Estimation of Monthly Mean Daily Global Solar Radiation in Tabriz Using Empirical Models and Artificial Neural Networks
- سال انتشار: 1395
- محل انتشار: مجله انرژی تجدیدپذیر و محیط زیست، دوره: 3، شماره: 3
- کد COI اختصاصی: JR_JREE-3-3_003
- زبان مقاله: انگلیسی
- تعداد مشاهده: 202
نویسندگان
Department of Biosystems Engineering, University of Tabriz, Tabriz, Iran
Department of Biosystems Engineering, University of Tabriz, Tabriz, Iran
Department of Mechanical Engineering, University of Tabriz, Tabriz, Iran
Department of Horticultural Science, Faculty of Agriculture,, University of Tabriz, Tabriz, Iran
Department of Agricultural Machinery and Mechanization, Ramin Agriculture and Natural Resources University of Khuzestan, Mollasani, Ahvaz, Iran
چکیده
Precise knowledge ofthe amount of global solar radiation plays an important role in designing solar energy systems. In this study, by using ۲۲-year meteorologicaldata, ۱۹ empirical models were tested for prediction of the monthly mean daily global solar radiation in Tabriz. In addition, various Artificial Neural Network (ANN) models were designed for comparison with empirical models. For this purpose, the meteorological data recorded by Iran Meteorological Organization (۱۹۹۲–۲۰۱۳) was used. These data include: monthly mean daily sunshine duration, monthly mean ambient temperature, monthly mean maximum and minimum ambient temperature and monthly mean relative humidity.Theresults showed that the yearly average solar radiation in the region was ۱۶.۳۷ MJ m .Among the empirical models, the best result was acquired for model (۱۹) with correlation coefficient (r) of ۰.۹۶۶۳. Results also showed that the ANN model trained with total meteorological data in input layer (ANN۵) produces better results in comparison to others. Root Mean Square Error (RMSE) and r for this model were۱.۰۸۰۰ MJ m-۲ and ۰.۹۷۱۴, respectively. Comparison betweenthe model ۱۹ and ANN۵, demonstrated that modeling the monthly mean daily global solar radiationthrough the use of the ANNtechnique, yields better estimates. Mean Percentage Errors (MPE) for these models were ۷.۴۷۵۴% and ۱.۰۰۶۰%, respectively. -۲ day-۱کلیدواژه ها
Solar Energy, Meteorological Data Sunshine Hours, prediction, Artificial Neural Networksاطلاعات بیشتر در مورد COI
COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.
کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.