Load identification method and device, electronic equipment and readable storage medium

Abstract

The invention provides a load identification method, and belongs to the field of load identification, and the method comprises the steps: receiving an edge load identification result sent by an edge device, the edge load identification result comprising a target power consumption waveform, a first matching degree between the target power consumption waveform and at least one preset power consumption waveform stored in the edge database is greater than a first preset threshold value, and the target power consumption waveform is obtained by collecting the power consumption waveform of the target point location by the edge device; acquiring scene information corresponding to the edge device, wherein the scene information corresponding to the edge device is obtained after analysis based on a historical edge load identification result corresponding to the edge device; performing load identification on the target power consumption waveform based on scene information corresponding to the edge device to obtain a cloud load identification result; and determining electric equipment corresponding to the target electric waveform based on the cloud load identification result. The load identification method provided by the invention can improve the accuracy of load identification.

Description

Technical Field

[0001] This application belongs to the field of load identification technology, and more specifically, relates to a load identification method and apparatus, electronic device, and readable storage medium. Background Technology

[0002] With the popularization of power Internet of Things technology, load identification is a core technology for scenarios such as power monitoring, energy consumption management, and safe electricity use early warning. Currently, the mainstream load identification solutions mainly rely on current transformers. The specific implementation method is as follows: deploy current transformers and other acquisition devices at the target power consumption point to collect the power consumption waveform of the main incoming line or a single device in real time, determine the corresponding type of power consumption device based on the power consumption waveform, and then complete the identification and subsequent alarm or statistical operations.

[0003] However, due to the limited storage capacity of current transformers in existing technologies, it is impossible to accumulate a sufficient amount of power waveforms. Consequently, when identifying loads, only simple waveform feature comparison can be achieved, making it difficult to achieve accurate waveform analysis. For example, the same power waveform may correspond to different electrical devices in different scenarios, and different devices may also exhibit highly similar waveform features under specific operating conditions. Relying solely on a single real-time waveform matching lacks scenario-based verification logic, resulting in poor accuracy in load identification.

[0004] Therefore, a load identification method is needed to improve the accuracy of load identification. Summary of the Invention

[0005] To address the aforementioned issues, this application provides a load identification method and apparatus, an electronic device, and a readable storage medium to improve the accuracy of load identification.

[0006] Firstly, a load identification method is provided, applicable to cloud platforms, including: The edge load identification result sent by the edge device is received. The edge load identification result includes the target power consumption waveform. The first matching degree between the target power consumption waveform and at least one preset power consumption waveform stored in the edge database is greater than the first preset threshold. The target power consumption waveform is obtained by the edge device from the power consumption waveform of the target point. Obtain the scene information corresponding to the edge device. The scene information corresponding to the edge device is used to characterize the scene information applied by the power equipment corresponding to the edge device. The scene information corresponding to the edge device is obtained after analyzing the historical edge load identification results corresponding to the edge device. Load identification is performed on the target power waveform based on the scene information corresponding to the edge device, and the load identification result in the cloud is obtained; The target electrical waveform is used to identify the electrical equipment corresponding to it based on the load identification results in the cloud.

[0007] Secondly, a load identification method is provided, applied to edge devices, including: Collect the power consumption waveform of the target point and match the power consumption waveform with each preset power consumption waveform stored in the edge database to obtain each matching degree. Each matching degree is the first matching degree between the power consumption waveform and each first preset power consumption waveform. If at least one first matching degree is greater than the first preset threshold, the power consumption waveform is taken as the target power consumption waveform, and the edge load identification result containing the target power consumption waveform is sent to the cloud platform so that the cloud platform can perform load identification based on the edge load identification result and obtain the power consumption equipment corresponding to the target power consumption waveform. The electrical equipment corresponding to the target power consumption waveform is identified by the cloud platform based on edge load identification results and through the following methods: Obtain the scene information corresponding to the edge device. The scene information corresponding to the edge device is used to characterize the scene information applied by the user equipment corresponding to the edge device. The scene information corresponding to the edge device is obtained after analyzing the historical edge load identification results corresponding to the edge device. Load identification is performed on the target power waveform based on the scene information corresponding to the edge device, and the load identification result in the cloud is obtained; The target electrical waveform is used to identify the electrical equipment corresponding to it based on the load identification results in the cloud.

[0008] Thirdly, a load identification device is provided for use on a cloud platform, including: The edge data receiving module is used to receive the edge load identification result sent by the edge device. The edge load identification result includes the target power consumption waveform. The first matching degree between the target power consumption waveform and at least one preset power consumption waveform stored in the edge database is greater than the first preset threshold. The target power consumption waveform is obtained by the edge device from the power consumption waveform of the target point. The scene information acquisition module is used to acquire scene information corresponding to the edge device. The scene information corresponding to the edge device is used to characterize the scene information applied by the power equipment corresponding to the edge device. The scene information corresponding to the edge device is obtained after analyzing the historical edge load identification results corresponding to the edge device. The cloud-based load identification module is used to identify the target power waveform based on the scene information corresponding to the edge device, and obtain the cloud-based load identification result; The electrical equipment identification module is used to determine the electrical equipment corresponding to the target power waveform based on the cloud load identification results.

