A new approach for interval forecasting of photovoltaic power based on generalized weather classification

Guo, Jun; Xu, Xunjian; Lian, Weiwei; Zhu, Hongguang

doi:10.1002/etep.2802

Cited by 11 publications

(5 citation statements)

References 18 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [13], the distribution of forecasting error was estimated based on the seasonal model and KDE to realize the interval prediction of PV power output. e hybrid models combined with ELM and KDE were established for interval forecasting PV power under weather classification [14]. A prediction intervals estimation method was proposed for solar generation based on GRU neural networks and KDE [15].…”

Section: Introductionmentioning

confidence: 99%

Interval Prediction of Photovoltaic Power Using Improved NARX Network and Density Peak Clustering Based on Kernel Mahalanobis Distance

et al. 2022

View full text Add to dashboard Cite

Photovoltaic (PV) power forecasting can provide strong support for the safe operation of the power system. Existing forecasting methods are ineffective for grid scheduling decisions or risk analysis. The novel multicluster interval prediction method is proposed to consider the volatility and randomness of PV power output. First, this method utilizes the sparse autoencoder (SAE) and Bayesian regularized NARX network (BRNARX) for point forecasting of PV power. Second, density peak clustering improved by kernel Mahalanobis distance (KMDDPC) is applied to classify the dataset into multiple clusters, including forecasting error and meteorological factors. Finally, the joint probability density is established by multivariate kernel density estimation (MKDE) to accomplish the PV power interval prediction. The proposed hybrid method is applied for the interval prediction of PV power at Yulara, Australia. Comparative research of point forecasting is implemented to evaluate the machine learning and deep learning methods, with the proposed SAE-BRNARX under four different periods. Results shows that the average values of nRMSE, MRE, nMAE, and R2 for the four periods are 4.45%, 0.90%, −0.15%, 3.39%, and 95.93%, respectively. Moreover, the results of interval prediction obtained by the other interval prediction approaches are compared with the proposed KMDDPC-MKDE. It shows that the average values of PICP, PINAW, ACE, and nMPICD for four periods are 93.93%, 9.50%, 3.93%, and 7.10% at 90% confidence level, respectively. Outcomes demonstrate that the proposed method can obtain more accuracy, a higher coverage rate, narrower average bandwidth, and a closer distance between the middle of interval and actual value than other methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Interval Prediction of Photovoltaic Power Using Improved NARX Network and Density Peak Clustering Based on Kernel Mahalanobis Distance

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Environmental deterioration and greenhouse gas emission is a cause of concern for many developing and developed countries 1‐4 . Among renewable energy sources, by 2020, wind power is likely to cater 12% of global electricity demands 5 .…”

Section: Introductionmentioning

confidence: 99%

Machine intelligent and deep learning techniques for large training data in short‐term wind speed and ramp event forecasting

Dhiman

Deb

2021

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Fluctuation in wind speed over the period of time can impact operation of a utility grid. Sudden large scale variation in turbine power, often termed as ramp event, can threaten the security of power system. In this work, we predict ramp events through a hybrid method based on discrete wavelet transform (DWT) and learning algorithms such as Twin Support vector regression (TSVR), random forest regression (RFR), and Convolutional neural networks (CNN) for onshore, offshore and hilly sites. Wavelet transform-based signal processing helps extract features from wind speed. Results suggest that SVR based prediction models are the best in forecasting among the available models. Besides, CNN predicts ramp events closer to the TSVR model and gives a better prediction performance for larger training datasets. The proposed hybrid version of TSVR, RFR, and CNN models are compared with existing SVM, ANN, and ELM models and indicate significant improvement in predicting ramp events. Compared to SVM, TSVR and RFR are 17.88% and 4.87% efficient in terms of RMSE, respectively. Further, randomness in ramp event signal for all the wind farm sites considered is evaluated using log-energy entropy. Results reveal that compared to wavelet transform, empirical mode decomposition yields lower randomness in predicted ramp event signals. K E Y W O R D Sempirical mode decomposition (EMD), ramp events, support vector regression (SVR), twin support vector regression (TSVR), wavelet transform (WT), wind forecasting | INTRODUCTIONEnvironmental deterioration and greenhouse gas emission is a cause of concern for many developing and developed countries. [1][2][3][4] Among renewable energy sources, by 2020, wind power is likely to cater 12% of global electricity

show abstract

“…But, the amount of solar irradiance that reaches the surface of the earth varies by the intermittency of cloud cover, impacting short-term solar energy production. As these variations create significant fluctuations in solar power feed into the grid, the methods that can be used to predict solar irradiance at ground level and thus the corresponding PV power generation are necessary to ensure the effective management of electrical grids [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Sky Image-Based Localized, Short-Term Solar Irradiance Forecasting for Multiple PV Sites via Cloud Motion Tracking

Dissawa

Godaliyadda

Ekanayake

et al. 2021

International Journal of Photoenergy

View full text Add to dashboard Cite

Power generation through solar photovoltaics has shown significant growth in recent years. However, high penetration of solar PV creates power system operational issues as a result of solar PV variability and uncertainty. Short-term PV variability mainly occurs due to the intermittency of cloud cover. Therefore, to mitigate the effects of PV variability, a sky-image-based, localized, global horizontal irradiance forecasting model was introduced considering the individual cloud motion, cloud thicknesses, and the elevations of clouds above the ground level. The proposed forecasting model works independently of any historical irradiance measurements. Two inexpensive sky camera systems were developed and placed in two different locations to obtain sky images for cloud tracking and cloud-based heights. Then, irradiance values for onsite and for a PV site located with a distance of 2 km from the main camera were forecasted for 1 minute, 5 minutes, and 15 minutes ahead of real-time. Results show that the three-level cloud categorization and the individual cloud movement tracking method introduced in this paper increase the forecasting accuracy. For partially cloudy and sunny days, the forecasting model for 15 min forecasting time interval achieved a positive skill factor concerning the persistent model. The accuracy of determining the correct irradiance state for a 1 min forecasting time interval using the proposed model is 81%. The average measures of RMSE, MAE, and SF obtained using the proposed method for 15 min forecasting time horizon are 101 Wm-2, 64 Wm-2, and 0.26, respectively. These forecasting accuracy levels are much higher than the other benchmarks considered in this paper.

show abstract

A new approach for interval forecasting of photovoltaic power based on generalized weather classification

Cited by 11 publications

References 18 publications

Interval Prediction of Photovoltaic Power Using Improved NARX Network and Density Peak Clustering Based on Kernel Mahalanobis Distance

Interval Prediction of Photovoltaic Power Using Improved NARX Network and Density Peak Clustering Based on Kernel Mahalanobis Distance

Machine intelligent and deep learning techniques for large training data in short‐term wind speed and ramp event forecasting

Sky Image-Based Localized, Short-Term Solar Irradiance Forecasting for Multiple PV Sites via Cloud Motion Tracking

Contact Info

Product

Resources

About