Analytic method, system and electronic device for building energy consumption

Abstract

To provide an analytic method for building energy consumption, an analytic system for building energy consumption, and an electronic device that have higher precision of an analysis result and provide real-time analysis.SOLUTION: A method includes the steps of: obtaining a sample data set including building energy consumption data and building-related data; determining, based upon the building-related data, feature data items including the geographic location, total area, height, direction, outer covering, ambient humidity, outdoor wind velocity, direct solar radiation load, outdoor ground surface temperature, and average ambient temperature; acquiring a training data set based upon the feature data items; training a machine-learning model based upon the training data set to obtain an analytic model for energy consumption; and analyzing the energy consumption based upon the analytic model for energy consumption.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to the field of building energy consumption analysis, and more particularly to a method, system and electronic device for analyzing building energy consumption. [Background technology]

[0002] At present, among various methods to resolve the contradiction between economic development and energy shortage, building energy conservation is considered to be the most direct and effective, and in order to realize building energy conservation, the building energy consumption must be accurately analyzed. Under this background, the analysis of building energy consumption has gradually become a research hotspot in the field of building energy conservation. Existing building energy consumption analysis mainly involves predictive analysis based on past energy consumption data, that is, obtaining the energy consumption rule of the target building based on the past energy consumption data of the target building, and then predicting the energy consumption of the target building at a specific time point in the future based on the energy consumption rule. However, such a building energy consumption analysis method based on past energy consumption data mainly has the following two problems:

[0003] First, the energy consumption rules obtained based on past energy consumption data cannot objectively and faithfully reflect the current and future energy consumption situations of the target building, and the analysis results have low accuracy and are suitable as auxiliary references.

[0004] Second, it is essentially a predictive method and does not allow for real-time analysis of building energy consumption. Summary of the Invention

[0005] The present invention aims to solve the problem that existing methods for analyzing building energy consumption based on past energy consumption data produce analysis results with low accuracy and make it impossible to realize real-time analysis.

[0006] In order to achieve the above object, the present invention provides a method, a system, and an electronic device for analyzing building energy consumption.

[0007] According to a first aspect of the present invention,

[0008] cleaning and labeling the pre-acquired source data to obtain a sample dataset including building energy consumption data and corresponding building-related data;

[0009] performing feature selection of the building related data against the building energy consumption data to determine feature data items including building geolocation, building total area, building height, building orientation, building envelope, building outdoor humidity, building outdoor wind speed, building direct solar load, building outdoor ground surface temperature, and building average outdoor temperature;

[0010] sampling the sample data set based on the determined feature data items to obtain a training data set;

[0011] training a pre-obtained machine learning model based on the training dataset to obtain an analytical model of building energy consumption;

[0012] and analyzing the building energy consumption based on the analytical model of the building energy consumption.

[0013] Optionally, the method for obtaining source data includes:

[0014] How to read the imported data file,

[0015] Based on a previously accessed database,

[0016] A method for receiving corresponding environmental parameters uploaded by the environmental parameter sensors is included.

[0017] Optionally, said step of performing feature selection of said building related data for said building energy consumption data is realized based on a PCA algorithm or a KPCA algorithm.

[0018] Optionally, the characteristic data items further include the outdoor air density of the building, the occupancy of the building and the total heat gain of the building.

[0019] Optionally, after the step of obtaining an analytical model of building energy consumption,

[0020] The method further includes optimizing the analytical model of building energy consumption based on a previously acquired test data set.

[0021] Optionally, the machine learning model is a support vector machine model.

[0022] According to a second aspect of the present invention,

[0023] a sample dataset acquisition module, which is used for cleaning and labeling the pre-acquired source data to obtain a sample dataset including building energy consumption data and corresponding building-related data;

[0024] a feature selection module, which is used for performing feature selection of the building-related data on the building energy consumption data to determine feature data items including a building geolocation, a building total area, a building height, a building orientation, a building envelope, a building outdoor humidity, a building outdoor wind speed, a building direct solar radiation load, a building outdoor ground surface temperature, and a building average outdoor temperature;

[0025] a training dataset obtaining module, which is used for sampling the sample dataset based on the determined feature data items to obtain a training dataset;

[0026] an analysis model acquisition module of building energy consumption, which is used to train a pre-acquired machine learning model based on the training data set to obtain an analysis model of building energy consumption;

[0027] A building energy consumption analysis system is provided, which includes a building energy consumption analysis implementation module and a functional module for analyzing building energy consumption based on the building energy consumption analysis model.

[0028] Optionally, the characteristic data items further include the outdoor air density of the building, the occupancy of the building and the total heat gain of the building.

[0029] According to a third aspect of the present invention, there is provided an electronic device including a processor and a memory, and realizing any one of the above-mentioned building energy consumption analysis methods when the processor executes a computer program stored in the memory.

