Electricity utilization information management method and system, intelligent electric meter and acquisition terminal

Abstract

The application is suitable for the technical field of smart electricity meters, and provides an electricity information management method, system, smart electricity meter and acquisition terminal. The smart electricity meter collects electrical parameters of a total circuit and detects electrical appliance state change events, then uploads key data to a cloud server for complex load identification calculation, finally receives an identification result and locally decomposes detailed electricity information of a single electrical appliance and generates an electricity management report. The embodiment of the application not only avoids the expensive cost and complex operation of installing a sensor for each electrical appliance, enables a user to clearly master the energy consumption of each electrical appliance and thus promotes energy saving optimization, but also fully plays the advantages of the strong computing capacity of the cloud and the real-time response of the edge by means of the cloud-edge collaborative architecture, improves the identification accuracy and system efficiency, and significantly improves the intelligent level of electricity management and user experience.

Description

Technical Field

[0001] This application belongs to the field of smart meter technology, and in particular relates to a method, system, smart meter and data acquisition terminal for electricity information management. Background Technology

[0002] With the rapid development of smart grid and Internet of Things (IoT) technologies, users' demand for refined management of electricity consumption information is becoming increasingly urgent. Traditional smart meters primarily measure the total electricity consumption of a household or business, failing to provide detailed electricity consumption information for individual appliances (such as air conditioners, refrigerators, and water heaters). While technical solutions exist for sub-metering by installing smart sockets or sensors on each appliance, this invasive monitoring method is costly in hardware and complex to install and deploy, especially difficult to cover embedded appliances (such as central air conditioning and built-in ovens), hindering large-scale application. Therefore, how to automatically identify and monitor the electricity consumption information of various appliances in a low-cost and convenient manner without modifying the user's internal wiring or installing additional sensors has become a pressing technical problem in this field. Summary of the Invention

[0003] In view of this, the embodiments of this application provide an electricity information management method, system, smart meter and data acquisition terminal, which can solve the problem that it is difficult to automatically identify and monitor the electricity information of various electrical appliances in the home in a low-cost and convenient manner without modifying the user's internal wiring or installing additional sensing equipment.

[0004] In a first aspect, embodiments of this application provide an electricity consumption information management method. The method is applied to smart meters in an electricity consumption information management system based on load identification. The load identification-based electricity consumption information management system further includes a cloud server. The method includes:

[0005] Collect electrical parameter data of the user's main circuit;

[0006] Detection of electrical appliance status change events based on electrical parameter data;

[0007] In response to the detection of an electrical status change event, electrical parameter data is uploaded to the cloud server;

[0008] The cloud server receives the identification results after identifying the load based on electrical parameter data. The identification results are used to characterize the type of electrical appliance that has undergone a state change.

[0009] Based on the identification results, the electricity consumption information of the corresponding appliances is extracted from the total electricity consumption.

[0010] Electricity management reports are generated based on electricity consumption information.

[0011] Secondly, embodiments of this application provide an electricity consumption information management method. The method is applied to a cloud server in a load-identification-based electricity consumption information management system, which further includes smart meters. The method includes:

[0012] Receive electrical parameter data uploaded by smart meters;

[0013] Feature extraction is performed on electrical parameter data to obtain electrical features, which include steady-state features, transient features, and noise features.

[0014] The electrical characteristics are identified based on the electrical characteristic database to obtain the identification results.

[0015] Thirdly, embodiments of this application provide an electricity information management system based on load identification, the system including smart meters and cloud servers;

[0016] Smart meters are used to collect electrical parameter data of the user's main circuit;

[0017] Smart meters are also used to detect changes in the state of electrical appliances based on electrical parameter data;

[0018] Smart meters are also used to upload electrical parameter data to a cloud server in response to detected changes in the state of electrical appliances;

[0019] The cloud server is used to receive electrical parameter data uploaded by smart meters;

[0020] The cloud server is also used to extract features from electrical parameter data to obtain electrical features, which include steady-state features, transient features, and noise features.

[0021] The cloud server is also used to identify electrical characteristics based on the electrical characteristic database to obtain the identification results;

[0022] Smart meters are also used to receive the identification results obtained by the cloud server after identifying the load based on electrical parameter data. The identification results are used to characterize the type of electrical appliance that has undergone a state change.

[0023] Smart meters are also used to extract the electricity consumption information of the corresponding appliances from the total electricity consumption based on the identification results;

[0024] Smart meters are also used to generate electricity management reports based on electricity consumption information.

[0025] Fourthly, embodiments of this application provide a smart meter, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the electricity information management method of the first aspect described above.

[0026] Fifthly, embodiments of this application provide a data acquisition terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The data acquisition terminal is applied to a load-based electricity consumption information management system, which further includes a cloud server. The data acquisition terminal is used to execute the steps of the electricity consumption information management method described in the second aspect above.

[0027] Sixthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described electricity information management method.

[0028] Seventhly, embodiments of this application provide a computer program product that, when running on a smart meter, causes the smart meter to execute the aforementioned electricity information management method.

[0029] The beneficial effects of this application embodiment compared to the prior art are as follows: This application embodiment collects the electrical parameters of the total circuit and detects changes in the status of electrical appliances through a smart meter. Then, it uploads the key data to a cloud server for complex load identification calculations. Finally, it receives the identification results and locally decomposes the detailed power consumption information of individual electrical appliances and generates a power management report. This application embodiment not only avoids the expensive cost and complex operation of installing sensors for each electrical appliance, allowing users to clearly understand the energy consumption of each appliance and thus promote energy-saving optimization, but also fully leverages the powerful computing capabilities of the cloud and the real-time response advantages of the edge through a cloud-edge collaborative architecture, improving identification accuracy and system efficiency, and significantly enhancing the intelligence level of power management and user experience. Attached Figure Description

[0030] 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.

[0031] Figure 1 This is a schematic diagram illustrating the implementation process of the electricity information management method provided in this application embodiment.

[0032] Figure 2 This is a schematic diagram illustrating the implementation process of the electricity information management method provided in this application embodiment.

[0033] Figure 3 This is a schematic diagram of the structure of the smart meter provided in the embodiments of this application.

[0034] Figure 4This is a schematic diagram of the data acquisition terminal provided in the embodiments of this application. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are protected by this application.

[0036] It should be noted that the terms "comprising," "including," and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application, are intended to cover non-exclusive inclusion. For example, a process, method, terminal, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices. Terms such as "first" and "second" in the claims, specification, and accompanying drawings of this application, as well as relational terms, are used merely to distinguish one entity / operation / object from another entity / operation / object, and do not necessarily require or imply any such immediate relationship or order between these entities / operations / objects.

