Irradiance Forecasting Research Articles

Combining quantiles of calibrated solar forecasts from ensemble numerical weather prediction

This work is concerned with optimally combining quantiles of several post-processed versions of ensemble solar forecasts, which is new in this field. Numerical weather prediction (NWP) serves grid integration of solar energy by issuing dynamical ensemble irradiance forecasts. However, these ensemble members often suffer from under-dispersion, which motivates statistical calibration via quantile regression (QR) or ensemble model output statistics (EMOS). Given the numerous variants of QR and EMOS, it is generally unclear which variant offers the best performance under what situation, which further motivates combining quantile forecasts. A framework for combining solar forecasts in the form of quantiles is proposed, and a constrained quantile regression averaging scheme is used to exemplify the framework. Using the strictly proper pinball loss, ensemble irradiance forecasts from the European Centre for Medium-Range Weather Forecasts (ECMWF) Ensemble Prediction System are first post-processed using five QR variants and five EMOS variants, and then combined through a linear program. It is found that combining quantiles is an effective strategy that can further improve the calibrated ECMWF forecasts across all locations herein considered.

A Novel Machine Learning Approach for Solar Radiation Estimation

Solar irradiation (Rs) is the electromagnetic radiation energy emitted by the Sun. It plays a crucial role in sustaining life on Earth by providing light, heat, and energy. Furthermore, it serves as a key driver of Earth’s climate and weather systems, influencing the distribution of heat across the planet, shaping global air and ocean currents, and determining weather patterns. Variations in Rs levels have significant implications for climate change and long-term climate trends. Moreover, Rs represents an abundant and renewable energy resource, offering a clean and sustainable alternative to fossil fuels. By harnessing solar energy, we can actively reduce greenhouse gas emissions. However, the utilization of Rs comes with its own challenges that must be addressed. One problem is its variability, which makes it difficult to predict and plan for consistent solar energy generation. Its intermittent nature also poses difficulties in meeting continuous energy demand unless appropriate energy storage or backup systems are in place. Integrating large-scale solar energy systems into existing power grids can present technical challenges. Rs levels are influenced by various factors; understanding these factors is crucial for various applications, such as renewable energy planning, climate modeling, and environmental studies. Overcoming the associated challenges requires advancements in technology and innovative solutions. Measuring and harnessing Rs for various applications can be achieved using various devices; however, the expense and scarcity of measuring equipment pose challenges in accurately assessing and monitoring Rs levels. In order to address this, alternative methods have been developed with which to estimate Rs, including artificial intelligence and machine learning (ML) models, like neural networks, kernel algorithms, tree-based models, and ensemble methods. To demonstrate the impact of feature selection methods on Rs predictions, we propose a Multivariate Time Series (MVTS) model using Recursive Feature Elimination (RFE) with a decision tree (DT), Pearson correlation (Pr), logistic regression (LR), Gradient Boosting Models (GBM), and a random forest (RF). Our article introduces a novel framework that integrates various models and incorporates overlooked factors. This framework offers a more comprehensive understanding of Recursive Feature Elimination and its integrations with different models in multivariate solar radiation forecasting. Our research delves into unexplored aspects and challenges existing theories related to solar radiation forecasting. Our results show reliable predictions based on essential criteria. The feature ranking may vary depending on the model used, with the RF Regressor algorithm selecting features such as maximum temperature, minimum temperature, precipitation, wind speed, and relative humidity for specific months. The DT algorithm may yield a slightly different set of selected features. Despite the variations, all of the models exhibit impressive performance, with the LR model demonstrating outstanding performance with low RMSE (0.003) and the highest R2 score (0.002). The other models also show promising results, with RMSE scores ranging from 0.006 to 0.007 and a consistent R2 score of 0.999.