[0030] The beneficial effects of the present invention are as follows:

[0031] The building energy consumption analysis method of the present invention first cleans and labels pre-acquired source data to obtain a sample dataset including building energy consumption data and corresponding building-related data, then performs feature selection of the building-related data for the building energy consumption data to determine feature data items including building geolocation, building total area, building height, building orientation, building envelope type, building outdoor humidity, building outdoor wind speed, building direct solar radiation load, building outdoor ground surface temperature and building average outdoor temperature, further samples the sample dataset based on the determined feature data items to obtain a training dataset, and then trains a pre-acquired machine learning model based on the training dataset to obtain an analysis model of building energy consumption, and finally analyzes building energy consumption based on the analysis model of building energy consumption.

[0032] The building energy consumption analysis method of the present invention performs feature selection of building-related data for building energy consumption data, obtains a training data set based on the determined feature data items, trains a machine learning model based on the training data set to obtain an analytical model of building energy consumption, and further analyzes building energy consumption based on the analytical model of building energy consumption. Compared with existing building energy consumption analysis methods based on past energy consumption data, the building energy consumption analysis method of the present invention realizes the analysis of building energy consumption based on the principle of data mining, and the accuracy of the analysis result is higher. In addition, the building energy consumption analysis method of the present invention can analyze the energy consumption of a building in real time based on the feature data acquired in advance and the feature data acquired in real time through the analytical model of building energy consumption.

[0033] From the above two aspects, it can be seen that by adopting the building energy consumption analysis method of the present invention, the problem that the analysis results of existing building energy consumption analysis methods based on past energy consumption data have low accuracy and cannot realize real-time analysis can be effectively solved.

[0034] The building energy consumption analysis system and electronic device of the present invention belong to the same general inventive concept as the above-mentioned building energy consumption analysis method and have at least the same beneficial effects as the above-mentioned building energy consumption analysis method, and therefore, their beneficial effects will not be described in detail here.

[0035] Other features and advantages of the present invention are described in detail in the Detailed Description section below. [Brief description of the drawings]

[0036] The present invention may be better understood by reference to the following description in conjunction with the drawings, in which the same or similar reference numerals are used throughout to represent the same or similar parts.

[0037] [Figure 1] 2 is a flowchart illustrating the implementation of a method for analyzing building energy consumption according to an embodiment of the present invention.

[0038] [Diagram 2] 1 is a block diagram showing the structure of a building energy consumption analysis system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0039] In order to allow those skilled in the art to more fully understand the technical solution of the present invention, the following will describe exemplary embodiments of the present invention in conjunction with the drawings in a more comprehensive and detailed manner. Of course, one or more embodiments of the present invention described below are merely one or more specific forms that can realize the technical solution of the present invention, and are not exhaustive. It should be understood that the technical solution of the present invention can be realized in other forms that belong to the general inventive concept, and should not be limited to the embodiments described for illustrative purposes. Based on one or more embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts should fall within the protection scope of the present invention.

[0040] FIG. 1 is a flowchart showing the implementation of the building energy consumption analysis method according to the embodiment of the present invention. As shown in FIG. 1, the building energy consumption analysis method according to the embodiment of the present invention includes:

[0041] Step S100 of cleaning and labeling pre-acquired source data to obtain a sample data set including building energy consumption data and corresponding building-related data;

[0042] S200: performing feature selection of the building-related data for the building energy consumption data to determine feature data items including a building geolocation, a building total area, a building height, a building orientation, a building envelope, a building outdoor humidity, a building outdoor wind speed, a building direct solar radiation load, a building outdoor ground surface temperature, and a building average outdoor temperature;

[0043] Sampling the sample data set based on the determined feature data items to obtain a training data set S300;

[0044] Step S400 of training a pre-obtained machine learning model based on the training data set to obtain an analytical model of building energy consumption;

[0045] and analyzing the building energy consumption based on the analysis model of the building energy consumption (S500).

[0046] Further, in step S100 of the embodiment of the present invention, the method for obtaining the source data includes:

[0047] How to read the imported data file,

[0048] Based on a previously accessed database,

[0049] A method for receiving corresponding environmental parameters uploaded by the environmental parameter sensors is included.

[0050] Furthermore, in step S200 of an embodiment of the present invention, the step of performing feature selection of the building-related data for the building energy consumption data is realized based on a PCA algorithm or a KPCA algorithm.

[0051] In addition, in step S200 of an embodiment of the present invention, the characteristic data items further include the outdoor air density of the building, the occupancy rate of the building, and the total heat gain of the building.

[0052] Specifically, in an embodiment of the present invention, the geographic location of the building is the coordinates of the building, and the height of the building is the height of the building above ground. The building envelope is divided into transparent and opaque parts, the opaque envelope includes walls, roofs and floors, and the transparent envelope includes windows, skylights, balconies and doors. The capacity of the building is the number of people per unit area of ​​the building, and the total heat gain of the building includes sensible heat gain and latent heat gain.