[0037] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0038] With the rapid development of smart grid and Internet of Things (IoT) technologies, users' demand for refined management of electricity consumption information is becoming increasingly urgent. Traditional smart meters primarily measure the total electricity consumption of a household or business, failing to provide detailed electricity consumption information for individual appliances (such as air conditioners, refrigerators, and water heaters). While technical solutions exist for sub-metering by installing smart sockets or sensors on each appliance, this invasive monitoring method is costly in hardware and complex to install and deploy, especially difficult to cover embedded appliances (such as central air conditioning and built-in ovens), hindering large-scale application. Therefore, how to automatically identify and monitor the electricity consumption information of various appliances in a low-cost and convenient manner without modifying the user's internal wiring or installing additional sensors has become a pressing technical problem in this field.

[0039] In view of this, this application provides an electricity information management method. This method collects the electrical parameters of the overall circuit using smart meters and detects changes in the status of electrical appliances. The key data is then uploaded to a cloud server for complex load identification calculations. Finally, the identification results are received, and detailed electricity consumption information for each individual appliance is extracted locally, generating an electricity management report. This application not only avoids the expensive cost and complex operation of installing sensors for each appliance, allowing users to clearly understand the energy consumption of each appliance and thus promoting energy-saving optimization, but also fully leverages the powerful computing capabilities of the cloud and the real-time response advantages of the edge through a cloud-edge collaborative architecture. This improves identification accuracy and system efficiency, significantly enhancing the intelligence level of electricity management and the user experience.

[0040] To illustrate the technical solution of this application, specific embodiments are described below.

[0041] Figure 1 The illustration shows a schematic diagram of an implementation process for an electricity consumption information management method provided in an embodiment of this application. This method can be applied to smart meters in an electricity consumption information management system based on load identification. The aforementioned electricity consumption information management system based on load identification may also include a cloud server.

[0042] Specifically, a smart meter is an electricity metering device installed on the main power circuit of a user's home. In addition to the basic electrical parameter measurement functions of a traditional meter, such as voltage, current, and power, it also integrates a data processing unit and a communication module, which can perform local calculations and interact with cloud servers.

[0043] A cloud server is a cluster of servers located in a remote data center. It has powerful computing and storage capabilities and can be used to run complex load identification algorithms and maintain a large database of appliance characteristics.

[0044] Specifically, the above-mentioned electricity information management method may include the following steps S101 to S106.

[0045] Step S101: Collect electrical parameter data of the user's main circuit.

[0046] Electrical parameter data refers to the digital representation of the original analog signals that reflect the electrical state of the overall circuit, collected by the smart meter through internal sensors (such as voltage transformers and current transformers). It can include instantaneous voltage values, instantaneous current value sequences, and derived parameters such as active power, reactive power, and harmonics can be calculated from them.

[0047] In embodiments of this application, a smart meter can synchronously sample voltage and current signals on the main household circuit at a high frequency (e.g., above 1 kHz) using its built-in voltage and current sensors. The raw data collected may include electrical parameters such as instantaneous voltage values, instantaneous current values, and instantaneous power calculated therefrom. This data is digitized by an analog-to-digital converter and stored with a timestamp in the smart meter's temporary cache.

[0048] Step S102: Detect electrical state change events based on the electrical parameter data.

[0049] Among them, electrical state change events refer to the moment or short process in which the overall electrical parameters (such as total active power) of a circuit change significantly due to the opening, closing or operation mode switching of a certain electrical device (such as the air conditioner switching from cooling mode to ventilation mode).

[0050] In the embodiments of this application, the smart meter can calculate the change in total active power within adjacent sampling points or a short time period (e.g., a 1-second window) in real time, and set a dynamic or static change threshold (e.g., 50 watts). When the absolute value of the power change exceeds this threshold, it is determined that an electrical appliance state change event has occurred, that is, an appliance is turned on, turned off, or its power is switched, thereby accurately capturing the critical point of the change in the state of electrical equipment from the continuous electrical data stream.

[0051] Step S103: In response to detecting the electrical appliance state change event, the electrical parameter data is uploaded to the cloud server.

[0052] In the embodiments of this application, when an event is determined to have occurred, the smart meter can immediately upload high-precision current waveform data and related electrical parameters within a time window before and after the event (e.g., 0.5 seconds before the event to 2 seconds after the event) to the cloud server via its communication module (such as 4G / 5G, Wi-Fi, or power line carrier PLC). This achieves effective transmission of key data, ensuring the data integrity required by the cloud recognition algorithm while minimizing unnecessary network traffic and cloud storage pressure.

[0053] Step S104: Receive the identification result obtained by the cloud server after identifying the load based on the electrical parameter data.

[0054] The identification result is used to characterize the type of appliance that underwent the state change. Specifically, the identification result refers to the structured information output by the cloud server after completing the load identification algorithm. It at least includes the appliance type identifier that triggered the event (such as "air conditioner" or "refrigerator"), and can be further extended to include the specific device identity (such as "living room air conditioner") and its operating mode (such as "cooling mode").

[0055] In the embodiments of this application, the smart meter can listen to and receive feedback data packets from the cloud server through a communication module. The feedback data packets contain the parsed identification results. After receiving the data, the smart meter can parse and store it, thereby completing the transmission of the cloud-based intelligent identification results back to the edge side. This provides clear instructions and basis for the edge side to perform specific electricity consumption information decomposition actions.

[0056] Step S105: Based on the identification result, extract the power consumption information of the appliance corresponding to the identification result from the total power consumption.

[0057] Among them, electricity consumption information refers to the detailed electricity consumption data of a specific appliance that is extracted from the total electricity consumption. This data may include the appliance's electricity consumption, average power, running time, start and stop timestamps, etc., during a specific period.

[0058] In the embodiments of this application, the smart meter can, based on the received identification result (such as "refrigerator is on"), subtract the corresponding typical operating power curve of the appliance from the continuously collected total power curve from the time the event occurs, thereby separating the power consumption of the appliance from the total, and recording its start-stop time, operating power curve, etc., and finally calculating the precise power consumption of each appliance in a specific time period, realizing the conversion from macro total power consumption to micro device-level power consumption information.

[0059] Step S106: Generate an electricity management report based on the electricity consumption information.

[0060] Among them, the electricity management report refers to the comprehensive information summary that is finally generated and presented to users. Its content is based on the decomposed electricity information and can be in the form of a mobile APP interface, web page or paper report. It is used to intuitively display the device-level electricity details, energy efficiency analysis, cost estimation and abnormal alarms to users.

