Forecasting for Green and Intelligent Migration of Traditional Energy Sources

Fossil-fuel-based power generation leads to higher energy costs and environmental impacts. Solar and wind energy are abundant important renewable energy sources (RES) that make the largest contribution to replacing fossil-fuel-based energy consumption. However, the uncertain solar radiation and highly fluctuating weather parameters of solar and wind energy require an accurate and reliable forecasting mechanism for effective and efficient load management, cost reduction, green environment, and grid stability. From the existing literature, artificial neural networks (ANN) are a better means for prediction, but the ANN-based renewable energy forecasting techniques lose prediction accuracy due to the high uncertainty of input data and random determination of initial weights among different layers of ANN. Therefore, the objective of this study is to develop a harmony search algorithm (HSA)-optimized ANN model for reliable and accurate prediction of solar and wind energy. In this study, we combined ANN with HSA and provided ANN feedback for its weights adjustment to HSA, instead of ANN. Then, the HSA optimized weights were assigned to the edges of ANN instead of random weights, and this completes the training of ANN. Extensive simulations were carried out and our proposed HSA-optimized ANN model for solar irradiation forecast achieved the values of MSE = 0.04754, MAE = 0.18546, MAPE = 0.32430%, and RMSE = 0.21805, whereas our proposed HSA-optimized ANN model for wind speed prediction achieved the values of MSE = 0.30944, MAE = 0.47172, MAPE = 0.12896%, and RMSE = 0.55627. Simulation results prove the supremacy of our proposed HSA-optimized ANN models compared to state-of-the-art solar and wind energy forecasting techniques.

Solar irradiance forecasting using a novel hybrid deep ensemble reinforcement learning algorithm

Solar irradiance forecasting is a major priority for the power transmission systems in order to generate and incorporate the performance of massive photovoltaic plants efficiently. As such, prior forecasting techniques that use classical modelling and single deep learning models that undertake feature extraction procedures manually were unable to meet the output demands in specific situations with dynamic variability. Therefore, in this study, we propose an efficient novel hybrid solar irradiance forecasting model based on three steps. In the first step, we employ a powerful variable input selection strategy named as partial mutual information (PMI) to calculate the linear and non-linear correlations of the original solar irradiance data. In the second step, unlike the traditional deep learning models designing their architectures manually, we utilize several deep long short term memory–convolutional neural network (LSTM–CNN) models optimized by a novel modified whale optimization algorithm in order to compute the forecasting results of the solar irradiance datasets. Finally, in the third step, we deploy a deep reinforcement learning strategy for selecting the best subset of the combined deep optimized LSTM–CNN models. Through analysing the forecasting results over two real-world datasets gathered from the USA solar irradiance stations, it can be inferred that our proposed algorithm outperforms other powerful benchmarked algorithms in 1-step, 2-step, 12-step, and 24-step ahead forecasting.

Forecasting Solar Radiation by the Machine Learning Algorithm & their Different Techniques

Abstract: The objective of this study is to give a summary of machine learning-based techniques for solar irradiation forecasting in this context. Despite the fact that numerous research describe methods like neural networks or support vector regression. Ranking the performance of such methods is difficult because of the diversity of the data collection, time step, forecasting horizon, setup, and performance indicators. The prediction inaccuracy is quite comparable overall. Others write. Global solar radiation recommended utilising ensemble forecasting or hybrid models to improve prediction accuracy. Forecasting the output power of solar systems is required for the smooth operation of the power grid or for the optimal control of the energy flows into the solar system. Prior to projecting the output of the solar system, it is essential to focus on solar irradiance. The two primary categories of methods for predicting the global solar radiation are machine learning algorithms and cloud pictures combined with physical models.

