Search Results (148)

Freely accessible weather APIs are an attractive input for photovoltaic (PV) power prediction, yet how their reference-based error carries through—under temporal aggregation—into day-ahead PV energy is rarely quantified before model development. This study audits eight freely accessible weather-data services—seven forecast services and the Meteostat observational archive—and finds that, for the endpoints, subscription tiers, and collection period evaluated here, only two of the forecast services expose hourly global horizontal irradiance (GHI), while a third advertised irradiance field returns empty—itself a material result for municipal integrators. The two irradiance-capable services are propagated through a common physical PV model of the 548 kWp east–west rooftop plant being built on a university campus in Bratislava, Slovakia, against independent references (CAMS irradiance; NASA POWER temperature and wind). Throughout, “error” denotes discrepancy against the reference, not measurement truth. Over a common 62-day spring–summer window, the day-ahead daily-energy mean absolute error (MAE, relative to mean reference daily energy) is 10–11% for both sources; Open-Meteo’s winter-inclusive own window raises its value to about 13%. On the matched window, Open-Meteo has the lower hourly GHI RMSE (121 vs. 128 W·m⁻²), yet this advantage does not carry through to day-ahead energy—the point-estimate ordering even changes—and neither matched-window difference is statistically resolved. Because daily aggregation rewards low bias over low scatter, this ordering change is already present in daily GHI energy—before the PV conversion—so hourly irradiance accuracy alone does not determine day-ahead energy. Propagated input-data auditing is therefore an advisable step before ML-based PV forecasting and day-ahead scheduling of urban distributed PV. Full article

Renewable energy technologies are increasingly recognized as essential solutions for mitigating energy insecurity and supporting sustainable development. Among solar thermal systems, parabolic trough collectors (PTCs) have attracted significant attention for medium-temperature heat generation due to their high optical concentration ratio and thermal conversion efficiency. However, the deployment of small-scale PTC systems in rural and resource-constrained regions remains limited due to high manufacturing costs, inadequate local designs, and insufficient experimental data on performance under African climatic conditions. This study presents the novel design, fabrication, and experimental evaluation of a low-cost small-scale PTC prototype specifically developed for the climatic conditions of Alice, South Africa. Unlike conventional systems primarily optimized for large-scale industrial applications, the proposed prototype integrates locally adaptable design parameters, including a 90° rim angle and a compact aperture width of 1.072 m, to enhance thermal performance while reducing fabrication complexity and material costs. The thermal performance of the system was experimentally evaluated using a CR1000 data acquisition system to continuously monitor solar irradiance, inlet and outlet fluid temperatures, ambient temperature, and wind conditions under real outdoor operating environments. The prototype achieved a peak thermal efficiency of 35% under a maximum global horizontal irradiance (GHI) of 470 W/m², demonstrating the technical feasibility of decentralized solar thermal energy systems for small-scale applications. The study further provides a detailed assessment of the influence of meteorological parameters on collector performance, revealing that solar irradiance is the dominant factor governing thermal output. In contrast, wind-induced convective heat losses substantially reduce system efficiency. The novelty of this work lies in the experimental validation of a cost-effective PTC design under South African climatic conditions, along with the identification of practical performance-enhancement strategies, including selective absorber coatings and improved thermal insulation, for small-scale solar thermal applications. Full article

Accurate photovoltaic (PV) power forecasting is essential for reliable microgrid operation, efficient energy dispatch, and improved utilization of renewable energy resources. Existing forecasting methods often have limited capacity to represent the nonlinear relationships between meteorological conditions and PV power output. They also tend to underrepresent the temporal dynamics of PV generation and the physical principles governing photovoltaic energy conversion. To address these limitations, this study proposes a hybrid forecasting framework, CNN-LSTM-PINNs, that integrates Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and Physics-Informed Neural Networks (PINNs). In the proposed framework, CNNs extract spatial dependencies among multivariate meteorological variables, LSTM networks capture temporal dependencies in PV generation, and PINNs incorporate soft physical constraints derived from photovoltaic energy conversion mechanisms. The proposed model is evaluated using publicly available datasets from three large-scale PV power stations in China, with observations recorded at 15-min intervals. The empirical results show that CNN-LSTM-PINNs outperform the conventional CNN-LSTM benchmark across the primary station-level datasets. Relative to the benchmark model, the proposed framework reduces Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) and improves the coefficient of determination (R²). These results indicate that embedding physical constraints into data-driven forecasting models can improve PV power prediction accuracy. The model also shows stronger robustness and generalization performance under heterogeneous operating conditions, although its effectiveness is contingent on relatively stable data distributions. Feature-importance analysis further indicates that global horizontal irradiance (GHI) and irradiance-derived variables are the most informative predictors of PV power output. Overall, this study provides a physics-informed hybrid modeling approach for high-resolution PV power forecasting in microgrid applications. Full article

