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

Abstract

The invention is suitable for the technical field of intelligent electric meters, and provides an electricity consumption information management method and system, an intelligent electric meter and an acquisition terminal.The intelligent electric meter acquires electrical parameters of a main circuit and detects an electric appliance state change event, and then key data is uploaded to a cloud server for complex load identification calculation; and finally, receiving an identification result, locally decomposing detailed power utilization information of a single electric appliance and generating a power utilization management report. According to the embodiment of the invention, high cost and complex operation for installing a sensor for each electric appliance are avoided, a user can clearly master the energy consumption condition of each electric appliance so as to promote energy-saving optimization, and the advantages of the powerful computing power of the cloud and the real-time response of the edge are fully exerted by means of the cloud-edge collaborative architecture; the recognition accuracy and the system efficiency are improved, and the intelligent level of power consumption management and the user experience are remarkably improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of smart meters, and particularly relates to a power consumption information management method and system, a smart meter and a collection terminal. BACKGROUND

[0002] With the rapid development of smart grids and Internet of Things technologies, users have increasingly urgent needs for fine management of power consumption information. Traditional smart meters mainly function to measure the total power consumption of a household or unit, and cannot provide specific power consumption details of internal various power-consuming devices (such as air conditioners, refrigerators, water heaters, etc.). Although there are technical solutions for realizing sub-metering by separately installing smart sockets or sensors on each power-consuming device, such an intrusive monitoring method has high hardware costs and complex installation and deployment, and is particularly difficult to cover embedded appliances (such as central air conditioners, embedded ovens, etc.), and is difficult to be widely applied. Therefore, how to automatically identify and monitor the power consumption information of various household appliances in a low-cost and convenient manner without modifying the internal circuit of a user and without installing additional sensing devices has become a technical problem to be solved in the field. SUMMARY

[0003] In view of this, the embodiments of the application provide a power consumption information management method and system, a smart meter and a collection terminal, which can solve the problem in the prior art that it is difficult to automatically identify and monitor the power consumption information of various household appliances in a low-cost and convenient manner without modifying the internal circuit of a user and without installing additional sensing devices.

[0004] In a first aspect, the embodiments of the application provide a power consumption information management method, which is applied to a smart meter in a power consumption information management system based on load identification, the power consumption information management system based on load identification further comprising a cloud server, and the method comprises: collecting electrical parameter data of a user's total circuit; detecting an electrical appliance state change event based on the electrical parameter data; uploading the electrical parameter data to the cloud server in response to detecting the electrical appliance state change event; receiving an identification result obtained by the cloud server after performing load identification based on the electrical parameter data, the identification result being used to represent a type of electrical appliance that has changed state; decomposing power consumption information of an electrical appliance corresponding to the identification result from total power consumption according to the identification result; generating a power consumption management report according to the power consumption information.

[0005] In a second aspect, the embodiments of the present application provide a power consumption information management method. The method is applied to a cloud server in a power consumption information management system based on load identification. The power consumption information management system based on load identification also includes a smart meter. The method includes the following steps. receiving electrical parameter data uploaded by the smart meter; extracting features from the electrical parameter data to obtain electrical features. The electrical features include steady-state features, transient-state features, and noise features; performing load identification on the electrical features according to an electrical feature database to obtain an identification result.

[0006] In a third aspect, the embodiments of the present application provide a power consumption information management system based on load identification. The system includes a smart meter and a cloud server. The smart meter is configured to collect electrical parameter data of a user's total circuit. The smart meter is further configured to detect an electrical appliance state change event based on the electrical parameter data. The smart meter is further configured to upload the electrical parameter data to the cloud server in response to detecting the electrical appliance state change event. The cloud server is configured to receive the electrical parameter data uploaded by the smart meter. The cloud server is further configured to extract features from the electrical parameter data to obtain electrical features. The electrical features include steady-state features, transient-state features, and noise features. The cloud server is further configured to perform load identification on the electrical features according to an electrical feature database to obtain an identification result. The smart meter is further configured to receive the identification result obtained by the cloud server after performing load identification on the electrical parameter data. The identification result is used to represent the type of electrical appliance that has changed state. The smart meter is further configured to decompose power consumption information of an electrical appliance corresponding to the identification result from total power consumption according to the identification result. The smart meter is further configured to generate a power consumption management report according to the power consumption information.