[0061] In the embodiments of this application, the smart meter can summarize, analyze and format the electricity consumption information (such as daily electricity consumption, monthly electricity consumption, peak power, etc.) of each appliance obtained from the decomposition, and generate an electricity management report that can be intuitively understood by the user. The report content may include a ranking of high-energy-consuming devices, electricity consumption habit analysis, electricity cost estimation, and abnormal power consumption warnings of devices, and is displayed to the user through a local display screen or network to the user's mobile APP, thereby transforming the raw electricity consumption data into decision information with practical guiding significance.

[0062] The beneficial effects of this application embodiment compared to the prior art are as follows: This application embodiment collects the electrical parameters of the total circuit and detects changes in the status of electrical appliances through a smart meter. Then, it uploads the key data to a cloud server for complex load identification calculations. Finally, it receives the identification results and locally decomposes the detailed power consumption information of individual electrical appliances and generates a power management report. This application embodiment not only avoids the expensive cost and complex operation of installing sensors for each electrical appliance, allowing users to clearly understand the energy consumption of each appliance and thus promote energy-saving optimization, but also fully leverages the powerful computing capabilities of the cloud and the real-time response advantages of the edge through a cloud-edge collaborative architecture, improving identification accuracy and system efficiency, and significantly enhancing the intelligence level of power management and user experience.

[0063] In some specific embodiments of this application, after generating the electricity management report based on the electricity consumption information, steps S401 to S405 may be included.

[0064] Step S401: Determine whether the identification result corresponds to an unidentifiable appliance type.

[0065] In the embodiments of this application, after receiving the identification result data packet returned by the cloud server, the smart meter can first parse the status code indicating whether the identification was successful or not and the confidence score of the identification result in the data packet. When the status code clearly indicates "identification failure" or the confidence score is lower than a preset threshold (e.g., 0.6), it is determined that the current identification result corresponds to an unidentifiable appliance type. This ensures that the self-learning function is only activated when the system actually encounters an unknown or uncertain appliance, avoiding unnecessary user interference and ensuring the validity of the sample data.

[0066] Step S402: If it is determined that the identification result corresponds to an unidentifiable appliance type, a device information input request is sent to the user terminal. The device information input request includes prompting the user to input the type identifier of the appliance.

[0067] The user terminal refers to the terminal device used by users to interact with the electricity information management system. Its specific form can be an application on a smartphone, a web platform on a computer, or a smart home control screen, etc.

[0068] In the embodiments of this application, when the smart meter determines that user assistance is required, the smart meter can immediately generate a structured device information input request instruction. This instruction can be sent to the user's bound mobile APP via the home LAN or mobile network. The request instruction not only includes text prompts (such as "The system has found a new device, please help confirm"), but also carries parameters for generating an interactive interface, guiding the user to select from a preset list of appliance categories or manually enter the appliance name.

[0069] Step S403: Receive device information returned by the user terminal, the device information including the type of electrical appliance confirmed by the user.

[0070] Device information refers to descriptive information about unidentified appliances provided by users through the user terminal. The core of this information is the appliance type identifier (such as "air conditioner" or "refrigerator") confirmed or entered by the user, and can be expanded to include more refined identity information such as user-defined device names (such as "master bedroom air conditioner") and brand models.

[0071] In the embodiments of this application, after the user completes the selection or input of the appliance type on the mobile APP and clicks to confirm, the APP will encapsulate the device information submitted by the user (such as "Type: Air Conditioner, Name: Study Air Conditioner") into a data packet and send it back to the smart meter or directly send it to the cloud server via the network. After receiving this information, the smart meter can parse and temporarily store it.

[0072] Step S404: Associate the device information with the electrical parameter data corresponding to the electrical state change event to generate self-learning sample data.

[0073] In the embodiments of this application, the smart meter can use the timestamp of the event as the association key to retrieve high-frequency sampled electrical parameter data (including voltage and current waveforms) of the appliance reported by the user from the local storage within a time window before and after the state change event. Then, the user-confirmed appliance type label is bound to these original waveform data or feature vectors extracted from the waveforms to generate a self-learning sample data package. This self-learning sample data package contains the "question" (electrical data) and the "answer" (appliance type), thereby providing direct learning material for the cloud server to update the model.

[0074] Step S405: Send the self-learning sample data to the cloud server to update the electrical appliance feature database in the cloud server.

[0075] In the embodiments of this application, the smart meter can upload the generated self-learning sample data to the cloud server through a secure communication link. After receiving the sample, the cloud server can store it in a sample pool to be processed. When a certain number of samples are accumulated or specific conditions are met, the model retraining process can be started, and the load identification algorithm can be optimized by using both new and old samples. Alternatively, the sample can be added directly to the database as a new feature template, enabling the load identification-based electricity information management system to continuously learn new knowledge from the actual usage environment. Ultimately, this achieves the dynamic growth of the electrical appliance feature database and the continuous evolution of identification capabilities.

[0076] This application incorporates user feedback into the closed-loop optimization process of load identification. When the system encounters unknown electrical appliances or insufficient identification confidence, it can proactively request user assistance in labeling. The labeled information is then combined with the corresponding electrical feature data to form high-quality training samples, which are fed back to the cloud to continuously optimize and expand the charger feature database. This effectively solves the identification blind spot problem caused by incomplete databases in the early stages of system deployment, significantly improving the initial applicability and user experience of the system. It allows the system to proactively adapt to new models of electrical appliances constantly emerging in the market and user-specific electrical equipment, significantly enhancing the long-term practical value of the system.

[0077] In some specific embodiments of this application, after receiving the identification result obtained by the cloud server after identifying the load based on the electrical parameter data, steps S501 to S505 may be included.

[0078] Step S501: Obtain the reference starting current and reference operating energy efficiency parameters of the electrical appliance corresponding to the identification result.

[0079] The reference starting current refers to the typical peak or effective value of the current extracted from the total circuit current waveform at the moment of startup of a specific electrical appliance in its factory standard state or in the early stage of healthy operation.

[0080] The benchmark operating energy efficiency parameters refer to the key parameters that characterize the energy conversion efficiency of an appliance after it enters steady-state operation under rated operating mode. These parameters include, for example, the ratio of active power to apparent power (power factor), or the unit energy consumption under a specific output.

[0081] In the embodiments of this application, after receiving the load identification result, the smart meter can query the standard parameter file of the identified appliance model (e.g., "air conditioner model XXX") in the local cache or cloud appliance feature database to obtain its benchmark starting current (e.g., 5A) and benchmark operating energy efficiency parameters (e.g., power factor 0.9). If the appliance is being identified for the first time or lacks a preset benchmark, its starting current and operating energy efficiency parameters can be automatically recorded and the average value calculated as an initial benchmark value stored in the database during the initial few identification and confirmed normal operation cycles.

