Title: Cooling Load Prediction by Weather Conditions using Taguchi and Neural Network Method
Abstract: The energy performance in the building is highly affected by several factors including weather conditions, building architectural configuration, material, and building operation such as occupancy, equipment, lighting and HVAC system. Accurate cooling load prediction can help energy management to optimize cooling energy consumption in the building. This paper studies the effect of several weather parameters including dry bulb and dew point temperature, direct normal and diffuse horizontal radiation, and wind speed on the cooling load for predicting cooling load. Several data sets of cooling load and various weather conditions were generated hourly using Energy Plus software. Static neural network model was developed to estimate cooling load using orthogonal arrays of weather parameter. Furthermore, analysis of variance was utilized to analyze the effect of each weather parameter. The results show that diffuse horizontal radiation, dew point and dry bulb temperature has significant effect on cooling load and considered as important parameters for cooling load prediction.
Publication Year: 2015
Publication Date: 2015-11-01
Language: en
Type: article
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot