Machine learning algorithms for photovoltaic system power output prediction

Forecasting systems reliability based on support vector regression with genetic algorithms

To explore an effective analysis model and method for estimating Cinnamomum camphora's (C. camphora's) growth using unmanned aerial vehicle (UAV) multispectral technology, we obtained C. camphora's canopy spectral reflectance using a UAV-mounted multispectral camera and simultaneously measured four single-growth indicators: Soil and Plant Analyzer Development (SPAD)value, aboveground biomass (AGB), plant height (PH), and leaf area index (LAI). The coefficient of variation and equal weighting methods were used to construct the comprehensive growth monitoring indicators (CGMI) for C. camphora. A multispectral inversion model of integrated C. camphora growth was established using the multiple linear regression (MLR), partial least squares (PLS), support vector regression (SVR), random forest (RF), radial basis function neural network (RBFNN), back propagation neural network (BPNN), and whale optimization algorithm (WOA)-optimized BPNN models. The optimal model was selected based on the coefficient of determination (R2), normalized root mean square error (NRMSE) and mean absolute percentage error (MAPE). Our findings indicate that apparent differences in the accuracy with different model, and the WOA-BPNN model is the best model to invert the growth potential of C. camphora, the R2 of the model test set was 0.9020, the RMSE was 0.0722, and the MAPE was 7%. The R2 of the WOA-BPNN model improved by 18%, the NRMSE decreased by 33%, and the MAPE decreased by 9% compared with the BPNN model. This study provides technical support for the modern field management of C. camphora essential oil and other dwarf forestry industries.

In this paper, the Artificial Neural Networks (ANN) model have been exploited for estimation of the energy production of the 20-MW solar photovoltaic (PV) plant installed in Adrar in terms of energy yield, using a minimal knowledge of meteorological parameter include global solar radiation, relative humidity, wind speed, and ambient or air temperature. A comparative analysis has been carried out between the proposed artificial neural networks model and multiple linear regression (MLR) models in PV output estimation and performance is measured based on evaluation indexes, namely mean absolute percentage error, normalized mean absolute error, and normalized root mean square error respectively. Further, the comparison of the ANN model with MLR based models reveals the advantages and supremacy of the ANN model.

Accurate day-ahead photovoltaic (PV) power output forecasting techniques are important for grid and plant operators. In this study, a methodology for PV power forecasting is proposed based on a synthetic generation of multiple Bayesian regularised neural network (BRNN) models. Specifically, different BRNN models were developed for every hour of each day within the power production period. The final PV power production forecasting was provided by combining the outputs of all the developed models. The accuracy of the developed model was experimentally validated by deploying it to a test system installed in Cyprus. The day ahead power production forecasting performance accuracy of the proposed methodology in terms of normalised root mean square error and mean absolute percentage error was 5.80% and 4.49%, respectively.

Various challenges should be considered when measuring photovoltaic array power and energy in pulse width modulation (PWM) charge controllers. These controllers are frequently used not only in stand-alone photovoltaic (SAPV) systems, but may also be found in photovoltaic (PV) self-consumption systems with battery storage connected to the electricity grid. An acceptable solution may be reached using expensive data acquisition systems (DASs), although this could be generally disproportionate to the relatively low cost of SAPV systems. Therefore, the aim of this paper is to develop new and effective monitoring techniques which will provide the PV array direct current (DC), output power (PA,dc), and PV array DC output energy (EA), thus avoiding the use of sophisticated DASs and providing high accuracy for the calculated parameters. Only transducers and electronic circuits that provide the average and true rms values of the PWM signals are needed. The estimation of these parameters through the aforementioned techniques showed high accuracy for both series and shunt PWM battery charge controllers. Normalized root mean square error (NRMSE) was lower than 2.4%, normalized mean bias error (NMBE) was between −1.5% and 1.1%, and mean absolute percentage error (MAPE) was within 1.6%.

With the increasing global warming and enormous pollution, it is very obvious to generate power from renewable energy sources. In fact, photo voltaic (PV) power is a main renewable energy source for sustainable power generation. But PV power generation is uncertain and intermittent in nature. Stable and reliable power supply may not be feasible with PV power. Power supply reliability is important as much as its availability. To handle the inconsistency of PV power generation, power sector is highly dependent on forecasting methods and techniques. In this paper the feed forward neural network (FFNN) of artificial neural networks(ANN) with optimization technique particle swarm optimization (PSO) and support vector regression (SVR) are used in short term PV power generation forecasting and their performance is compared with the error calculation in terms of the mean absolute error (MAE) and root mean squared error (RMSE). The PV power and meteorological data of solar irradiation and temperature of Kolkata region of India was used for forecasting. Similar days of the year sunny days, cloudy days and rainy days are clustered using k-means clustering technique. Thereafter, a feed forward neural network is implemented to forecast a day head PV power and week ahead photo voltaic power. PSO is used to optimize the weights of the neural network. The performance of the proposed forecasting method is compared to a data mining approach, support vector regression (SVR).In this paper, the significance of proper selection of input parameters in PV power forecasting is emphasized. With the application of K-means clustering, the accuracy of ANN-PSO approach is improved significantly in a day ahead PV power forecasting and a week ahead PV power forecasting with a good margin. Even the accuracy of ANN-PSO approach after K-means clustering is better than SVR model in a week ahead forecasting