[0082] Step S502: Monitor the current starting current and current operating energy efficiency parameters of the electrical appliance in real time.

[0083] The current starting current refers to the maximum or characteristic value of the transient starting current captured in real time from the total current sampling data in the most recent detected electrical starting event.

[0084] Current operating energy efficiency parameters refer to the energy efficiency index calculated based on real-time voltage and current data after the appliance has entered a stable state in the latest operating cycle.

[0085] In the embodiments of this application, whenever the load identification result confirms that an appliance is in operation, the smart meter can accurately analyze the current waveform data before and after the appliance starts, extract the current starting current (usually the peak current during the transient process of starting), and calculate the current operating energy efficiency parameters (such as power factor) based on the voltage and current data within a time window after the appliance enters a stable operating state (such as 30 seconds after starting).

[0086] Step S503: Compare the current starting current with the reference starting current to obtain a first comparison result, and compare the current operating energy efficiency parameter with the reference operating energy efficiency parameter to obtain a second comparison result.

[0087] In embodiments of this application, the smart meter can calculate the absolute difference or relative percentage change between the current starting current and the reference starting current as a first comparison result, and simultaneously calculate the difference or ratio between the current operating energy efficiency parameter and the reference operating energy efficiency parameter as a second comparison result. For example, if the current starting current is 6.1A and the reference is 5A, the first comparison result is a 22% increase in current. If the current power factor is 0.8 and the reference is 0.9, the second comparison result is an approximately 11% decrease in efficiency.

[0088] Step S504: When the first comparison result and / or the second comparison result exceed the corresponding preset health alarm threshold, generate device health status warning information.

[0089] In the embodiments of this application, the smart meter can compare the first comparison result and the second comparison result with preset health alarm thresholds (for example, the threshold for increased starting current is set to 20%, and the threshold for decreased energy efficiency is set to 10%). If any comparison result or its combination (such as weighted score) exceeds the threshold, the alarm generation logic is triggered to automatically create an alarm message for the device health status, which includes the abnormal device ID, abnormal parameters (such as "starting current exceeds the standard"), the extent of the exceedance, the timestamp, and the recommended maintenance action.

[0090] Step S505: Incorporate the device health status early warning information into the power consumption management report.

[0091] In the embodiments of this application, the smart meter can add the generated device health status warning information as an independent chapter or tag to the data structure of the electricity management report that is being generated or already exists. Then, it can be visualized through the local display of the smart meter or sent to the user's mobile APP, computer terminal, etc. via the communication module, so that the user can clearly see specific warning content such as "Your master bedroom air conditioner has an abnormally high starting current, which may be due to aging. It is recommended to contact maintenance".

[0092] This application's implementation method automatically acquires personalized baseline parameters of electrical appliances and continuously compares them with real-time operating data. It can detect abnormalities in the early stages when equipment performance deteriorates slightly (such as increased current due to increased motor starting resistance) or operating efficiency decreases (such as decreased energy efficiency due to compressor aging). This generates accurate equipment health status warnings and integrates them into the power consumption report. This allows users and maintenance personnel to shift from the traditional "post-fault repair" to a preventive maintenance mode of "pre-fault warning," reducing the risk of power outages and economic losses caused by sudden equipment failures and extending the service life of the equipment.

[0093] In some specific embodiments of this application, the electrical parameter data includes voltage signals and current signals, and the detection of electrical state change events based on the electrical parameter data may specifically include steps S601 to S604.

[0094] Step S601: Calculate the total active power within a set time window based on the voltage signal and the current signal.

[0095] The set time window is a continuous data processing period, the length of which is configurable (e.g., 1 second or 2 seconds).

[0096] Total active power refers to the average active power value calculated based on the integral (or approximate summation) of the product of instantaneous voltage signal and instantaneous current signal within a set time window. It can reflect the actual power consumed by the load within that window.

[0097] In the embodiments of this application, the smart meter can read synchronously sampled instantaneous voltage signal sequences and instantaneous current signal sequences from the cache. For each set time window (e.g., a length of 1 second containing 4000 sampling points), the instantaneous voltage value and the instantaneous current value at the same moment are multiplied to obtain the instantaneous power. Then, all instantaneous power values ​​within the window are accumulated and averaged to calculate the average total active power within the time window. This calculation process is continuously rolled over, and an active power value is calculated for each window, thereby forming a series of active power sequences that change with time. This transforms the original voltage and current waveform data into time series features that can intuitively reflect the overall load level and are easy to process.

[0098] Step S602: Calculate the absolute value of the change in total active power between adjacent time windows based on the total active power.

[0099] The absolute value of the change in total active power refers to the absolute value of the difference between the total active power values ​​of two adjacent set time windows, which can be used to capture power step changes caused by appliance switching or mode switching.

[0100] In the embodiments of this application, whenever the total active power value of a new time window is calculated, the smart meter can immediately retrieve the total active power value of the previous time window from the cache, then calculate the difference between the two and take the absolute value, thereby obtaining the absolute value of the change in total active power between adjacent time windows, thus transforming the continuous active power sequence into a series of abrupt change data, highlighting the moment when the total load of the circuit changes significantly.

[0101] Step S603: Compare the absolute value of the total active power change with a preset event detection threshold.

[0102] In the embodiments of this application, the smart meter can compare the absolute value of the power change with a preset event detection threshold (e.g., 50 watts) to determine whether the absolute value of the power change is greater than the preset event detection threshold.

[0103] Step S604: When the absolute value of the change in active power is greater than the event detection threshold, it is determined that an electrical appliance state change event has occurred.

[0104] In the embodiments of this application, when the comparison result is true, that is, the absolute value of the power change is greater than the preset event detection threshold, the smart meter can generate a flag signal of "electrical appliance status change event" and give the event a precise timestamp, recording the time of the event, the magnitude of the power change and the direction of change (increase / decrease), and then the event signal will trigger the subsequent data upload process.

[0105] This application's implementation utilizes voltage and current signals conventionally collected by smart meters. It calculates the total active power within a set time window and converts it into power changes in adjacent windows, then compares this with a reasonably set threshold to accurately capture state change events such as appliance start-up / stopping or mode switching. The algorithm in this application has low computational complexity, making it ideal for real-time execution on resource-constrained smart meters. This avoids continuous reliance on cloud computing resources and significantly reduces the amount of data that needs to be uploaded (uploaded only when an event is detected), thereby significantly reducing communication bandwidth requirements and overall system power consumption.