[0009] Fourthly, a load identification device is provided for use in edge devices, comprising: The waveform acquisition module is used to acquire the power consumption waveform of the target point and match the power consumption waveform with each preset power consumption waveform stored in the edge database to obtain each matching degree. Each matching degree is the first matching degree between the power consumption waveform and each first preset power consumption waveform. The identification result sending module is used to take the power waveform as the target power waveform and send the edge load identification result containing the target power waveform to the cloud platform if at least one first matching degree is greater than the first preset threshold, so that the cloud platform can perform load identification based on the edge load identification result and obtain the power equipment corresponding to the target power waveform. The electrical equipment corresponding to the target power consumption waveform is identified by the cloud platform based on edge load identification results and through the following methods: Obtain the scene information corresponding to the edge device. The scene information corresponding to the edge device is used to characterize the scene information applied by the user equipment corresponding to the edge device. The scene information corresponding to the edge device is obtained after analyzing the historical edge load identification results corresponding to the edge device. Load identification is performed on the target power waveform based on the scene information corresponding to the edge device, and the load identification result in the cloud is obtained; The target electrical waveform is used to identify the electrical equipment corresponding to it based on the load identification results in the cloud.

[0010] Fifthly, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described load identification method.

[0011] In a sixth aspect, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the above-described load identification method.

[0012] In a seventh aspect, a computer program product is provided, comprising a computer program or computer-executable instructions, wherein when the computer program or computer-executable instructions are executed by a processor, the steps of the above-described load identification method are implemented.

[0013] The beneficial effects of the embodiments of this application are as follows: In this embodiment, the cloud platform receives edge load identification results sent by the edge device. The target power waveform in this result has been matched with preset power waveforms in the edge database, and the matching degree is greater than a first preset threshold. This ensures the initial screening quality of the target power waveform data to a certain extent. Based on this, the cloud platform further obtains the scene information corresponding to the edge device. This scene information is obtained based on the analysis of historical edge load identification results of the edge device and reflects the scene characteristics of the actual application of the power device. The cloud platform performs load identification again on the target power waveform based on the scene information to obtain the cloud load identification result. Compared with the identification method relying solely on a single dimension of power waveform, this solution combines data from both power waveform and scene information. This multi-dimensional comprehensive analysis can more accurately determine the power device corresponding to the target power waveform, effectively improving the accuracy of load identification. This embodiment adopts a two-layer screening mechanism of edge device and cloud platform. First, after the edge device collects the power waveform of the target location, it performs preliminary matching and screening with preset power waveforms in the edge database. Only when at least one matching degree is greater than the first preset threshold is the power waveform sent to the cloud platform as the target power waveform. This step performs an initial screening of the power consumption waveform, eliminating a large number of irrelevant waveforms that differ significantly from the known preset waveforms. This reduces the amount of data processed by the cloud platform and avoids interference from irrelevant waveforms in the identification process, laying the foundation for improved identification accuracy. After receiving the target power consumption waveform, the cloud platform does not directly perform identification but instead performs secondary screening and in-depth identification based on the acquired scenario information, further improving the accuracy of load identification. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 A schematic flowchart of a load identification method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the architecture of a load identification system provided in one embodiment of this application; Figure 3 A flowchart illustrating another load identification method provided in an embodiment of this application. Figure 4 A structural block diagram of a load identification device provided in an embodiment of this application; Figure 5 A structural block diagram of another load identification device provided in an embodiment of this application; Figure 6 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0016] To enable those skilled in the art to better understand the technical solutions in the embodiments of this application, the technical solutions in 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. All other embodiments obtained by those skilled in the art based on the embodiments in the specific implementation of this application should fall within the protection scope of the embodiments of this application.

[0017] To keep the drawings concise, each drawing only schematically shows the parts relevant to the disclosure; these do not represent the actual structure of the product. Furthermore, for ease of understanding, in some drawings, only one of components with the same structure or function is schematically shown, or only one is labeled. In this document, "one" not only means "only one," but can also mean "more than one," and "several" includes "two" and "more than two."

[0018] Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0019] It should be understood that, unless the context clearly states otherwise, the terms "comprising," "including," or "having" as used herein refer to the presence of an element, but do not exclude the presence or addition of one or more other elements. Furthermore, "comprising" and / or "including" as used herein specify the presence of shapes, numbers, steps, operations, members, elements, and / or combinations thereof, and do not exclude the presence or addition of one or more other shapes, numbers, operations, elements, and / or combinations thereof. Some embodiments of this application are described in detail below with reference to the accompanying drawings. Where there is no conflict between the embodiments, the following embodiments and features can be combined with each other. The steps in the following method embodiments are for illustrative purposes only and are not intended to limit this application.

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0021] This application provides a load identification method, such as... Figure 1 As shown, this method can be executed by a cloud platform and may include: S101-S104.

[0022] S101: Receive the edge load identification result sent by the edge device.

[0023] In this embodiment, reference Figure 2 Edge devices communicate with the cloud platform. There can be one or more edge devices. Edge devices can be waveform acquisition devices used to collect waveform information of target points. Target points refer to specific nodes in the electrical system used for monitoring, control or data acquisition. Specifically, they can be configured as: the wiring node of the main incoming line of a shop, the control signal node of the main switch of a rental house, the detection node of the power supply line of a certain device, etc.

[0024] In this embodiment, the edge load identification result includes the target power consumption waveform. The first matching degree between the target power consumption waveform and at least one preset power consumption waveform stored in the edge database is greater than a first preset threshold. The target power consumption waveform is obtained by the edge device collecting the power consumption waveform of the target location.

[0025] S102: Obtain scene information corresponding to the edge device.

[0026] In this embodiment, the scene information corresponding to the edge device is used to characterize the scene information applied by the power-consuming equipment corresponding to the edge device. The scene information corresponding to the edge device is obtained by analyzing the historical edge load identification results corresponding to the edge device.