Accurate forecast of carbon dioxide (CO2) emissions plays a significant role in China's carbon peaking and carbon neutrality policies. A novel two-stage forecast procedure based on support vector regression (SVR), random forest (RF), ridge regression (Ridge), and artificial neural network (ANN) is proposed and evaluated by comparing it with the single-stage forecast procedure. Nine independent variables’ data (study period: 1985–2020) are used to forecast the CO2 emissions in China. Our results reveal that, when the time gap, h increases from 1 to 8, the average root mean squared error (RMSE) and mean absolute error (MAE) of SVR–SVR, SVR–RF, SVR–Ridge, and SVR–ANN are almost uniformly lower than errors arising from their single-stage version, respectively. Among these two-stage models, SVR–ANN exhibits the lowest forecast errors, whereas SVR–RF admits the highest. The mean percentage decrease in forecast errors of SVR–SVR vs. SVR, SVR–RF vs. RF, SVR–Ridge vs. Ridge, and SVR–ANN vs. ANN are 36.06, 5.98, 43.05, and 14.81 for RMSE, and 36.06, 6.91, 43.27, and 15.35 for MAE. Our two-stage procedure is also suitable to forecast other variables, such as fossil fuel and renewable energy consumption.

Optimizing asphalt mix design through predicting effective asphalt content and absorbed asphalt content using machine learning

Remotely sensed air temperature data from NASA POWER are widely used in regions with scarce climatic observations, particularly for agricultural applications such as calculating crop water requirements. This study employed a suite of machine learning (ML) algorithms to correct biases in NASA POWER air temperature outputs, including multiple support vector regression (SVR) variants—Linear SVR, Quadratic SVR, Cubic SVR, Fine Gaussian SVR, Medium Gaussian SVR, Coarse Gaussian SVR—and ensemble decision tree models: bagged trees (BGT) and boosted trees (BT). The objective of this study was to assess the ability of different ML algorithms to reduce biases in NASA POWER air temperature data, with the broader goal of identifying the most suitable ML method for air temperature bias correction in Nigeria. For this analysis, we used daily air temperature records from seven meteorological stations across diverse regions of Nigeria. The performance of NASA POWER minimum and maximum air temperature datasets was evaluated using standard error metrics. Subsequent application of ML algorithms significantly improved data accuracy: the normalized root mean square error (NRMSE) of the corrected outputs was mostly below 10%, indicating excellent predictive performance when ML was integrated. Among the SVR variants tested, Fine Gaussian SVR consistently yielded the best prediction results. This finding suggests that Fine Gaussian SVR is a robust tool for enhancing the reliability of air temperature data—critical for improving the accuracy of crop water requirement calculations in regions where in-situ air temperature observations are limited.

Kalman filter based on a fractional discrete-time stochastic augmented CoVid-19 model

This paper presents modeling and experimental studies on water spray coolers for commercial photovoltaic modules. This paper has compared the energy yield of four photovoltaic commercial modules that were installed with a fixed tilt angle being equal to the local latitude in central Vietnam, including one photovoltaic module using a water spray cooler and three photovoltaic modules without cooling. Experimental results on sunny days have been shown that the energy yield difference between four PV modules under the same working condition is lower than 1%. In addition, on sunny days when the set working temperature of the water spray cooler is 45 °C, the average improvement efficiency of a photovoltaic module using a water spray cooler compared to three reference photovoltaic modules is 2.64%, 3.83%, and 6.18%, for an average of 4.22%. A simple thermal–electrical model of a photovoltaic module with a water spray cooler has been developed and tested. The normalized root mean square error between simulated and measured results of photovoltaic module power output on a sunny day without cooling and with water spray cooler reached 6.5% and 8.5%, respectively. The obtained results are also demonstrated that the reasonableness of the simple thermal–electrical model of the photovoltaic module with water spray cooler and the feasibility of a cooling system is improved to increase the efficiency of the photovoltaic module. In addition, they can be considered as a basis for new experimental models in the future.