Accurate and spatially representative estimation of Global Horizontal Irradiance (GHI) is critical for solar energy planning in tropical regions characterized by strong atmospheric variability and complex topography. This study aims to evaluate the performance and robustness of four semi-empirical satellite-derived GHI models, Beyer, Perez, Hammer, and Rigollier, under heterogeneous tropical conditions in West Java, Indonesia. Hourly GHI data for 2022 were derived from GK2A satellite observations and validated against ground measurements from eight stations representing coastal, lowland, and mountainous areas. Model performance was assessed at annual and seasonal scales using relative Root Mean Square Error (rRMSE) and relative Mean Bias Error (rMBE). The results show significant variability in model performance across locations, with the average annual rRMSE computed per model and averaged over the eight stations being similar among models: 41.10% (Perez), 41.18% (Beyer), 42.44% (Hammer), and 42.49% (Rigollier). Perez showed the most consistent performance, with station-level rRMSE values ranging from 35.36% to 43.32% and rMBE ranging from −18.20% to 22.09%. Seasonal analysis indicates higher errors during the rainy season, 41.16% (Perez), 45.23% (Beyer), 42.74% (Hammer), and 46.34% (Rigollier), while lower errors were observed during the dry season, particularly for Beyer (36.16%) and Rigollier (36.29%). Spatial analysis indicates higher irradiance in coastal and lowland areas compared to mountainous regions. These findings emphasize the importance of climate- and topography-aware model selection for reliable solar resource assessment in tropical environments. Full article

Integrating solar power into electricity grids requires accurate short-term forecasting of the global horizontal irradiance to accurately predict the expected solar power generation. This paper compares five tree-based machine learning models against a Persistence baseline for multi-resolution forecasting in arid climates. A 13-year dataset from Basra, Iraq, has been employed in this study for verification purposes, and the models are tested across various very-short- to short-term forecasting horizons of 5, 10, 15, 30, and 60 min. Unlike most existing studies that focus on single forecasting horizons or mixed climatic conditions, this work systematically benchmarks multi-resolution irradiance forecasting under distinct sky conditions in a hot arid environment using a strict anti-data-leakage framework. To avoid data leakage in these models, feature engineering has used only lagged inputs. The dataset has been split into three groups for training, validation, and testing (respectively 70, 15, and 15% of the entire available dataset). The models were then tested separately under clear, partly cloudy, and cloudy skies. Numerical studies prove that picking the best model depends heavily on the forecast horizon. For very-short-term predictions, the Persistence model was competitive (RMSE = 21.32 W/m²), while the Gradient Boosting model proved slightly more accurate (RMSE = 17.65 W/m²). For the 60 min horizon, the boosting models took a clear lead. The HistGradientBoosting model resulted in a 67% reduction in the RMSE compared to the Persistence baseline. Also, the top-performing model changed depending on the weather and the time scale. Gradient Boosting was the clear winner for short-term clear sky forecasts, while XGBoost handled the longer horizons. Partly cloudy skies showed a rotating mix of different boosting algorithms taking the lead. However, studies show that when skies were fully overcast, complex machine learning models fail to capture chaotic patterns, making the simple Persistence baseline a necessary reliability safeguard. The results reveal that no single model consistently dominates all forecasting horizons and weather conditions, highlighting the necessity of adaptive model selection for operational solar forecasting. These findings highlight the importance of horizon- and weather-adaptive model selection for operational solar forecasting. Rather than relying on a single universal algorithm, grid operators in arid regions can improve forecasting reliability by dynamically selecting models based on prevailing sky conditions and forecast horizons. Full article

