CN-122020103-A - Building-oriented energy consumption data correction method and device, electronic equipment and medium

CN122020103ACN 122020103 ACN122020103 ACN 122020103ACN-122020103-A

Abstract

The embodiment of the application provides a building-oriented energy consumption data correction method and device, electronic equipment and medium, and belongs to the technical field of artificial intelligence. The method includes obtaining a service usage type for each unit subspace in a target building. The method comprises the steps of obtaining corresponding energy consumption collecting data aiming at each unit subspace in a target building, analyzing energy consumption fluctuation event of each service application type to obtain a compliance energy consumption event type, carrying out anomaly detection on the energy consumption collecting data according to the compliance energy consumption event type to obtain anomaly energy consumption data, wherein an collecting time period corresponding to the anomaly energy consumption data is an energy consumption anomaly time period, obtaining historical energy consumption data, and screening the historical energy consumption data according to the energy consumption anomaly time period to obtain reference energy consumption data. The historical energy consumption data is earlier than the abnormal energy consumption data, and the abnormal energy consumption data is corrected based on the reference energy consumption data. The embodiment of the application can accurately correct abnormal energy data in the building.

Inventors

ZHAO LU
ZHANG BAOLI
SONG JUNCHANG
YU XURI
ZHENG SHUZHEN

Assignees

深圳泛和科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260414

Claims (10)

1. A method for building-oriented energy consumption data correction, the method comprising: Acquiring the service usage type of each unit subspace in the target building; acquiring corresponding energy consumption acquisition data aiming at each unit subspace in the target building; Carrying out energy consumption fluctuation event analysis on each service use type to obtain a compliance energy consumption event type; performing anomaly detection on the energy consumption acquisition data according to the type of the compliance energy consumption event to obtain abnormal energy consumption data, wherein an acquisition period corresponding to the abnormal energy consumption data is an energy consumption abnormal period; Acquiring historical energy consumption data, and screening the historical energy consumption data according to the energy consumption abnormal time period to obtain reference energy consumption data, wherein the historical energy consumption data is earlier than the abnormal energy consumption data; and correcting the abnormal energy consumption data based on the reference energy consumption data.
2. The method according to claim 1, wherein the performing anomaly detection on the energy consumption collection data according to the type of the compliant energy consumption event to obtain anomaly energy consumption data includes: analyzing the time period characteristics aiming at the current acquisition time period to obtain the current time period characteristics; determining a homogeneous acquisition period from a plurality of historical acquisition periods based on the current period characteristics; comparing the energy consumption acquisition data of the current acquisition period with the historical energy consumption data of the homogeneous acquisition period to obtain energy consumption deviation data; If the energy consumption deviation data meets a preset deviation abnormal condition, acquiring a business event corresponding to the unit subspace in the current acquisition period; Performing energy consumption fluctuation compliance judgment on the business event corresponding to the current acquisition period based on the type of the compliance energy consumption event to obtain a judgment result; And responding to the judging result to reflect that the business event corresponding to the current acquisition period does not fall into the type of the compliant energy consumption event, and determining the energy consumption acquisition data of the current acquisition period as the abnormal energy consumption data.
3. The method according to claim 2, wherein the performing the time period feature analysis for the current acquisition time period to obtain the current time period feature includes: analyzing the operation cycle characteristics aiming at the current acquisition period to obtain operation cycle period characteristics; analyzing the service scheduling characteristics aiming at the current acquisition period to obtain the service scheduling period characteristics; analyzing the public event characteristics aiming at the current acquisition period to obtain the public event period characteristics; analyzing the environmental factor characteristics aiming at the current acquisition period to obtain environmental factor period characteristics; Analyzing the object operation and maintenance features according to the current acquisition period to obtain object operation and maintenance period features; and carrying out feature integration based on the operation period time period feature, the service scheduling time period feature, the public event time period feature, the environment factor time period feature and the object Xiang Yunwei time period feature to obtain the current time period feature.
4. The method according to claim 2, characterized in that after said if said energy consumption deviation data satisfies a preset deviation anomaly condition, comprising: acquiring service change information corresponding to the unit subspace; re-determining the service usage type of the unit subspace in the current acquisition period based on the service change information; And carrying out energy consumption fluctuation event analysis on the unit subspace based on the redetermined service use type so as to update the type of the compliant energy consumption event.
5. The method according to any one of claims 1 to 4, wherein said performing energy consumption fluctuation event analysis on each of said business usage types to obtain a compliance energy consumption event type comprises: Acquiring a plurality of alternative public event sub-types and a plurality of alternative environment event sub-types; carrying out service property analysis on the service use types of each unit subspace in the target building to obtain corresponding service event sub-types; The method further includes determining the compliance energy consumption event type based on a plurality of the business event subtypes, a plurality of the common event subtypes, and a plurality of the environmental event subtypes.
6. The method according to any one of claims 1 to 4, wherein the screening the historical energy consumption data according to the energy consumption abnormality period to obtain reference energy consumption data includes: Performing time period characteristic analysis on the energy consumption abnormal time period to obtain abnormal time period characteristics; determining a reference acquisition period from a plurality of historical acquisition periods based on the anomaly time period characteristics; and determining the historical energy consumption data corresponding to the reference acquisition period as the reference energy consumption data.
7. The method of any of claims 1 to 4, wherein the reference energy consumption data comprises a plurality of sets of reference sub-data, each of the reference sub-data configured with a reference weight, the correcting the abnormal energy consumption data based on the reference energy consumption data comprising: acquiring an abnormal data sampling interval corresponding to the abnormal energy consumption data; Converting the abnormal energy consumption data into an abnormal data sequence based on the abnormal data sampling interval; Based on the abnormal data sampling interval, performing alignment operation on each group of reference sub-data to obtain a reference data sequence corresponding to each group of reference sub-data; Performing correction analysis on the abnormal data sequence based on the reference data sequence and the reference weight, and determining a corresponding data correction parameter; based on the data correction parameters, correcting the abnormal data sequence; and carrying out data reduction processing based on the abnormal data sequence after the correction operation to obtain corrected abnormal energy consumption data.
8. A building-oriented energy consumption data correction device, the device comprising: the first acquisition module is used for acquiring the service usage type of each unit subspace in the target building; the second acquisition module is used for acquiring corresponding energy consumption acquisition data aiming at each unit subspace in the target building; The energy consumption fluctuation analysis module is used for carrying out energy consumption fluctuation event analysis on each service use type to obtain a compliance energy consumption event type; The abnormal detection module is used for carrying out abnormal detection on the energy consumption acquisition data according to the type of the compliance energy consumption event to obtain abnormal energy consumption data, wherein the acquisition period corresponding to the abnormal energy consumption data is an energy consumption abnormal period; The reference data screening module is used for acquiring historical energy consumption data, and screening the historical energy consumption data according to the energy consumption abnormal time period to obtain reference energy consumption data, wherein the historical energy consumption data is earlier than the abnormal energy consumption data; And the data correction module is used for correcting the abnormal energy consumption data based on the reference energy consumption data.
9. An electronic device comprising a memory storing a computer program and a processor implementing the method of any of claims 1 to 7 when the computer program is executed by the processor.
10. A computer readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the method of any one of claims 1 to 7.

