Journal ArticleDOI
Irradiance Forecasting for the Power Prediction of Grid-Connected Photovoltaic Systems
TLDR
An approach to predict regional PV power output based on forecasts up to three days ahead provided by the European Centre for Medium-Range Weather Forecasts (ECMWF) and an approach to derive weather specific prediction intervals for irradiance forecasts are presented.Abstract:
The contribution of power production by photovoltaic (PV) systems to the electricity supply is constantly increasing. An efficient use of the fluctuating solar power production will highly benefit from forecast information on the expected power production. This forecast information is necessary for the management of the electricity grids and for solar energy trading. This paper presents an approach to predict regional PV power output based on forecasts up to three days ahead provided by the European Centre for Medium-Range Weather Forecasts (ECMWF). Focus of the paper is the description and evaluation of the approach of irradiance forecasting, which is the basis for PV power prediction. One day-ahead irradiance forecasts for single stations in Germany show a rRMSE of 36%. For regional forecasts, forecast accuracy is increasing in dependency on the size of the region. For the complete area of Germany, the rRMSE amounts to 13%. Besides the forecast accuracy, also the specification of the forecast uncertainty is an important issue for an effective application. We present and evaluate an approach to derive weather specific prediction intervals for irradiance forecasts. The accuracy of PV power prediction is investigated in a case study.read more
Citations
More filters
Journal ArticleDOI
Design of experiments using artificial neural network ensemble for photovoltaic generation forecasting
M.O. Moreira,Pedro Paulo Balestrassi,Anderson Paulo de Paiva,Paulo F. Ribeiro,Benedito Donizeti Bonatto +4 more
TL;DR: A methodology for photovoltaic generation forecasting is addressed for a horizon of one week ahead, using a new approach based on an artificial neural network (ANN) ensemble, which allowed the change of the number of factors to be used in the experimental arrangement, the forecast model, and the desired forecast horizon, enhancing the forecasting determination.
Qualified Forecast of Ensemble Power Production by Spatially Dispersed Grid-Connected PV Systems
TL;DR: In this paper, an approach to predict regional PV power output based on irradiance forecasts provided by the European Centre for Medium-Range Weather Forecasts (ECMWF) is presented.
Journal ArticleDOI
Bi-model short-term solar irradiance prediction using support vector regressors
TL;DR: An accurate short-term solar irradiance prediction scheme via support vector regression using two separated regression models based on the cloud obstruction conditions near the solar disk is proposed.
Proceedings ArticleDOI
Research on short-term module temperature prediction model based on BP neural network for photovoltaic power forecasting
TL;DR: In this paper, a short-term step-wise temperature prediction model for PV module based on back propagation neural network is proposed, where the impact factors of PV module temperature are determined according to the PV module physical characteristics and the correlation coefficient.
Journal ArticleDOI
Improved model output statistics of numerical weather prediction based irradiance forecasts for solar power applications
TL;DR: In this paper, a model output statistics (MOS) method is proposed to estimate the solar irradiance of the first forecast day averaged over an ensemble of 27 stations corrected with this model, which reduces the relative root mean square error (rRMSE) to 22.7%.
References
More filters
BookDOI
Forecast verification: a practitioner's guide in atmospheric science
TL;DR: Jolliffe et al. as mentioned in this paper proposed a framework for verification of spatial fields based on binary and categorical events, and proved the correctness of the proposed framework with past, present and future predictions.
Book
Statistical Intervals: A Guide for Practitioners
TL;DR: In this article, a detailed exposition of statistical intervals and emphasizes applications in industry is presented. But the discussion differentiates at an elementary level among different kinds of statistical interval and gives instruction with numerous examples and simple math on how to construct such intervals from sample data, including confidence intervals to contain a population percentile, confidence intervals on probability of meeting specified threshold value and prediction intervals to include observation in a future sample.
Evaluation of models to predict insolation on tilted surfaces
TL;DR: In this paper, an empirical study was performed to evaluate the validity of various insolation models which employ either an isotropic or an anisotropic distribution approximation for sky light when predicting insolation on tilted surfaces.