WRF Parameterizations of Short-Term Solar Radiation Forecasts for Cold Fronts in Central and Eastern Europe

The solar power industry is a rapidly growing sector of renewable energy, and it is crucial that the available energy is accurately forecast. Using numerical weather prediction models, we can forecast the global horizontal irradiance on which the amount of energy produced by photovoltaic systems depends. This study presents the forecast effects for one of the most challenging weather conditions in modelling, occurring in central and eastern Europe. The dates of the synoptic situations were selected from 2021 and 2022. Simulations were carried out for 18 days with a cold front and, in order to verify the model configuration, for 2 days with a warm front, 2 days with an occlusion front and 2 days with a high pressure situation. Overall, 24 forecasts were made for each of the three parameterizations of the Weather Research and Forecasting model. The data were compared with the values measured in situ at the station performing the actinometric measurements belonging to Germany’s National Meteorological Service. This paper presents the spatial distribution of the global horizontal irradiance parameters for several terms to explain the differences between the results of the different simulations.

Global Horizontal Irradiance in West Africa: Evaluation of the WRF-Solar Model in Convection-Permitting Mode with Ground Measurements

Abstract The number of solar power plants has increased in West Africa in recent years. Reliable reanalysis data and short-term forecasting of solar irradiance from numerical weather prediction models could provide an economic advantage for the planning and operation of solar power plants, especially in data-poor regions such as West Africa. This study presents a detailed assessment of different shortwave (SW) radiation schemes from the Weather Research and Forecasting (WRF) Model option Solar (WRF-Solar), with appropriate configurations for different atmospheric conditions in Ghana and the southern part of Burkina Faso. We applied two 1-way nested domains (D1 = 15 km and D2 = 3 km) to investigate four different SW schemes, namely, the Community Atmosphere Model, Dudhia, RRTMG, Goddard, and RRTMG without aerosol and with aerosol inputs (RRTMG_AERO). The simulation results were validated using hourly measurements from different automatic weather stations established in the study region in recent years. The results show that the RRTMG_AERO_D01 generally outperforms the other SW radiation schemes to simulate global horizontal irradiance under all-sky condition [RMSE = 235 W m−2 (19%); MAE = 172 W m−2 (14%)] and also under cloudy skies. Moreover, RRTMG_AERO_D01 shows the best performance on a seasonal scale. Both the RRTMG_AERO and Dudhia experiments indicate a good performance under clear skies. However, the sensitivity study of different SW radiation schemes in the WRF-Solar model suggests that RRTMG_AERO gives better results. Therefore, it is recommended that it be used for solar irradiance forecasts over Ghana and the southern part of Burkina Faso.

Reducing nutrient imbalance in recirculating drainage solution of stone wool grown tomato

Recirculation of drainage solution reduces the emission of water, nutrients and plant protection products from both substrate-based and water-based growing systems. During cultivation, deviations in nutrient ratios in the root environment may potentially affect yield and quality as well as motivate a grower to discharge the drainage solution. Our objective was to quantify imbalances in nutrient ratios and to assess what part of the nutrient imbalances can be prevented with practical measures. included daily balances for water and individual nutrients, using data from a commercial cherry-tomato grower. The balances showed plant water uptake and uptake of individual nutrients were not strictly correlated. It was also possible to establish individual relations between solar radiation sum and water uptake as well as uptake per individual nutrient. After 200 days of production, an adapted balance was prepared and then used as a model. This model was used to compare various nutrient supply strategies to reduce daily fluctuations in nutrient ratios. Simulations showed the imbalances between supply and uptake could be halved compared with the original grower strategy. This was realized by using a combination of drainage volume percentage, the supply EC and the correlation of the supplied solution EC with solar radiation forecast. The conclusion is that nutrient balances can deliver plant uptake data for water and individual nutrients, which can then be correlated with solar radiation. This can be used to identify and reduce deviations from targeted ratios between nutrients in the supplied solution as well as in the root solution. These conclusions take advantage of information available in practice.

ARIMA Models in Solar Radiation Forecasting in Different Geographic Locations

The increasing demand for clean energy and the global shift towards renewable sources necessitate reliable solar radiation forecasting for the effective integration of solar energy into the energy system. Reliable solar radiation forecasting has become crucial for the design, planning, and operational management of energy systems, especially in the context of ambitious greenhouse gas emission goals. This paper presents a study on the application of auto-regressive integrated moving average (ARIMA) models for the seasonal forecasting of solar radiation in different climatic conditions. The performance and prediction capacity of ARIMA models are evaluated using data from Jordan and Poland. The essence of ARIMA modeling and analysis of the use of ARIMA models both as a reference model for evaluating other approaches and as a basic forecasting model for forecasting renewable energy generation are presented. The current state of renewable energy source utilization in selected countries and the adopted transition strategies to a more sustainable energy system are investigated. ARIMA models of two time series (for monthly and hourly data) are built for two locations and a forecast is developed. The research findings demonstrate that ARIMA models are suitable for solar radiation forecasting and can contribute to the stable long-term integration of solar energy into countries’ systems. However, it is crucial to develop location-specific models due to the variability of solar radiation characteristics. This study provides insights into the use of ARIMA models for solar radiation forecasting and highlights their potential for supporting the planning and operation of energy systems.

