Research On The Intelligent Control Technology Of Energy Consumption Statistics Analysis And Forecast Optimization Of Campus Buildings

Rapid development of economy witnesses the increasing number of large-scale public buildings and the increasingly serious contradiction between their high energy .consumption and energy shortage in our country, which has already drawn people's attention. Colleges, as one of the important members of society, own a large number of large-scale buildings and consume more and more energy, which far exceeds consumption per capita consumption of China's national energy. In recent years, to respond to the'national call of "building a resource-saving and environment-friendly society", domestic colleges carry out a series of policies to build a conservation-oriented campus, such as to establish the energy management system and to monitor energy consumption in campus. The main work of this paper will be carried out in this aspect.Chapter one first introduces the background and significance of the construction of a conservation-oriented campus, analyzes and summarizes the current situation of conservation-oriented campus, which leads to the significance and content of this paper, as well as the organizational structure herein. Then, drawing on the experience of campus energy regulation system construction in domestic universities, such as Zhejiang University and Beijing Institute of Technology, this paper proposes an intelligent control platform of campus building energy consumption for a certain university, and build this platform with Internet of Things, cloud computing and other related mature technology. Chapter three introduces statistical indicators of campus building energy consumption, explains the composition of evaluation indicators for campus buildings total energy consumption, focusing on the calculation methods of statistical indicators on electricity consumption and water consumption and thus proposes the campus building energy-saving indicators based on the practical use. Chapter four will explore how to analyze, process and unload the campus energy consumption data captured by real-time sensing device, and compare and rank with statistical methods. Chapter five focus on the intelligent control of the platform, analyzing the factors affecting energy consumption, constructing prediction model of campus building energy consumption with intelligent arithmetic and explaining it in detail. Chapter six is for the test and application of the platform and model proposed above. It first summarizes the content of Chapter three and four and apply to conduct energy consumption statistics, and then use the model in Chapter five to make experimental tests and compare the predicted results obtained from optimized BP neural network based on GA and the common one, which shows that predicted result based on improved genetic algorithm is better than the other one. After that, we choose a campus building to conduct the practical application of the model, capturing its alarm data, whose results also show that the model can relatively predict accurate data to be used in the platform. In summary, the proposed model can correctly assist the formulation of relevant rules and measures to provide technical means for the construction of a conservation-oriented campus.