Solar Irradiance Forecasting Research Articles

Variational mode decomposition based random forest model for solar radiation forecasting: New emerging machine learning technology

Forecasting of solar radiation (Radn) can provide an insight vision for the amount of green and friendly energy sources. Owing to the non-linearity and non-stationarity challenges caused by meteorological variables in forecasting Radn, a variational mode decomposition method is integrated with simulated annealing and random forest (VMD-SA-RF) for resolving this problem. Firstly, the input parameters are separated into training and testing phases​ after generating a one-day ahead significant lags at (t – 1). Secondly, the variational mode decomposition is set to factorize multivariate meteorological data of train and test sets, independently, into their band-limited signals. Thirdly, the simulate annealing based feature selection system is engaged to select the best band-limited signals. Finally, using the pertinent band-limited signals, the daily Radn is forecasted via random forest (RF) model. The outcomes are benchmarked with other comparative models. The hybrid fusion VMD-SA-RF model is tested geographically in Australia, generates reliable performance to forecast Radn. The hybrid VMD-SA-RF system combining the pertinent meteorological features, as the model predictors have substantial implications for renewable and sustainable energy resource management.

IrradianceNet: Spatiotemporal deep learning model for satellite-derived solar irradiance short-term forecasting

The presence of clouds is widely identified as the primary uncertainty in current surface solar global horizontal irradiance (GHI) forecasts. Despite a wealth of historical satellite-derived irradiance observations, only limited research has investigated this problem from a purely data-driven perspective, something that has seen tremendous success in related domains such as radar- and satellite-based precipitation short-term forecasting. This paper presents IrradianceNet, a novel satellite-based neural network for spatiotemporal forecasting of surface solar irradiance up to 4 h in the future over Europe. Our method is fully data-driven and needs no post-processing or calibration based on sparse ground-based measurements of irradiance. We demonstrate superior forecasting performance compared to several persistence models, the TV-L1 algorithm, and ERA5 reanalysis data for satellite-derived solar irradiance using the European SARAH-2.1 dataset. We also validate these results using ground-based pyranometer observations from the Baseline Surface Radiation Network. Our conclusions remain unchanged when we account for hourly and monthly seasonality. Finally, applying a simple cloud mask scheme, we demonstrate that our performance improvement arises due to a considerable reduction in cloudy pixel errors. This is initial evidence that purely data-driven methods might better approximate and infer future cloud dynamics and their impact on surface solar irradiance.

A novel ensemble learning approach for hourly global solar radiation forecasting

A novel ensemble learning approach for hourly global solar radiation forecasting

A novel approach based on integration of convolutional neural networks and deep feature selection for short-term solar radiation forecasting

In this study, a novel deep solar forecasting approach is proposed based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), continuous wavelet transform (CWT), feature extraction networks, RReliefF feature selection, and extreme learning machine (ELM). The global solar radiation is decomposed into mode functions with the CEEMDAN method. The CWT reconstructs one-dimensional data into two-dimensional scalogram images to include both frequency and the time of the daily and hourly correlations. For the feature extraction process, a cascade convolutional neural network architecture, which consists of AlexNet and GoogLeNet, was designed to extract distinctive deep features. As the high-performance features provide a high level of forecasting accuracy, these are concatenated as the subset feature vector and RReliefF utilized to rank and select the most distinctive features from the subset. The designed ELM is then trained with the selected features and the fully-trained ELM model is then used to evaluate the forecast performance. In the experiments, root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) of the proposed method were observed as 0.0642, 0.0241, and 0.1201 for one-step ahead, 0.0686, 0.0285, and 0.1279 for two-step ahead, and 0.0724, 0.0315, and 0.1317 for three-step ahead, respectively. The obtained results show that the proposed method exhibits accurate and robust forecasting performance and outperforms conventional regression models.

