Research On Energy Consumption Prediction Model And Supervision System Of Large Public Buildings

At present,the operation energy consumption of large public buildings in China accounts for more than 20% of the total energy consumption in urban areas,and the energy use efficiency is about 30%,which has the typical characteristics of "high energy consumption and low energy efficiency".At the same time,the domestic large public building energy consumption data is extensive,the lack of scientific use of energy supervision and prediction,seriously hindered the development of large public buildings energy saving work.Therefore,the research of large public building energy consumption prediction model and regulatory system is particularly important.The research contents of this paper include the following four aspects:(1)Under the background of smart city,we describe the Internet of things architecture,cloud computing data center and big data regulatory platform of large-scale public building energy consumption supervision system.At the same time,the edge calculation model of the large-scale public building energy consumption supervision system is put forward,which aims to reduce the data center of the cloud computing by preprocessing and standardization of energy consumption data.(2)Based on embedded industrial control machine,the energy consumption measurement system of large public buildings is designed through LabView development platform and MySQL database,and the functions of collecting,storing and analyzing energy consumption data are realized.(3)The equipment capacity,load grade,operation time and equipment failure rate are selected as the evaluation indexes of the deployment optimization of the electric energy metering device of large public buildings.The weight vector of each evaluation index is determined by the analytic hierarchy process,and the fuzzy evaluation model is built to optimize the deployment of the metering device.Taking a large public building as an example,through optimization,its electric energy metering device is reduced by 30.4%,and the equipment cost and data storage cost decrease by 28.8% and 30.4%,respectively.(4)Based on BP neural network and NAR neural network,a large-scale public building energy consumption prediction model is established.Taking the energy consumption data of an office building as a sample,the prediction accuracy of the two models is evaluated by mean relative error and average absolute error.The results show that the NAR neural network model has a good prediction effect for the prediction of the energy consumption of large public buildings with time series characteristics.Through the study of the energy consumption prediction model and supervision system of large public buildings,the energy consumption of large public buildings can be grasps fully and clearly,and a reasonable energy saving control strategy is made,which is of great significance to the energy saving and consumption reduction of large public buildings.