[0106] In some specific embodiments of this application, the step of extracting the power consumption information of the appliance corresponding to the identification result from the total power consumption based on the identification result may specifically include steps S701 to S704.

[0107] Step S701: Based on the identification result, obtain the typical operating power curve of the corresponding electrical appliance from the pre-stored electrical appliance feature database.

[0108] Among them, the typical operating power curve refers to the regular waveform or data sequence of the active power of a specific model of electrical appliance changing over time under standard test conditions or typical operating modes. This curve can be obtained through laboratory measurement or learning from a large amount of historical operating data and is pre-stored in the electrical appliance characteristic database as a benchmark template for decomposing the power consumption of the electrical appliance. Its characteristics include start-up transient, steady-state operating power and shutdown curve, etc.

[0109] In the embodiments of this application, after receiving the load identification result, the smart meter can query the appliance characteristic database maintained locally or in the cloud based on the appliance type identifier (such as "air conditioner model ABC") determined in the identification result, retrieve and obtain the typical operating power curve data corresponding to that appliance model. The typical operating power curve data is usually stored in the form of a time-power value array, covering the full cycle power change mode of the appliance from startup, steady-state operation to shutdown. If the appliance operates in multiple modes (such as the cooling and ventilation modes of an air conditioner), the corresponding specific curve can be obtained based on the operating mode information in the identification result.

[0110] Step S702: Based on the appliance start-stop time in the identification result, extract the power sequence for the corresponding time period from the total power consumption data.

[0111] Among them, the start-stop time of an appliance refers to the specific timestamp of the change in the state of the appliance, including the moment of turning on (such as a sudden increase in power) and turning off (such as a sudden decrease in power).

[0112] A power sequence is an array of power values ​​arranged in chronological order within a continuous time period extracted from the total active power data continuously collected by smart meters, based on the start-stop time of appliances. This sequence reflects the detailed changes in the total circuit power during that time period.

[0113] In the embodiments of this application, the smart meter can extract all active power samples from the historical active power data buffer stored cyclically in the smart meter, based on the precise start and stop timestamps (e.g., start time T_start, stop time T_end) carried in the identification result. The sample range is from a short time before T_start (e.g., 0.5 seconds earlier to capture the start-up transient) to a short time after T_end (e.g., 0.5 seconds later to capture the stop-down transient), forming a continuous power sequence. Since this power sequence may contain the power superposition of other parallel-operating appliances, baseline correction or filtering preprocessing can be performed.

[0114] Step S703: Match the power sequence with the typical operating power curve to calculate and decompose the independent power consumption of the appliance within the time period.

[0115] In the embodiments of this application, the smart meter can employ signal processing algorithms. Specifically, the smart meter can calculate the cross-correlation function between the actual power sequence and the typical power curve to find the optimal alignment point. Then, it can estimate a scaling factor using the least squares method, or scale and translate the typical curve and fit it with the actual sequence by minimizing the difference. The meter can then calculate the proportion coefficient contributed by the appliance represented by the typical curve in the actual power sequence, thereby decomposing the total power sequence into the power component of the appliance and the power components of the remaining appliances. Finally, it can integrate (i.e. sum) the power component of the appliance over time to obtain its independent electricity consumption during the start-stop period.

[0116] Step S704: Generate the power consumption information of the appliance based on the independent power consumption, the power consumption information including power consumption and operating time.

[0117] In the embodiments of this application, the smart meter can associate the calculated independent electricity consumption with the running time calculated based on the start-stop time difference to generate a structured electricity consumption record. This record can at least include fields such as appliance ID, electricity consumption, running time, and time period start timestamp, and can further calculate derived indicators such as average power and peak power, and store them in a local database or send them to the user terminal.

[0118] This application's implementation utilizes pre-stored high-precision typical operating power curves of electrical appliances as decomposition templates and performs intelligent matching calculations with the real-time acquired total power sequence. This effectively isolates the power contribution of specific electrical appliances from the mixed total load signal, thereby calculating their independent power consumption and operating time. This implementation employs a waveform matching-based decomposition method, which has strong anti-interference capabilities and significantly improves the accuracy and reliability of non-intrusive load decomposition, making it particularly suitable for distinguishing electrical appliances with similar power characteristics.

[0119] Figure 2 The illustration shows a schematic diagram of an implementation process for an electricity consumption information management method according to an embodiment of this application. This method can be applied to a cloud server in an electricity consumption information management system based on load identification. The aforementioned electricity consumption information management system based on load identification may also include smart meters.

[0120] Specifically, the method may include steps S801 to S803.

[0121] Step S801: Receive electrical parameter data uploaded by the smart meter.

[0122] In the embodiments of this application, the cloud server can continuously listen to and receive data packets uploaded from the smart meter. These data packets can be compressed and encrypted. The cloud server can first unpack, decrypt and verify them to restore valid electrical parameter data. The data should include complete timestamp information and the voltage and current instantaneous value sequence collected by the smart meter or the power data after preliminary processing. The received data will be stored in the real-time database or message queue in the cloud for subsequent processing.

[0123] Step S802: Extract features from the electrical parameter data to obtain electrical features, which include steady-state features, transient features, and noise features.

[0124] Among them, steady-state characteristics are the features of electrical appliances under stable operating conditions, such as steady-state active power, reactive power, total harmonic distortion (THD) of current, and the amplitude and phase of each harmonic (such as the 3rd and 5th harmonics).

[0125] Transient characteristics are the features exhibited by electrical appliances during the transition process of turning on, turning off, or switching power, such as the peak value of the starting current, rise time, and duration.

[0126] Noise characteristics are the spectral distribution features of high-frequency noise in a specific frequency band (such as 2kHz-150kHz) of a current signal. Different electrical appliances produce unique noise fingerprints due to the different operating modes of their internal power electronic components.

[0127] In the embodiments of this application, after retrieving electrical parameter data from the cache, the cloud server calls its built-in feature extraction algorithm module to first preprocess the current and voltage waveform data, such as denoising, filtering, and calibration. Then, it performs multi-dimensional feature calculations in parallel or serially. For example, it calculates the mean and variance of active / reactive power through a sliding window to obtain steady-state features, captures parameters of power mutation points through edge detection and waveform analysis to obtain transient features, and applies Fast Fourier Transform (FFT) or wavelet transform to analyze the spectral energy distribution of the current signal in the high-frequency band (such as 2kHz-150kHz) to obtain noise features. Finally, it combines these parameters that reveal the operating characteristics of electrical appliances from different dimensions into a high-dimensional feature vector, thereby transforming the original waveform data into a set of mathematical features that can effectively distinguish different types of electrical appliances.