Evaluating the Performance of Autoregressive Model for Solar Radiation Forecasting

The solar radiation data taken from 14 meteorological stations in Nigeria has been analyzed. The periodic component of the data which covered a period of 13 (mostly 1977-1989) years was removed via Fourier analysis while the residual series was subjected to autoregressive analysis. It was evident from the t-test and autocorrelation plots of the modified (i.e. without the periodic component) series that there exist significant persistence at nine stations including Sokoto, Nguru, Kano, Maiduguri, Bauchi, Yola, Minna, Ibadan, and Benin. The autocorrelation at Jos, Bida, Ikeja, Enugu and Port Harcourt were however found to be insignificant. As the sample partial autocorrelation function cuts off after lag 1, a non-seasonal autoregressive model of order 1, AR (1), was identified for stations with autocorrelation. The Q-statistic of error series suggested that the models were adequate as identified. Moreover, the exploratory plots of the model residual series showed agreement with the quantitative statistics and thus enforces the inference that the models were adequate for monthly mean daily global solar radiation forecasts at some of the study stations. It is interesting to note that all the stations within the sub-sahelian region showed significant persistence whereas all the stations in the coastal region except Benin were found with insignificant autocorrelation. Expectedly, the performance evaluation of the model gave impressive result for the stations within the sub-sahelian region but a relatively weak result for the coastal region. The result for the midland region was mixed whereas it was difficult to conclude on the Guinea savannah region with result from only one station.

A review on solar radiation assessment and forecasting in Algeria

Solar radiation forecasting is an important component in many areas related to either the production or exploitation of renewable energies. This field has attracted the attention of many Algerian researchers due to its important solar potential specially in the southern desert areas. In a comprehensive review of the works in this domain, we propose a comprehensive review of the different models and studies for predicting solar radiation in Algeria. Various techniques have been proposed including artificial stochastic models and intelligence.

Multi-view deep forecasting for hourly solar irradiance with error correction

Short-term solar irradiance forecasting is crucial in managing power network operations and solar photovoltaic applications. In this paper, a Multi-view Deep Forecasting method with Error Correction (MvDF_EC) for 1-hour ahead solar forecasting is proposed. MvDF_EC comprises of the Multi-view Deep Forecasting method (MvDF) and a robust Radial Basis Function Neural Network trained via minimizing the Localized Generalization Error for compensating the solar forecasting error of MvDF. MvDF consists of three deep neural networks which learn representations of input data from different views. The three views are 1) the hierarchical local temporal information extracted by the Temporal Convolutional Neural Network (TCN), 2) the key context sequential information captured by the Bi-directional Long Short-Term Memory Neural Network with Temporal Attention (BLSTMattn), and 3) long-term temporal dependencies between local temporal patterns filtered by the Convolutional Gated Recurrent Unit Neural Network (C_GRU). The solar forecasting performance of the proposed MvDF_EC is evaluated with the National Solar Radiation Database. Simulation results show that MvDF_EC yields the most accurate solar prediction compared with the benchmarks including the smart persistence and the state-of-the-art models. The lowest relative Root Mean Square Error values for Maraba and Labelle are 22.08% and 27.40%, respectively in 1-hour ahead solar forecasting.

Influence of design data availability on the accuracy of physical photovoltaic power forecasts

Accurate photovoltaic (PV) power forecasts are essential for the grid integration of the technology. Most solar forecasting studies deal only with solar irradiance forecasting, which highlights the importance of the irradiance to power conversion methods to enable the practical utilization of the advanced irradiance forecasting techniques. The PV power output is commonly calculated with physical model chains that rely on the main design parameters of the PV plants. This study presents an analysis of how the unavailability or uncertain knowledge of the design parameters affects the physical power forecast accuracy. The analysis is performed by verifying the power forecasts created by the bests of 32,400 model chains for 16 PV plants in Hungary for five data availability scenarios based on numerical weather prediction data. The results show that even though the knowledge of all relevant design parameters ensures the lowers errors, the critical parameters are only the nameplate capacities and the module orientation. The increase in mean absolute error and root mean square error is only 1.3% and 0.5%, respectively, if only these crucial parameters are known compared to the baseline scenario. If necessary, the tilt and azimuth angles can also be inferred, where the resulting inaccuracy depends on the estimation errors. The results reveal that the physical model chains can be used with a decent accuracy for power forecast calculations even if the design parameters are unknown, which highly broadens the applicability of the physical method.

