Irradiance Forecasting Research Articles

Spatio-Temporal Deep Learning-Based Forecasting of Surface Solar Irradiance: Leveraging Satellite Data and Feature Selection

Spatio-Temporal Deep Learning-Based Forecasting of Surface Solar Irradiance: Leveraging Satellite Data and Feature Selection

Evaluation of the WRF-solar model for 72-hour ahead forecasts of global horizontal irradiance in West Africa: A case study for Ghana

Accurate global horizontal irradiance (GHI) forecasting is critical for integrating solar energy into the power grid and operating solar power plants. The Weather Research and Forecasting model with its solar radiation extension (WRF-Solar) has been used to forecast solar irradiance in different regions around the world. However, the application of the WRF-Solar model to the prediction of GHI in West Africa, particularly Ghana, has not yet been investigated. The aim of this study is to evaluate the performance of the WRF-Solar model for predicting GHI in Ghana, focusing on three automatic weather stations (Akwatia, Kumasi and Kologo) for the year 2021. We used two one-way nested domains (D1 = 15 km and D2 = 3 km) to investigate the ability of the fully coupled WRF-Solar model to forecast GHI up to 72-hour ahead under different atmospheric conditions. The initial and lateral boundary conditions were taken from the ECMWF high-resolution operational forecasts. Our findings reveal that the WRF-Solar model performs better under clear skies than cloudy skies. Under clear skies, Kologo performed best in predicting 72-hour GHI, with a first day nRMSE of 9.62 %. However, forecasting GHI under cloudy skies at all three sites had significant uncertainties. Additionally, WRF-Solar model is able to reproduce the observed GHI diurnal cycle under high AOD conditions in most of the selected days. This study enhances the understanding of the WRF-Solar model’s capabilities and limitations for GHI forecasting in West Africa, particularly in Ghana. The findings provide valuable information for stakeholders involved in solar energy generation and grid integration towards optimized management in the region.

Machine Learning-Based Forecasting of Temperature and Solar Irradiance for Photovoltaic Systems

The integration of photovoltaic (PV) systems into the global energy landscape has been boosted in recent years, driven by environmental concerns and research into renewable energy sources. The accurate prediction of temperature and solar irradiance is essential for optimizing the performance and grid integration of PV systems. Machine learning (ML) has become an effective tool for improving the accuracy of these predictions. This comprehensive review explores the pioneer techniques and methodologies employed in the field of ML-based forecasting of temperature and solar irradiance for PV systems. This article presents a comparative study between various algorithms and techniques commonly used for temperature and solar radiation forecasting. These include regression models such as decision trees, random forest, XGBoost, and support vector machines (SVM). The beginning of this article highlights the importance of accurate weather forecasts for the operation of PV systems and the challenges associated with traditional meteorological models. Next, fundamental concepts of machine learning are explored, highlighting the benefits of improved accuracy in estimating the PV power generation for grid integration.

Solar radiation forecasting using gradient boosting based ensemble learning model for various climatic zones

India is seeing a massive boost in solar power installations in the recent years. It is expected that solar energy utilization will be increasing exponentially in near future. Solar radiation forecasting is an essential tool to obtain the optimal performance out of the solar systems. An ensemble model using gradient boosting has been developed for hourly global horizontal irradiance forecasting is proposed for the various climatic zones of India. The gradient boost-based model is benchmarked with Auto Regressive Integrated Moving Average (ARIMA),2-layer feed forward neural network, and Long Short-Term Memory (LSTM). Gradient boosting obtained with marginally better performance metrics, mean absolute error (20.97 W/m2) and mean square error (1357 W2/m4) as compared to that of the neural network (21.66 W/m2, 1479.53 W2/m4) and performed much better than ARIMA and LSTM in terms of mean absolute error (251.66 W/m2) & mean square error (82,290 W2/m4) and mean absolute error (67.60 W/m2) & mean square error (8123 W2/m4). The diverse climatic zones in India and feature importance analysis have been considered during the model development and testing phase. The proposed model is also intended to have practical implications in obtaining solar irradiance data in locations with minimal availability of solar radiation data and solar power systems due to the model ability to provide good performance metrics in a smaller timeframe making it an ideal candidate for real-time solar power predicting model.