Forecasting global solar radiation using a robust regularization approach with mixture kernels

AbstractAccurately forecasting global solar radiation plays a key role in photovoltaic evaluations. To quantify and control the uncertainties in global solar radiation forecasting, this study developed a robust and accurate forecasting model. This was constructed in the reproducing kernel Hilbert space with a novel regularization. Global solar radiation datasets were collected from the autonomous region of Tibet in China. Experimental results demonstrate that the proposed model can quantify uncertainties and obtain more accurate forecasting compared with machine learning models.

A Hybrid Ensemble Model for Solar Irradiance Forecasting: Advancing Digital Models for Smart Island Realization

This study introduces HYTREM, a hybrid tree-based ensemble learning model conceived with the sustainable development of eco-friendly transportation and renewable energy in mind. Designed as a digital model, HYTREM primarily aims to enhance solar power generation systems’ efficiency via accurate solar irradiance forecasting. Its potential application extends to regions such as Jeju Island, which is committed to advancing renewable energy. The model’s development process involved collecting hourly solar irradiance and weather-related data from two distinct regions. After data preprocessing, input variables configuration, and dataset partitioning into training and testing sets, several tree-based ensemble learning models—including extreme gradient boosting, light gradient boosting machine, categorical boosting, and random forest (RF)—were employed to generate prediction values in HYTREM. To improve forecasting accuracy, separate RF models were constructed for each hour. Experimental results validated the superior performance of HYTREM over state-of-the-art models, demonstrating the lowest mean absolute error, root mean square error (RMSE), and normalized RMSE values across both regions. Due to its transparency and efficiency, this approach suits energy providers with limited computational resources. Ultimately, HYTREM is a stepping stone towards developing advanced digital twin systems, highlighting the importance of precise forecasting in managing renewable energy.

A probabilistic perspective on predictability of solar irradiance using bootstrapped correlograms and ensemble predictability error growth

Recently in “Correlogram, predictability error growth, and bounds of mean square er-ror of solar irradiance forecasts” [Renew. Sustain. Energy Rev. 167 (2022) 112736], a new measure of predictability, applicable to solar irradiance in particular, was proposed. That predictability measure is expressed as one minus the ratio of the smallest attainable and highest tolerable root mean square errors (RMSEs) for a specific forecasting situation. Whereas the smallest attainable RMSE can be derived from the predictability error growth (PEG) of a numerical weather prediction model, the highest tolerable RMSE is computed from the forecasts of a naïve standard of reference. Despite that proposal has pioneered our understanding on the predictability of solar irradiance, answers to some technical challenges remain opaque. One of those technical challenges is the lack of uncertainty quantification of the predictability estimate, which is what this work seeks to resolve. Two conceptions, namely, ensemble PEG and bootstrapped correlograms, are herein introduced to facilitate the probabilistic representations of the smallest attainable and highest tolerable RMSEs, respectively. It is found that the uncertainty in predictability estimates is very small as compared to the range over which predictability varies across climatic conditions and forecast horizons.

