Some Applications of ANN to Solar Radiation Estimation and Forecasting for Energy Applications

Jean Laurent Duchaud,Alexis Fouilloy,Marie Laure Nivet,Gilles Notton,Cyril Voyant

doi:10.3390/app9010209

Abstract

In solar energy, the knowledge of solar radiation is very important for the integration of energy systems in building or electrical networks. Global horizontal irradiation (GHI) data are rarely measured over the world, thus an artificial neural network (ANN) model was built to calculate this data from more available ones. For the estimation of 5-min GHI, the normalized root mean square error (nRMSE) of the 6-inputs model is 19.35%. As solar collectors are often tilted, a second ANN model was developed to transform GHI into global tilted irradiation (GTI), a difficult task due to the anisotropy of scattering phenomena in the atmosphere. The GTI calculation from GHI was realized with an nRMSE around 8% for the optimal configuration. These two models estimate solar data at time, t, from other data measured at the same time, t. For an optimal management of energy, the development of forecasting tools is crucial because it allows anticipation of the production/consumption balance; thus, ANN models were developed to forecast hourly direct normal (DNI) and GHI irradiations for a time horizon from one hour (h+1) to six hours (h+6). The forecasting of hourly solar irradiation from h+1 to h+6 using ANN was realized with an nRMSE from 22.57% for h+1 to 34.85% for h+6 for GHI and from 38.23% for h+1 to 61.88% for h+6 for DNI.

Highlights

Solar thermal or electrical systems require high quality solar radiation measurement instruments in order to accurately measure solar energy received on the plant
The minimum normalized root mean square error (nRMSE) was obtained for the 10 inputs model with a value of 18.65% compared to 73.91% for the worst configuration (2 inputs: WD and WS)
DNIthe values of the performance metrics computed on the test data set

Summary

Introduction

Solar thermal or electrical systems require high quality solar radiation measurement instruments in order to accurately measure solar energy received on the plant. Investments and maintenance costs for each measurement site are not negligible and even in industrialized countries, the national network often consists in a relatively small number of solar radiation stations [2]; and the measurement quality varies from a network to another, often by lack of maintenance and calibration. The measuring devices’ price is an important part of the process cost of collecting solar data, especially for non-profit institutions, such as schools or universities [2]. The amount of meteorological stations measuring solar irradiance through the world is difficult to count because various sources give different information [3]. Only 1000 continental stations around the world are measuring solar radiation [4]

Methods

Results

Conclusion