Evaluation of surface shortwave downward radiation forecasts by the numerical weather prediction model AROME

Abstract. With the worldwide development of the solar energy sector, the need for reliable surface shortwave downward radiation (SWD) forecasts has significantly increased in recent years. SWD forecasts of a few hours to a few days based on numerical weather prediction (NWP) models are essential to facilitate the incorporation of solar energy into the electric grid and ensure network stability. However, SWD errors in NWP models can be substantial. In order to characterize the performances of AROME in detail, the operational NWP model of the French weather service Météo-France, a full year of hourly AROME forecasts is compared to corresponding in situ SWD measurements from 168 high-quality pyranometers covering France. In addition, to classify cloud scenes at high temporal frequency and over the whole territory, cloud products derived from the Satellite Application Facility for Nowcasting and Very Short Range Forecasting (SAF NWC) from geostationary satellites are also used. The 2020 mean bias is positive, with a value of 18 W m−2, meaning that AROME on average overestimates the SWD. The root-mean-square error is 98 W m−2. The situations that contribute the most to the bias correspond to cloudy skies in the model and in the observations, situations that are very frequent (66 %) and characterized by an annual bias of 24 W m−2. Part of this positive bias probably comes from an underestimation of cloud fraction in AROME, although this is not fully addressed in this study due to the lack of consistent observations at kilometer resolution. The other situations have less impact on SWD errors. Missed cloudy situations and erroneously predicted clouds, which generally correspond to clouds with a low impact on the SWD, also have low occurrence (4 % and 11 %). Likewise, well-predicted clear-sky conditions are characterized by a low bias (3 W m−2). When limited to overcast situations in the model, the bias in cloudy skies is small (1 W m−2) but results from large compensating errors. Indeed, further investigation shows that high clouds are systematically associated with a SWD positive bias, while low clouds are associated with a negative bias. This detailed analysis shows that the errors result from a combination of incorrect cloud optical properties and cloud fraction errors, highlighting the need for a more detailed evaluation of cloud properties. This study also provides valuable insights into the potential improvement of AROME physical parametrizations.

An Analysis of the Effects of Clouds in High-Resolution Forecasting of Surface Shortwave Radiation in South Africa

Abstract We assess site-specific surface shortwave radiation forecasts from two high-resolution configurations of the South African Weather Service numerical weather prediction model, at 4 and 1.5 km. The models exhibit good skill overall in forecasting surface shortwave radiation, with zero median error for all radiation components. This information is relevant to support a growing renewable energy sector in South Africa, particularly for photovoltaics. Further model performance analysis has shown an imbalance between cloud and solar radiation forecasting errors. In addition, cloud overprediction does not necessarily equate to underestimating solar radiation. Overcast cloud regimes are predicted too often with an associated positive mean radiation bias, whereas the relative abundance of partly cloudy regimes is underpredicted by the models with mixed radiation biases. Challenges highlighted by the misrepresentation of partly cloudy regimes in solar radiation error attribution may be used to inform improvements to the numerical core, namely, the cloud and radiation schemes. Significance Statement This paper provides the first comprehensive assessment of high-resolution site-specific NWP forecasts of surface shortwave radiation in South Africa, exploring clouds as the main drivers of prediction biases. Error attribution analyses of this kind are close to none for this part of the world. Our study contributes to understanding how cloud and radiation schemes perform over South Africa, representing a step forward in the state of the art. In addition to the scientific interest, the capabilities developed through this work may benefit the second largest economy of the continent. In a country where energy security is of critical relevance, the availability of useful and usable weather information is paramount to support its industry and socioeconomic growth.

An innovative machine learning based on feed-forward artificial neural network and equilibrium optimization for predicting solar irradiance