Error revision during morning period for deep learning and multi-variable historical data-based day-ahead solar irradiance forecast: towards a more accurate daytime forecast

Error revision during morning period for deep learning and multi-variable historical data-based day-ahead solar irradiance forecast: towards a more accurate daytime forecast

Hybrid Models for Daily Global Solar Radiation Assessment

Daily solar radiation forecasting has recently become critical in developing solar energy and its integration into grid systems. Despite the huge number of proposed forecasting techniques, an accurate estimation remains a significant challenge because of the non-stationary variation of solar radiation components due to the continuously changing climatic conditions. Usually, several input data predictors are used for the forecasting process, which can cause redundancy and correlation between data features. This work assesses a set of feature selection techniques to check their ability to select the relevant predictors and reduce redundant and irrelevant information. An Artificial Neural Network is used to fit the measured solar radiation based on the selected features. The developed model is evaluated through various objective evaluation metrics using historical data of three years measured at the Ghardaiaregion inAlgeria. Results show the effectiveness of the proposed method, where values of 0,0189, 0.0286, 5.4387, and 98.28% have been found as MABE, RMSE, nRMSE and r, respectively.

Assessment of ECMWF Sub-Seasonal Solar Irradiance Forecast over Indo-China Peninsula

Assessment of ECMWF Sub-Seasonal Solar Irradiance Forecast over Indo-China Peninsula

A point and interval forecasting of solar irradiance using different decomposition based hybrid models

A point and interval forecasting of solar irradiance using different decomposition based hybrid models

Calibration of GFS Solar Irradiation Forecasts: A Case Study in Romania

Models based on Numerical Weather Prediction (NWP) are widely used for the day-ahead forecast of solar resources. This study is focused on the calibration of the hourly global solar irradiation forecasts provided by the Global Forecast System (GFS), a model from the NWP class. Since the evaluation of GFS raw forecasts sometimes shows a high degree of uncertainty (the relative error exceeding 100%), a procedure for reducing the errors is needed as a prerequisite for engineering applications. In this study, a deep analysis of the error sources in relation to the state of the atmosphere is reported. Of special note is the use of sky imagery in the identification process. Generally, it has been found that the largest errors are determined by the underestimation of cloud coverage. For calibration, a new ensemble forecast is proposed. It combines two machine learning approaches, Support Vector Regression and Multi-Layer Perceptron. In contrast to a typical calibration, the objective function is constructed based on the absolute error instead of the traditional root mean squared error. In terms of normalized root mean squared error, the calibration roughly reduces the uncertainty in hourly global solar irradiation by 16%. The study was conducted with high-quality ground-measured data from the Solar Platform of the West University of Timisoara, Romania. To ensure high accessibility, all the parameters required to run the proposed calibration procedures are provided.

Multi-model approach applied to meteorological data for solar radiation forecasting using data-driven approaches

The accuracy of the solar forecasting model depends upon various factors such as attributes of the data, time horizon, time interval, length of the data, etc. This means attributes of data selection are an important feature of any solar forecasting model. A lot of research has been done on solar forecasting using deep learning and machine learning approaches, providing better accuracy for a particular type of model and data. However, how to accurately apply the multi-model techniques in the data-driven approaches of the solar radiation prediction model is still a challenging issue due to the complexity of the temporal resolution, length, and attribute selection of the data. This paper proposes a multi-model technique using data-driven approaches to get an improvised solar forecasting model with respect to the attributes of data. In this research, a multi-model method based on data-driven approaches is developed for short-term solar radiation forecasting. Three years of weather data with different temporal resolutions taken from reliable online sources were used for training and testing in this work. The weather data considered various input parameters such as temperature, humidity, pressure, wind speed, and wind direction; solar radiation data is considered the model’s target variable. This work is a two-stage process. In the first stage, multi-model methods are analyzed based on solar forecasts at different temporal resolutions, and best-performing models are selected. The optimization technique is applied to the best model in the second stage to obtain an improvised solar forecasting model. It is observed that the multi-model forecasts provide better accuracy in terms of R2, nRMSE, and MAE than the conventional forecasting model. In this work, the performance parameters of nRMSE = 0.34, MAE = 4.71, and R2 = 0.93 are obtained before optimization, and nRMSE = 0.25, MAE = 1.39 and R2 = 0.96 are obtained after optimization in the testing stage for an hourly dataset. For daily datasets, the performance parameters nRMSE = 0.24, MAE = 3.19, and R2 = 0.93 are obtained before optimization, and nRMSE = 0.16, MAE = 2.61, and R2 = 0.95 are obtained after optimization in the testing stage. As a result, the proposed algorithm focused on an efficient model to predict solar radiation. Accurate solar radiation prediction models are highly in demand in various smart grid applications. Therefore, the proposed work may help in suggesting a suitable model for solar energy forecasting.