[0007] In a fourth aspect, the embodiments of the present application provide a smart meter. The smart meter includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the power consumption information management method of the first aspect are implemented.

[0008] In a fifth aspect, the embodiments of the present application provide a collection terminal. The collection terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The collection terminal is applied to a power consumption information management system based on load identification. The power consumption information management system based on load identification also includes a cloud server. The collection terminal is configured to execute the steps of the power consumption information management method of the second aspect.

[0009] In a sixth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps of the power consumption information management method.

[0010] In a seventh aspect, the embodiments of the present application provide a computer program product, which, when executed on a smart meter, causes the smart meter to perform the power consumption information management method.

[0011] Compared with the prior art, the embodiments of the present application have the beneficial effects that: the embodiments of the present application collect the electrical parameters of the total circuit and detect the electrical appliance state change event by the smart meter, then upload the key data to the cloud server for complex load identification calculation, finally receive the identification result and locally decompose the detailed power consumption information of the single electrical appliance and generate the power consumption management report. The embodiments of the present application not only avoid the expensive cost and complex operation of installing sensors for each electrical appliance, but also enable the user to clearly grasp the energy consumption of each electrical appliance to promote energy saving optimization, and further, by means of the cloud-edge collaborative architecture, the embodiments of the present application fully exert the strong computing power of the cloud and the edge real-time response advantage, improve the identification accuracy and system efficiency, and significantly improve the intelligent level of power consumption management and user experience. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0013] Figure 1 is an implementation flow diagram of the power consumption information management method provided by the embodiments of the present application.

[0014] Figure 2 is an implementation flow diagram of the power consumption information management method provided by the embodiments of the present application.

[0015] Figure 3 is a structural diagram of the smart meter provided by the embodiments of the present application.

[0016] Figure 4 is a structural diagram of the collection terminal provided by the embodiments of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor belong to the present application.

[0018] It should be noted that the terms "include", "contain" and "have" in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusion. For example, a process, method, terminal, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device. The terms such as "first" and "second" and the like in the claims, specification and drawings of the present application are only used to distinguish one entity / operation / object from another entity / operation / object, and do not necessarily require or imply any such real-time relationship or sequence between the entities / operations / objects.

[0019] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment can be included in at least one embodiment of the application. The appearance of the phrase in various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily independent or alternative embodiments to other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0020] With the rapid development of smart grid and Internet of Things technology, users' demand for fine management of electricity information is increasingly urgent. The main function of the traditional smart meter is to measure the total electricity consumption of a household or unit, and it cannot provide detailed electricity consumption of each internal electricity-consuming device (such as air conditioners, refrigerators, water heaters, etc.). Although there are technical solutions for sub-metering by installing smart sockets or sensors on each electricity-consuming device, this invasive monitoring method has high hardware costs and complex installation and deployment, especially for embedded appliances (such as central air conditioners, embedded ovens, etc.), making it difficult to promote and apply on a large scale. Therefore, how to automatically identify and monitor the electricity information of each household appliance without modifying the internal wiring of the user and without installing additional sensor devices at a low cost and in a convenient way has become a technical problem to be solved in the field.

[0021] In view of this, the embodiment of the present application provides a power consumption information management method, which collects the electrical parameter of the total circuit and detects the state change event of the electrical appliance through the smart meter, then uploads the key data to the cloud server for complex load identification calculation, finally receives the identification result and locally decomposes the detailed power consumption information of the single electrical appliance and generates the power consumption management report. The embodiment of the present application not only avoids the expensive cost and complex operation of installing sensors for each electrical appliance, but also enables the user to clearly grasp the energy consumption of each electrical appliance to promote energy saving optimization, and makes full use of the strong computing power of the cloud and the edge real-time response advantage of the edge to improve the identification accuracy and system efficiency, and significantly improves the intelligent level of power consumption management and user experience.