[0027] Specifically, in addition to the corresponding historical target power consumption waveform, the historical edge load identification results of the edge device may also contain the power consumption equipment identified by the edge device. The scene information can be determined based on the power consumption equipment in the historical edge load identification results of the edge device and the sending time of the historical edge load identification results. Alternatively, if the historical edge identification results only contain the corresponding historical target power consumption waveform, the scene information can be determined based on the power consumption equipment in the identification results of the corresponding historical target power consumption waveform in the historical edge identification results of the edge device and the sending time of the historical edge load identification results of the cloud platform.

[0028] In this embodiment, the method of determining scene information based on transmission time and power-consuming equipment can be implemented through a preset mapping table, as shown in Table 1: Table 1 Mapping table of electrical equipment, sending time and scenario information

[0029] Table 1 is only a partial example, and the transmission time features therein are obtained by integrating the transmission time based on the historical edge load identification results.

[0030] S103: Based on the scene information corresponding to the edge device, the target power waveform is identified to obtain the load identification result in the cloud.

[0031] In this embodiment, since different electrical devices sometimes correspond to similar power waveforms, it is difficult to distinguish them. Therefore, the analysis of electrical devices can be carried out in combination with different scenarios. That is, different scenario information can correspond to different sets of power waveforms, and the target power waveform can be matched with the power waveform set under the corresponding scenario.

[0032] In this embodiment, load identification of the target power waveform is performed based on the scene information corresponding to the edge device to obtain the cloud load identification result. Specifically, this may include: selecting a candidate power waveform set from a standard database based on the scene information corresponding to the edge device. The standard database stores preset power waveforms corresponding to each scene information, and the number of preset power waveforms stored in the standard database is greater than the number of preset power waveforms stored in the edge database; load identification of the target power waveform is performed based on the candidate power waveform set to obtain the cloud load identification result.

[0033] In this embodiment, because edge devices are limited by local storage and computing power, they typically only store typical waveforms of commonly used devices, such as 1-2 types of induction cooker waveforms. This means the cloud can store a more comprehensive and larger-scale power waveform feature library, including multiple preset power waveforms for the same device under different brands, models, and operating modes. The standard database is the full waveform library stored on the cloud platform, which stores preset power waveforms for all devices categorized by scenario. The candidate power waveform set refers to a subset of waveforms specific to a particular scenario selected from the standard database, such as induction cooker waveforms, range hood waveforms, and freezer waveforms for a catering scenario. Multiple waveforms for each type of device exist on the cloud platform.

[0034] Since the candidate power consumption waveform set corresponds to the current power consumption scenario, the waveforms in the candidate power consumption waveform set are highly correlated with the target waveform. For example, the target waveform in the catering scenario may be similar to the waveform of an induction cooker or a range hood, which can reduce irrelevant interference during comparison.

[0035] In this embodiment, waveform comparison of edge devices and waveform comparison of cloud platforms can both be achieved by calculating Euclidean distance. For example, the sum of the straight-line distances between the corresponding data points of the target power waveform and the waveform to be compared can be calculated. The smaller the sum, the higher the similarity.

[0036] S104: Determine the electrical equipment corresponding to the target power waveform based on the cloud load identification results.

[0037] In this embodiment, the cloud load identification result contains the identified electrical equipment and the corresponding similarity, which can also be understood as confidence or accuracy. The similarity can be determined based on the aforementioned Euclidean distance.

[0038] In this embodiment, after determining the electrical device corresponding to the target power waveform, the method may further include: in response to the fact that the electrical device belongs to a preset non-compliant electrical appliance, and the time when the edge device sends the edge recognition result does not belong to the preset safe power consumption period corresponding to the non-compliant electrical appliance, an alarm is triggered.

[0039] For example, if the identified electrical device is a hair dryer, which is preset as an illegal electrical appliance, and the edge device sends the edge load identification result at 2:15 AM, while the preset safe electricity usage period for the hair dryer is 9:00 PM to 11:00 PM daily, then the cloud will immediately trigger an alarm.

[0040] As can be seen from the above, in this embodiment, the cloud platform receives the edge load identification result sent by the edge device. The target power waveform in this result has been matched with the preset power waveform in the edge database, and the matching degree is greater than the first preset threshold. This, to a certain extent, ensures the initial screening quality of the target power waveform data. On this basis, the cloud platform further obtains the scene information corresponding to the edge device. This scene information is obtained based on the analysis of the historical edge load identification results of the edge device and can reflect the scene characteristics of the actual application of the power device. The cloud platform performs load identification again on the target power waveform based on the scene information to obtain the cloud load identification result. Compared with the identification method that relies solely on the single dimension of power waveform, this solution combines data from both the power waveform and scene information. Multi-dimensional comprehensive analysis can more accurately determine the power device corresponding to the target power waveform, effectively improving the accuracy of load identification. In this embodiment, the edge device first performs preliminary load identification screening, sends the target power waveform that meets a certain matching degree to the cloud platform, and the cloud platform then performs secondary identification in combination with the scene information. This hierarchical identification mechanism makes the entire load identification process more rigorous. The initial screening of edge devices reduces the amount of data processed by the cloud platform, while ensuring that the data entering the cloud platform for secondary identification has a certain quality foundation. The cloud platform uses scene information for further analysis, avoiding misidentification caused by similar single power waveforms, and enhancing the reliability of the final identification results.

[0041] In one embodiment of this application, load identification is performed on the target power waveform based on a candidate power waveform set to obtain a cloud-based load identification result. The power equipment corresponding to the target power waveform is then determined based on the cloud-based load identification result. Specifically, this may include: The target power consumption waveform is matched with the candidate power consumption waveform set to obtain the first matching result; The electrical devices corresponding to the candidate electrical waveforms with a second matching degree greater than the second preset threshold are taken as the electrical devices corresponding to the target electrical waveforms.