A New Hybrid Short Term Solar Irradiation Forecasting Method Based on CEEMDAN Decomposition Approach and BiLSTM Deep Learning Network with Grid Search Algorithm

An accurate and efficient forecasting of solar energy is necessary for managing the electricity generation and distribution in today’s electricity supply system. However, due to its random character in its time series, accurate forecasting of solar irradiation is a difficult task; but it is important for grid management, scheduling and its balancing. To fully utilize the solar energy in order to balance the generation and consumption, this paper proposed an ensemble approach using CEEMDAN-BiLSTM combination to forecast short term solar irradiation. In this, Complete Ensemble Empirical Mode Decomposition with adaptive noise (CEEMDAN) extract the inherent characteristics of time series data by decomposing it into low and high frequency Intrinsic Mode Functions (IMF’s) and Bidirectional Long Short Term Memory (BiLSTM) used as a forecasting tool to forecast the solar Global Horizontal Irradiance (GHI). Furthermore, using extensive experimental analysis, the research minimizes the number of IMF’s by integrating the CEEMDAN decomposed component (IMF1–IMF14) in order to increase the prediction accuracy. Then, for each IMF subseries, the trained standalone BiLSTM network are assigned to carry out the forecasting. In last stage, the forecasted results of each BiLSTM network are aggregate to compile final results. Two year data (2012–13) of Delhi, India from National Solar Radiation Database (NSRDB) has been used for training while one year data (2014) used for testing purpose for the same location. The proposed model performance is measured in terms of root mean square error (RMSE), mean absolute percentage error (MAPE), Correlation coefficient (R22) and forecast skill (FS). For the comparative analysis of proposed model, several others models: persistence model, unidirectional deep learning models: long short term memory (LSTM), gated recurrent unit (GRU), BiLSTM and two CEEMDAN based BiLSTM models are developed. The proposed model achieved lowest annual average RMSE (18.86 W/m22, 22.24 W/m22, 26.25 W/m22) and MAPE (2.19%, 4.81%, 6.77%) among the other developed models for 1-hr, 2-hr and 3-hr ahead solar GHI forecasting respectively. The maximum correlation coefficient (R22) obtained by the proposed model is 96.4 for 1-hr ahead respectively; on the other hand, forecast skill (%) of 89% with reference to benchmark model. Various test such as: Diebold Mariano Hypothesis test (DMH) and directional change in forecasting (DC) are used to analyze the sensitivity with reference to the difference in forecasted and observed value.

Intelligent Fuzzy Models: WM, ANFIS, and Patch Learning for the Competitive Forecasting of Environmental Variables

This paper focuses on the application of fuzzy modeling methods in the field of environmental engineering. Since predicting meteorological data is considered to be a challenging task, the current work aimed to assess the performance of various fuzzy models on temperature, solar radiation, and wind speed forecasting. The models studied were taken from the fuzzy systems literature, varying from well-established to the most recent methods. Four cases were considered: a Wang–Mendel (WM)-based fuzzy predictive model, an adaptive network fuzzy inference system (ANFIS), a fuzzy system ensemble, and patch learning (PL). The prediction systems were built from input/output data without any prior information, in a model-free approach. The ability of the models to display high performance on complex real datasets, provided by the National Observatory of Athens, was demonstrated through numerical studies. Patch learning managed to not only display a similar approximation ability to that of strong machine learning models, such as support vector machines and Gaussian processes, but also outperform them on the highly demanding problem of wind speed prediction. More accurately, as far as wind speed prediction is concerned, patch learning produced a 0.9211 root mean squared error for the training data and a value of 0.9841 for the testing data. The support vector machine provided a 0.9306 training root mean squared error and a 0.9891 testing value. The Gaussian process model resulted in a 0.9343 root mean squared error for the training data and a value of 0.9861 for the testing data. Finally, as shown by the numerical experiments, the fuzzy system ensemble exhibited the highest generalisation performance among all the intelligent models.