As is known, having a reliable analysis of energy sources is an important task toward sustainable development. Solar energy is one of the most advantageous types of renewable energy. Compared to fossil fuels, it is cleaner, freely available, and can be directly exploited for electricity. Therefore, this study is concerned with suggesting novel hybrid models for improving the forecast of Solar Irradiance (IS). First, a predictive model, namely Feed-Forward Artificial Neural Network (FFANN) forms the non-linear contribution between the IS and dominant meteorological and temporal parameters (including humidity, temperature, pressure, cloud coverage, speed and direction of wind, month, day, and hour). Then, this framework is optimized using several metaheuristic algorithms to create hybrid models for predicting the IS. According to the accuracy assessments, metaheuristic algorithms attained satisfying training for the FFANN by using 80% of the data. Moreover, applying the trained models to the remaining 20% proved their high proficiency in forecasting the IS in unseen environmental circumstances. A comparison among the optimizers revealed that Equilibrium Optimization (EO) could achieve a higher accuracy than Wind-Driven Optimization (WDO), Optics Inspired Optimization (OIO), and Social Spider Algorithm (SOSA). In another phase of this study, Principal Component Analysis (PCA) is applied to identify the most contributive meteorological and temporal factors. The PCA results can be used to optimize the problem dimension, as well as to suggest effective real-world measures for improving solar energy production. Lastly, the EO-based solution is yielded in the form of an explicit formula for a more convenient estimation of the IS.

Daily Global Solar Radiation estimation for Gran Canaria Island using Artificial Neural Networks

Forecasting of global solar radiation is an important tool for power systems planning and operation, especially in island grids. The aim of this paper is the analysis of an artificial neural network as a reliable method to obtain a daily forecast for solar radiation. Some different tests are proposed to obtain the optimal ANN that will capture the underlying physical process that generates the data. In the present study, the available data come from seven measuring stations throughout the Gran Canaria Island along six years. ANN was trained and tested only with past ground measurement solar radiation and other meteorological data available at measurement stations as inputs.

Enhancing Solar Radiation Forecasting in Diverse Moroccan Climate Zones: A Comparative Study of Machine Learning Models with Sugeno Integral Aggregation

Hourly solar radiation (SR) forecasting is a vital stage in the efficient deployment of solar energy management systems. Single and hybrid machine learning (ML) models have been predominantly applied for precise hourly SR predictions based on the pattern recognition of historical heterogeneous weather data. However, the integration of ML models has not been fully investigated in terms of overcoming irregularities in weather data that may degrade the forecasting accuracy. This study investigated a strategy that highlights interactions that may exist between aggregated prediction values. In the first investigation stage, a comparative analysis was conducted utilizing three different ML models including support vector machine (SVM) regression, long short-term memory (LSTM), and multilayer artificial neural networks (MLANN) to provide insights into their relative strengths and weaknesses for SR forecasting. The comparison showed the proposed LSTM model had the greatest contribution to the overall prediction of six different SR profiles from numerous sites in Morocco. To validate the stability of the proposed LSTM, Taylor diagrams, violin plots, and Kruskal–Wallis (KW) tests were also utilized to determine the robustness of the model’s performance. Secondly, the analysis found coupling the models outputs with aggregation techniques can significantly improve the forecasting accuracy. Accordingly, a novel aggerated model that integrates the forecasting outputs of LSTM, SVM, MLANN with Sugeno λ-measure and Sugeno integral named (SLSM) was proposed. The proposed SLSM provides spatially and temporary interactions of information that are characterized by uncertainty, emphasizing the importance of the aggregation function in mitigating irregularities associated with SR data and achieving an hourly time scale forecasting accuracy with improvement of 11.7 W/m2.

Short-Term Solar Irradiance Prediction with a Hybrid Ensemble Model Using EUMETSAT Satellite Images

Accurate short-term solar irradiance forecasting is crucial for the efficient operation of solar energy-driven photovoltaic (PV) power plants. In this research, we introduce a novel hybrid ensemble forecasting model that amalgamates the strengths of machine learning tree-based models and deep learning neuron-based models. The hybrid ensemble model integrates the interpretability of tree-based models with the capacity of neuron-based models to capture complex temporal dependencies within solar irradiance data. Furthermore, stacking and voting ensemble strategies are employed to harness the collective strengths of these models, significantly enhancing the prediction accuracy. This integrated methodology is enhanced by incorporating pixels from satellite images provided by the European Organization for the Exploitation of Meteorological Satellites (EUMETSAT). These pixels are converted into structured data arrays and employed as exogenous inputs in the algorithm. The primary objective of this study is to improve the accuracy of short-term solar irradiance predictions, spanning a forecast horizon up to 6 h ahead. The incorporation of EUMETSAT satellite image pixel data enables the model to extract valuable spatial and temporal information, thus enhancing the overall forecasting precision. This research also includes a detailed analysis of the derivation of the GHI using satellite images. The study was carried out and the models tested across three distinct locations in Austria. A detailed comparative analysis was carried out for traditional satellite (SAT) and numerical weather prediction (NWP) models with hybrid models. Our findings demonstrate a higher skill score for all of the approaches compared to a smart persistent model and consistently highlight the superiority of the hybrid ensemble model for a short-term prediction window of 1 to 6 h. This research underscores the potential for enhanced accuracy of the hybrid approach to advance short-term solar irradiance forecasting, emphasizing its effectiveness at understanding the intricate interplay of the meteorological variables affecting solar energy generation worldwide. The results of this investigation carry noteworthy implications for advancing solar energy systems, thereby supporting the sustainable integration of renewable energy sources into the electrical grid.

