cqu_8561+ATTACHMENT01+ATTACHMENT01.3.pdf (651.76 kB)
Download file

Historical weather data supported hybrid renewable energy forecasting using artificial neural network (ANN)

Download (651.76 kB)
This paper aims to develop a novel hybrid system for wind and solar energy forecasting. The uniqueness or novelty of the proposed system is obvious because there are no available research works related to the hybrid forecasting system of renewable energy. The proposed "Hybrid (wind-solar) Energy Forecasting Model‟ is dedicated to short-term forecasting (three-hour ahead) based on artificial neural network (ANN) learning algorithm. The network learning or training algorithm will be implemented using ANN Toolbox which is widely used simulation software incorporated in MATLAB. Eleven different climatological parameters of the last six years of a typical subtropical climate based area Rockhampton in Central Queensland; Australia has been taken for analysis investigation purpose and will be considered as the inputs of ANN model for hybrid (wind-solar) energy forecasting. The ANN will be trained in such a way that with minor modifications in the programming codes, it can perform the hybrid forecasting within the range from hourly (short term forecasting) to daily (medium term forecasting). This feature is one of the major innovations and indicating the great robustness of the proposed hybrid renewable energy forecasting system. As the hybrid forecasting system is quite a novel approach, the accuracy of the system will be revealed by comparing the results with the corresponding values of stand-alone forecasting model referred to as the persistent model. Finally, the fully developed system package may be commercialized and/or utilized in further research projects for researchers to analyze, validate and visualize their models on related domains.

Funding

Category 3 - Industry and Other Research Income

History

Volume

14

Start Page

1035

End Page

1040

Number of Pages

6

eISSN

1876-6102

Location

Netherlands

Publisher

Elsevier

Language

en-aus

Peer Reviewed

Yes

Open Access

Yes

External Author Affiliations

Faculty of Sciences, Engineering and Health; Institute for Resource Industries and Sustainability (IRIS); Power Engineering Research Group;

Era Eligible

Yes

Journal

Energy procedia.