[0022] In order to illustrate the technical solutions of the present application, the following will be illustrated by specific embodiments.

[0023] Figure 1 A power consumption information management method implementation flowchart provided by the embodiment of the present application is shown, which can be applied to the smart meter in the power consumption information management system based on load identification. And the above-mentioned power consumption information management system based on load identification can also include a cloud server.

[0024] Specifically, the smart meter is a power metering device installed on the user's total household circuit, which has the functions of measuring basic electrical parameters such as voltage, current and power of traditional meters, and also integrates a data processing unit and a communication module, which can perform local calculation and data interaction with the cloud server.

[0025] The cloud server is a server cluster located in a remote data center, which has strong computing and storage capacity and can be used to run complex load identification algorithms and maintain a large electrical appliance feature database.

[0026] Specifically, the above-mentioned power consumption information management method can include the following steps S101 to S106.

[0027] Step S101, collecting the electrical parameter data of the user's total circuit.

[0028] Among them, the electrical parameter data refers to the digitized representation of the original analog signal reflecting the electrical state of the total circuit collected by the smart meter through internal sensors (such as voltage transformer, current transformer), which can include instantaneous voltage value, instantaneous current value sequence, and can calculate derived parameters such as active power, reactive power and harmonics.

[0029] In the embodiments of the present application, the smart meter can synchronously sample the voltage signal and current signal on the household circuit through its built-in voltage and current sensors at a high frequency (e.g., higher than 1 kHz). The specific collected raw data can include instantaneous voltage values, instantaneous current values, and instantaneous power and other electrical parameters calculated therefrom, which are digitized by an analog-to-digital converter and stored in the temporary cache of the smart meter with a time stamp.

[0030] Step S102, detecting an electrical appliance state change event based on the electrical parameter data.

[0031] Among them, the electrical appliance state change event refers to the moment or short process when the total electrical parameter (such as total active power) in the circuit changes significantly due to the start, stop or running mode switching (such as air conditioner switching from cooling mode to air supply mode) of a certain electrical equipment.

[0032] In the embodiments of the present application, the smart meter can calculate the change amount of total active power in adjacent sampling points or a short period of time (e.g., 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 amount exceeds the threshold, it is determined that there is an electrical appliance state change event, that is, an electrical appliance is turned on, turned off or power is switched, which realizes the accurate capture of the critical point of the change of the state of the electrical equipment from the continuous electrical data stream.

[0033] Step S103, uploading the electrical parameter data to the cloud server in response to detecting the electrical appliance state change event.

[0034] In the embodiments of the present application, when it is determined that an event occurs, the smart meter can immediately upload the high-precision current waveform data and related electrical parameters in a time window (e.g., 0.5 seconds before the event to 2 seconds after the event) before and after the event through its communication module (such as 4G / 5G, Wi-Fi or power line carrier PLC) to the cloud server, which realizes the effective transmission of key data, not only guarantees the data integrity required by the cloud recognition algorithm, but also maximizes the unnecessary network traffic and cloud storage pressure.

[0035] Step S104, receiving the recognition result obtained by the cloud server after load identification according to the electrical parameter data.

[0036] Among them, the recognition result is used to represent the type of electrical appliance that has changed state. Specifically, the recognition result refers to the structured information output by the cloud server after completing the load identification algorithm, which at least includes the identification of the electrical appliance type (such as "air conditioner", "refrigerator") that triggers the event, and can further extend to include the specific device identity (such as "living room air conditioner") and its working mode (such as "cooling mode") In the embodiments of the present application, the smart meter can listen to and receive feedback data packets from the cloud server through the communication module, and the feedback data packets contain parsed recognition results. After receiving, the smart meter can parse and store them, thereby completing the feedback of the cloud-side intelligent recognition results to the edge side, and providing clear instructions and basis for the edge side to perform specific power consumption information decomposition actions.