An interpretable horizontal federated deep learning approach to improve short-term solar irradiance forecasting

Solar irradiance forecasting is critical in the planning and operation of solar power plants for production scheduling, energy trading, and maintenance planning. Accurate solar irradiance forecasting is crucial for efficient and stable power systems. Various deep learning (DL) methods have been researched in solar irradiance forecasting because of their powerful capabilities of nonlinear mapping. However, traditional DL models face challenges with small sample sizes, irradiance fluctuations, and data privacy concerns. On this foundation, it is also critical to ensure the interpretability of artificial intelligence (AI) models, as interpretable and trustworthy predictive models can help operators make effective decisions. Focusing on the above-mentioned issues, a privacy-preserving, interpretable, and DL-based model is proposed to improve the forecast accuracy of solar irradiance while ensuring the data available but not visible to each participant and prediction comprehensibility. This model is constructed by horizontal federated framework (HFF), self-attention (SA) mechanism, convolutional neural network (CNN), and long short-term memory (LSTM) network, named HFF-based SA-CNN-LSTM. A series of comprehensive experiments spanning various climate regions are designed to assess model performance under different federated conditions. The experiments show that this method significantly improves forecasting accuracy, especially in scenarios with incomplete data and highly fluctuating irradiance when federated with other datasets, and the model exhibits interpretability, adjusting attention for precise predictions at different time points. Moreover, the effects of different federated scales on the predictive performance of the target model are fully discussed for future practical applications. These findings hold significant promise for enhancing the accuracy of irradiance forecasting, contributing to energy efficiency, grid stability, and data privacy.

Neuromorphic Computing-Based Model for Short-Term Forecasting of Global Horizontal Irradiance in Saudi Arabia

Neuromorphic Computing-Based Model for Short-Term Forecasting of Global Horizontal Irradiance in Saudi Arabia

Advancing solar energy forecasting with modified ANN and light GBM learning algorithms

<abstract> <p>In the evolving field of solar energy, precise forecasting of Solar Irradiance (SI) stands as a pivotal challenge for the optimization of photovoltaic (PV) systems. Addressing the inadequacies in current forecasting techniques, we introduced advanced machine learning models, namely the Rectified Linear Unit Activation with Adaptive Moment Estimation Neural Network (RELAD-ANN) and the Linear Support Vector Machine with Individual Parameter Features (LSIPF). These models broke new ground by striking an unprecedented balance between computational efficiency and predictive accuracy, specifically engineered to overcome common pitfalls such as overfitting and data inconsistency. The RELAD-ANN model, with its multi-layer architecture, sets a new standard in detecting the nuanced dynamics between SI and meteorological variables. By integrating sophisticated regression methods like Support Vector Regression (SVR) and Lightweight Gradient Boosting Machines (Light GBM), our results illuminated the intricate relationship between SI and its influencing factors, marking a novel contribution to the domain of solar energy forecasting. With an R<sup>2</sup> of 0.935, MAE of 8.20, and MAPE of 3.48%, the model outshone other models, signifying its potential for accurate and reliable SI forecasting, when compared with existing models like Multi-Layer Perceptron, Long Short-Term Memory (LSTM), Multilayer-LSTM, Gated Recurrent Unit, and 1-dimensional Convolutional Neural Network, while the LSIPF model showed limitations in its predictive ability. Light GBM emerged as a robust approach in evaluating environmental influences on SI, outperforming the SVR model. Our findings contributed significantly to the optimization of solar energy systems and could be applied globally, offering a promising direction for renewable energy management and real-time forecasting.</p> </abstract>

Very short-term probabilistic and scenario-based forecasting of solar irradiance using Markov-chain mixture distribution modeling