[0042] In this embodiment, the first matching result includes a second matching degree between the target power consumption waveform and each candidate power consumption waveform. The second matching degree refers to the quantified value of the similarity between the target power consumption waveform and a specific preset waveform in the candidate power consumption waveform set. The second preset threshold is a similarity qualification benchmark set by the cloud. Only when the similarity exceeds this benchmark is the target waveform and the device corresponding to the preset waveform considered to be of the same type. The second preset threshold can be set based on preferences.

[0043] In one embodiment of this application, the edge load identification result further includes a first candidate power device identifier, which is the power device identifier corresponding to a preset power waveform with a first matching degree greater than a first preset threshold. In this embodiment, load identification is performed on the target power waveform based on the candidate power waveform set to obtain a cloud load identification result. The power device corresponding to the target power waveform is determined based on the cloud load identification result, which may specifically include: Target candidate power waveforms are selected from the candidate power waveform set. The target candidate power waveforms are the preset power waveforms corresponding to the identifiers of each first candidate power device. For a power device, the number of preset power waveforms stored in the standard database is greater than the number of preset power waveforms stored in the edge database. The target power consumption waveform is matched with the target candidate power consumption waveform to obtain a second matching result. The second matching result includes a third matching degree between the target power consumption waveform and each target candidate power consumption waveform. The electrical equipment corresponding to the target candidate power consumption waveform with a third matching degree greater than the third preset threshold is taken as the electrical equipment corresponding to the target power consumption waveform.

[0044] In this embodiment, the first candidate device identifier refers to the device initially identified by the edge device, and the target candidate waveform refers to the full cloud waveform corresponding to the first candidate device identifier, which is further filtered from the candidate waveform set. For example, it could be the preset waveforms of all models and operating states of an induction cooker. The third matching degree refers to the quantified value of the similarity between the target waveform and the target candidate waveform, and the third preset threshold refers to the similarity qualification line set in the cloud platform. Because it is a deep matching after focusing on the device, the requirements are stricter, so the third preset threshold can be higher than the second preset threshold.

[0045] In this embodiment, the first candidate device identifier is a high-probability device that has been preliminarily verified by the edge device. The cloud platform no longer needs to compare the waveforms corresponding to the entire scene set one by one, but only focuses on the suspected devices sent by the edge device, further reducing the amount of computation. The edge device is limited by local storage and computing power and can only store the typical waveform of a certain device, while the cloud can store the full waveform of the device, making the matching of the cloud platform more comprehensive and accurate.

[0046] As can be seen from the above, the embodiments of this application first filter out target candidate power consumption waveforms from the candidate power consumption waveform set. These target candidate power consumption waveforms are the full cloud waveforms corresponding to the first candidate power consumption device identifier initially identified by the edge device. Since the cloud stores the full waveform of the power consumption device, compared with the edge device which can only store the typical waveform of a certain power consumption device, the cloud platform has a wider and more comprehensive matching range. On this basis, the target power consumption waveform is matched with the target candidate power consumption waveforms to obtain a second matching result, and the power consumption device corresponding to the target candidate power consumption waveform with a third matching degree greater than a third preset threshold is taken as the power consumption device corresponding to the target power consumption waveform. This deep matching method after focusing on the power consumption device has more stringent requirements and can further improve the accuracy of load identification, avoiding the problem of inaccurate identification caused by the storage and computing power limitations of the edge device.

[0047] The edge device first performs preliminary load identification, obtaining an edge load identification result containing the identifier of the first candidate power user. The first candidate power user identifier is a high-probability power user that has been initially verified by the edge device. After receiving this result, the cloud platform does not need to compare the waveforms corresponding to the entire scene set one by one. It only needs to focus on the suspected devices sent by the edge device, that is, to filter out the target candidate power user waveform from the candidate power user waveform set for further matching. This processing method greatly reduces the computational load of the cloud platform, improves the operating efficiency of the entire load identification system, and enables the system to provide identification results faster, meeting the real-time requirements of scenarios such as power monitoring and energy consumption management.

[0048] In one embodiment of this application, the edge load identification result further includes a first candidate power device identifier and its corresponding first matching degree. The candidate power device identifier is the power device identifier corresponding to a preset power waveform whose first matching degree is greater than a first preset threshold. In this embodiment, load identification is performed on the target power waveform based on the candidate power waveform set to obtain the cloud load identification result. The power device corresponding to the target power waveform is determined based on the cloud load identification result, which may specifically include: The target power consumption waveform is matched with the candidate power consumption waveform set to obtain the third matching result, which includes the fourth matching degree between the power consumption waveform and each candidate power consumption waveform. The device identifier corresponding to the candidate power consumption waveform with a fourth matching degree greater than the third preset threshold is determined as the second candidate device identifier; For each first candidate electrical equipment identifier, if the second candidate electrical equipment identifier contains the first candidate electrical equipment identifier, then the matching degree of the first candidate electrical equipment identifier is increased to obtain the fifth matching degree corresponding to each first candidate electrical equipment identifier. Based on each fifth matching degree, the electrical equipment corresponding to the target power waveform is determined.

[0049] In this embodiment, the second candidate electrical equipment identifier refers to the suspected electrical equipment screened by the cloud platform, which is a high-probability electrical equipment independently judged by the cloud. The third preset threshold refers to the similarity qualification line for the second candidate identifier screened by the cloud, which is used to filter low similarity matching results in the cloud.