Empirical Modelling of Global Solar Radiation in Hatay (Turkey) Province

There are many models used in global solar radiation prediction. However, these prediction models vary according to the climate and geographic characteristics of the region involved. When the prediction model determined for a region is used in a different region, the prediction model may not work. In order to gain absolute and stable results from these models, the studies should be either custom-made or tested. In this study, 7 different models were examined, comparison charts were created and statistical interpretations were made in order to determine the monthly average global solar radiation coming to the horizontal plane taking into account the climatic characteristics of Hatay province, located in the eastern 39.92º latitude and northern longitude 36.16º, covering an area of 5403 km, and has a humid climate with a value of 41.3, based on De Martonne-Gottmann’s drought index and 50.6 based on Erinç's rainfall efficiency index. Under the scope of this study, the most ideal global solar radiation prediction model was selected by making a statistical evaluation according to the parameters of determination coefficient (R²), mean percentage error (MPE), mean deviation error (MBE), root mean square error (RMSE). A general assessment of the graphics and statistical parameters of the predictions obtained by using the models and the measured data has indicated Model 4 as the most successful model by an RMSE value of 0.17306, and the least successful model was Model 3 by an RMSE value of 2.11851. When the models are interpreted according to the determination coefficient, it has been observed that other models are generally successful. However, this situation does not coincide with the comparison charts of the predicted and measured data. For this reason, it was seen that the determination coefficient was not sufficient in the statistical evaluation of the prediction models. In the interpretation of the models, it was observed that the interpretation of root mean square error, mean percentage error and mean deviation error values together gave more accurate results. In conclusion, it has been suggested that Model 4 should be preferred for the global solar radiation forecast of Hatay province.

Short-Term Global Horizontal Irradiance Forecasting Using a Hybrid Convolutional Neural Network-Gate Recurrent Unit Method

The effectiveness of photovoltaic power generation systems—a clean and renewable use of solar energy—depends on the amount of solar radiation. Consequently, solar radiation forecasting (especially short-term) is crucial for photovoltaic plants. In this paper, a hybrid convolutional neural network (CNN) and gate recurrent unit (GRU) method is proposed for short-term (10-min) solar radiation forecasting based on image and time-series data (i.e., radiation data at different times). The method aims to achieve high performance in solar radiation forecasting, which can be useful for PV plant adjustment. CNN–GRU consists of two branches. One is based on the ResNet-18 structure, which can extract features from sky images. The other is a GRU branch, which consists of three fully connected layers used for meteorological feature extraction. Experiments on a public dataset showed that our method predicts the mean absolute error better than other benchmark models. The ablation experiments demonstrated that the hybrid model performs better than a single model and, therefore, shows promise for application in solar radiation forecasting.

Cloud Classification of Ground-based Cloud Images based on Convolutional Neural Network

Cloud is a crucial meteorological factor, and also a key factor affecting solar radiation variables for solar energy, especially the attenuation of different cloud types on solar radiation. However, there are few researches on the cloud classification based on the ground-based cloud image in order to predict solar energy. In this paper, the ground-based cloud images were collected, and then they were classified into five classes based on colour, texture and the attenuation on the theoretical clear-sky solar radiation. The ResNet18 model was trained to classify the ground-based cloud images automatically. The experimental results show that the classification accuracy of the ResNet18 is up to 91%, which is higher than the other two convolutional neural networks (AlexNet and VGG16) and is also much higher than the traditional machine learning classifiers. This work provides a new perspective and important supporting data for solar radiation forecast.

A validation frame for deterministic solar irradiance forecasts

A novel validation frame for deterministic solar irradiance forecasts is presented. It bases on the perception that a perfect forecast of a random variable must be indistinguishable from its observation. In mathematical terms: The random variables observation and forecast must be exchangeable. This implies that they have the same probability distribution and that the pertaining copula is symmetric. The validation frame tallies the equality of the probability distributions of observed and forecast solar irradiance, the symmetry of the pertaining copula, and the forecasting skill with well-defined measures, namely the Kolmogorov-Smirnov test statistic, copula asymmetry, and Spearman's ρ. The three measures are scale-invariant under strictly increasing transformations of observation and forecast. Thus, the frame is particularly suited for benchmarking solar irradiance forecasts from different locations, different calendar days, and over different periods. The frame is demonstrated on 24-h-ahead solar irradiance forecasts from two sites with different climates. Yet, it can be applied to any forecast of a continuous random variable. Additional theoretical insights connect the method to present-day practice, such as the Murphy-Winkler framework and the skill score.

