Load identification method, device and equipment of zero-carbon building and storage medium

Abstract

The application discloses a load identification method, device and equipment of zero-carbon building and a storage medium. The zero-carbon building is grouped and classified by using a cross classification method, and a plurality of device groups of the zero-carbon building are obtained. For each device group, a direct clustering method is used to cluster daily load data of each electrical equipment in the device group, a first daily load clustering center curve of the electrical equipment is obtained, and the same type of electrical equipment is grouped and clustered to obtain a second daily load clustering center curve. The daily load center curve is determined according to the device grouping, so that the load model can be quickly locked for different buildings, the device load of the zero-carbon building can be quickly and effectively identified, and finally, the load state of the zero-carbon building is identified according to the daily load data of the electrical equipment and the second daily load clustering center curve, so that the zero-carbon building can be quickly and effectively identified, and the carbon emission of the zero-carbon building can be adjusted according to the load state.

Description

Technical Field

[0001] This application relates to the field of energy technology, and in particular to a load identification method, apparatus, equipment and storage medium for zero-carbon buildings. Background Technology

[0002] With global economic development, carbon emissions and per capita emissions from the demand for energy such as electricity and oil across all economic sectors worldwide have increased significantly. However, with global warming, countries are striving to reduce greenhouse gas emissions, and zero-carbon buildings are gaining increasing popularity. Zero-carbon buildings are buildings with zero carbon emissions.

[0003] Currently, constructing zero-carbon buildings requires assessing the sources of their carbon emissions. However, since energy sources such as electricity generation, oil, and natural gas all generate significant carbon emissions, current methods primarily focus on identifying carbon emissions from the energy sector, lacking an approach to identifying carbon emissions from the load side of zero-carbon buildings. Therefore, there is an urgent need for a method to effectively classify and identify the loads of zero-carbon buildings. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for load identification of zero-carbon buildings, enabling rapid and effective load identification of zero-carbon buildings.

[0005] To address the aforementioned technical problems, in a first aspect, this application provides a load identification method for zero-carbon buildings, comprising:

[0006] Using cross-classification, the electrical equipment in zero-carbon buildings is grouped and classified to obtain multiple equipment groups for the zero-carbon buildings.

[0007] For each of the equipment groups, a direct clustering method is used to cluster the daily load data of each electrical device in the equipment group to obtain the first daily load cluster center curve of the electrical device;

[0008] Using the load cluster center curve of the first day, the electrical equipment of the same type is grouped and clustered to obtain the load cluster center curve of the second day;

[0009] The load status of the zero-carbon building is identified based on the daily load data of the electrical equipment and the second daily load cluster center curve.

[0010] In some implementations, the cross-classification method is used to group and classify the electrical equipment of the zero-carbon building, resulting in multiple equipment groups for the zero-carbon building, including:

[0011] Using cross-classification, the electrical equipment in the zero-carbon building is grouped according to its equipment type.

[0012] Based on the geographical location of the electrical equipment in the zero-carbon building, the electrical equipment is grouped into multiple equipment groups, and the electrical equipment in each equipment group is of the same type.

[0013] In some implementations, the direct clustering method includes at least one of the following: K-means clustering algorithm, K-centroid partitioning algorithm, and hierarchical clustering algorithm.

[0014] In some implementations, the step of clustering the daily load data of each electrical device in each equipment group to obtain the first daily load cluster center curve of the electrical device includes:

[0015] For each of the equipment groups, the daily load data of any electrical device in the equipment group is randomly selected as the initial cluster center for the K-means clustering algorithm;

[0016] Using the initial cluster centers, the daily load data of all electrical equipment in the equipment group are clustered to obtain the first daily load cluster center curve corresponding to the equipment group.

[0017] In some implementations, the step of using the first day's load cluster center curve to group and cluster the same type of electrical equipment to obtain the second day's load cluster center curve includes:

[0018] Compare the first-day load cluster center curves of each equipment group corresponding to the same type of electrical equipment;

[0019] The two equipment groups whose Euclidean distance between the first day load cluster center curves is less than a preset threshold are merged to obtain the second day load cluster center curve.