[0050] In this embodiment, the cloud platform does not rely on preliminary edge detection, avoiding the impact of edge misjudgment. For example, even if the edge detection does not identify the steamer as the first candidate electrical device, the cloud platform may still consider it if it finds a high waveform similarity through full matching. In this embodiment, the cloud platform's matching scope is a scene-specific candidate waveform set, rather than suspected edge devices, ensuring the comprehensiveness of cloud-based judgment and not overlooking any possible devices within the scene.

[0051] The cloud platform compares the first candidate device identifier with the second candidate device identifier. If a device belongs to both, its first matching score is increased to a fifth matching score. Devices belonging to only one of the identifiers are not activated, and their original first matching score is retained. This makes alarms more accurate. For example, if the cloud platform calculates a matching score of 90% for a device, and the alarm similarity is set to 93%, no alarm will be triggered. However, if an edge device also considers the device a suspected device, the matching score calculated by the cloud platform will be increased by 5%, reaching 95%, which is the alarm threshold.

[0052] As can be seen from the above, in this embodiment, the cloud platform does not rely on the preliminary judgment results of the edge devices, but independently matches the target power consumption waveform with the candidate power consumption waveform set to obtain a third matching result including a fourth matching degree. It then filters out second candidate power consumption device identifiers whose fourth matching degree is greater than a third preset threshold, effectively avoiding misjudgment problems caused by various factors from the edge devices. The cloud platform compares the first candidate power consumption device identifier with the second candidate power consumption device identifier. For power consumption devices belonging to both identifiers, its matching degree is increased to obtain a fifth matching degree; for power consumption devices belonging to only one identifier, the original first matching degree is retained. This method, which comprehensively considers the recognition results from both the edge and cloud, can fully utilize the advantages of both and further improve the accuracy of power consumption device matching.

[0053] In one embodiment of this application, a standard database stores multiple candidate power consumption waveform sets corresponding to different scene information. Each candidate power consumption waveform set contains a preset power consumption waveform corresponding to each power consumption identifier among multiple power consumption device identifiers. The load identification method further includes: If a waveform update command is received from the cloud, the candidate power consumption waveform set to be updated is determined based on the scenario information carried in the cloud waveform update command. Based on the update device identifier and the update power waveform corresponding to the update device identifier carried in the cloud waveform update instruction, the preset power waveform corresponding to the update device identifier of the candidate power waveform to be updated is updated. The target edge device is determined based on the scene information carried in the cloud waveform update command, and an edge waveform update command is generated based on the update device identifier and the update power waveform corresponding to the update device identifier carried in the cloud waveform update command. The target edge device is the edge device to be updated in the edge database. Send an edge waveform update command to the target edge device so that the target edge device updates the corresponding edge waveform feature library based on the edge waveform update command.

[0054] In this embodiment, the cloud-based waveform update command can be initiated manually by relevant personnel or automatically generated by the system after detecting a new type of device. The cloud-based waveform update command should contain corresponding scenario information, an update device identifier, and the update waveform. The candidate waveform set to be updated refers to a subset of waveforms specific to a particular scenario in the standard database that needs to be updated, such as the candidate waveform set for the catering scenario. This means the update only applies to this scenario and does not affect waveform sets for other scenarios. The update device identifier indicates the name of the device consuming the updated waveform, and the updated waveform refers to the new waveform data used to replace or supplement it. The target edge device refers to the edge devices that need to be updated synchronously, i.e., all edge devices corresponding to the scenario information in the cloud-based waveform update command. The edge waveform update command contains the update device identifier and the update waveform.

[0055] It should be noted that, in order to prevent insufficient computing power or storage of edge devices, for the same update device, the update power waveform in the edge waveform update instruction can be one of the update power waveforms in the cloud waveform update instruction. Alternatively, for the same update device, the update power waveform in the cloud waveform update instruction can also be pre-marked with an edge distribution identifier, which can be pre-defined by relevant personnel. When determining the edge waveform update instruction, the update power waveform in the edge waveform update instruction can be determined as a waveform with an edge distribution identifier.

[0056] As can be seen from the above, this embodiment allows updating the candidate power waveform set corresponding to a specific scenario in the standard database according to the cloud waveform update command. This embodiment generates an edge waveform update command and sends it to the target edge device, enabling the edge device's edge waveform feature library to be synchronized with the standard database. When the edge device performs preliminary load identification locally, it relies on the data in its edge waveform feature library. Timely updating of the edge database ensures that the edge device uses the latest waveform data during identification, avoiding identification errors caused by outdated data, thereby improving the accuracy and reliability of the entire load identification system in different scenarios.

[0057] This embodiment also considers the potential for insufficient computing power or storage in edge devices, and provides a flexible edge device update strategy. For the same updating device, the update waveform in the edge waveform update command can be one of the update waveforms in the cloud waveform update command, or a specific waveform can be selected and sent to the edge device based on a pre-marked edge distribution identifier. This flexible processing method can reasonably allocate update data according to the actual capabilities of the edge device, ensuring that the edge device can successfully complete the update operation without affecting its normal operation due to excessive data volume, thus enhancing the system's adaptability and stability under different hardware conditions.

[0058] Based on the above embodiments, this application provides another load identification method, such as... Figure 3 As shown, the method can be executed by an edge device and may include: S201-S202.

[0059] S201: Collect the power consumption waveform of the target point and match the power consumption waveform with each preset power consumption waveform stored in the edge database to obtain each matching degree. Each matching degree is the first matching degree between the power consumption waveform and each first preset power consumption waveform.

[0060] S202: If at least one first matching degree is greater than the first preset threshold, the power consumption waveform is taken as the target power consumption waveform, and the edge load identification result containing the target power consumption waveform is sent to the cloud platform so that the cloud platform can perform load identification based on the edge load identification result and obtain the power consumption equipment corresponding to the target power consumption waveform.