[0128] Step S803: Perform load identification on the electrical features according to the electrical feature database to obtain the identification result.

[0129] In the embodiments of this application, the cloud server can input the feature vector into a pre-trained machine learning classification model (such as a deep learning neural network, support vector machine SVM, or gradient boosting decision tree). This model is trained on a feature sample library of massive known electrical appliances (i.e., an electrical appliance feature database). The model can perform similarity calculation or probability classification between the input feature vector and the feature templates of various electrical appliances stored in the library, and finally output one or more most likely electrical appliance types and their confidence scores, thereby obtaining the recognition result.

[0130] This application's implementation fully utilizes the powerful computing capabilities and storage space of cloud servers to run highly complex feature extraction algorithms (such as deep neural networks) and compare against a massive library of electrical appliance feature templates. This significantly improves the accuracy of load identification and the range of identifiable electrical appliances, overcoming the bottleneck of performing complex calculations locally on resource-constrained smart meters. Simultaneously, the cloud-based solution reduces the hardware computing power requirements of the terminal smart meter, helping to control terminal costs and power consumption, while centralized processing facilitates deeper aggregation and analysis of regional electricity consumption data.

[0131] In some specific embodiments of this application, the step of identifying the electrical characteristics based on the electrical characteristic database to obtain the identification result may specifically include steps S901 to S906.

[0132] Step S901: Perform feature vectorization processing on the electrical features to generate standardized feature vectors.

[0133] In the embodiments of this application, the cloud server can first perform data cleaning on the electrical features to remove outliers, and then use a normalization algorithm (such as Z-score standardization or min-max scaling) to scale each feature value to the range of [0,1] to avoid the influence of dimensions. Then, a dimensionality unification technique (such as principal component analysis PCA) can be used to reduce the high-dimensional features to a fixed dimension (such as 50 dimensions) to generate a standardized feature vector, which can be used as the input for subsequent similarity calculation.

[0134] Step S902: Calculate the similarity between the standardized feature vector and multiple typical feature vectors pre-stored in the electrical appliance feature database to obtain a set of similarity values.

[0135] In the embodiments of this application, the cloud server can employ a cosine similarity algorithm to calculate the similarity between the input vector and each template vector. Specifically, the cloud server can first treat the vectors as points in space and calculate the cosine value of the angle between them. Then, it iterates through all templates in the database to obtain a set of similarity values, forming a similarity value set.

[0136] Step S903: Select the maximum similarity value from the set of similarity values ​​and determine the corresponding appliance type as the candidate recognition result.

[0137] In the embodiments of this application, the cloud server can identify the maximum similarity value by traversing the set and using a maximum value search algorithm (such as linear scanning or sorting). Then, based on the index of the value in the set, it can map it to the corresponding appliance type in the appliance feature database (such as the maximum similarity value corresponding to index 0 for air conditioner and index 1 for refrigerator) as a candidate identification result, including appliance type (such as "air conditioner") and maximum similarity value.

[0138] Step S904: Compare the maximum similarity value with a preset confidence threshold.

[0139] In the embodiments of this application, the cloud server can perform numerical comparisons. If the maximum similarity value is greater than or equal to a preset confidence threshold, it is marked as high confidence; otherwise, it is marked as low confidence. This yields a Boolean flag (true or false) to drive subsequent branches.

[0140] Step S905: If the maximum similarity value is greater than or equal to the preset confidence threshold, then the candidate recognition result is output as the recognition result.

[0141] In the embodiments of this application, if the maximum similarity value is greater than or equal to the preset threshold, the cloud server can directly output the candidate appliance type as the final identification result without additional calculation. Simultaneously, the cloud server can record the result in a log and prepare to send it back to the smart meter.

[0142] Step S906: If the maximum similarity value is less than the preset confidence threshold, the standardized feature vector is input into the machine learning recognition model for load recognition, and the recognition result is output.

[0143] In the embodiments of this application, if the maximum similarity value is less than the preset confidence threshold, the cloud server can first input the standardized feature vector into the machine learning recognition model. The machine learning recognition model can calculate the output probability distribution through forward propagation, and then select the appliance type with the highest probability as the recognition result. For example, the model may output a probability of 0.7 for "air conditioner" and a probability of 0.3 for "refrigerator", and finally select "air conditioner".

[0144] This application's implementation method unifies the feature scale through feature vectorization, avoiding calculation biases caused by differences in units. Combined with similarity calculation and threshold verification, it can accurately match known appliances and reduce misjudgments. Secondly, a machine learning-assisted path serves as a backup, automatically activated when similarity matching is insufficient, enabling the system to adapt to new appliances or complex operating modes and enhancing robustness.

[0145] This application provides an electricity information management system based on load identification, the system including smart meters and a cloud server;

[0146] The smart meter is used to collect electrical parameter data of the user's main circuit;

[0147] The smart meter is also used to detect electrical appliance status change events based on the electrical parameter data;

[0148] The smart meter is also used to upload the electrical parameter data to a cloud server in response to detecting a change in the state of the electrical appliance;

[0149] The cloud server is used to receive electrical parameter data uploaded by the smart meter;

[0150] The cloud server is also used to extract features from the electrical parameter data to obtain electrical features, which include steady-state features, transient features, and noise features.

[0151] The cloud server is also used to identify the electrical characteristics based on the electrical characteristic database and obtain the identification result;

[0152] The smart meter is also used to receive the identification result obtained by the cloud server after load identification based on the electrical parameter data, and the identification result is used to characterize the type of electrical appliance that has undergone a state change;

[0153] The smart meter is also used to extract the electricity consumption information of the appliance corresponding to the identification result from the total electricity consumption based on the identification result;

[0154] The smart meter is also used to generate an electricity management report based on the electricity consumption information.

[0155] like Figure 3 The diagram shown is a schematic of a smart meter according to an embodiment of this application. The smart meter 3 may include a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301, such as a load-based electricity consumption information management program. When the processor 301 executes the computer program 303, it implements the steps described in the various load-based electricity consumption information management embodiments, for example... Figure 1 Steps S101 to S106 are shown.

[0156] A computer program can be divided into one or more modules / units. One or more modules / units are stored in memory 302 and executed by processor 301 to complete this application. One or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in a smart meter.