[0020] In some implementations, identifying the load status of the zero-carbon building based on the daily load data of the electrical equipment and the second daily load cluster center curve includes:

[0021] Based on a preset cutting method, the second daily load cluster center curve is cut into multiple segmented curves, and the daily load data of all the electrical equipment in the equipment group is cut into multiple segmented data.

[0022] Calculate the maximum deviation between the piecewise curve and the piecewise data;

[0023] The load status of the zero-carbon building is determined based on the maximum deviation value.

[0024] In some implementations, the preset cutting method is to cut time periods based on peak and off-peak electricity consumption periods.

[0025] Secondly, this application also provides a load identification device for zero-carbon buildings, comprising:

[0026] The grouping module is used to group and classify the electrical equipment of the zero-carbon building using a cross-classification method, thereby obtaining multiple equipment groups for the zero-carbon building.

[0027] The first clustering module is used to cluster the daily load data of each electrical device in each equipment group using the direct clustering method to obtain the first daily load cluster center curve of the electrical device.

[0028] The second clustering module is used to group and cluster the electrical equipment of the same type using the first day's load clustering center curve to obtain the second day's load clustering center curve.

[0029] The identification module is used to identify the load status of the zero-carbon building based on the daily load data of the electrical equipment and the second daily load cluster center curve.

[0030] Thirdly, this application also provides a computer device, including a processor and a memory, the memory being used to store a computer program, which, when executed by the processor, implements the load identification method for zero-carbon buildings as described in the first aspect.

[0031] Fourthly, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the load identification method for zero-carbon buildings as described in the first aspect.

[0032] Compared with the prior art, this application has at least the following beneficial effects:

[0033] By utilizing cross-classification, the electrical equipment in zero-carbon buildings is grouped and classified to obtain multiple equipment groups for the zero-carbon building. This makes the identification of the load of each piece of equipment in the building more organized, facilitating the determination of the building's zero-carbon status. Then, for each equipment group, a direct clustering method is used to cluster the daily load data of each piece of electrical equipment in the group, obtaining the first daily load cluster center curve of the electrical equipment. Using the first daily load cluster center curve, the electrical equipment of the same type is grouped and clustered to obtain the second daily load cluster center curve. The daily load center curve is determined based on the equipment group, thereby enabling the rapid locking of the load model for different buildings and the rapid and effective identification of the equipment load in zero-carbon buildings. Finally, based on the daily load data of the electrical equipment and the second daily load cluster center curve, the load status of the zero-carbon building is identified, achieving rapid and effective load identification of zero-carbon buildings, thus facilitating the adjustment of carbon emissions of zero-carbon buildings according to the load status. Attached Figure Description

[0034] Figure 1 This is a schematic flowchart illustrating the load identification method for zero-carbon buildings according to an embodiment of this application;

[0035] Figure 2 This is a schematic diagram of the load identification device for zero-carbon buildings shown in an embodiment of this application;

[0036] Figure 3 This is a schematic diagram of the structure of a computer device shown in an embodiment of this application. Detailed Implementation

[0037] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0038] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a load identification method for zero-carbon buildings provided in an embodiment of this application. The load identification method for zero-carbon buildings in this embodiment can be applied to computer devices, including but not limited to smartphones, laptops, tablets, desktop computers, physical servers, and cloud servers. Figure 1 As shown, the load identification method for zero-carbon buildings in this embodiment includes steps S101 to S104, which are detailed below:

[0039] Step S101: Using cross-classification, the electrical equipment of the zero-carbon building is grouped and classified to obtain multiple equipment groups of the zero-carbon building.

[0040] In this step, loads are grouped according to physical categories, and then further grouped and merged based on load type to achieve accurate load identification.

[0041] In some embodiments, step S101 includes:

[0042] Using cross-classification, the electrical equipment in the zero-carbon building is grouped according to its equipment type.

[0043] Based on the geographical location of the electrical equipment in the zero-carbon building, the electrical equipment is grouped into multiple equipment groups, and the electrical equipment in each equipment group is of the same type.

[0044] In this embodiment, the devices are first grouped according to their type, including air conditioners, office power supplies, lighting, charging piles, low-voltage equipment rooms and generator rooms, domestic water pumps, fire-fighting power supplies, monitoring centers and fire control centers. Then, the devices are grouped a second time according to their geographical location, with the geographical location division being at least accurate to the floor level. The devices in the second group are of the same category.