[0037] In step S105, the power consumption information of the electrical appliance corresponding to the recognition result is decomposed from the total power consumption according to the recognition result.

[0038] The power consumption information refers to the power consumption data details of a specific electrical appliance decomposed from the total power consumption, which can include the power consumption, average power, running time, start and stop time stamp, etc. of the electrical appliance in a specific time period.

[0039] In the embodiments of the present application, the smart meter can subtract the typical running power curve of the corresponding electrical appliance in the cloud feature library from the continuously collected total power curve from the moment of event occurrence according to the received recognition result (such as “refrigerator turned on”), thereby stripping the power consumption of the electrical appliance from the total amount, recording the start and stop time, running power curve, etc., and finally calculating the accurate power consumption of each electrical appliance in a specific time period, realizing the conversion from macro total power consumption to micro device-level power consumption information.

[0040] In step S106, a power consumption management report is generated according to the power consumption information.

[0041] The power consumption management report refers to the comprehensive information summary finally generated and presented to the user, which is based on the decomposed power consumption information and can be in the form of a mobile phone APP interface, a web page or a paper report, used to intuitively show the device-level power consumption details, energy efficiency analysis, cost estimation and abnormal alarm, etc. to the user.

[0042] In the embodiments of the present application, the smart meter can summarize, analyze and format the power consumption information (such as daily power consumption, monthly power consumption, peak power, etc.) of each electrical appliance obtained by decomposition, generate a power consumption management report that can be intuitively understood by the user, and the report content can include high-energy-consumption device ranking, power consumption habit analysis, electricity cost estimation, device abnormal power consumption warning, etc. and be displayed to the user through a local display screen or sent to the user's mobile phone APP, etc. to display to the user, thereby converting the original power consumption data into decision-making information with practical guiding significance.

[0043] Compared with the prior art, the embodiment of the present application has the beneficial effects that: the embodiment of the present application collects electrical parameters of a total circuit and detects state change events of electrical appliances through a smart meter, then uploads key data to a cloud server for complex load identification calculation, finally receives an identification result and locally decomposes detailed power consumption information of a single electrical appliance and generates a power consumption management report. The embodiment of the present 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 to promote energy saving optimization, but also takes advantage of a cloud-edge collaborative architecture to fully exert the powerful computing capability of the cloud and the edge real-time response advantage, improves the identification accuracy and system efficiency, and significantly improves the intelligent level of power consumption management and user experience.

[0044] In some specific embodiments of the present application, after the power consumption management report is generated according to the power consumption information, steps S401 to S405 can be further included.

[0045] Step S401, determining whether the identification result corresponds to an electrical appliance type that cannot be identified.

[0046] In the embodiment of the present application, after receiving the identification result data packet returned by the cloud server, the smart meter can first parse the state code for indicating whether the identification is successful and the confidence score of the identification result in the data packet. When the state code is explicitly indicated as “identification failure” or the confidence score is lower than a preset threshold (for example, 0.6), it is determined that the current identification result corresponds to an electrical appliance type that cannot be identified, ensuring that the self-learning function is only activated when the system actually encounters an unknown or uncertain electrical appliance, avoiding unnecessary user interference, and also ensuring the effectiveness of the sample data.

[0047] Step S402, if it is determined that the identification result corresponds to an electrical appliance type that cannot be identified, sending a device information input request to a user terminal, the device information input request including prompting the user to input a type identifier of the electrical appliance.

[0048] The user terminal refers to a terminal device used by a user to interact with the power consumption information management system, and its specific form can be an application program on a smart phone, a web platform on a computer terminal, or a smart home central control screen, etc.

