Univariate and multivariate methods for very short-term solar photovoltaic power forecasting

Rana, Mashud; Koprinska, Irena; Agelidis, Vassilios G.

doi:10.1016/j.enconman.2016.05.025

Cited by 188 publications

(79 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To verify the validity of the proposed RCC-LSTM model, several typical networks, including RCC-BPNN, RCC-RBFNN [47], RCC-Elman, and LSTM-RNN [55] are chosen to make comparison, and the test are conducted in four seasons and two different PV systems. In addition, four different evaluation metrics (RMSE, MAPE, MAE, and R2) are applied to verify the prediction accuracy of the RCC-LSTM model.…”

Section: Resultsmentioning

confidence: 99%

Very-Short-Term Power Prediction for PV Power Plants Using a Simple and Effective RCC-LSTM Model Based on Short Term Multivariate Historical Datasets

et al. 2020

View full text Add to dashboard Cite

Improving the accuracy of very-short-term (VST) photovoltaic (PV) power generation prediction can effectively enhance the quality of operational scheduling of PV power plants, and provide a reference for PV maintenance and emergency response. In this paper, the effects of different meteorological factors on PV power generation as well as the degree of impact at different time periods are analyzed. Secondly, according to the characteristics of radiation coordinate, a simple radiation classification coordinate (RCC) method is proposed to classify and select similar time periods. Based on the characteristics of PV power time-series, the selected similar time period dataset (include power output and multivariate meteorological factors data) is reconstructed as the training dataset. Then, the long short-term memory (LSTM) recurrent neural network is applied as the learning network of the proposed model. The proposed model is tested on two independent PV systems from the Desert Knowledge Australia Solar Centre (DKASC) PV data. The proposed model achieving mean absolute percentage error of 2.74–7.25%, and according to four error metrics, the results show that the robustness and accuracy of the RCC-LSTM model are better than the other four comparison models.

show abstract

Section: Resultsmentioning

confidence: 99%

Very-Short-Term Power Prediction for PV Power Plants Using a Simple and Effective RCC-LSTM Model Based on Short Term Multivariate Historical Datasets

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Deep learning architectures to predict photovoltaic production 5.1. MLP with past photovoltaic values First, we define a baseline model (similar to the univariate model in (Rana et al, 2016)) with a multilayer perceptron (MLP) network. This network takes in only historical photovoltaic power values p as input to forecast the variation ∆p t 0 as in eq.…”

mentioning

confidence: 99%

Deep photovoltaic nowcasting

et al. 2018

View full text Add to dashboard Cite

Predicting the short-term power output of a photovoltaic panel is an important task for the efficient management of smart grids. Short-term forecasting at the minute scale, also known as nowcasting, can benefit from sky images captured by regular cameras and installed close to the solar panel. However, estimating the weather conditions from these images-sun intensity, cloud appearance and movement, etc.-is a very challenging task that the community has yet to solve with traditional computer vision techniques. In this work, we propose to learn the relationship between sky appearance and the future photovoltaic power output using deep learning. We train several variants of convolutional neural networks which take historical photovoltaic power values and sky images as input and estimate photovoltaic power in a very short term future. In particular, we compare three different architectures based on: a multi-layer perceptron (MLP), a convolutional neural network (CNN), and a long short term memory (LSTM) module. We evaluate our approach quantitatively on a dataset of photovoltaic power values and corresponding images gathered in Kyoto, Japan. Our experiments reveal that the MLP network, already used similarly in previous work, achieves an RMSE skill score of 7% over the commonly-used persistence baseline on the 1-minute future photovoltaic power prediction task. Our CNN-based network improves upon this with a 12% skill score. In contrast, our LSTM-based model, which can learn the temporal dependencies in the data, achieves a 21% RMSE skill score, thus outperforming all other approaches.

show abstract

“…After Rana et al . developed short‐term (5–60 min ahead) PV power forecasting model using neural network techniques, results show that the univariate models performed similarly to the multivariate models, achieving mean relative error of 4.15%–9.34% . This confirms that PV power output can be predicted accurately by using only previous PV power data.…”

Section: Introductionmentioning

confidence: 53%

“…Chu et al proposed a real time short term forecasting of power output of a 48 MW solar PV method based on artificial neural network optimization which applied to the intra-hour PV power prediction models [15]. After Rana et al developed short-term (5-60 min ahead) PV power forecasting model using neural network techniques, results show that the univariate models performed similarly to the multivariate models, achieving mean relative error of 4.15%-9.34% [16]. This confirms that PV power output can be predicted accurately by using only previous PV power data.…”

Section: Introductionmentioning

confidence: 99%

Predictive analysis of photovoltaic plants specific yield with the implementation of multiple linear regression tool

Babatunde

Abbasoğlu

2018

Env Prog and Sustain Energy

View full text Add to dashboard Cite

The objective of this study is to develop a model that can predict the specific yield of PV plant and statistically examine the significance of independent variables during the process. The methods presented will help investors make quick and reliable decisions about installing PV plant at a particular site. To determine the best‐fit model for energy prediction, data from all variables were collected and a relevance check was conducted by examining the relationship between independent variables and dependent variable. The forecasting method makes use of Multiple Linear Regression model. Seven models were developed and two models with the best accuracy are proposed in this article. Variance Inflation Factor, which assesses potential multicollinearity among independent variables, was used to optimize the models that have similar characteristics. The first proposed model has coefficient of multiple determination of goodness of fit (R2) of 96.8%. The second model has R2 of 96%. The models were applied to data series selected from same site; prediction accuracies of 97% and 95% were obtained, respectively. They were also validated with Middle East Technical University North Cyprus Campus PV plant, yielding prediction accuracies of PV specific yield of 92% and 90%, respectively. It could be concluded that the results presented in this study will guide the energy experts about the reliability of the methods used to analyze the technical feasibility of medium or large scale PV projects. © 2018 American Institute of Chemical Engineers Environ Prog, 38:e13098, 2019

show abstract

Univariate and multivariate methods for very short-term solar photovoltaic power forecasting

Cited by 188 publications

References 24 publications

Very-Short-Term Power Prediction for PV Power Plants Using a Simple and Effective RCC-LSTM Model Based on Short Term Multivariate Historical Datasets

Very-Short-Term Power Prediction for PV Power Plants Using a Simple and Effective RCC-LSTM Model Based on Short Term Multivariate Historical Datasets

Deep photovoltaic nowcasting

Predictive analysis of photovoltaic plants specific yield with the implementation of multiple linear regression tool

Contact Info

Product

Resources

About