[0045] It should be noted that grouping makes the various devices in the building more organized, and secondary grouping further reduces the omission of devices during testing, making it more convenient to make zero-carbon determinations.

[0046] Step S102: For each of the equipment groups, the direct clustering method is used to cluster the daily load data of each electrical device in the equipment group to obtain the first daily load cluster center curve of the electrical device.

[0047] In this step, the daily load data of electrical equipment in each equipment group are clustered to obtain the load characteristics of the equipment in the same group, which facilitates the subsequent rapid analysis of the load status of zero-carbon buildings.

[0048] Optionally, the daily load data includes the load values ​​of the equipment at n sampling points throughout the day. The load values ​​are scalars, and the load values ​​from the n sampling points form an n-dimensional vector, where n is set according to actual needs. Optionally, the direct clustering method includes at least one of the following: K-means clustering algorithm, K-centroid partitioning algorithm, and hierarchical clustering algorithm.

[0049] In some embodiments, step S102 includes:

[0050] For each of the equipment groups, the daily load data of any electrical device in the equipment group is randomly selected as the initial cluster center for the K-means clustering algorithm;

[0051] Using the initial cluster centers, the daily load data of all electrical equipment in the equipment group are clustered to obtain the first daily load cluster center curve corresponding to the equipment group.

[0052] In this embodiment, the daily load data of any user equipment in the equipment group is randomly selected as the initial center of the K-means algorithm, and the initial cluster number K=1 is set to start clustering. After each clustering is completed, the clustering quality parameter is detected and verified whether the clustering quality parameter is within the preset threshold range. If it is, the clustering result of the equipment group is the first daily load cluster center curve. If it is not, the cluster number is incremented by one, and the clustering process is repeated until the clustering quality parameter is within the preset threshold range. Based on the final number of clusters, the electrical equipment in the equipment group is re-divided, and the first daily load cluster center curve of each re-divided equipment group is obtained.

[0053] Step S103: Using the first day's load cluster center curve, group the electrical equipment of the same type into clusters to obtain the second day's load cluster center curve.

[0054] In this step, step S102 obtains the first day load cluster center curves of multiple equipment groups. In order to reduce the omission of equipment in the identification process, the same type of equipment is grouped and clustered.

[0055] In some embodiments, step S103 includes:

[0056] Compare the first-day load cluster center curves of each equipment group corresponding to the same type of electrical equipment;

[0057] The two equipment groups whose Euclidean distance between the first day load cluster center curves is less than a preset threshold are merged to obtain the second day load cluster center curve.

[0058] In this embodiment, the first-day load cluster center curves of each group of the same type of equipment are compared pairwise, and the Euclidean distance is calculated. Two equipment groups with an Euclidean distance less than a preset threshold are merged. When multiple equipment groups are merged into a new equipment group, the Euclidean distance between each pair of the multiple equipment groups before the merger must be less than the preset threshold. The second-day load cluster center curve of the new equipment group after the merger is the average value of the first-day load cluster center curves of the multiple equipment groups before the merger.

[0059] Step S104: Identify the load status of the zero-carbon building based on the daily load data of the electrical equipment and the second daily load cluster center curve.

[0060] In this step, the daily load data and the second-day load cluster center curve are input into the preset load model. The load deviation is determined by comparing the electrical equipment with the second-day load cluster center curve. Adjustments can then be made based on the load deviation to meet the requirements of zero carbon emissions.

[0061] In some embodiments, step S104 includes:

[0062] Based on a preset cutting method, the second daily load cluster center curve is cut into multiple segmented curves, and the daily load data of all the electrical equipment in the equipment group is cut into multiple segmented data.

[0063] Calculate the maximum deviation between the piecewise curve and the piecewise data;

[0064] The load state of the zero-carbon building is determined based on the maximum deviation value.

[0065] In this embodiment, the rigid load in the load model is a variable, and the flexible load is a constant. The method for identifying the flexible load is as follows: the first day load cluster center curve is cut into several curve segments, and the daily load data of all equipment in the equipment group is correspondingly cut into several data segments. The daily load data of all equipment after the cutting is compared with the second day load cluster center curve after the cutting to determine the maximum deviation value, wherein the deviation value is the Euclidean distance between the daily load data and the second day load cluster center curve.

