چکیده مقاله
Predicting hourly dry bulb temperature is important and it can use for different studies like forecasting building energy consumption, architectural, agriculture and etc So, it is necessary to develop and compare forecasting methods In this study two Forecasting methods, statistical regression and exponential smoothing 5 cases and neuralnetwork 12 cases have been used to predict hourly dry bulb temperature Hourly dry bulb temperature 8760 hour is available for period of 1998 2019 of Tabriz Iran The goal of paper is predicting data of year 2019 using past available data 1998 2018 and compare mentioned methods In statistical methods, linear regression method withlow error rate has been selected as the best method with error of 4 07 for Mean Squared Error MSE , 2 02 for Root Mean Squared Error RMSE , and 0 8 for Mean Absolute Error MAE In the neural network method, best prediction case has Errors 0 8, 0 9 and 0 7 for MSE, RMSE and MAE Result shows that using regression method to predict data have high error Also using neural network method only in some special case has good agreement with data Bayesian Regularization training method: 2 layers with higher than 20 neurons
کلیدواژهها
نویسندگان
Ali Maboudi Reveshti
Department of Mechanical Engineering, Tabriz Branch, Islamic Azad University, Tabriz, Iran
Fatemeh Rafizadeh
Department of Natural Geography, Faculty of Geography, University of Tehran, Tehran, Iran
شیوه ارجاع
Maboudi Reveshti, Ali and Rafizadeh, Fatemeh,1402,Comparison of Weather Parameter Forecasting Results using Statistical and Artificial Neural Network Methods,The 8th international conference on modern architecture, geography and sustainable environment,Mashhad
ارائهشده در
مجموعه مقالات هشتمین همایش بین المللی ایده های نوین در معماری، شهرسازی، جغرافیا و محیط زیست پایدار1 شهریور 1402 · مشهد