[0157] Smart meters may include, but are not limited to, processor 301 and memory 302. Those skilled in the art will understand that... Figure 3 This is merely an example of a smart meter and does not constitute a limitation on smart meters. It may include more or fewer components than shown in the illustration, or combine certain components, or different components. For example, a smart meter may also include input / output devices, network access devices, buses, etc.

[0158] The processor 301 may be a Central Processing Unit (CPU), or 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.

[0159] The memory 302 can be an internal storage unit of the smart meter, such as the hard drive or memory of the smart meter. The memory 302 can also be an external storage device of the smart meter, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 302 can include both internal and external storage units of the smart meter. The memory 302 is used to store computer programs and other programs and data required by the smart meter. The memory 302 can also be used to temporarily store data that has been output or will be output.

[0160] It should be noted that, for the sake of convenience and brevity, the structure of the smart meter described above can also be referred to the specific description of the structure in the method embodiment, which will not be repeated here.

[0161] like Figure 4The diagram shown is a schematic of a data acquisition terminal provided in an embodiment of this application. The data acquisition terminal 4 may include: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401, such as a load-based electricity consumption information management program. When the processor 401 executes the computer program 403, it implements the steps in the various load-based electricity consumption information management embodiments described above, for example... Figure 2 Steps S801 to S803 are shown.

[0162] Specifically, the data acquisition terminal can be deployed within a distribution substation (such as a community power distribution room), serving as a core hub connecting the upper-level master station system with numerous user-side smart meters. The data acquisition terminal can collect and manage data from dozens to hundreds of smart meters within its subordinate area. It is a more powerful edge computing node with stronger processing capabilities, storage capacity, and communication capabilities.

[0163] A computer program can be divided into one or more modules / units. One or more modules / units are stored in memory 402 and executed by processor 401 to complete this application. One or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the acquisition terminal.

[0164] The data acquisition terminal may include, but is not limited to, a processor 401 and a memory 402. Those skilled in the art will understand that... Figure 4 This is merely an example of a data acquisition terminal and does not constitute a limitation on the data acquisition terminal. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the data acquisition terminal may also include input / output devices, network access devices, buses, etc.

[0165] The processor 401 may be a Central Processing Unit (CPU), or 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.

[0166] The memory 402 can be an internal storage unit of the acquisition terminal, such as a hard disk or RAM. The memory 402 can also be an external storage device of the acquisition terminal, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 402 can include both internal and external storage units. The memory 402 is used to store computer programs and other programs and data required by the acquisition terminal. The memory 402 can also be used to temporarily store data that has been output or will be output.

[0167] It should be noted that, for the sake of convenience and brevity, the structure of the above-mentioned data acquisition terminal can also be referred to the specific description of the structure in the method embodiment, which will not be repeated here.

[0168] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0169] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps in the above-described electricity information management method.

[0170] This application provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps in the above-mentioned electricity information management method.

[0171] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0172] 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, or a combination of computer software and electronic hardware. 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 various specific applications, but such implementations should not be considered beyond the scope of this application.

[0173] In the embodiments provided in this application, it should be understood that the disclosed devices / smart meters and methods can be implemented in other ways. For example, the device / smart meter embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0174] 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 this embodiment according to actual needs.

[0175] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0176] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a 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 the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0177] The embodiments described above are merely illustrative of the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for managing electricity consumption information based on load identification, characterized in that, The method is applied to smart meters in a load-identification-based electricity consumption information management system, wherein the load-identification-based electricity consumption information management system further includes a cloud server, and the method includes: Collect electrical parameter data of the user's main circuit; Detect electrical state change events based on the aforementioned electrical parameter data; In response to the detection of the electrical appliance status change event, the electrical parameter data is uploaded to the cloud server; The cloud server receives the identification result obtained after performing load identification based on the electrical parameter data. The identification result is used to characterize the type of electrical appliance that has undergone a state change. Based on the identification results, the electricity consumption information of the appliances corresponding to the identification results is extracted from the total electricity consumption; An electricity management report is generated based on the electricity consumption information; The step of extracting the electricity consumption information of the appliance corresponding to the identification result from the total electricity consumption based on the identification result includes: Based on the identification results, the typical operating power curve of the corresponding appliance is obtained from the pre-stored appliance feature database; Based on the appliance start-stop time in the identification results, extract the power sequence for the corresponding time period from the total power consumption data; The power sequence is matched with the typical operating power curve to calculate and decompose the independent power consumption of the appliance within the time period; Based on the independent power consumption, power consumption information of the appliance is generated, including power consumption and operating time; The process includes, after receiving the identification result obtained by the cloud server after performing load identification based on the electrical parameter data, the following: Obtain the reference starting current and reference operating energy efficiency parameters of the electrical appliance corresponding to the identification result; Real-time monitoring of the current starting current and current operating energy efficiency parameters of the electrical appliance; The current starting current is compared with the reference starting current to obtain a first comparison result, and the current operating energy efficiency parameter is compared with the reference operating energy efficiency parameter to obtain a second comparison result; When the first comparison result and / or the second comparison result exceed the corresponding preset health alarm threshold, a device health status warning message is generated. The device health status early warning information will be incorporated into the electricity management report.

2. The electricity consumption information management method based on load identification as described in claim 1, characterized in that, After generating the electricity management report based on the electricity consumption information, the method further includes: Determine whether the identification result corresponds to an unidentifiable appliance type; If the identification result is determined to correspond to an unidentifiable appliance type, a device information input request is sent to the user terminal. The device information input request includes prompting the user to input the type identifier of the appliance. Receive device information returned by the user terminal, the device information including the type of appliance confirmed by the user; The device information is associated with the electrical parameter data corresponding to the electrical state change event, and self-learning sample data is generated. The self-learning sample data is sent to the cloud server to update the electrical appliance feature database in the cloud server.

3. The electricity consumption information management method based on load identification as described in claim 1, characterized in that, The electrical parameter data includes voltage and current signals, and the detection of electrical state change events based on the electrical parameter data includes: Calculate the total active power within a set time window based on the voltage signal and the current signal; Based on the total active power, calculate the absolute value of the change in total active power between adjacent time windows; The absolute value of the total active power change is compared with a preset event detection threshold. When the absolute value of the change in total active power is greater than the event detection threshold, it is determined that an electrical appliance status change event has occurred.