Mountain photovoltaic (PV) stations are increasingly deployed in complex terrain, where generation is jointly controlled by solar-resource variability, near-surface meteorology, and local topography. However, the quantitative contribution of topographic factors to regional-scale PV generation remains insufficiently evaluated, and many prediction studies rely on single-station or short-term records. In this study, monthly measured generation from 118 standardized village-level mountain PV stations in Badong County, western Hubei Province, China (2019–2021), was integrated with Solargis Global Horizontal Irradiance (GHI)-related solar-resource data, high-resolution gridded meteorological data, a 25 m digital elevation model, seasonal-cycle variables, and historical-generation features. After seasonally grouped median-absolute-deviation (MAD) outlier screening, GIS-based spatial matching, terrain extraction, and viewshed-derived shading analysis, regression models and climatology baselines were compared under both chronological validation and station-exclusion spatial cross-validation. Under the strict chronological validation, CatBoost achieved the best temporal performance among the tested models (R² = 0.3119, MAE = 2719.7 kWh, RMSE = 3245.6 kWh), slightly outperforming the monthly climatology baseline. In the station-exclusion spatial cross-validation, XGBoost achieved the highest mean R² (0.8659), indicating good spatial transferability to unseen stations. Correlation and partial-correlation analyses showed that the temperature-related variable group and monthly radiation were the dominant meteorological controls, whereas elevation, slope, and terrain shading showed weak direct correlations with monthly generation for already-sited stations. Annual 90% prediction intervals were further estimated using residual bootstrapping, with an empirical coverage of 94.9%. The proposed framework provides a practical basis for monthly generation forecasting and operational assessment of already-built distributed PV stations in mountainous regions, while its application to greenfield site selection requires additional site engineering and near-field obstruction information. Full article

The rapid transition toward renewable energy requires transparent and spatially explicit methods for identifying suitable photovoltaic (PV) development areas. This study develops a geospatial artificial intelligence (GeoAI) decision-support framework for PV site suitability assessment in Rajasthan, India. Eleven harmonized predictors were used: global horizontal irradiance (GHI), photovoltaic power output (PVOUT), temperature, wind speed, aerosol optical depth (AOD), elevation, slope, albedo, land use/land cover (LULC), distance to roads, and distance to power lines. Reference labels were generated from an explicit rule-derived suitability index, class thresholds, and exclusion logic; therefore, the machine-learning task was to reproduce a transparent suitability framework rather than to predict observed PV yield or project-level performance. Extreme Gradient Boosting (XGBoost) was compared with simpler baseline models, evaluated using random and spatial-block validation, and interpreted using SHapley Additive exPlanations (SHAP). Independent overlays with known solar-installation records, presence-background robustness testing, and uncertainty/sensitivity analysis were used to examine spatial plausibility, spatial autocorrelation, deterministic label effects, and parameter uncertainty. The resulting outputs include pixel-level suitability zones, contiguous candidate polygons, district-level capacity-oriented summaries, and planning-priority classes. The framework is intended as a risk-aware regional screening tool: high model agreement indicates consistency with the constructed suitability labels, while final project decisions require parcel-scale land, grid, environmental, social, and economic assessment. Full article

Accurate short-term estimation of clear-sky Global Horizontal Irradiance (GHI) is vital for solar resource assessment and grid operations, yet existing methods rely on sparse radiometers and coarse global weather reanalysis (e.g., MERRA-2 at 50–70 km spatial resolution with 1 month latency). To achieve scalability in high-precision estimation, we propose a framework that removes dependence on ground measurements by combining multi-satellite observations with reanalysis variables in a physics-supervised machine-learning paradigm. We developed a multi-source-fused high-resolution environmental dataset with 5 min granularity and 1 km spatial precision, incorporating Geostationary Operational Environmental Satellite (GOES-16) observations, polar-orbiting satellite (AURA) data, and MERRA-2 reanalysis. As supervisory physics, we harmonized two complementary parameterized radiative transfer models (MAC2 and REST2V5). The harmonized GHI estimates are used as training labels for a Multilayer Perceptron (MLP) and a Residual Long Short-Term Memory (LSTM) network model. The trained MLP model achieved a root mean square error (RMSE) of 66.67 $\mathrm{W}/{\mathrm{m}}^2$, representing a 7.50% reduction over the conventional MERRA-2-driven baseline. For 30-min-ahead forecasting, the LSTM model reduced RMSE by 29.37% over the persistence baseline. Evaluated at four climatically diverse U.S. sites, the system achieves ground-sensor-like accuracy and is deployable anywhere within GOES-16 coverage. Full article