Short–term global solar radiation forecasting based on an improved method for sunshine duration prediction and public weather forecasts

Accurate forecasting of daily global solar radiation (Rs) is important for photovoltaic power and other sectors. Numerical models coupled with public weather forecasts information is a feasible method to predict short–term daily Rs. Here, we propose a novel sunshine duration converting method (n_new) based on forecasted air temperature and weather types data, which we validated using measurements from 86 radiation stations. A widely-used, generalized sunshine–based Rs model (Rs_n) was then coupled with the n_new method (Rs_n new) for forecasting daily Rs. This was further compared to Rs_n incorporated with the common sunshine duration converting method (n_com) using only weather types data (Rs_n com) and a recently developed generalized temperature–based model (Rs_T). The results indicated that the n_new method produced better estimates than the n_com method, as indicated by increased mean correlation coefficient (R; 13.0%–24.5%) and index of agreement (dIA; 2.9%–9.5%) and decreased mean root mean squared error (RMSE; 12.8%–14.8%) for the 1–7 days lead time over 86 sites. The Rs_n new model improved the accuracy for 98% of sites when compared to the Rs_n com model, with mean values of R and dIA increasing by 7.7%–11.0% and 2.1%–4.8% and that of RMSE decreasing by 9.7%–12.5% for the 1–7 days lead time. The results suggest that the Rs_n new model is advantageous in short–term forecasts. The Rs_n new model ranked first for 52.3%–74.4% of sites for the 1–7 days lead time, followed by the Rs_T model (25.6%–47.7%). Moreover, there was generally a better performance for the Rs_n new model to forecast daily Rs at a longer lead time. Therefore, the Rs_n new model using weather forecasts information is highly recommended to forecast short–term daily Rs.

Forecasting day-ahead 1-minute irradiance variability from numerical weather predictions

Accurate forecasts of solar irradiance are required for the large-scale integration of solar photovoltaic (PV) systems. Fluctuations of energy generation in the order of minutes can lead to issues on the electricity grid, therefore reliable forecasts of minute-to-minute irradiance variability are required. However, state of the art numerical weather predictions (NWP) deliver forecasts at a much coarser temporal resolution, e.g. hourly, missing crucial information on meteorological variability such as clouds. In this work we present a methodology to forecast minute-to-minute irradiance variability in terms of its probability density function (PDF) based on hourly NWP results, by applying statistical postprocessing using machine learning. The algorithm is tested using the 2.5 × 2.5 km2 HARMONIE-AROME (HA) mesoscale model as input, with 1-minute irradiance observations for 18 meteorological stations throughout the Netherlands used as a ground truth. The applicability of the algorithm to 31 × 31 km2 global-scale models is investigated using ERA5 reanalysis data, which yields comparable accuracies. We find that almost half of the inaccuracy of the postprocessed result is due to errors in the radiation forecast of the NWP model used as input. Finally, the proposed post-processing algorithm is compared to the next generation weather models based on high resolution Large Eddy Simulation (LES), at 75 m horizontal grid spacing, on a case study spanning four days. While LES underestimates values of high irradiance due to lack of 3D radiative effects, it enables detailed analysis of cloud and irradiance dynamics at high spatial and temporal resolution unreachable by statistical postprocessing.

The Role of Weather Predictions in Electricity Price Forecasting Beyond the Day-Ahead Horizon

Forecasts of meteorology-driven factors, such as intermittent renewable generation, are commonly included in electricity price forecasting models. We show that meteorological forecasts can be used directly to improve price forecasts multiple days in advance. We introduce an autoregressive multivariate linear model with exogenous variables and LASSO for variable selection and regularization. We used variants of this model to forecast German wholesale prices up to ten days in advance and evaluate the benefit of adding meteorological forecasts, namely wind speed and direction, solar irradiation, cloud cover, and temperature forecasts of selected locations across Europe. The resulting regression coefficients are analyzed with regard to their spatial as well as temporal distribution and are put in context with underlying power market fundamentals. Wind speed in northern Germany emerges as a particularly strong explanatory variable. The benefit of adding meteorological forecasts strongest when autoregressive effects are weak, yet the accuracy of the meteorological forecasts is sufficient for the model to identify patterns. Forecasts produced 2-4 days in advance exhibit an improvement in RMSE by 10-20%. Furthermore, the forecasting horizon is shown to impact the choice of the regularization penalty that tends to increase at longer forecasting horizons.