Rising penetration levels of (residential) photovoltaic (PV) power as distributed energy resource pose a number of challenges to the electricity infrastructure. High quality, general tools to provide accurate forecasts of power production are urgently needed. In this article, we propose a supervised deep learning model for end-to-end forecasting of PV power production. The proposed model is based on two seminal concepts that led to significant performance improvements of deep learning approaches in other sequence-related fields, but not yet in the area of time series prediction: the sequence to sequence architecture and attention mechanism as a context generator. The proposed model leverages numerical weather predictions and high-resolution historical measurements to forecast a binned probability distribution over the prognostic time intervals, rather than the expected values of the prognostic variable. This design offers significant performance improvements compared to common baseline approaches, such as fully connected neural networks and one-block long short-term memory architectures. Using normalized root mean square error based forecast skill score as a performance indicator, the proposed approach is compared to other models. The results show that the new design performs at or above the current state of the art of PV power forecasting.

Soil salinization affects crop production and food security. Mapping spatial distribution and severity of salinity is essential for agricultural management and development. This study was aimed to test the effectiveness of machine learning algorithms for soil salinity mapping taking the Mussaib area in Central Mesopotamia as an example. A combined dataset consisting of Landsat 5 Thematic Mapper (TM) and ALOS L‐band radar data acquired at the same time was used for fulfilling the task. Relevant biophysical indicators were derived from the TM images, and the soil component was retrieved by removing the vegetation contribution from the L‐band radar backscattering coefficients. Field‐measured salinity at the three corner plots of triangles were averaged to represent the salinity of these triangular areas. These averaged plots were converted into raster by either direct rasterization or buffering‐based rasterization into different cell size to create the training set (TS). One of the three triangle corners was randomly selected to constitute a validation set (VS). Using this TS, the support vector regression (SVR) and random forest regression (RFR) algorithms were then applied to the combined dataset for salinity prediction. Results revealed that RFR performed better than SVR with higher accuracy (93.4–94.2% vs. 85.2–89.4%) and less normalized root mean square error (NRMSE; 6.10–7.69% vs. 10.29–10.52%) when calibrated with both TS and VS. In comparison, prediction by multivariate linear regression (MLR) achieved in our previous study using the same datasets also showed less NRMSE than SVR. Hence, both RFR and MLR are recommended for soil salinity mapping.

Estimating the wake losses in a wind farm is critical in the short term forecast of wind power, following the Numerical Weather Prediction (NWP) approach. Understanding the intensity of the wakes and the nature of its propagation within the wind farm still remains a challenge to scientist, engineers and utility operators. In this paper, five different machine learning methods are used to estimate the power deficit experienced by wind turbines due to the wake losses. Production data from the Horns Rev offshore wind farm, Denmark, have been used for the study. The methods used are linear regression, linear regression with feature engineering, nonlinear regression, Artificial Neural Networks (ANN) and Support Vector Regression (SVR). Power developed by individual turbines located at different positions within the farm were computed based on the above methods and compared with the actual power measurements. With the respective Variance Normalized Root Mean Square Error (VNRMSE) of 0.21 and 0.22, models based on ANN and SVR could estimate the wind farm wake effects at an acceptable accuracy level. The study shows that suitable machine learning methods can effectively be used in estimating the power deficits due to wake effects experienced in large wind farms.

ABSTRACTUpdating of reservoir models by history matching of 4D seismic data along with production data gives us a better understanding of changes to the reservoir, reduces risk in forecasting and leads to better management decisions. This process of seismic history matching requires an accurate representation of predicted and observed data so that they can be compared quantitatively when using automated inversion. Observed seismic data is often obtained as a relative measure of the reservoir state or its change, however. The data, usually attribute maps, need to be calibrated to be compared to predictions. In this paper we describe an alternative approach where we normalize the data by scaling to the model data in regions where predictions are good. To remove measurements of high uncertainty and make normalization more effective, we use a measure of repeatability of the monitor surveys to filter the observed time‐lapse data.We apply this approach to the Nelson field. We normalize the 4D signature based on deriving a least squares regression equation between the observed and synthetic data which consist of attributes representing measured acoustic impedances and predictions from the model. Two regression equations are derived as part of the analysis. For one, the whole 4D signature map of the reservoir is used while in the second, 4D seismic data is used from the vicinity of wells with a good production match. The repeatability of time‐lapse seismic data is assessed using the normalized root mean square of measurements outside of the reservoir. Where normalized root mean square is high, observations and predictions are ignored. Net: gross and permeability are modified to improve the match.The best results are obtained by using the normalized root mean square filtered maps of the 4D signature which better constrain normalization. The misfit of the first six years of history data is reduced by 55 per cent while the forecast of the following three years is reduced by 29 per cent. The well based normalization uses fewer data when repeatability is used as a filter and the result is poorer. The value of seismic data is demonstrated from production matching only where the history and forecast misfit reductions are 45% and 20% respectively while the seismic misfit increases by 5%. In the best case using seismic data, it dropped by 6%. We conclude that normalization with repeatability based filtering is a useful approach in the absence of full calibration and improves the reliability of seismic data.