4. A method for electricity consumption information management based on load identification, characterized in that, The method is applied to a cloud server in a load-identification-based electricity consumption information management system, which further includes smart meters. The method includes: The smart meter is used for: Collect electrical parameter data of the user's main circuit; Detect electrical state change events based on the aforementioned electrical parameter data; In response to the detection of the electrical appliance status change event, the electrical parameter data is uploaded to the cloud server; The cloud server is used for: Receive electrical parameter data uploaded by the smart meter; The electrical parameter data is subjected to feature extraction to obtain electrical features, which include steady-state features, transient features and noise features; The electrical characteristics are identified by load based on the electrical characteristic database to obtain the identification result; The smart meter is also used for: The cloud server receives the identification result obtained after performing load identification based on the electrical parameter data. The identification result is used to characterize the type of electrical appliance that has undergone a state change. Based on the identification results, the electricity consumption information of the appliances corresponding to the identification results is extracted from the total electricity consumption; An electricity management report is generated based on the electricity consumption information; The step of extracting the electricity consumption information of the appliance corresponding to the identification result from the total electricity consumption based on the identification result includes: Based on the identification results, the typical operating power curve of the corresponding appliance is obtained from the pre-stored appliance feature database; Based on the appliance start-stop time in the identification results, extract the power sequence for the corresponding time period from the total power consumption data; The power sequence is matched with the typical operating power curve to calculate and decompose the independent power consumption of the appliance within the time period; Based on the independent power consumption, power consumption information of the appliance is generated, including power consumption and operating time; The process includes, after receiving the identification result obtained by the cloud server after performing load identification based on the electrical parameter data, the following: Obtain the reference starting current and reference operating energy efficiency parameters of the electrical appliance corresponding to the identification result; Real-time monitoring of the current starting current and current operating energy efficiency parameters of the electrical appliance; The current starting current is compared with the reference starting current to obtain a first comparison result, and the current operating energy efficiency parameter is compared with the reference operating energy efficiency parameter to obtain a second comparison result; When the first comparison result and / or the second comparison result exceed the corresponding preset health alarm threshold, a device health status warning message is generated. The device health status early warning information will be incorporated into the electricity management report.

5. The electricity consumption information management method based on load identification as described in claim 4, characterized in that, The step of identifying the electrical characteristics based on the electrical characteristic database to obtain the identification result includes: The electrical features are processed into feature vectors to generate standardized feature vectors; Calculate the similarity between the standardized feature vector and multiple typical feature vectors pre-stored in the electrical appliance feature database to obtain a set of similarity values; The maximum similarity value is selected from the set of similarity values, and the corresponding appliance type is determined as the candidate recognition result; The maximum similarity value is compared with a preset confidence threshold. If the maximum similarity value is greater than or equal to the preset confidence threshold, then the candidate recognition result is output as the recognition result; If the maximum similarity value is less than the preset confidence threshold, the standardized feature vector is input into the machine learning recognition model for load recognition, and the recognition result is output.

6. A power consumption information management system based on load identification, characterized in that, The system includes smart meters and a cloud server; The smart meter is used to collect electrical parameter data of the user's main circuit; The smart meter is also used to detect electrical appliance status change events based on the electrical parameter data; The smart meter is also used to upload the electrical parameter data to a cloud server in response to detecting a change in the state of the electrical appliance; The cloud server is used to receive electrical parameter data uploaded by the smart meter; The cloud server is also used to extract features from the electrical parameter data to obtain electrical features, which include steady-state features, transient features, and noise features. The cloud server is also used to identify the electrical characteristics based on the electrical characteristic database and obtain the identification result; The smart meter is also used to receive the identification result obtained by the cloud server after load identification based on the electrical parameter data, and the identification result is used to characterize the type of electrical appliance that has undergone a state change; The smart meter is also used to extract the electricity consumption information of the appliance corresponding to the identification result from the total electricity consumption based on the identification result; The smart meter is also used to generate an electricity management report based on the electricity consumption information; The smart meter is also used to obtain the typical operating power curve of the corresponding appliance from a pre-stored appliance feature database based on the recognition result. Based on the appliance start-stop time in the identification results, extract the power sequence for the corresponding time period from the total power consumption data; The power sequence is matched with the typical operating power curve to calculate and decompose the independent power consumption of the appliance within the time period; Based on the independent power consumption, power consumption information of the appliance is generated, including power consumption and operating time; The smart meter is further configured to, after receiving the identification result obtained by the cloud server after performing load identification based on the electrical parameter data: Obtain the reference starting current and reference operating energy efficiency parameters of the electrical appliance corresponding to the identification result; Real-time monitoring of the current starting current and current operating energy efficiency parameters of the electrical appliance; The current starting current is compared with the reference starting current to obtain a first comparison result, and the current operating energy efficiency parameter is compared with the reference operating energy efficiency parameter to obtain a second comparison result; When the first comparison result and / or the second comparison result exceed the corresponding preset health alarm threshold, a device health status warning message is generated. The device health status early warning information will be incorporated into the electricity management report.

7. A smart meter, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the load identification-based electricity information management method as described in any one of claims 1 to 3.

8. A data acquisition terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the data acquisition terminal being applied to a load-identification-based electricity consumption information management system, the load-identification-based electricity consumption information management system further comprising a cloud server, the data acquisition terminal being used for: Collect electrical parameter data of the user's main circuit; Detect electrical state change events based on the aforementioned electrical parameter data; In response to the detection of the electrical appliance status change event, the electrical parameter data is uploaded to the cloud server; The cloud server receives the identification result obtained after performing load identification based on the electrical parameter data. The identification result is used to characterize the type of electrical appliance that has undergone a state change. Based on the identification results, the electricity consumption information of the appliances corresponding to the identification results is extracted from the total electricity consumption; An electricity management report is generated based on the electricity consumption information; The step of extracting the electricity consumption information of the appliance corresponding to the identification result from the total electricity consumption based on the identification result includes: Based on the identification results, the typical operating power curve of the corresponding appliance is obtained from the pre-stored appliance feature database; Based on the appliance start-stop time in the identification results, extract the power sequence for the corresponding time period from the total power consumption data; The power sequence is matched with the typical operating power curve to calculate and decompose the independent power consumption of the appliance within the time period; Based on the independent power consumption, power consumption information of the appliance is generated, including power consumption and operating time; The process includes, after receiving the identification result obtained by the cloud server after performing load identification based on the electrical parameter data, the following: Obtain the reference starting current and reference operating energy efficiency parameters of the electrical appliance corresponding to the identification result; Real-time monitoring of the current starting current and current operating energy efficiency parameters of the electrical appliance; The current starting current is compared with the reference starting current to obtain a first comparison result, and the current operating energy efficiency parameter is compared with the reference operating energy efficiency parameter to obtain a second comparison result; When the first comparison result and / or the second comparison result exceed the corresponding preset health alarm threshold, a device health status warning message is generated. The device health status early warning information will be incorporated into the electricity management report.

Images