A State-of-Art-Review on Machine-Learning Based Methods for PV

In the current era, Artificial Intelligence (AI) is becoming increasingly pervasive with applications in several applicative fields effectively changing our daily life. In this scenario, machine learning (ML), a subset of AI techniques, provides machines with the ability to programmatically learn from data to model a system while adapting to new situations as they learn more by data they are ingesting (on-line training). During the last several years, many papers have been published concerning ML applications in the field of solar systems. This paper presents the state of the art ML models applied in solar energy’s forecasting field i.e., for solar irradiance and power production forecasting (both point and interval or probabilistic forecasting), electricity price forecasting and energy demand forecasting. Other applications of ML into the photovoltaic (PV) field taken into account are the modelling of PV modules, PV design parameter extraction, tracking the maximum power point (MPP), PV systems efficiency optimization, PV/Thermal (PV/T) and Concentrating PV (CPV) system design parameters’ optimization and efficiency improvement, anomaly detection and energy management of PV’s storage systems. While many review papers already exist in this regard, they are usually focused only on one specific topic, while in this paper are gathered all the most relevant applications of ML for solar systems in many different fields. The paper gives an overview of the most recent and promising applications of machine learning used in the field of photovoltaic systems.

A cyclostationary model for temporal forecasting and simulation of solar global horizontal irradiance

AbstractAs part of Saudi Vision 2030, a major strategic framework developed by the Council of Economic and Development Affairs of Saudi Arabia, the country aims to reduce its dependency on oil and promote renewable energy for domestic power generation. Among the sustainable energy resources, solar energy is one of the leading resources because of the endowment of Saudi Arabia with plentiful sunlight exposure and year‐round clear skies. This essentializes to forecast and simulate solar irradiance, in particular global horizontal irradiance (GHI), as accurately as possible, mainly to be utilized by the power system operators among many others. Motivated by a dataset of hourly solar GHIs, this article proposes a model for short‐term point forecast and simulation of GHIs. Two key points, that make our model competent, are: (1) the consideration of the strong dependency of GHIs on aerosol optical depths and (2) the identification of the periodic correlation structure or cyclostationarity of GHIs. The proposed model is shown to produce better forecasts and more realistic simulations than a classical model, which fails to recognize the GHI data as cyclostationary. Further, simulated samples from both the models as well as the original GHI data are used to calculate the corresponding photovoltaic power outputs to provide a comprehensive comparison among them.

Forecasting of Energy Production for Photovoltaic Systems Based on ARIMA and ANN Advanced Models

Accurate forecasting of solar energy is essential for photovoltaic (PV) plants, to facilitate their participation in the energy market and for efficient resource planning. This article is dedicated to two forecasting models: (1) ARIMA (Autoregressive Integrated Moving Average) statistical approach to time series forecasting, using measured historical data, and (2) ANN (Artificial Neural Network) using machine learning techniques. The main contributions of the authors could be synthetized as follows: (1) analysis and discussion of the experimental and simulated results regarding solar radiation forecast, as well as energy production prediction and forecasting based on ARIMA and ANN models for two case studies: (a) laboratory BIPV system developed at the Polytechnic University of Bucharest and (b) large PV park placed in a specific site of the south of Romania. A variability index of solar radiation was introduced for the model improvement; (2) comparison between the ARIMA and ANN results to highlight the ARIMA model which is more efficient than the ANN one; (3) optimized method defined by the GMDH model (Group Method of Data Handling) proposed to provide a software program for calculation of the PV energy production.