[0066] In some embodiments, the preset cutting method is to cut the time period based on peak and off-peak electricity consumption periods, so as to identify the load in a targeted manner according to the differences in building carbon emissions at different times.

[0067] To implement the load identification method for zero-carbon buildings corresponding to the above method embodiments, and to achieve the corresponding functional and technical effects. See [link to documentation]. Figure 2 , Figure 2 This diagram illustrates a structural block diagram of a load identification device for a zero-carbon building according to an embodiment of this application. For ease of explanation, only the parts relevant to this embodiment are shown. The load identification device for a zero-carbon building provided in this embodiment includes:

[0068] Grouping module 201 is used to group and classify the electrical equipment of zero-carbon buildings using cross-classification method to obtain multiple equipment groups of the zero-carbon building;

[0069] The first clustering module 202 is used to cluster the daily load data of each electrical device in each equipment group using the direct clustering method to obtain the first daily load cluster center curve of the electrical device.

[0070] The second clustering module 203 is used to group and cluster the electrical equipment of the same type using the first day's load clustering center curve to obtain the second day's load clustering center curve.

[0071] The identification module 204 is used to identify the load status of the zero-carbon building based on the daily load data of the electrical equipment and the second daily load cluster center curve.

[0072] In some embodiments, the grouping module 201 is specifically used for:

[0073] Using cross-classification, the electrical equipment in the zero-carbon building is grouped according to its equipment type.

[0074] Based on the geographical location of the electrical equipment in the zero-carbon building, the electrical equipment is grouped into multiple equipment groups, and the electrical equipment in each equipment group is of the same type.

[0075] In some embodiments, the direct clustering method includes at least one of K-means clustering algorithm, K-centroid partitioning algorithm, and hierarchical clustering algorithm.

[0076] In some embodiments, the first clustering module 202 is specifically used for:

[0077] For each of the equipment groups, the daily load data of any electrical device in the equipment group is randomly selected as the initial cluster center for the K-means clustering algorithm;

[0078] Using the initial cluster centers, the daily load data of all electrical equipment in the equipment group are clustered to obtain the first daily load cluster center curve corresponding to the equipment group.

[0079] In some embodiments, the second clustering module 203 is specifically used for:

[0080] Compare the first-day load cluster center curves of each equipment group corresponding to the same type of electrical equipment;

[0081] The two equipment groups whose Euclidean distance between the first day load cluster center curves is less than a preset threshold are merged to obtain the second day load cluster center curve.

[0082] In some embodiments, the identification module 204 is specifically used for:

[0083] Based on a preset cutting method, the second daily load cluster center curve is cut into multiple segmented curves, and the daily load data of all the electrical equipment in the equipment group is cut into multiple segmented data.

[0084] Calculate the maximum deviation between the piecewise curve and the piecewise data;

[0085] The load status of the zero-carbon building is determined based on the maximum deviation value.

[0086] In some embodiments, the preset cutting method is to cut time periods based on peak and off-peak electricity consumption periods.

[0087] The load identification device for zero-carbon buildings described above can implement the load identification method for zero-carbon buildings described in the above method embodiments. The options in the above method embodiments are also applicable to this embodiment, and will not be detailed here. The remaining contents of this application embodiment can be referred to the contents of the above method embodiments, and will not be repeated in this embodiment.

[0088] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Figure 3 As shown, the computer device 3 of this embodiment includes: at least one processor 30 ( Figure 3(Only one is shown) a processor, a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30, wherein the processor 30 executes the computer program 32 to implement the steps in any of the above method embodiments.

[0089] The computer device 3 may be a smartphone, tablet, desktop computer, or cloud server, among other computing devices. This computer device may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will understand that... Figure 3 The computer device 3 is merely an example and does not constitute a limitation on the computer device 3. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0090] The processor 30 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0091] In some embodiments, the memory 31 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 31 may be an external storage device of the computer device 3, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 3. Furthermore, the memory 31 may include both internal and external storage units of the computer device 3. The memory 31 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 31 can also be used to temporarily store data that has been output or will be output.

[0092] In addition, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the above method embodiments.

