A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct Solar Radiation

Boussaada, Zina; Curea, Octavian; Remaci, Ahmed; Camblong, Haritza; Bellaaj, Najiba Mrabet

doi:10.3390/en11030620

Cited by 256 publications

(120 citation statements)

References 33 publications

Supporting

Mentioning

115

Contrasting

Unclassified

Order By: Relevance

“…Nonlinear autoregressive with exogenous input (NARX) neural network is used in this study to predict and forecast TWS GRACE time series over ten African watersheds. Given our previous knowledge of the spatiotemporal variabilities in TWS GRACE over the African watersheds and how they are controlled by natural and anthropogenic interventions [9,74], NARX model was selected because it provides effective, efficient, and powerful (1) nonlinear systems modelling and predictive tool, (2) learning algorithm that discovers, and is not affected by, the long temporal dependence in the model outputs and/or inputs [75,76], and (3) faster convergence in reaching the optimal weights of the connections between neurons and/or inputs [77][78][79][80].…”

Section: Introductionmentioning

confidence: 99%

Forecasting GRACE Data over the African Watersheds Using Artificial Neural Networks

et al. 2019

View full text Add to dashboard Cite

The GRACE-derived terrestrial water storage (TWS GRACE ) provides measurements of the mass exchange and transport between continents, oceans, and ice sheets. In this study, a statistical approach was used to forecast TWS GRACE data using 10 major African watersheds as test sites. The forecasted TWS GRACE was then used to predict drought events in the examined African watersheds. Using a nonlinear autoregressive with exogenous input (NARX) model, relationships were derived between TWS GRACE data and the controlling and/or related variables (rainfall, temperature, evapotranspiration, and Normalized Difference Vegetation Index). The performance of the model was found to be "very good" (Nash-Sutcliffe (NSE) > 0.75; scaled root mean square error (R*) < 0.5) for 60% of the investigated watersheds, "good" (NSE > 0.65; R* < 0.6) for 10%, and "satisfactory" (NSE > 0.50; R* < 0.7) for the remaining 30% of the watersheds. During the forecasted period, no drought events were predicted over the Niger basin, the termination of the latest (March-October 2015) drought event was observed over the Zambezi basin, and the onset of a drought event (January-March 2016) over the Lake Chad basin was correctly predicted. Adopted methodologies generate continuous and uninterrupted TWS GRACE records, provide predictive tools to address environmental and hydrological problems, and help bridge the current gap between GRACE missions.

show abstract

Section: Introductionmentioning

confidence: 99%

Forecasting GRACE Data over the African Watersheds Using Artificial Neural Networks

et al. 2019

View full text Add to dashboard Cite

show abstract

“…A feed-forward automatic nonlinear NARX (nonlinear autoregressive network with exogenous) method, which uses measured values as inputs to dynamic neural networks, was employed to improve the predictive performance of the model. The NARX method is preferred to predict a time series dataset [20,21]. Figure 2 shows the schematic diagram of the predictive model of chiller energy consumption using the ANN model.…”

Section: Development Of a Predictive Model Of Energy Consumption Of Tmentioning

confidence: 99%

Modeling and Optimizing a Chiller System Using a Machine Learning Algorithm

2019

View full text Add to dashboard Cite

This study was conducted to develop an energy consumption model of a chiller in a heating, ventilation, and air conditioning system using a machine learning algorithm based on artificial neural networks. The proposed chiller energy consumption model was evaluated for accuracy in terms of input layers that include the number of input variables, amount (proportion) of training data, and number of neurons. A standardized reference building was also modeled to generate operational data for the chiller system during extended cooling periods (warm weather months). The prediction accuracy of the chiller’s energy consumption was improved by increasing the number of input variables and adjusting the proportion of training data. By contrast, the effect of the number of neurons on the prediction accuracy was insignificant. The developed chiller model was able to predict energy consumption with 99.07% accuracy based on eight input variables, 60% training data, and 12 neurons.

show abstract

“…A comparative study of the impact of horizontal-to-tilted solar irradiance conversion in modelling small PV array performance was presented in [22]. A neural network model was employed to predict daily direct solar radiation in [23]. Frydrychowicz-Jastrzębska et al compared selected isotropic and anisotropic mathematical models to calculate the distribution of solar radiation on the photovoltaic module plane with any spatial orientation for Poland [24].…”

Section: State Of the Artmentioning

confidence: 99%

A Comprehensive Approach for Modelling Horizontal Diffuse Radiation, Direct Normal Irradiance and Total Tilted Solar Radiation Based on Global Radiation under Danish Climate Conditions

et al. 2018

View full text Add to dashboard Cite

A novel combined solar heating plant with flat plate collectors (FPC) and parabolic trough collectors (PTC) was constructed and put into operation in Taars, 30 km north of Aalborg, Denmark in August 2015. To assess the thermal performance of the solar heating plant, global radiation, direct normal irradiance (DNI) and total radiation on the tilted collector plane of the flat plate collector field were measured. To determine the accuracy of the measurements, the calculated solar radiations, including horizontal diffuse radiation, DNI and total tilted solar radiation with seven empirical models, were compared each month based on an hourly time step. In addition, the split of measured global radiation into diffuse and beam radiation based on a model developed by DTU (Technical University of Denmark) and the Reduced Reindl correlation model was investigated. A new method of combining empirical models, only based on measured global radiation, was proposed for estimating hourly total radiation on tilted surfaces. The results showed that the DTU model could be used to calculate diffuse radiation on the horizontal surface, and that the anisotropic models (Perez I and Perez II) were the most accurate for calculation of total radiation on tilted collector surfaces based only on global radiation under Danish climate conditions. The proposed method was used to determine reliable horizontal diffuse radiation, DNI and total tilted radiation with only the measurement of global radiation. Only a small difference compared to measured data, was found. The proposed method was cost-effective and needed fewer measurements to obtain reliable DNI and total radiation on the tilted plane. This method may be extended to other Nordic areas that have similar weather.

show abstract

A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct Solar Radiation

Cited by 256 publications

References 33 publications

Forecasting GRACE Data over the African Watersheds Using Artificial Neural Networks

Forecasting GRACE Data over the African Watersheds Using Artificial Neural Networks

Modeling and Optimizing a Chiller System Using a Machine Learning Algorithm

A Comprehensive Approach for Modelling Horizontal Diffuse Radiation, Direct Normal Irradiance and Total Tilted Solar Radiation Based on Global Radiation under Danish Climate Conditions

Contact Info

Product

Resources

About