Estimation of solar power generating capacity

摘要: Solar energy is one of the most promising renewable sources. In order to integrate this type source into an existing power distribution system, system planners need accurate model that predicts availability generating capacity. resources are known exhibit a high variability in space and time due influence other climatic factors such as cloud cover. The probability irradiance fluctuations difficult predict various uncertainties. For efficient conversion utilization solar resource, resource modelling essential tools for proper development, planning, maintenance scheduling pricing system. This paper proposes Mathematical Neural Network Prediction models estimation radiation Singapore. Meteorological geographical data (latitude, longitude, altitude, month, mean sunshine duration, etc.) were used inputs models. estimated results compared with field obtained from pyranometer installed on panel tilt 15°. relevance performance each Singapore's weather context then evaluated using statistical tools, namely Mean Bias Error, Root Squared Error Absolute Percentage Error. show correlation coefficients between proposed actual daily higher than 90%, thus suggesting reliability evaluation received These can be easily preliminary design applications.