This study investigates probabilistic and scenario-based forecasting of solar irradiance with Markov-chain mixture (MCM) distribution modeling, Persistence Ensemble (PeEn) and Climatology. Forecasts from MCM models with uniform and empirical emission distribution settings, respectively, are compared with PeEn and Climatology in terms of probabilistic forecasting performance. The MCM model is also extended with scenario generation capabilities and compared to scenario generation of the Climatology by means of Monte Carlo sampling. Forecasts were made on minute resolution normalized solar irradiance, i.e. the clear-sky index, from National Renewable Energy Laboratory and Swedish Meteorological and Hydrological Institute for two climatic regions: Oahu, Hawaii, USA and Norrköping, Sweden, respectively. Results show that the MCM models are neither necessarily the most reliable, nor the sharpest in terms of Prediction Normalized Average Width (PINAW), but they are the most accurate in terms of Continuous Ranked Probability Score (CRPS). MCM models with uniform and empirical emission distribution settings perform similar in the tested probabilistic forecasting metrics. In terms of scenario forecasting, MCM models with N=30 perform similar in probability distribution goodness-of-fit and autocorrelation Mean Absolute Error (MAE) and superior to N=2 and N=10 number of states. Mathematically, forecasts from the MCM model with empirical distribution setting are shown to correspond to PeEn and Climatology forecasts given special settings of the MCM model. Based on the conclusions, the suggestion is to use the MCM scenario forecast generator with uniform emission distribution setting as benchmark for scenario forecasts of very short-term solar irradiance.

Application of nowcasting to reduce the impact of irradiance ramps on PV power plants

Short-term fluctuations in photovoltaic power plants, known as ramps and caused by clouds, challenge grid stability and efficient energy use. These issues are traditionally managed with battery energy storage systems, which, while effective, are expensive. We propose an alternative solution: the use of short-term irradiance forecasts, or nowcasts. Using a photovoltaic power plant in Germany and its simulated model, we demonstrated that nowcasts could cut ramp rate violations by 81%. This led to a reduction in required battery capacity by 71% and the required maximum battery power provided by 48%, at the cost of a 13% curtailment loss, i.e. loss through reduction of power. Our data set of 18 chosen days from 2020 with high variability conditions was scaled up to a year for the economic analysis. From an economic standpoint, nowcasts could lower the Levelized Cost of Electricity by 5.5% from 4.74 to 4.48 EUR cents, and even by 35% to 3.09 EUR cents with ideal forecasting, showing its potential. While nowcasts cannot completely replace batteries, they substantially reduce the need for such storage solutions. This results in cost savings and adherence to grid stability requirements, making nowcasts a complement or partial alternative to battery systems for mitigating power fluctuations in photovoltaic power plants.

Holistic and Lightweight Approach for Solar Irradiance Forecasting

Holistic and Lightweight Approach for Solar Irradiance Forecasting

Solar Irradiance Forecasting using Improved Sample Convolution and Interactive learning

Renewable energy sources, driven by the global concern for climate change and the urgent need to reduce greenhouse gas emissions, are gaining increasing importance. Among them, solar energy stands out as a crucial renewable source and accurate solar irradiance forecasting is vital for its effective utilisation. Deep learning (DL) techniques have emerged as state-of-the-art solar irradiance forecasting methods in past years. However, traditional models that are widely used have inferior accuracy in forecasting. To bridge this gap, this paper presents an improved state-of-the-art model that leverages the convolutional property to forecast the time series data. We got a reduction of 8.32% in MAE compared to the base model. The paper's findings highlight the potential of DL-based approaches to significantly improve the accuracy of solar irradiance forecasts.