Solar Radiation Prediction by Machine Learning Algorithm & their Techniques

Abstract: For the power grid to run smoothly or for the best control of the energy flows into the solar system, it is necessary to forecast the output power of solar systems. It is crucial to concentrate the prediction on solar irradiance before predicting the solar system's output. There are numerous ways to anticipate the global solar radiation, but the two main categories are machine learning algorithms and cloud images mixed with physical models. This paper's goal is to provide an overview of machine learning-based algorithms for solar irradiation forecasting in this setting. Despite the fact that many studies explain techniques like support vector regression or neural networks. Due to the variability of the data collection, time step, forecasting horizon, setup, and performance measures, ranking the performance of such methods is challenging. Overall, the prediction error is very similar. Some write. Global solar radiation suggested using hybrid models or an ensemble forecast technique to boost prediction accuracy

Optimal Scheduling of Neural Network-Based Estimated Renewable Energy Nanogrid

In developing countries, many areas are deprived of electrical energy. Access to cleaner, more affordable energy is critical for improving the poor’s living conditions in developing countries. With the advent of smart grid technology, the integration and coordination of small grids, known as nanogrids, has become very easy. The purpose of this research is to propose a nanogrid model that will serve the purpose of providing the facility of electrical power to the poor rural community in Pakistan using hybrid renewable energy sources. This paper targets the electrification of a poor rural community of Akora Khatak, a small district located in Pakistan. The mathematical modeling of solar and wind energy, neural network-based forecasting of solar irradiance and wind velocity, and the social analysis to calculate the payback period for the community have been discussed in this paper.

A comprehensive review of solar irradiation estimation and forecasting using artificial neural networks: data, models and trends.

Solar irradiation data are imperatively required for any solar energy-based project. The non-accessibility and uncertainty of these data can greatly affect the implementation, management, and performance of photovoltaic or thermal systems. Developing solar irradiation estimation and forecasting approaches is an effective way to overcome these issues. Practically, prediction approaches can help anticipate events by ensuring good operation of the power network and maintaining a precise balance between the demand and supply of the power at every moment. In the literature, various estimation and forecasting methods have been developed. Artificial Neural Network (ANN) models are the most commonly used methods in solar irradiation prediction. This paper aims to firstly review, analyze, and provide an overview of different aspects required to develop an ANN model for solar irradiation prediction, such as data types, data horizon, data preprocessing, forecasting horizon, feature selection, and model type. Secondly, a highly detailed state of the art of ANN-based approaches including deep learning and hybrid ANN models for solar irradiation estimation and forecasting is presented. Finally, the factors influencing prediction model performances are discussed in order to propose recommendations, trends, and outlooks for future research in this field.

The Impact of Stochastic Perturbations in Physics Variables for Predicting Surface Solar Irradiance

We present a probabilistic framework tailored for solar energy applications referred to as the Weather Research and Forecasting-Solar ensemble prediction system (WRF-Solar EPS). WRF-Solar EPS has been developed by introducing stochastic perturbations into the most relevant physical variables for solar irradiance predictions. In this study, we comprehensively discuss the impact of the stochastic perturbations of WRF-Solar EPS on solar irradiance forecasting compared to a deterministic WRF-Solar prediction (WRF-Solar DET), a stochastic ensemble using the stochastic kinetic energy backscatter scheme (SKEBS), and a WRF-Solar multi-physics ensemble (WRF-Solar PHYS). The performances of the four forecasts are evaluated using irradiance retrievals from the National Solar Radiation Database (NSRDB) over the contiguous United States. We focus on the predictability of the day-ahead solar irradiance forecasts during the year of 2018. The results show that the ensemble forecasts improve the quality of the forecasts, compared to the deterministic prediction system, by accounting for the uncertainty derived by the ensemble members. However, the three ensemble systems are under-dispersive, producing unreliable and overconfident forecasts due to a lack of calibration. In particular, WRF-Solar EPS produces less optically thick clouds than the other forecasts, which explains the larger positive bias in WRF-Solar EPS (31.7 W/m2) than in the other models (22.7–23.6 W/m2). This study confirms that the WRF-Solar EPS reduced the forecast error by 7.5% in terms of the mean absolute error (MAE) compared to WRF-Solar DET, and provides in-depth comparisons of forecast abilities with the conventional scientific probabilistic approaches (i.e., SKEBS and a multi-physics ensemble). Guidelines for improving the performance of WRF-Solar EPS in the future are provided.

