Cloud Platform For Building Energy Consumption Prediction System Based On CFD Simulation And SVM Algorithm

Accurate prediction of building energy consumption is of great significance to energy-saving design in the early stage of architectural design or in the process of building transformation.The monitoring of micro meteorological environment in building is very important for people's healthy life and work,and it is also of great significance for further prediction of building energy consumption in the later period.This thesis starts with the temperature parameters which have a great influence on the energy consumption of the building,establishes the energy consumption prediction model of the whole building through simulation and algorithm,and finally builds a physical test platform to verify the accuracy of the prediction model.In order to predict the energy consumption of buildings more accurately,a building energy consumption prediction system based on computational fluid dynamics(CFD)simulation technology and support vector machines(SVM)algorithm is designed.Firstly,the 3D model of building is established and simulated by CFD method,and several input and output samples are obtained;the samples are divided into training set and test set.SVM algorithm is used to train training set to obtain a energy consumption prediction model;finally,the test set is put into the model for verification.The results show that the error percentage of the SVM energy consumption prediction model is [-1.133%,1.132%];after experimental test,the error percentage between the real energy consumption value and the predicted energy consumption value is [-6.211%,8.118%].When the environment conditions change,the actual energy consumption value and the predicted energy consumption value change trend is consistent.In order to monitor the indoor micro meteorological data and test the prediction model in kind,the hardware circuit system is designed.Firstly,the sensor module is used to collect indoor micro meteorological data and voltage and current data,and the actual energy consumption value of the building is calculated according to the collected voltage and current data;then,the data is sent to Alibaba cloud platform through Wi Fi communication module;finally,the software platform is developed by the separation technology of front and rear end,and users can monitor indoor micro micro data remotely and in real time through browser or mobile terminal Climate and environment information.The prediction system designed in this thesis uses the method of CFD simulation and SVM algorithm.The whole prediction system has high accuracy.The SVM algorithm of the system can achieve high prediction accuracy without too large sample set,which significantly reduces the data cost;meanwhile,through monitoring the micro meteorological data in the building,it can help users to monitor the indoor micro meteorological environment information in real time The software platform is deployed on Alibaba cloud,which can facilitate user access and data storage.These historical data can also provide support for the establishment of more accurate building energy consumption prediction system in the future.