User behavior-based method for optimizing building energy conservation design in severe cold areas

Abstract

The invention discloses a user behavior-based method for optimizing building energy conservation design in severe cold areas. The method comprises the following steps of: aiming at special weather conditions in severe cold areas, carrying out analysis by utilizing survey data so as to obtain a building design parameter set of actuating energy conservation behaviors; learning behavior measured data by applying a machine learning algorithm in a data mining technology so as to obtain a more correct user random behavior mode; obtaining an optimization energy conservation performance design parameter set through a behavior mode optimization traditional prediction model and a Bayesian theory-based Gaussian process correction prediction model; coupling the actuating energy conservation behaviors and the optimization energy conservation performance design parameter set to obtain an optimized parameter set; and finally combining an optimal design parameter set and an energy consumption prediction model to establish a new process for building energy conservation design in the severe cold areas. According to the method disclosed by the invention, the influences, on the prediction models, of uncertainty can be reduced, and a more optimal parameter screening process, more correct energy conservation effect prediction, a more rational building energy conservation design process and a more correct estimated building design result can be obtained.

Description

technical field [0001] The invention belongs to the technical field of building energy conservation, and in particular relates to a design optimization method for building energy conservation in severe cold regions based on user behavior. Background technique [0002] Building energy-saving design is an interdisciplinary research involving many fields and disciplines. Under the background of the rapid development of digital technology and the trend of building performance-based design, building energy-saving design is not only related to the research of building energy consumption prediction, but also closely related to the development of digital simulation technology and machine learning technology. [0003] At present, building energy consumption prediction methods mainly include time series method, Fourier series models, regression models, artificial neural network models and fuzzy logic models, etc. Although the building energy consumption prediction model has been init...

AI Technical Summary

Problems solved by technology

In the current simulation analysis work, more emphasis is often placed on meteorological parameters, enclosure structures, and equipment systems, and human behavior is mostly described in a simplified manner, which cannot effectively reflect the various significant impacts of human behavior. Therefore, In many cases, the simulation analysis results deviate greatly from the actual situation, which affects the accuracy of analysis, prediction and evaluation of building energy consumption

Since the existing building energy consumption and performance simulation platform cannot accurately and specifically describe the behavior of building users, the simulation results are difficult to reflect the actual energy consumption level and building performance after the building plan is completed, resulting in prediction results and The actual data has a large deviation

Due to the lack of detailed description of the characteristics of the users, the performance of some architectural technical measures in the actual building cannot be reasonably reflected in the simulation calculation, and the simulation evaluation conclusion is likely to be inconsistent with the actual measurement.

Due to the motivating factors of user behavior, there is still a lack of in-depth research related to architectural design elements, which cannot provide theoretical support for building energy-saving design that promotes energy-saving behavior of users

Images