Accurate day-ahead solar irradiance forecasting is essential for reliable photovoltaic (PV) power generation and power system operation. This study proposes a machine-learning-based approach for site-specific day-ahead forecasting of plane-of-array (POA) irradiance using satellite-derived global horizontal irradiance (GHI) and meteorological predictors. Seven machine learning and deep learning models are evaluated using time-series data to forecast day-ahead POA irradiance from satellite-derived GHI. Training and evaluation are performed within a rolling-window validation framework, while hyperparameters are optimized using grid search and automated tuning. As baseline references, satellite-derived GHI is directly used as a proxy for site POA irradiance and compared with measured values, while a day-ahead persistence model is introduced as a simple benchmark. The experimental setup is designed to reflect an operational forecasting setting while relying on idealized meteorological inputs to isolate the modeling capability and assess the maximum achievable accuracy of day-ahead POA irradiance forecasting, which can be interpreted as an upper-bound performance scenario. The results show that machine learning models reduce the RMSE from 154.45 W/m² to 75.5 W/m² on the validation set, corresponding to an improvement of approximately 51% relative to the persistence baseline. Additionally, the impact of changepoint detection on the training process is investigated to account for structural shifts in the time series, and the influence of irradiance forecasting accuracy on photovoltaic power generation is evaluated through comparative PV energy yield calculations. The findings indicate that regression-based site adaptation of satellite-derived irradiance represents an effective approach for improving site-specific day-ahead POA irradiance forecasting while highlighting the importance of controlled evaluation conditions when assessing model performance. Full article

Rooftop photovoltaic systems are a key component of sustainable urban energy strategies; however, their performance is strongly influenced by environmental variability across spatial scales. This study develops and validates a mathematical model to quantify the influence of Global Horizontal Irradiation (GHI), air temperature, wind speed, and dust on rooftop solar energy efficiency at country, regional, and city levels. The model is applied to environmental and energy data from 96 countries and 17 regions and further validated using four large-scale rooftop PV projects in Bahrain. The results show strong agreement between predicted and actual solar energy production, with coefficients of determination of R² = 0.77 at the country level, R² = 0.84 at the regional level, and R² = 0.998 at the city level, while mean absolute percentage errors generally remain below 10%. Regression and sensitivity analyses showed that at least one environmental factor exerts a statistically significant influence on rooftop solar energy yield, supporting the alternative research hypothesis. GHI is identified as the most influential driver at the national scale, whereas temperature and dust effects become more pronounced at finer spatial resolutions. Deployment gap analysis further reveals substantial untapped rooftop solar potential, highlighting the importance of non-environmental constraints in shaping real-world solar adoption. Full article

Accurate measurements of global horizontal irradiance (GHI) are fundamental for solar energy assessment. However, the cost and deployment constraints of standard pyranometers limit their widespread use. This work presents a low-cost pseudo-pyranometer based on photovoltaic current measurements combined with a hybrid physical-machine learning approach. A custom data acquisition system was developed and deployed in Piatra-Neamț, Romania, consisting of a Raspberry Pi 5, INA219 current sensor, and a 0.3 W photovoltaic panel mounted horizontally. One-minute resolution measurements were collected between August 2024 and June 2025 and augmented with modeled solar geometry and clear-sky irradiance using pvlib. Temporal effects were encoded using sinusoidal representations of the time of the day and the day of the year. Clear-sky current samples were identified using a tolerance-based normalization with respect to modeled clear-sky irradiance and used to train an artificial neural network to estimate the clear-sky panel current. Feature importance was assessed using SHAP analysis, highlighting the dominant role of solar geometry and temporal encoding. The resulting clear-sky current model was combined with measured current through a clearness index formulation to estimate GHI. To evaluate performance, the system was redeployed in parallel with a reference pyranometer in Cluj-Napoca, Romania, enabling direct comparison under real operating conditions. The results demonstrate that the proposed hybrid approach can approximate pyranometer measurements with low-cost hardware, supporting scalable and redeployable solar monitoring networks in geographically localized regions. Full article

The transition to smart cities is accelerating distributed wind and solar deployment. However, their intermittency challenges grid operation, thereby making accurate machine-learning-based prediction of wind speed and global horizontal irradiance (GHI) crucial. This study presents a cost-effective approach that enhances prediction accuracy by extracting additional features from timestamp records for deep learning models used to forecast GHI and wind speed. Unlike conventional methods that require onsite meteorological measurements, the proposed approach uses only date and time information as inputs to multivariate deep neural networks, including recurrent neural networks, gated recurrent units, long short-term memory (LSTM), bidirectional LSTM, and convolutional neural networks. For wind speed prediction, the proposed configuration achieves R² up to 0.9987, with RMSE as low as 0.067 m/s for 3 d ahead forecasting, outperforming univariate baselines and matching models. For GHI forecasting, the time-based configuration attains R² values above 0.9994 in 12 h ahead predictions, with the RMSE reduced to approximately 4.47 W/m², representing a substantial improvement over univariate models. The proposed framework maintains strong performance, particularly under clear and sunny conditions. These results demonstrate that timestamp-engineered features can deliver forecasting accuracy comparable to conventional multivariate meteorological models while significantly reducing infrastructure requirements, making the approach well-suited for scalable smart city energy management. Full article