Short-term solar radiation forecast using total sky imager via transfer learning

Ground-based sky cameras, which capture hemispherical images, have been extensively used for localized monitoring of clouds. This paper proposes a short-term forecasting approach based on transfer learning using Total Sky-Imager (TSI) images of the Southern Great Plains (SGP) site obtained from the Atmospheric Radiation Measurement (ARM) dataset. An accurate estimation of solar irradiance using TSI is key for short-term solar energy generation forecasting and optimal energy consumption planning. We make use of deep neural network architectures such as AlexNet and ResNet-101 to extract the underlying deep convolution features from TSI images and then train using an ensemble learning approach to model and forecast solar radiation. We demonstrate the performance of the proposed approach by showcasing the best and worst cases. Thus, the transfer learning approach significantly reduces the time and resources required for modeling solar radiation. We outperform with reference to another state-of-art technique for solar modeling using TSI images at different forecast lead times.

An Integrated Framework Based on an Improved Gaussian Process Regression and Decomposition Technique for Hourly Solar Radiation Forecasting

The precise forecast of solar radiation is exceptionally imperative for the steady operation and logical administration of a photovoltaic control plant. This study proposes a hybrid framework (CBP) based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), an enhanced Gaussian process regression with a newly designed physical-based combined kernel function (PGPR), and the backtracking search optimization algorithm (BSA) for solar radiation forecasting. In the CEEMDAN-BSA-PGPR (CBP) model, (1) the CEEMDAN is executed to divide the raw solar radiation into a few sub-modes; (2) PACF (partial autocorrelation coefficient function) is carried out to pick the appropriate input variables; (3) PGPR is constructed to predict each subcomponent, respectively, with hyperparameters optimized by BSA; (4) the final forecasting result is produced by combining the forecasted sub-modes. Four hourly solar radiation datasets of Australia are introduced for comprehensive analysis and several models available in the literature are established for multi-step ahead prediction to demonstrate the superiority of the CBP model. Comprehensive comparisons with the other nine models reveal the efficacy of the CBP model and the superb impact of CEEMDAN blended with the BSA, respectively. The CBP model can produce more precise results compared with the involved models for all cases using different datasets and prediction horizons. Moreover, the CBP model is less complicated to set up and affords extra decision-making information regarding forecasting uncertainty.

Solar Irradiance Probabilistic Forecasting Using Machine Learning, Metaheuristic Models and Numerical Weather Predictions

Solar-power-generation forecasting tools are essential for microgrid stability, operation, and planning. The prediction of solar irradiance (SI) usually relies on the time series of SI and other meteorological data. In this study, the considered microgrid was a combined cold- and power-generation system, located in Tahiti. Point forecasts were obtained using a particle swarm optimization (PSO) algorithm combined with three stand-alone models: XGboost (PSO-XGboost), the long short-term memory neural network (PSO-LSTM), and the gradient boosting regression algorithm (PSO-GBRT). The implemented daily SI forecasts relied on an hourly time-step. The input data were composed of outputs from the numerical forecasting model AROME (Météo France) combined with historical meteorological data. Our three hybrid models were compared with other stand-alone models, namely, artificial neural network (ANN), convolutional neural network (CNN), random forest (RF), LSTM, GBRT, and XGboost. The probabilistic forecasts were obtained by mapping the quantiles of the hourly residuals, which enabled the computation of 38%, 68%, 95%, and 99% prediction intervals (PIs). The experimental results showed that PSO-LSTM had the best accuracy for day-ahead solar irradiance forecasting compared with the other benchmark models, through overall deterministic and probabilistic metrics.

An integrated framework of robust local mean decomposition and bidirectional long short-term memory to forecast solar irradiance

ABSTRACT An accurate forecasting of solar global horizontal irradiance (GHI) provides the estimation of future output from photovoltaic (PV) cells, resulting in guaranteed sustainable functioning of solar integrated smart grids. Traditional forecasting algorithms find it relatively hard to obtain the intrinsic non-linearity of solar GHI, leading to poor forecasting accuracy. This work offers a deep learning (DL)-based hybrid model called RLMD BILSTM that combines robust local mean decomposition (RLMD) algorithm with bidirectional long short-term memory (BILSTM) predictor. The proposed RLMD BILSTM model has been developed and evaluated for two separate Indian locations: Hisar and Jaipur, by comparing with benchmark models: persistence, long short-term memory (LSTM), gated recurrent unit (GRU), BILSTM, and their RLMD-based hybrid variations (RLMD LSTM and RLMD GRU). The performance of the proposed model has been verified by the statistical and visual results of short-term annual and seasonal forecast of solar GHI. From the results, it has been observed that the proposed model achieved lower root mean square error (RMSE) (16.34 W/m2-35.07 W/m2) compared to contrast mforecastsodels. The higher annual R2 yielding a value of 0.977–0.995 for the proposed model compared to the contrast model proved its better fitness. Moreover, the study showed that the RLMD with BILSTM improved the RMSE (59.16%–88.88%) and mean absolute error (MAE) (66.45%–92.22%) over various contrast models. The study also conducted the sensitivity analysis using the forecasting efficacy and forecast skill to prove the significance of the proposed model.