[0061] The electrical equipment corresponding to the target power consumption waveform is identified by the cloud platform based on the edge load identification results and through the following methods: obtaining the scene information corresponding to the edge device, which is used to characterize the scene information applied by the user equipment corresponding to the edge device, and the scene information corresponding to the edge device is obtained after analyzing the historical edge load identification results corresponding to the edge device; performing load identification on the target power consumption waveform based on the scene information corresponding to the edge device to obtain the cloud load identification result; and determining the electrical equipment corresponding to the target power consumption waveform based on the cloud load identification result.

[0062] In this embodiment, the computing power and storage capacity of the cloud platform are greater than those of the edge devices. However, since the cloud platform may correspond to multiple edge devices, if the edge devices only act as data acquisition devices and send data to the cloud platform, the computational load of the cloud platform will also be too large. Therefore, in this embodiment, the edge devices can collect data at a preset frequency, such as a millisecond-level acquisition frequency. Since there are fewer waveforms stored in its database, data comparison can be performed quickly. Only when the matching degree exceeds the first preset threshold will the power waveform be marked as the target power waveform. That is, the edge devices can filter out most of the noise and atypical waveforms for the cloud platform, reducing the data processing load of the cloud platform.

[0063] Specifically, the specific implementation of load identification shown in the embodiments of this application can be found in the above embodiments, and will not be repeated here.

[0064] Corresponding to the load identification method in the above embodiments, Figure 4 This is a structural block diagram of a load identification device provided in one embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 4 The load identification device 30 is applied to a cloud platform. The device 30 includes: an edge data receiving module 31, a scene information acquisition module 32, and a cloud load identification module 33.

[0065] Among them, the edge data receiving module 31 is used to receive the edge load identification result sent by the edge device. The edge load identification result includes the target power consumption waveform. The first matching degree between the target power consumption waveform and at least one preset power consumption waveform stored in the edge database is greater than the first preset threshold. The target power consumption waveform is obtained by the edge device from the power consumption waveform of the target point. The scene information acquisition module 32 is used to acquire scene information corresponding to the edge device. The scene information corresponding to the edge device is used to characterize the scene information applied by the power equipment corresponding to the edge device. The scene information corresponding to the edge device is obtained after analyzing the historical edge load identification results corresponding to the edge device. The cloud load identification module 33 is used to identify the target power waveform based on the scene information corresponding to the edge device, obtain the cloud load identification result, and determine the power device corresponding to the target power waveform based on the cloud load identification result.

[0066] In one embodiment of this application, the cloud load identification module 33 is specifically used to filter out a set of candidate power consumption waveforms from a standard database based on the scene information corresponding to the edge device. The standard database stores preset power consumption waveforms corresponding to each scene information. The number of preset power consumption waveforms stored in the standard database is greater than the number of preset power consumption waveforms stored in the edge database. Load identification is performed on the target power waveform based on the candidate power waveform set to obtain the load identification result in the cloud.

[0067] In one embodiment of this application, the cloud load identification module 33 is further configured to match the target power consumption waveform with the candidate power consumption waveform set to obtain a first matching result, wherein the matching result includes a second matching degree between the target power consumption waveform and each candidate power consumption waveform; The electrical devices corresponding to the candidate electrical waveforms with a second matching degree greater than the second preset threshold are taken as the electrical devices corresponding to the target electrical waveforms.

[0068] In one embodiment of this application, the edge load identification result further includes a first candidate power device identifier, which is the power device identifier corresponding to a preset power waveform with a first matching degree greater than a first preset threshold. The cloud load identification module 33 is specifically used to filter out target candidate power waveforms from the candidate power waveform set. The target candidate power waveforms are preset power waveforms corresponding to the identifiers of each first candidate power device. For a power device, the number of preset power waveforms stored in the standard database is greater than the number of preset power waveforms stored in the edge database. The target power consumption waveform is matched with the target candidate power consumption waveform to obtain a second matching result. The second matching result includes a third matching degree between the target power consumption waveform and each target candidate power consumption waveform. The electrical equipment corresponding to the target candidate power consumption waveform with a third matching degree greater than the third preset threshold is taken as the electrical equipment corresponding to the target power consumption waveform.

[0069] In one embodiment of this application, the edge load identification result further includes a first candidate power device identifier and its corresponding first matching degree. The candidate power device identifier is the power device identifier corresponding to a preset power waveform whose first matching degree is greater than a first preset threshold. The cloud-based load identification module 33 is specifically used to match the target power consumption waveform with the candidate power consumption waveform set to obtain a third matching result. The third matching result includes a fourth matching degree between the power consumption waveform and each candidate power consumption waveform. The device identifier corresponding to the candidate power consumption waveform with a fourth matching degree greater than the third preset threshold is determined as the second candidate device identifier; For each first candidate electrical equipment identifier, if the second candidate electrical equipment identifier contains the first candidate electrical equipment identifier, then the matching degree of the first candidate electrical equipment identifier is increased to obtain the fifth matching degree corresponding to each first candidate electrical equipment identifier. Based on each fifth matching degree, the electrical equipment corresponding to the target power waveform is determined.

[0070] In one embodiment of this application, a standard database stores multiple candidate power consumption waveform sets corresponding to different scenario information. Each candidate power consumption waveform set contains a preset power consumption waveform corresponding to each power consumption identifier among multiple power consumption device identifiers. The load identification device 30 also includes a waveform update module, which is used to determine the candidate power consumption waveform set to be updated based on the scenario information carried in the cloud waveform update instruction if a cloud waveform update instruction is received. Based on the update device identifier and the update power waveform corresponding to the update device identifier carried in the cloud waveform update instruction, the preset power waveform corresponding to the update device identifier of the candidate power waveform to be updated is updated. The target edge device is determined based on the scene information carried in the cloud waveform update command, and an edge waveform update command is generated based on the update device identifier and the update power waveform corresponding to the update device identifier carried in the cloud waveform update command. The target edge device is the edge device to be updated in the edge database. Send an edge waveform update command to the target edge device so that the target edge device updates the corresponding edge waveform feature library based on the edge waveform update command.

