www.seipub.org/aee Advances in Energy Engineering (AEE) Volume 1 Issue 3, July 2013 66 New Regression Model to Estimate Global Solar Radiation Using Artificial Neural Network Rajesh Kumar, RK Aggarwal * and J D Sharma Department of Physics, Shoolini University, Bajhol, Solan 173 212 (India); Department of Environmental Science, Dr Y S Parmar University of Horticulture & Forestry, Nauni (Solan), 173230 (India); rajesh.shoolini@gmail.com; rajeev1792@rediffmail.com; sharmajyotid@yahoo.com Abstract The main objective of the present study was to develop a new model for the solar radiation estimation in hilly areas of North India for the determination of constants ȁaȂ and ȁbȂ by taking only latitude and altitude of the place into consideration. In this study, new model was developed based on Angstrom-Prescott Model to estimate the monthly average daily global solar radiation only using sunshine duration data. The monthly average global solar radiation data of four different locations in North India was analyzed with the neural fitting tool (nftool) of neural network of MATLAB Version 7.11.0.584 (R2010b) with 32-bit (win 32). The neural network model was used with 10 hidden neurons. Eight months data was used to train the neural network. Two months data was used for the validation purpose and the remaining two months for the testing purpose. The new developed model estimated the values of ȁaȂ which range from Ŗ.ŘŖş to Ŗ.ŘŘŘ and values of ȁbȂ ranging from 0.253 to 0.407. The values of maximum percentage error (MPE) and mean bias error (MBE) were in good agreement with the actual values. Artificial neural network application showed that data was best fitted for the regression coefficient of 0.99558 with best validation performance of 0.85906 for Solan. This will help to advance the state of knowledge of global solar radiation to the point where it has applications in the estimation of monthly average daily global solar radiation. Keywords Artificial Neural Network; Global Solar Radiation; Extraterrestrial Radiation; Solar Constant; Sunshine Hour Research Highlights  Development of new model for solar energy estimation  Use of Artificial Neural Network to analyze global solar radiation  Regression coefficient representation  Graphical representation of the best validation performance Introduction Solar radiation data are required in different areas, such as solar water heating, wood drying, stoves, ovens, photovoltaic, atmospheric energy balance studies, thermal load analyses on buildings, agricultural studies, and meteorological forecasting which should be reliable and readily available for design, optimization and performance evaluation of solar technologies for any particular location as given by Bezir et al. (2010) and El-Sebaii et al. (2010). Compared to measurements of other meteorological variables, the measurement of solar radiation is more prone to errors and often encounters more problems such as technical failure and operation related problems given by Tang et al. (2010). These problems could be one of many: calibration problems, problems with dirt on the sensor, accumulated water, shading of the sensor by masts, etc. Even at stations where global solar radiation is observed, there could be many days when global solar radiation data are missing or lie outside the expected range due to these equipment failures and other problems as given by Rahimikhoob (2010). Nevertheless, for many developing countries, solar radiation measurements are not easily available because of the incapability to afford the measuring equipments and techniques involved as given by Bezir et al. (2010). Therefore, it is necessary to develop methods to predict solar radiation from the available meteorological data. Himachal Pradesh is located in north India with Latitude 30 o 22' 40" N to 33 o 12' 40" N, Longitude 75 o 45' 55" E to 79 o 04' 20" E, height (From mean sea Level) 350 meter to 6975 meter and average rainfall 1469 mm. The study has been initiated by introducing different