[0093] This application provides a computer program product that, when run on a computer device, enables the computer device to execute the steps described in the various method embodiments above.

[0094] In the several embodiments provided in this application, it will be understood that each block in the flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the figures. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved.

[0095] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0096] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above descriptions are merely specific embodiments of this application and are not intended to limit the scope of protection of this application. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application for those skilled in the art.

Claims

1. A load identification method for zero-carbon buildings, characterized in that, include: Using cross-classification, the electrical equipment in zero-carbon buildings is grouped and classified to obtain multiple equipment groups for the zero-carbon buildings. For each of the equipment groups, a direct clustering method is used to cluster the daily load data of each electrical device in the equipment group to obtain the first daily load cluster center curve of the electrical device; Using the load cluster center curve of the first day, the electrical equipment of the same type is grouped and clustered to obtain the load cluster center curve of the second day; Based on the daily load data of the electrical equipment and the second daily load cluster center curve, the load status of the zero-carbon building is identified, including: Based on a preset cutting method, the second daily load cluster center curve is cut into multiple segmented curves, and the daily load data of all the electrical equipment in the equipment group is cut into multiple segmented data. Calculate the maximum deviation between the piecewise curve and the piecewise data; The load status of the zero-carbon building is determined based on the maximum deviation value. The preset cutting method is to cut time periods based on peak and off-peak electricity consumption periods.

2. The load identification method for zero-carbon buildings as described in claim 1, characterized in that, The method of cross-classification is used to group and classify the electrical equipment of zero-carbon buildings, resulting in multiple equipment groups for the zero-carbon buildings, including: Using cross-classification, the electrical equipment in the zero-carbon building is grouped according to its equipment type. Based on the geographical location of the electrical equipment in the zero-carbon building, the electrical equipment is grouped into multiple equipment groups, and the electrical equipment in each equipment group is of the same type.

3. The load identification method for zero-carbon buildings as described in claim 1, characterized in that, The direct clustering method includes at least one of the following: K-means clustering algorithm, K-centroid partitioning algorithm, and hierarchical clustering algorithm.

4. The load identification method for zero-carbon buildings as described in claim 3, characterized in that, The step of clustering the daily load data of each electrical device in each equipment group to obtain the first daily load cluster center curve of the electrical device includes: For each of the equipment groups, the daily load data of any electrical device in the equipment group is randomly selected as the initial cluster center for the K-means clustering algorithm; Using the initial cluster centers, the daily load data of all electrical equipment in the equipment group are clustered to obtain the first daily load cluster center curve corresponding to the equipment group.

5. The load identification method for zero-carbon buildings as described in claim 1, characterized in that, The step of using the first day's load cluster center curve to group and cluster the same type of electrical equipment to obtain the second day's load cluster center curve includes: Compare the first-day load cluster center curves of each equipment group corresponding to the same type of electrical equipment; The two equipment groups whose Euclidean distance between the first day load cluster center curves is less than a preset threshold are merged to obtain the second day load cluster center curve.

6. A load identification device for zero-carbon buildings, characterized in that, include: The grouping module is used to group and classify the electrical equipment of the zero-carbon building using a cross-classification method, thereby obtaining multiple equipment groups for the zero-carbon building. The first clustering module is used to cluster the daily load data of each electrical device in each equipment group using the direct clustering method to obtain the first daily load cluster center curve of the electrical device. The second clustering module is used to group and cluster the electrical equipment of the same type using the first day's load clustering center curve to obtain the second day's load clustering center curve. The identification module is used to identify the load status of the zero-carbon building based on the daily load data of the electrical equipment and the second daily load cluster center curve, including: Based on a preset cutting method, the second daily load cluster center curve is cut into multiple segmented curves, and the daily load data of all the electrical equipment in the equipment group is cut into multiple segmented data. Calculate the maximum deviation between the piecewise curve and the piecewise data; The load status of the zero-carbon building is determined based on the maximum deviation value. The preset cutting method is to cut time periods based on peak and off-peak electricity consumption periods.

7. A computer device, characterized in that, It includes a processor and a memory, the memory being used to store a computer program that, when executed by the processor, implements the load identification method for zero-carbon buildings as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the load identification method for zero-carbon buildings as described in any one of claims 1 to 5.

Images