[0071] Corresponding to the load identification method in the above embodiments, Figure 5 This is a structural block diagram of a load identification device provided in one embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 5 The load identification device 40 is applied to edge devices, and the device 40 includes a waveform acquisition module 41 and an identification result transmission module 42.

[0072] Among them, the waveform acquisition module 41 is used to acquire the power consumption waveform of the target point and match the power consumption waveform with each preset power consumption waveform stored in the edge database to obtain each matching degree. Each matching degree is the first matching degree between the power consumption waveform and each first preset power consumption waveform. The identification result sending module 42 is used to take the power waveform as the target power waveform if at least one first matching degree is greater than the first preset threshold, and send the edge load identification result containing the target power waveform to the cloud platform so that the cloud platform can perform load identification based on the edge load identification result and obtain the power equipment corresponding to the target power waveform. The electrical equipment corresponding to the target power consumption waveform is identified by the cloud platform based on edge load identification results and through the following methods: Obtain the scene information corresponding to the edge device. The scene information corresponding to the edge device is used to characterize the scene information applied by the user equipment corresponding to the edge device. The scene information corresponding to the edge device is obtained after analyzing the historical edge load identification results corresponding to the edge device. Load identification is performed on the target power waveform based on the scene information corresponding to the edge device, and the load identification result in the cloud is obtained; The target electrical waveform is used to identify the electrical equipment corresponding to it based on the load identification results in the cloud.

[0073] See Figure 6 , Figure 6 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 6 The electronic device 500 in this embodiment may include one or more processors 501, one or more input devices 502, one or more output devices 503, and one or more memories 504. The processors 501, input devices 502, output devices 503, and memories 504 communicate with each other via a communication bus 505. The memories 504 store computer programs, including program instructions. The processors 501 execute the program instructions stored in the memories 504. Specifically, the processors 501 are configured to invoke the program instructions to perform the functions of the modules in the aforementioned device embodiments, for example... Figure 4 The functions of the edge data receiving module 31, scene information acquisition module 32, and cloud load identification module 33 shown are as follows: Figure 5 The waveform acquisition module 41 and the recognition result transmission module 42 shown have the following functions. In other words, the electronic device 500 can be either the cloud platform shown above or the edge device shown above.

[0074] It should be understood that, in the embodiments of this application, the processor 501 may be a central processing unit (CPU), but it may also 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. The general-purpose processor may be a microprocessor or any conventional processor.

[0075] Input device 502 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 503 may include a display (LCD, etc.), a speaker, etc.

[0076] The memory 504 may include read-only memory and random access memory, and provides instructions and data to the processor 501. A portion of the memory 504 may also include non-volatile random access memory. For example, the memory 504 may also store device type information.

[0077] In specific implementations, the processor 501, input device 502, and output device 503 described in the embodiments of this application can execute the implementation method described in the load identification method provided in the embodiments of this application, or they can execute the implementation method of the electronic device described in the embodiments of this application, which will not be repeated here.

[0078] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to implement these processes. The computer program can be stored in the computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0079] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0080] This application provides a computer program product, which includes computer-executable instructions or a computer program. The computer-executable instructions or computer program are stored in a computer-readable storage medium. The processor of an electronic device reads the computer-executable instructions from the computer-readable storage medium and executes the computer-executable instructions, causing the electronic device to perform the load identification method described in this application embodiment.

[0081] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0082] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0083] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces or units, or they may be electrical, mechanical, or other forms of connection.

[0084] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0085] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0086] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A load identification method, characterized in that, Applied to cloud platforms, including: The edge load identification result sent by the edge device is received. The edge load identification result includes a target power consumption waveform. The first matching degree between the target power consumption waveform and at least one preset power consumption waveform stored in the edge database is greater than a first preset threshold. The target power consumption waveform is obtained by the edge device from the power consumption waveform of the target point. The scene information corresponding to the edge device is obtained. The scene information corresponding to the edge device is used to characterize the scene information applied by the power equipment corresponding to the edge device. The scene information corresponding to the edge device is obtained after analyzing the historical edge load identification results corresponding to the edge device. Based on the scene information corresponding to the edge device, the target power waveform is identified to obtain the cloud load identification result; Based on the cloud load identification results, the electrical equipment corresponding to the target power consumption waveform is determined.

2. The method according to claim 1, characterized in that, The process of identifying the target power waveform based on the scene information corresponding to the edge device to obtain the cloud-based load identification result includes: Based on the scene information corresponding to the edge device, a set of candidate power consumption waveforms is selected from the standard database. The standard database stores preset power consumption waveforms corresponding to each scene information. The number of preset power consumption waveforms stored in the standard database is greater than the number of preset power consumption waveforms stored in the edge database. Based on the candidate power consumption waveform set, the target power consumption waveform is identified by load recognition to obtain the cloud-based load recognition result.

3. The method according to claim 2, characterized in that, Based on the candidate power consumption waveform set, load identification is performed on the target power consumption waveform to obtain a cloud-based load identification result. Based on the cloud-based load identification result, the electrical equipment corresponding to the target power consumption waveform is determined, including: The target power consumption waveform is matched with the candidate power consumption waveform set to obtain a first matching result, and the matching result includes a second matching degree between the target power consumption waveform and each candidate power consumption waveform; The electrical devices corresponding to the candidate power consumption waveforms with a second matching degree greater than a second preset threshold are taken as the electrical devices corresponding to the target power consumption waveform.