Integration of the radial basis functional network and sliding mode control for the sunshine radiation forecast

<abstract> <p>In this paper, we propose a forecasting system of sunshine radiation for planners to quickly and accurately predict the output of solar power. The field data, including observation time, temperature, relational humidity, wind speed and global radiation, were collected, and the data clusters were embedded in the Excel Database. To improve the computational performance, the data selection technique was used in the stage of data cleaning, data integration and data reduction. Using the Integration of the Radial Basis Function Network (RBFN) and Sliding Mode Control (SMC), a Sliding Mode Radial Basis Function Network (SMRBFN) was proposed to solve this forecasting problem. Since the Sliding Mode Control has the design's sense of optimal parameters, three parameters in the SMRBFN were dynamically adjusted to promote the accurate and reliability of forecasting system. Linking the SMRBFN and Excel database, the learning stage and testing stage of SMRBFN retrieved the input data from Excel Database to perform and analyze the forecasting system. The proposed algorithm was tested on Kaohsiung district in summer and winter. The average prediction error of MAPE and RMSE obtained from the forecasting results are about 9% and 0.223, respectively. It can be proved that SMRBFN can efficiently forecast the sunshine radiation and accurately provide the output of solar power in an uncertainty environment.</p> </abstract>

The Application of Deep Learning Methods in the Forecasting and Imputation of Solar Irradiance Data

Accurate solar radiation forecasts are necessary for solar power plants and local energy grids. Precise solar predictions can optimise plant operations and assist in managing power generation fluctuations. High-quality solar data are required to perform solar forecasting and may be accessed through open databases such as the Baseline Surface Radiation Network. Due to maintenance and malfunctioning equipment, these databases may have missing data. Deep learning methods can extract relevant features and non-linearities in data, which make them suitable for forecasting and imputation tasks. The development of the transformer architecture in 2017 marked an improvement from recurrent sequence processing using RNN (recurrent neural net) architectures to parallel sequence handling using self-attention mechanisms. Previous deep learning irradiance forecasting models utilised a RNN or RNN extension architecture. This paper presents novel applications of Transformer models to solar imputation and forecasting. Two deep learning architectures – Transformer and SAITS (Self-Attention-based Imputation for Time Series) – were trained to impute time series of global horizontal irradiance. Additionally, a Temporal Fusion Transformer (TFT) deep learning architecture was trained to forecast future values of global horizontal irradiance time series. Feature concatenation allows for the combination of differing exogenous variables into a single input vector for a deep learning solar forecasting model. Previous solar forecasting models do not incorporate cloud data or otherwise utilise an exogenous simple categorical mask to indicate cloud cover. In this paper, GOES-16 cloud optical depth and particle size datasets provide an improved representation of cloud properties. Classical imputation and forecasting models were also developed and used as baselines for comparison with deep learning models. The models were evaluated using standard statistical metrics for time series. It was found that the deep learning TFT forecasting model produced better forecasts than the classical regression model. However, the classical KNN imputer performed better than the two deep learning imputation models.

Evaluation and performance comparison of different models for global solar radiation forecasting: a case study on five cities

AbstractRecently, solar energy has emerged as the most promising renewable energy source to meet the world’s energy demands. However, to harness the potential of solar energy, accurate data on solar radiation are crucial. It is considered the first step in assessing solar resources for various applications and achieving energy sustainability goals. Due to the unavailability of solar radiation measurements in many parts of the world, several models have been developed to predict global solar radiation (GSR) at these locations. Thus, this study aims to evaluate the proficiency of several GSR models at five new locations and determine the most suitable one for GSR prediction. The study has further developed solar radiation models for these new locations, as well as general ones for the entire region, which does not have any GSR models despite the existence of many planned solar energy facilities in this area. Additionally, the study investigates the effect of changing the length of the validation dataset on models’ performance and accuracy, as well as assesses the introduced models’ generalization capability. To achieve these objectives, the observed data of GSR for approximately 37 years at studied locations are used to develop and validate the proposed models. The study’s findings reveal that Model 1 provides the best performance at all locations, with accuracy, coefficient of determination ($$R^{2}$$ R 2 ), ranging from 95 to 98%, except for the coastal location, where it is from 91 to 95%. The remaining performance indicators of the best models, such as RMSE, MABE, MAPE, and $$r$$ r , are good, and their values range from 0.7863 to 1.9097 (MJ m−2 day−1), from 0.6430 to 1.7060 (MJ m−2 day−1), from 3.4319 to 10.0890 (%), and from 0.9914 to 0.9981, respectively. The length of the validation dataset has a slight effect on the models’ performance, ranging from about 1% to 2%. Therefore, Model 1 is the recommended solar radiation model, which can provide precise and rapid estimates of global solar radiation. This approach could be used in the design and performance evaluation of many solar applications. The primary benefit of this approach in the current investigation is that temperature data are continuously and effortlessly recorded for various purposes.