The accurate estimation of the instantaneous UV Index (UVI) is critical for public health, yet it is often attempted using broadband pyranometers (measuring Global Horizontal Irradiance GHI) or photometers (measuring Lux). This approach is known to be unreliable, particularly under the complex radiative conditions induced by clouds. However, the physical mechanisms driving this failure, specifically the changes in the spectral quality of sunlight, are not fully quantified. This study utilizes a high-resolution spectroradiometer and pyranometer at a Mediterranean site (Rende, Italy), analyzing instantaneous UVI, GHI and a set of derived analytical metrics: the Erythemal Efficacy, the UV Spectral Quality Ratio and the Clearness Index. The core metric of the paper is the Erythemal Efficacy, designed to quantify the “spectral quality” or “biological hazard” per unit of total energy. It is defined as the ratio of the instantaneous UV Index to the instantaneous GHI measured by the pyranometer. The analysis confirms a decoupling between instantaneous UVI and broadband GHI, exhibiting a wide, non-functional scatter. The paper shows that this failure is caused by the high variability of the Erythemal Efficacy, which is not a constant. Its variability is shown to be linearly governed by the internal Ultraviolet A to Ultraviolet B (UVA/UVB) spectral ratio. Most critically, the Erythemal Efficacy was found to follow a counter-intuitive trend, increasing significantly as the Clearness Index decreases. The common assumption of clouds as spectrally “grey” attenuators is flawed. Clouds act as selective filters, attenuating the GHI, dominated by Visible to Near-Infrared (VIS/NIR), more severely than the UVI. This increases the relative biological hazard of the light that penetrates thick cloud cover. This study provides a physical explanation for the failure of broadband proxies and demonstrates that instantaneous GHI or Lux-based UVI alerts are fundamentally unreliable, as they fail to capture the critical variability of spectral quality. Full article

Rapid urbanization and climate change have increased urban air temperatures and intensified the urban heat island effect through the expansion of impervious surfaces, loss of green areas, and high-density development. This study quantitatively evaluates the heat-mitigation performance and outdoor-thermal-comfort benefits of a high-pressure micro-mist cooling-fog system installed in the Oncheoncheon area of Busan, South Korea. Five environmental sensors were deployed in Gwajeong Park to monitor the near-pedestrian air temperature and relative humidity, and thermal comfort was assessed using the Universal Thermal Climate Index and the Physiological Equivalent Temperature derived from meteorological variables. Both indices indicated improved thermal comfort during fog operation relative to the control condition. The relationship between air temperature and perceived thermal conditions was strong, while the mean radiant temperature exhibited substantial dispersion even under similar air temperatures. Higher global horizontal irradiance (GHI: incoming solar radiation on a horizontal surface) was associated with elevated mean radiant temperature, highlighting the importance of radiative load in pedestrian thermal stress. Overall, the findings provide field-based evidence that high-pressure micro-misting can improve outdoor thermal comfort and function as practical cooling infrastructure for heat-stress mitigation and urban climate resilience. Full article

The accurate short-term forecasting of global horizontal irradiance (GHI) is essential to optimizing the operation and integration of solar energy systems into the power grid. This study evaluates the performance of the Weather Research and Forecasting (WRF) model in predicting GHI over a 48 h forecast horizon at an Italian site: the ENEA Casaccia Research Center, near Rome (central Italy). The instantaneous GHI provided by WRF at model output frequency was post-processed to derive the mean GHI over the preceding hour, consistent with typical energy forecasting requirements. Furthermore, a decomposition model was applied to estimate direct normal irradiance (DNI) and diffuse horizontal irradiance (DHI) from the forecasted GHI. These derived components enable the estimation of solar energy yield for both concentrating solar power (CSP) and photovoltaic (PV) technologies (on tilted surfaces) by accounting for direct, diffuse, and reflected components of solar radiation. Model performance was evaluated against ground-based pyranometer and pyrheliometer measurements by using standard statistical indicators, including RMSE, MBE, and correlation coefficient (r). Results demonstrate that WRF-based forecasts, combined with suitable post-processing and decomposition techniques, can provide reliable 48 h predictions of GHI and DNI at the study site, highlighting the potential of the WRF framework for operational solar energy forecasting in the Mediterranean region. Full article