[0053] Furthermore, in step S400 of an embodiment of the present invention, the machine learning model is a support vector machine model.

[0054] Similarly, based on the method for analyzing building energy consumption proposed by the embodiment of the present invention, the embodiment of the present invention further proposes a system for analyzing building energy consumption.

[0055] FIG. 2 is a block diagram showing the structure of a building energy consumption analysis system according to an embodiment of the present invention. As shown in FIG. 2, the building energy consumption analysis system according to the embodiment of the present invention includes:

[0056] a sample dataset acquisition module, which is used for cleaning and labeling the pre-acquired source data to obtain a sample dataset including building energy consumption data and corresponding building-related data;

[0057] a feature selection module, which is used for performing feature selection of the building-related data on the building energy consumption data to determine feature data items including a building geolocation, a building total area, a building height, a building orientation, a building envelope, a building outdoor humidity, a building outdoor wind speed, a building direct solar radiation load, a building outdoor ground surface temperature, and a building average outdoor temperature;

[0058] a training dataset obtaining module, which is used for sampling the sample dataset based on the determined feature data items to obtain a training dataset;

[0059] an analysis model acquisition module of building energy consumption, which is used to train a pre-acquired machine learning model based on the training data set to obtain an analysis model of building energy consumption;

[0060] The building energy consumption analysis implementation module is used for analyzing the building energy consumption based on the building energy consumption analysis model.

[0061] Moreover, in an embodiment of the present invention, the characteristic data items further include the outdoor air density of the building, the occupancy of the building, and the total heat gain of the building.

[0062] Similarly, based on the method for analyzing building energy consumption proposed by an embodiment of the present invention, the embodiment of the present invention further proposes an electronic device including a processor and a memory, which, when the processor executes a computer program stored in the memory, realizes the method for analyzing building energy consumption proposed by the embodiment of the present invention.

[0063] Although one or more embodiments of the present invention have been described above, it should be understood by those skilled in the art that the present invention may be embodied in any other form without departing from the spirit and scope of the present invention. Accordingly, the embodiments described above are illustrative rather than restrictive, and many modifications and substitutions may be apparent to those skilled in the art without departing from the spirit and scope of the present invention as defined by the appended claims.

Claims

1. A method for analyzing building energy consumption, comprising: cleaning and labeling the pre-acquired source data to obtain a sample dataset including building energy consumption data and corresponding building-related data; performing feature selection of the building related data against the building energy consumption data to determine feature data items including building geolocation, building total area, building height, building orientation, building envelope, building outdoor humidity, building outdoor wind speed, building direct solar load, building outdoor ground surface temperature, and building average outdoor temperature; sampling the sample data set based on the determined feature data items to obtain a training data set; training a pre-obtained machine learning model based on the training dataset to obtain an analytical model of building energy consumption; and analyzing building energy consumption based on the analytical model of building energy consumption.

2. The method for acquiring the source data includes: How to read the imported data file, Based on a previously accessed database, 2. The method of claim 1, further comprising receiving corresponding environmental parameters uploaded by an environmental parameter sensor.

3. The method for analyzing building energy consumption according to claim 1 , characterized in that the step of performing feature selection of the building-related data for the building energy consumption data is realized based on a PCA algorithm or a KPCA algorithm.

4. The method for analyzing building energy consumption according to claim 1 , wherein the characteristic data items further include the outdoor air density of the building, the occupancy of the building, and the total heat gain of the building.

5. After said step of obtaining an analytical model of building energy consumption, The method for analyzing building energy consumption according to claim 1 , further comprising optimizing the analytical model of building energy consumption based on a test data set obtained in advance.

6. The method for analyzing building energy consumption according to claim 1 , wherein the machine learning model is a support vector machine model.

7. A building energy consumption analysis system, comprising: a sample dataset acquisition module, which is used for cleaning and labeling the pre-acquired source data to obtain a sample dataset including building energy consumption data and corresponding building-related data; a feature selection module, which is used for performing feature selection of the building-related data on the building energy consumption data to determine feature data items including a building geolocation, a building total area, a building height, a building orientation, a building envelope, a building outdoor humidity, a building outdoor wind speed, a building direct solar radiation load, a building outdoor ground surface temperature, and a building average outdoor temperature; a training dataset obtaining module, which is used for sampling the sample dataset based on the determined feature data items to obtain a training dataset; an analysis model acquisition module of building energy consumption, which is used to train a pre-acquired machine learning model based on the training data set to obtain an analysis model of building energy consumption; and a building energy consumption analysis implementation module used for analyzing building energy consumption based on the building energy consumption analysis model.

8. The system for analyzing building energy consumption according to claim 7, wherein the characteristic data items further include the outdoor air density of the building, the occupancy of the building, and the total heat gain of the building.

9. An electronic device comprising a processor and a memory, and realizing the building energy consumption analysis method according to any one of claims 1 to 6 when the processor executes a computer program stored in the memory.

Images