Daily global solar radiation prediction from air temperatures using kernel extreme learning machine: A case study for Iran

Shamshirband, Shahaboddin; Mohammadi, Kasra; Chen, Huiling; Samy, Ganthan Narayana; Petković, Dalibor; Ma, Chao

doi:10.1016/j.jastp.2015.09.014

Cited by 110 publications

(32 citation statements)

References 63 publications

(58 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the accuracy of models for DSR forecasting is affected by the quality of DSR time series data. In measured DSR data, there have been some contradictions and abnormalities in the values mainly because of malfunctioning instruments [6]. After the data sorting, Energies 2019, 12, 1416 4 of 23 every missing value was replaced with interpolated values by means of various approaches for time series analysis.…”

Section: Data Collectionmentioning

confidence: 99%

“…Solar radiation is spatially and temporarily variable, and therefore site measurements are necessary. However, due to various problems (e.g., lack of instruments and fiscal issues), the authentic DSR are scarce [5,6]. Thus, it is clear that applying efficient methods are important for estimating DSR based on other input variables such as meteorological and geographical variables [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting Daily Solar Radiation Using CEEMDAN Decomposition-Based MARS Model Trained by Crow Search Algorithm

Rezaie-Balf

Maleki²,

Kim

et al. 2019

Energies

View full text Add to dashboard Cite

The precise forecasting of daily solar radiation (DSR) is receiving prominent attention among thriving solar energy studies. In this study, three standalone models, including gene expression programing (GEP), multivariate adaptive regression splines (MARS), and self-adaptive MARS (SaMARS), were evaluated to forecast DSR. A SaMARS model was classified as MARS model when using the crow search algorithm (CSA). In addition, to overcome the limitations of the standalone models, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was employed to enhance the accuracy of DSR forecasting. Therefore, three hybrid models including CEEMDAN-GEP, CEEMDAN-MARS, and CEEMDAN-SaMARS were proposed to forecast DSR in Busan and Incheon stations in South Korea. The performance of proposed models were evaluated and affirmed that the accuracy of the CEEMDAN-SaMARS model (NSE = 0.878–0.883) outperformed CEEMDAN-MARS (NSE = 0.819–0.818), CEEMDAN-GEP (NSE = 0.873–0.789), SaMARS (NSE = 0.846–0.769), MARS (NSE = 0.819–0.758), and GEP (NSE = 0.814–0.755) models at both stations. Therefore, it can be concluded that the optimized CEEMDAN-SaMARS model significantly enhanced the accuracy of DSR forecasting compared to that of standalone models.

show abstract

Section: Data Collectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Forecasting Daily Solar Radiation Using CEEMDAN Decomposition-Based MARS Model Trained by Crow Search Algorithm

Rezaie-Balf

Maleki²,

Kim

et al. 2019

Energies

View full text Add to dashboard Cite

show abstract

“…Relative root mean square error (RRMSE¸ %) is expressed as: RRMSE is calculated by dividing RMSE with the average value of the measured observational data. A model's precision level is excellent if the RRMSE < 10%, good if 10% < RRMSE < 20%, fair if 20% < RRMSE < 30% and poor if the RRMSE > 30% (Dawson, Abrahart, & See, 2007;Ravinesh C. Deo & Şahin, 2017;Jamieson, Porter, & Wilson, 1991;Moriasi, Arnold, Van Liew, Bingner, Harmel, & Veith, 2007;Shamshirband, Mohammadi, Chen, Narayana Samy, Petković, & Ma, 2015).…”

Section: Mbe Ws Wsmentioning

confidence: 99%

Optimization of Windspeed Prediction Using an Artificial Neural Network Compared With a Genetic Programming Model

Deo

Ghimire

Downs

et al. 2018

Advances in Computational Intelligence and Robotics

View full text Add to dashboard Cite

show abstract

“…16 And the proposed new model has been widely studied and utilized in time series prediction in the past five years, and its prediction ability is stronger than SVM. 17,18 However, there are few application cases of KELM model in terms of rolling bearing condition monitoring or fault prognostics. The main reason is that the rolling bearing monitoring data has strong nonlinear and non-stationary characteristics and is imbalanced in both date type scale and time changing scale.…”

Section: Introductionmentioning

confidence: 99%

Rolling Bearing Fault Trend Prediction Based on Composite Weighted KELM

Yu¹,

Li²,

Tian³

et al. 2018

IJAV

View full text Add to dashboard Cite

The abilities of different degradation feature types to characterize rolling bearing fault trend are distinctive. And even the characteristic ability of the same degradation feature can change at various times. Thus these feature samples possess heteroscedasticity. However, traditional kernel extreme learning machine (KELM) model assumes that different input samples' effects on the predicted value are equal, which results in low prediction precision and low computing efficiency. To solve this problem, a novel composite weighted KELM (CWKELM) prediction model, which is fused with explicit weighting and implicit weighting, is proposed. In both feature type scale and sample time scale, the feature samples and the prediction model are weighted according to the prediction error. An adaptive mutation particle swarm optimization (AMPSO) algorithm is applied in optimizing the penalty factor and the kernel parameter in the model. Taking various entropy features as the input samples, the proposed model is adopted to conduct one-step and multi-step prediction for rolling bearing fault trend. Experimental results show that this prediction model has higher prediction accuracy and computing efficiency compared with the traditional KELM model.

show abstract

Daily global solar radiation prediction from air temperatures using kernel extreme learning machine: A case study for Iran

Cited by 110 publications

References 63 publications

Forecasting Daily Solar Radiation Using CEEMDAN Decomposition-Based MARS Model Trained by Crow Search Algorithm

Forecasting Daily Solar Radiation Using CEEMDAN Decomposition-Based MARS Model Trained by Crow Search Algorithm

Optimization of Windspeed Prediction Using an Artificial Neural Network Compared With a Genetic Programming Model

Rolling Bearing Fault Trend Prediction Based on Composite Weighted KELM

Contact Info

Product

Resources

About