SolarRadnet: A novel variant input scoring optimized recurrent neural network for solar irradiance prediction

ABSTRACT Solar irradiance prediction is an essential one in providing renewable energy proficiently. The solar irradiance plays a major role in solar power system, solar thermal system, and photovoltaic grid-connected system, owing to uncertainty and variability. Conventional data analysis approaches are complex for demonstrating superior generalization. Therefore, the resource planners are flexible in accommodating these uncertainties while executing planning. To enhance the performance of solar irradiance forecasting, a new Variant Input Scoring Optimized Recurrent Neural Network (VIS-ORNN) is developed. The suggested approach includes two stages that are data collection and three stage simulation. At first, the data are gathered from the various meteorological standard dataset. Then, the prediction begins with feeding data directly to the ORNN. Here, the parameters of RNN are optimized with the help of Adaptive Escaping Energy-based Harris Hawks Coyote Optimization (AEE-HHCO) algorithm. Thus, the first score prediction is obtained. In the second phase, the first order statistical features act as an input, and it is given to the same ORNN, in which the second score is determined. In the third phase, the deep features are extracted by Convolutional Neural Network (CNN) that is subjected to the same ORNN for attaining the score. Finally, the final simulation is determined by taking the average of three prediction models. From the experimental results, while taking the MAE, the suggested AEE-HHCO-ORNN method has correspondingly secured 34.3% enhanced than PSO-ORNN, 7.7% enhanced than WOA-ORNN, 21.7% enhanced than COA-ORNN and 26.5% enhanced than HHO-ORNN. Thus, the simulation outcomes reveal that the offered method ensures maximum accuracy while validating with other baseline methodologies.

Complex-valued time series based solar irradiance forecast

A new method for short-term probabilistic forecasting of global solar irradiance from complex-valued time series is explored. The measurement defines the real part of the time series while the estimate of the volatility is the imaginary part. A complex autoregressive model (capable to capture quick fluctuations) is then applied with data gathered on the Corsica island (France). Results show that even if this approach is easy to implement and requires very little resource and data, both deterministic and probabilistic forecasts generated by this model are in agreement with experimental data (root mean square error ranging from 0.196 to 0.325 considering all studied horizons). In addition, it exhibits sometimes a better accuracy than classical models such as the Gaussian process, bootstrap methodology, or even more sophisticated models such as quantile regression. Many studies and many fields of physics could benefit from this methodology and from the many models that could result from it.

Combining simple and less time complex ML models with multivariate empirical mode decomposition to obtain accurate GHI forecast

Accurate solar irradiance forecasting requires several climatological variables whose seasonal variation affects the stability of the solar irradiance forecast. A less time complex ensemble model has been integrated with multivariate empirical mode decomposition (MEMD) to resolve the non-linearity and non-stationarity of meteorological variables into several intrinsic mode functions (IMFs). The ensemble model combines three base models (kNN-distance-based nonlinear model, DTR-tree-based nonlinear model, ridge-regularized linear model) to ensure good prediction accuracy with less time complexity. For better generalization and reliability of the model, the results have been validated for three Indian locations, viz. Roorkee, Greater Noida, and Gangtok. The MEMD-stacked model outperformed the modern and more complex ML techniques with a minimum % RMSE (% MAE) reduction of 48.51 (37.52) compared to RF, 47.43 (35.11) compared to ANN, and 46.46 (29.36) compared to LSTM. Moreover, in a seasonal analysis, the reported highest RMSE by the proposed model (53.57 W/m2) for the monsoon season was significantly less than that of LSTM (102.36 W/m2). This paper reflects the potential to combine simpler, less time-complex ML algorithms with MEMD to obtain more accurate GHI forecasts with lesser time complexity vis-à-vis the more popular complex ML models.

