Retraction Note to: Potential of support vector regression for solar radiation prediction in Nigeria (original) (raw)

ABSTRACT In this paper, the accuracy of soft computing technique in solar radiation prediction based on series of measured meteorological data (monthly mean sunshine duration, monthly mean maximum and minimum temperature) taking from Iseyin meteorological station in Nigeria was examined. The process, which simulates the solar radiation with support vector regression (SVR), was constructed. The inputs were monthly mean maximum temperature (T max), monthly mean minimum temperature (T min) and monthly mean sunshine duration ( \( \bar{n} \) ). Polynomial and radial basis functions (RBF) are applied as the SVR kernel function to estimate solar radiation. According to the results, a greater improvement in estimation accuracy can be achieved through the SVR with polynomial basis function compared to RBF. The SVR coefficient of determination R 2 with the polynomial function was 0.7395 and with the radial basis function, the R 2 was 0.5877.

The performance of solar radiation distribution models is highly dependent on the location of use. This makes the need for location dependent validation necessary. An empirical validation of three solar radiation distribution models was carried out in this work using empirical data obtained from the Nigeria Meteorological Agency (NIMET). The models include the Angstrom-Prescott, Hargreaves and Garcia model. Four standard statistical tools of correlation ratio (R), mean bias error (MBE), mean percentage error (MPE), root mean square error (RMSE) were used for the validation. Results from the work reveal that the Angstrom-Prescott model had the least MBE with an average value of 0.1 making it the most reliable among the three models. In terms of MPE values, the Angstrom-Prescott model also performed best with an average MPE value of 0.1 while the Hargreaves and Garcia model had an average MPE performance of 0.2 and 0.15 respectively. In terms of the RMSE and correlation ratio, the Ang...

The performance of both temperature and sunshine dependent models were evaluated for different selected tropical sites, which are situated across four different climatic zones, viz. Sahelian, Guinea Savannah, Midland and Coastal area in Nigeria. The regression constants were obtained for the first, second and third order Angstrom type [Garcia J V, Principios F'isicos de la Climatolog'ia. Ediciones UNALM (Universidad Nacional Agraria La Molina: Lima, Peru), 1994; Hargreaves G & Samani Z, Estimating potential evapotranspiration, J Irrigat Drainage Eng (USA), 108 (1982) pp 225-230] models for all the stations using the method of regression analysis. Model evaluation performance analyses were carried out to determine which model is more suitable for a given climatic condition. The results indicated that the third order Angstrom type correlations do not improve the accuracy of estimation of global radiation. In addition, the results also revealed that temperature and sunshine hou...

In this paper, the value of monthly average global solar radiation for Yola area has been estimated using different empirical models. The values of monthly average global solar radiation were calculated using the regression constants in the models (both linear and quadratic). The predictive efficiency was validated and compared based on mean percentage error (MPE), mean biased error (MBE) and root mean square error (RMSE). On comparison it was observed that the quadratic model is overall more accurate for calculating the Global Solar Radiation for Yola region, because of the fine agreement found between the estimated and the measured values and may be used reasonably well for estimating the solar radiation at a given location and possibly in elsewhere with similar climatic conditions.

A model for estimating sunshine hours from some meteorological parameters was developed. Ten years (2001-2010) period of Sunshine hour and Solar radiation at Maiduguri, Nigeria (11.85 o N, longitude is 13.08°E) was analyzed. A correlation equation of the Angstrom type was developed to predict the monthly mean daily global solar radiation incident on a horizontal surface in Maiduguri, Nigeria: ̅ ̅ =. +. ̅ ̅. The statistical error estimations such as RMSE, MPE and MBE used to test the correlation between the measured global solar radiation and the calculated global solar radiation. The RMSE was found to be 0.05 as low as expected, the MBE was also found to be 0.015 and MPE to be 0.062 values are low. The developed model can be used in estimating global solar radiation for Port Harcourt and other locations with similar climatic conditions.