Prediction of daily and mean monthly global solar radiation using support vector machine in an arid climate

Accurate solar photovoltaic (PV) power forecasting is an essential tool for mitigating the negative effects caused by the uncertainty of PV output power in systems with high penetration levels of solar PV generation. Weather classification based modeling is an effective way to increase the accuracy of day-ahead short-term (DAST) solar PV power forecasting because PV output power is strongly dependent on the specific weather conditions in a given time period. However, the accuracy of daily weather classification relies on both the applied classifiers and the training data. This paper aims to reveal how these two factors impact the classification performance and to delineate the relation between classification accuracy and sample dataset scale. Two commonly used classification methods, K-nearest neighbors (KNN) and support vector machines (SVM) are applied to classify the daily local weather types for DAST solar PV power forecasting using the operation data from a grid-connected PV plant in Hohhot, Inner Mongolia, China. We assessed the performance of SVM and KNN approaches, and then investigated the influences of sample scale, the number of categories, and the data distribution in different categories on the daily weather classification results. The simulation results illustrate that SVM performs well with small sample scale, while KNN is more sensitive to the length of the training dataset and can achieve higher accuracy than SVM with sufficient samples.

show abstract

“…These methods are mainly used for forecasting and evaluating the solar energy for time horizons larger than 6 h [34][35][36].…”

Section: Introductionmentioning

confidence: 99%

Comparative Study on KNN and SVM Based Weather Classification Models for Day Ahead Short Term Solar PV Power Forecasting

et al. 2017

View full text Add to dashboard Cite

show abstract

“…In the last 20 years, machine learning techniques (ML) have been tested and used to estimate solar radiation and have shown to be a good tool [8][9][10][11]. Using ANN and comparing it with empirical models, Soares et al [8] estimated diffuse solar radiation in São Paulo city.…”

Section: Introductionmentioning

confidence: 98%

“…The authors compared the performance of SVR with that of empirical models and obtained RMSE = 2.004 MJ m À2 for daily estimates and RMSE = 0.450 MJ m À2 for monthly estimates with SVR, which shows better performance for ML. Considering both ML and SVM, the latter has better performance solving classification and regression problems due to its better generalization ability [9,17]. There are several studies assessing estimates of solar radiation data using ML and most of them analyzed estimates of daily global radiation [18,19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Assessment of ANN and SVM models for estimating normal direct irradiation (Hb)

Santos

Escobedo

Teramoto

et al. 2016

Energy Conversion and Management

View full text Add to dashboard Cite

a b s t r a c tThis study evaluates the estimation of hourly and daily normal direct irradiation (H b ) using machine learning techniques (ML): Artificial Neural Network (ANN) and Support Vector Machine (SVM). Time series of different meteorological variables measured over thirteen years in Botucatu were used for training and validating ANN and SVM. Seven different sets of input variables were tested and evaluated, which were chosen based on statistical models reported in the literature. Relative Mean Bias Error (rMBE), Relative Root Mean Square Error (rRMSE), determination coefficient (R 2 ) and ''d" Willmott index were used to evaluate ANN and SVM models. When compared to statistical models which use the same set of input variables (R 2 between 0.22 and 0.78), ANN and SVM show higher values of R 2 (hourly models between 0.52 and 0.88; daily models between 0.42 and 0.91). Considering the input variables, atmospheric transmissivity of global radiation (kt), integrated solar constant (H sc ) and insolation ratio (n/N, n is sunshine duration and N is photoperiod) were the most relevant in ANN and SVM models. The rMBE and rRMSE values in the two time partitions of SVM models are lower than those obtained with ANN. Hourly ANN and SVM models have higher rRMSE values than daily models. Optimal performance with hourly models was obtained with ANN4 h (rMBE = 12.24%, rRMSE = 23.99% and ''d" = 0.96) and SVM4 h (rMBE = 1.75%, rRMSE = 20.10% and ''d" = 0.96). Optimal performance with daily models was obtained with ANN2 d (rMBE = À3.09%, rRMSE = 18.95% and ''d" = 0.97) and SVM2 d (rMBE = 0.60%, rRMSE = 19.39% and ''d" = 0.97). ANN and SVM models improved H b estimations as compared with other results from the literature. SVM has better performance than ANN to estimate H b , and it should be the first option of choice.

show abstract

“…The work in Ref. [26] tackles a problem of global solar energy prediction with SVRs considering different prediction time horizons. Finally, in Refs.…”

Section: Introductionmentioning

confidence: 99%

A CRO-species optimization scheme for robust global solar radiation statistical downscaling

et al. 2017

View full text Add to dashboard Cite

a b s t r a c tThis paper tackles the prediction of the global solar radiation (GSR) at a given point, using as predictive variables the outputs of a numerical weather model (the WRF meso-scale model) obtained at a different grid points. Prediction is obtained in this work using a Multilayer Perceptron (MLP) trained with Extreme Learning Machines (ELMs). Provided that the number of WRF outputs is vast, we propose the use of a Coral Reefs Optimization algorithm with species (CRO-SP) to obtain a reduced number of significant predictive variables, therefore improving the global solar radiation prediction attained without feature selection. The proposed system has been tested on real data from a radiometric station located at Toledo (Spain) and average best results of RMSE of 69.19 W=m 2 have been achieved, resulting in a 21.62% improvement over the average prediction without considering the CRO-SP for the feature selection.

show abstract

Prediction of daily and mean monthly global solar radiation using support vector machine in an arid climate

Cited by 147 publications

References 40 publications

Comparative Study on KNN and SVM Based Weather Classification Models for Day Ahead Short Term Solar PV Power Forecasting

Comparative Study on KNN and SVM Based Weather Classification Models for Day Ahead Short Term Solar PV Power Forecasting

Assessment of ANN and SVM models for estimating normal direct irradiation (Hb)

A CRO-species optimization scheme for robust global solar radiation statistical downscaling

Contact Info

Product

Resources

About