期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：4
页码：7292
DOI：10.15680/IJIRCCE.2017.05040138
出版社：S&S Publications
摘要：Galaxy position based solar power prediction system is a prediction system used to aid the design ofsolar power systems more accurately irrespective of the climate conditions, geographical locations and availability ofsun light. This ensures the design of solar power system which ensures the availability of minimum powerrequirements. The application aims to build a tool in designing the solar power systems irrespective of location andclimate conditions. This basically calculates the availability of sun light of any location from the provided locationsgeographical coordinates and the time of installation provided. Calculates suns position at time and angle of incident oflight on earths provided location. Based on this availability of sun light and climate conditions we calculate the no ofcells required to cater the needs to our power consumption. Also this application gives expert opinion on the angle ofinstallation of the solar panels. This also takes care of the climate conditions. The forecasts are based on previouspower output and weather data, and weather prediction for the next day. We present a new approach that forecasts allthe power outputs for the next day simultaneously. It builds separate prediction models for different types of days,where these types are determined using clustering of weather patterns. As prediction models it uses ensembles of neuralnetworks, trained to predict the power output for a given day based on the weather data. This application has thefollowing modules including location identifier, climate Fetcher, prediction Logic .Based on the information collectedby the above modules the system gives the detailed deployment specifications to the user, using these technicians candesign a solar system which satisfies the power requirements in all climate conditions
关键词：Solar tracking; PV; Machine Learning; GPS; ANN