4. The method according to claim 2, characterized in that, The edge load identification result also includes a first candidate electrical equipment identifier, which is the electrical equipment identifier corresponding to a preset electrical waveform with a first matching degree greater than a first preset threshold. The step of identifying the target power consumption waveform based on the candidate power consumption waveform set to obtain a cloud-based load identification result, and determining the power consumption equipment corresponding to the target power consumption waveform based on the cloud-based load identification result, includes: Target candidate power consumption waveforms are selected from the candidate power consumption waveform set. The target candidate power consumption waveforms are preset power consumption waveforms corresponding to the identifiers of each first candidate power consumption device. For a power consumption device, the number of preset power consumption waveforms stored in the standard database is greater than the number of preset power consumption waveforms stored in the edge database. The target power consumption waveform is matched with the target candidate power consumption waveform to obtain a second matching result. The second matching result includes a third matching degree between the target power consumption waveform and each target candidate power consumption waveform. The electrical equipment corresponding to the target candidate power consumption waveform with a third matching degree greater than a third preset threshold is taken as the electrical equipment corresponding to the target power consumption waveform.

5. The method according to claim 2, characterized in that, The edge load identification result also includes a first candidate electrical equipment identifier and its corresponding first matching degree. The candidate electrical equipment identifier is the electrical equipment identifier corresponding to a preset electrical waveform with a first matching degree greater than a first preset threshold. The step of identifying the target power consumption waveform based on the candidate power consumption waveform set to obtain a cloud-based load identification result, and determining the power consumption equipment corresponding to the target power consumption waveform based on the cloud-based load identification result, includes: The target power consumption waveform is matched with the candidate power consumption waveform set to obtain a third matching result, which includes a fourth matching degree between the power consumption waveform and each candidate power consumption waveform. The device identifier corresponding to the candidate power consumption waveform with a fourth matching degree greater than the third preset threshold is determined as the second candidate device identifier; For each first candidate electrical device identifier, if the second candidate electrical device identifier contains the first candidate electrical device identifier, then the matching degree of the first candidate electrical device identifier is increased to obtain the fifth matching degree corresponding to each first candidate electrical device identifier; Based on each of the fifth matching degrees, the electrical equipment corresponding to the target power waveform is determined.

6. The load identification method according to any one of claims 2-5, characterized in that, The standard database stores multiple candidate power consumption waveform sets corresponding to different scenario information. Each candidate power consumption waveform set contains a preset power consumption waveform corresponding to each power consumption identifier among multiple power consumption device identifiers. The method further includes: If a cloud waveform update instruction is received, the candidate power consumption waveform set to be updated is determined based on the scenario information carried in the cloud waveform update instruction. Based on the update device identifier and the update power consumption waveform corresponding to the update device identifier carried in the cloud waveform update instruction, the preset power consumption waveform corresponding to the update device identifier in the candidate power consumption waveform set to be updated is updated. The target edge device is determined based on the scene information carried in the cloud waveform update instruction, and an edge waveform update instruction is generated based on the update device identifier carried in the cloud waveform update instruction and the update power waveform corresponding to the update device identifier. The target edge device is the edge device to be updated in the edge database. The edge waveform update instruction is sent to the target edge device so that the target edge device updates the corresponding edge waveform feature library based on the edge waveform update instruction.

7. A load identification method, characterized in that, Applied to edge devices, including: Collect the power consumption waveform of the target point and match the power consumption waveform with each preset power consumption waveform stored in the edge database to obtain each matching degree. Each matching degree is the first matching degree between the power consumption waveform and each first preset power consumption waveform. If at least one first matching degree is greater than a first preset threshold, the power consumption waveform is taken as the target power consumption waveform, and the edge load identification result containing the target power consumption waveform is sent to the cloud platform, so that the cloud platform can perform load identification based on the edge load identification result to obtain the power consumption equipment corresponding to the target power consumption waveform; The electrical equipment corresponding to the target power consumption waveform is obtained by the cloud platform based on the edge load identification result and through the following method: The scene information corresponding to the edge device is obtained. The scene information corresponding to the edge device is used to characterize the scene information applied by the user equipment corresponding to the edge device. The scene information corresponding to the edge device is obtained after analyzing the historical edge load identification results corresponding to the edge device. Based on the scene information corresponding to the edge device, the target power waveform is identified to obtain the cloud load identification result; Based on the cloud load identification results, the electrical equipment corresponding to the target power consumption waveform is determined.

8. A load identification device, characterized in that, Applied to cloud platforms, including: An edge data receiving module is used to receive edge load identification results sent by an edge device. The edge load identification results include a target power consumption waveform. The first matching degree between the target power consumption waveform and at least one preset power consumption waveform stored in the edge database is greater than a first preset threshold. The target power consumption waveform is obtained by the edge device from the power consumption waveform of the target location. The scene information acquisition module is used to acquire the scene information corresponding to the edge device. The scene information corresponding to the edge device is used to characterize the scene information applied by the power-consuming equipment corresponding to the edge device. The scene information corresponding to the edge device is obtained after analyzing the historical edge load identification results corresponding to the edge device. The cloud load identification module is used to identify the target power waveform based on the scene information corresponding to the edge device, obtain the cloud load identification result, and determine the power device corresponding to the target power waveform based on the cloud load identification result.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 6 or the steps of the method as described in claim 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6 or the steps of the method as described in claim 7.

Images