Description

Building-oriented energy consumption data correction method and device, electronic equipment and medium Technical Field The present application relates to the field of artificial intelligence technologies, and in particular, to a method and an apparatus for correcting energy consumption data for a building, an electronic device, and a medium. Background In buildings such as office buildings and markets, energy consumption (e.g., electricity consumption, cold consumption, water consumption, etc.) is usually counted and analyzed periodically to assist in energy management. However, in the actual data acquisition process, an abnormal situation in which the energy consumption data fluctuates greatly or is missing may be caused by the failure of the data acquisition device. In the related art, abnormal data is generally replaced by calculating an average value of the data, or manually corrected depending on manual experience. However, these methods often process the data too mechanically, lack sufficient understanding and adaptation to the abnormal situation, and result in that the accuracy of the correction data cannot be effectively ensured. Therefore, how to accurately correct abnormal energy consumption data in a building becomes a technical problem to be solved. Disclosure of Invention The embodiment of the application mainly aims to provide a building-oriented energy consumption data correction method and device, electronic equipment and medium, and aims to accurately correct abnormal energy data in a building. To achieve the above object, a first aspect of an embodiment of the present application provides a building-oriented energy consumption data correction method, including: Acquiring the service usage type of each unit subspace in the target building; acquiring corresponding energy consumption acquisition data aiming at each unit subspace in the target building; Carrying out energy consumption fluctuation event analysis on each service use type to obtain a compliance energy consumption event type; performing anomaly detection on the energy consumption acquisition data according to the type of the compliance energy consumption event to obtain abnormal energy consumption data, wherein an acquisition period corresponding to the abnormal energy consumption data is an energy consumption abnormal period; Acquiring historical energy consumption data, and screening the historical energy consumption data according to the energy consumption abnormal time period to obtain reference energy consumption data, wherein the historical energy consumption data is earlier than the abnormal energy consumption data; and correcting the abnormal energy consumption data based on the reference energy consumption data. In some embodiments, the performing anomaly detection on the energy consumption collected data according to the type of the compliant energy consumption event to obtain abnormal energy consumption data includes: analyzing the time period characteristics aiming at the current acquisition time period to obtain the current time period characteristics; determining a homogeneous acquisition period from a plurality of historical acquisition periods based on the current period characteristics; comparing the energy consumption acquisition data of the current acquisition period with the historical energy consumption data of the homogeneous acquisition period to obtain energy consumption deviation data; If the energy consumption deviation data meets a preset deviation abnormal condition, acquiring a business event corresponding to the unit subspace in the current acquisition period; Performing energy consumption fluctuation compliance judgment on the business event corresponding to the current acquisition period based on the type of the compliance energy consumption event to obtain a judgment result; And responding to the judging result to reflect that the business event corresponding to the current acquisition period does not fall into the type of the compliant energy consumption event, and determining the energy consumption acquisition data of the current acquisition period as the abnormal energy consumption data. In some embodiments, the analyzing the time period characteristic for the current acquisition time period to obtain the current time period characteristic includes: analyzing the operation cycle characteristics aiming at the current acquisition period to obtain operation cycle period characteristics; analyzing the service scheduling characteristics aiming at the current acquisition period to obtain the service scheduling period characteristics; analyzing the public event characteristics aiming at the current acquisition period to obtain the public event period characteristics; analyzing the environmental factor characteristics aiming at the current acquisition period to obtain environmental factor period characteristics; Analyzing the object operation and maintenance features according to the current acquisitio