Abstract

High quality of solar radiation data is essential for solar resource assessment. For remote areas this is a challenge, as often only satellite data with low spatial resolution are available. This paper presents an interpolation method based on topographic data in digital elevation model format to improve the resolution of solar radiation maps. The refinement is performed with a data mining method based on first-order Sugeno type Adaptive Neuro-Fuzzy Inference System. The training set contains topographic characteristics such as terrain aspect, slope and elevation which may influence the solar radiation distribution. An efficient sampling method is proposed to obtain representative training sets from digital elevation model data. The proposed geographic information system based approach makes this method reproducible and adaptable for any region. A case study is presented on the remote Amhara region in North Shewa, Ethiopia. Results are shown for interpolation of solar radiation data from 10 km × 10 km to a resolution of 1 km × 1 km and are validated with data from the PVGIS and SWERA projects.

Highlights

  • Solar energy yield is related to the quantity of radiation received at a specific geographical location which in turn depends on a number of environmental factors

  • The data mining model has been implemented with Matlab Adaptive Neuro-Fuzzy Inference System (ANFIS)

  • With the trained ANFIS model, solar radiation is estimated for the entire region under study with a resolution of 1 km × 1 km

Read more

Summary

Introduction

Solar energy yield is related to the quantity of radiation received at a specific geographical location which in turn depends on a number of environmental factors. There are other factors such as temperature, but still, estimation of solar radiation is fundamental requisite for siting of photovoltaic and solar thermal installations. These estimations are calculated from radiation data obtained in meteorological stations or on-site measurements but satellite data is gaining more and more importance. Accurate modeling of solar radiation is a difficult job due to the high number of atmospheric parameters and their spatio-temporal variations. It received special attention over the last three decades due to the rise of solar applications worldwide. Image processing models based on data obtained from satellite observations with ground measurement validation

Classical Solar Resource Data Modeling Approaches
Solar Resource Modeling Based on GIS
Solar Resource Modeling Based on Satellite Data
Proposed Resource Modeling with Data Mining
General Considerations
Data Mining Using ANFIS
Case Study
Definition of ANFIS Training Parameters
Representative Data Sampling for ANFIS Training
Training of Neuro-Fuzzy Network
Estimation of High-Resolution Radiation Data
Validation of Results
Findings
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call