Short-term solar radiation forecasting with a novel image processing-based deep learning approach

— In this study, an image processing-based deep learning approach for short-term forecast of solar radiation has been developed. For this purpose, firstly, cloud movements occurred during the day are tracked and future cloud movements are forecasted, accordingly. Subsequently, using the cloud motion estimation and extraterrestrial solar radiation data, 1-min averaged solar radiation values are estimated for 5-min time horizon. Shi-Tomasi method is employed to determine the feature points to be tracked on the sky images whereas, Lucas-Kanade optical flow method is employed to track the determined feature points on the sequential images. Average cloud velocity and directions are calculated by the help of linear regression method from tracked cloud movements. A hybrid approach including K-means and red/blue ratio is built to classify the pixels of the image whether they are clouds or sky. Finally, short-term solar radiations are estimated using the Long-Short Term Memory (LSTM) deep learning method. The performance of the proposed approach is compared with other methods in the literature. As a result it is concluded that, developed approach outperforms most methods in the literature with RMSE values of 47.576, 53.830, 68.103, and 92.386 for four different days and can be used as an alternative approach.

Wind speed and global radiation forecasting based on differential, deep and stochastic machine learning of patterns in 2-level historical meteo-quantity sets

AbstractAccurate forecasting of wind speed and solar radiation can help operators of wind farms and Photo-Voltaic (PV) plants prepare efficient and practicable production plans to balance the supply with demand in the generation and consumption of Renewable Energy (RE). Reliable Artificial Intelligence (AI) forecast models can minimize the effect of wind and solar power fluctuations, eliminating their intermittent character in system dispatch planning and utilization. Intelligent wind and solar energy management is essential in load scheduling and decision-making processes to meet user requirements. The proposed 24-h prediction schemes involve the beginning detection and secondary similarity re-evaluation of optimal day-data sequences, which is a notable incremental improvement against state-of-the-art in the consequent application of statistical AI learning. 2-level altitude measurements allow the identification of data relationships between two surface layers (hill and lowland) and adequate interpretation of various meteorological situations, whose differentiate information is used by AI models to recognize upcoming changes in the mid-term day horizon. Observations at two professional meteorological stations comprise specific quantities, of which the most valuable are automatically selected as input for the day model. Differential learning is a novel designed unconventional neurocomputing approach that combines derivative components produced in selected network nodes in the weighted modular output. The complexity of the node-stepwise composed model corresponds to the patterns included in the training data. It allows for representation of high uncertain and nonlinear dynamic systems, dependent on local RE production, not substantially reducing the input vector dimensionality leading to model over simplifications as standard AI does. Available angular and frequency time data (e.g., wind direction, humidity, and irradiation cycles) are combined with the amplitudes to solve reduced Partial Differential Equations (PDEs), defined in network nodes, in the periodical complex form. This is a substantial improvement over the previous publication design. The comparative results show better efficiency and reliability of differential learning in representing the modular uncertainty and PDE dynamics of patterns on a day horizon, taking into account recent deep and stochastic learning. A free available C++ parametric software together with the processed meteo-data sets allow additional comparisons with the presented model results.

Simplified Energy Model and Multi-Objective Energy Consumption Optimization of a Residential House

Some analyses state that buildings contribute to overall energy consumption by 20–40%, which, in the context of the recent geopolitical energy crisis, makes them a critical issue to study. Finding solutions for better energy management in buildings can have a significant impact on the energy sector, thus reducing EU energy dependencies and contributing to the fulfillment of the REPowerEU goals. This paper focuses on proposing a simplified model of a residential house considering the main appliances, heating and cooling, a photovoltaic system, and electric vehicle recharging. Weather and solar irradiance forecasts are taken into account. The model predicts the energy demands of a house based on online weather forecasts and the desired indoor temperature. The article also focuses on the analysis of how weather forecast uncertainty affects energy demand prediction. This model can be used to better understand and predict the energy demand of either a single house or a set of houses. A multi-objective optimization approach that takes into account the preferences of users/inhabitants is developed to provide a compromise between the price paid for the electricity and temperature comfort. The authors plan to apply the proposed model to a residential house’s real-time control system. The model will be tuned, its predictions will be tested, and it will be used for energy demand optimization.