In the absence of measuring equipment, global solar radiation can be estimated from fairly reliable models. Several researchers
have attempted to formulate models especially empirical models, which could be used to estimate global solar radiation. There has been a challenge in designing estimation models which give more reliable estimates. Other methods other than the empirical method have been explored, such as
artificial neural networks. An artificial neural networks model employs artificial intelligence techniques which are synonymous to the human brain and is built from sample data subjected to it. Artificial neural networks have been used in a broad range of applications such as classification, prediction and diagnostics. The study for which this paper was written explored the possibility of designing an estimation model using artificial neural networks, which could be used to estimate monthly average daily global solar irradiation for locations in a selected country. The design of the model employed weather station data:
sunshine duration, maximum temperature, cloud cover and location parameters: latitude, longitude, altitude. Results showed good agreement between the estimated and measured values of global solar irradiation, based on correlation and error analysis. The comparison between the artificial neural networks and empirical method emphasized the superiority of the proposed artificial neural networks model.