Global solar radiation prediction: Application of novel hybrid data-driven model

One of the significant prerequisites for harvesting solar energy is precise global solar radiation (GHI) forecasts. However, variability and uncertainty are inherent characteristics of solar radiation. It is challenging to show better generalization using current data analysis approaches. Thus, this research presents a new intelligence framework by hybridizing Support Vector Regression (SVR) with the Grasshopper Optimization Algorithm (GOA) and the Boruta-based feature selection algorithm (BA) for forecasting GHI values at different sites of Saudi Arabia. Interestingly, the most significant distinction that differentiates this proposed prediction model (SVR-GOA-BAK) from other models is that the GOA is automatically employed to search for optimal SVR’s hyperparameters. In contrast, these hyperparameters are chosen randomly and manually in conventional models. Consequently, the contribution helps save time, reduce cost, and avoid the possibility of models’ overfitting or underfitting caused by random and manual selection. A diversity of statistical measures has justified the proposed model’s effectiveness and superiority. In terms of mean absolute percentage error (MAPE), the proposed model outperformed the standalone SVR models by 32.15–39.69% at different study sites. In tuning the SVR’s parameters, GOA outperforms popular optimization algorithms. All the simulation test results demonstrate the superiority of the proposed model. Hence, the proposed approach provides a foundation for precise solar radiation forecasting, which can aid in the growth of renewable-energy-based technologies.

Review for the Solar Radiation Forecasting Methods Based on Machine Learning Approaches

Predictions of solar potential for these systems’ production are important, whether they ensure sound activity or the perfect control of an energy discharge heading to the solar system. It is important to base the prediction on solar irradiance before predicting solar systems performance. The measurement of solar radiation elements is a very significant criterion for applications of solar energy. Several globalized solar radiation prediction modes can be done in the two major categories: cloud imagery with physical models and machine learning techniques are correlated. In this paper, the methods used to predict solar radiation are explained with machine learning algorithms.

A Review on Solar Radiation Assessment and Forecasting in Algeria (Part 1: Solar Radiation Assessment)

Solar energy takes a prime place in the energetic transition towards renewable energies. Solar radiation data plays a major role in the expansion of this energy. However, the unavailability of these data due to the reduced number of meteorological stations has imposed the use of various solar radiation estimation and prediction models. Moreover, the geostrategic location of Algeria, its enormous area and its huge solar potential places it among the promising solar energy countries. The main objective of this part is to review the studies done upon estimation and assessment of solar radiation for Algerian sites. Different techniques are proposed including semi-empirical models, satellite imaging and solar maps. The study shows that semi-empirical models have been the most widely used due to the unavailability of solar data.

Comparative Study of Neural Network and Tree-Based Models in Solar Irradiance Prediction

Solar Photovoltaic Systems have become the most promising technology for clean energy generation in recent years. Solar irradiation is one of the critical factors that affect Photovoltaic output. Since the Photovoltaic output varies significantly during the day, accurate solar irradiation forecasting is essential for predicting Photovoltaic output. Many machine-learning models have been used to forecast solar irradiation in the last few decades. This paper evaluates the performance of two basic machine-learning models: Artificial Neural Networks and Tree-based methods for solar irradiance prediction. Two neural networks such as Multilayer Perceptron, Radial Basis Function Neural Network, and three tree-based models such as Classification and Regression Tree, Alternating Model Tree, and Random Forest are applied to predict the solar irradiance using the NASA Solar Irradiation dataset. The performance of those methods is assessed using various metrics like the Correlation Coefficient, Mean Absolute Error, and Root Mean Squared Error. The experimental results show that the tree-based ensemble methods perform significantly better than neural network models for solar irradiance prediction.

Solar Irradiance Forecast Based on Cloud Movement Prediction

Solar energy production based on a photovoltaic system is closely related to solar irradiance. Therefore, the planning of production is based on the prediction of solar irradiance. The optimal use of different energy storage systems requires an accurate prediction of solar irradiation with at least an hourly time horizon. In this work, a solar irradiance prediction method is developed based on the prediction of solar shading by clouds. The method is based on determining the current cloud position and estimating the velocity from a sequence of multiple images taken with a 180-degree wide-angle camera with a resolution of 5 s. The cloud positions for the next hour interval are calculated from the estimated current cloud position and velocity. Based on the cloud position, the percentage of solar overshadowing by clouds is determined, i.e., the solar overshadowing curve for the next hour interval is calculated. The solar irradiance is determined by normalizing the percentage of the solar unshadowing curve to the mean value of the irradiance predicted by the hydrometeorological institute for that hourly interval. Image processing for cloud detection and localization is performed using a computer vision library and the Java programming language. The algorithm developed in this work leads to improved accuracy and resolution of irradiance prediction for the next hour interval. The predicted irradiance curve can be used as a predicted reference for solar energy production in energy storage system optimization.