[0049] In the embodiment of the present application, when the smart meter determines that the user's assistance is needed, the smart meter can immediately generate a structured device information input request instruction. The instruction can be sent to the user's bound mobile phone APP through a home local area network or a mobile network. The request instruction not only contains text prompt information (such as “the system finds a new device, please help confirm”), but also carries parameters for generating an interactive interface, guiding the user to select or manually input the electrical appliance name from a preset electrical appliance classification list.

[0050] Step S403, receiving the device information returned by the user terminal, wherein the device information comprises the appliance type confirmed by the user.

[0051] The device information refers to the descriptive information about the unrecognized appliance fed back by the user through the user terminal, and the core is the appliance type identification (such as "air conditioner" and "refrigerator") confirmed or input by the user, and the device name (such as "master bedroom air conditioner") defined by the user and the more detailed identity information such as the brand and model can be extended.

[0052] In the embodiments of the present application, after the user completes the selection or input of the appliance type on the mobile phone APP and clicks to confirm, the APP encapsulates the device information (such as "type: air conditioner, name: study air conditioner") submitted by the user into a data packet and returns it to the smart meter or directly sends it to the cloud server through the network. After receiving the information, the smart meter can analyze and temporarily store it.

[0053] Step S404, associating the device information with the electrical parameter data corresponding to the appliance state change event, to generate self-learning sample data.

[0054] In the embodiments of the present application, the smart meter can retrieve the high-frequency sampling electrical parameter data (including voltage and current waveforms) of the user feedback appliance within a time window before and after the state change event occurs from the local storage by using the timestamp of the event occurrence as the association key, and then bind the appliance type label confirmed by the user with the original waveform data or the feature vector extracted from the waveform, thereby generating a self-learning sample data packet. The self-learning sample data packet contains "questions" (electrical data) and "answers" (appliance type), thereby providing direct learning materials for the cloud server to update the model.

[0055] Step S405, sending the self-learning sample data to the cloud server to update the appliance feature database in the cloud server.

[0056] In the embodiments of the present 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 for processing. When a certain number of samples are accumulated or a specific condition is met, the retraining process of the model can be started, the load identification algorithm can be optimized by using new and old samples, or the sample can be directly added to the database as a new feature template, so that the power consumption information management system based on load identification has the ability to continuously learn new knowledge from the actual use environment, and finally realizes the dynamic growth of the appliance feature database and the continuous evolution of the identification ability.

[0057] The embodiments of the present application incorporate user feedback into the closed-loop optimization process of load identification. When the system encounters unknown electrical appliances or insufficient identification confidence, it can actively request user assistance for labeling, and combine the labeling information with the corresponding electrical characteristic data to form high-quality training samples, which are fed back to the cloud to continuously optimize and expand the electrical appliance characteristic database. This effectively solves the problem of identification blind spots caused by incomplete database at the initial deployment of the system, significantly improves the initial applicability and user experience of the system, and enables the system to actively adapt to new models of electrical appliances and user-specific electrical equipment emerging in the market, significantly improving the long-term practical value of the system.

[0058] In some embodiments of the present application, after receiving the identification result obtained by the cloud server according to the electrical parameter data, steps S501 to S505 can also be included.

[0059] Step S501, obtaining the reference starting current and reference running energy efficiency parameter of the electrical appliance corresponding to the identification result.

[0060] The reference starting current refers to the typical current peak value or effective value extracted from the total circuit current waveform at the starting moment of a specific electrical appliance in the standard state or at the initial stage of healthy operation.

[0061] The reference running energy efficiency parameter refers to a key parameter representing the energy conversion efficiency of an electrical appliance after it enters a steady state under the rated working mode, such as the ratio of active power to apparent power (power factor) or unit energy consumption under a specific output.

[0062] In the embodiments of the present application, the smart meter can query the standard parameter profile of the identified electrical appliance type (such as "air conditioner model XXX") from the local cache or the cloud electrical appliance characteristic database, obtain its reference starting current (e.g., 5A) and reference running energy efficiency parameter (e.g., power factor 0.9), after receiving the load identification result. If the electrical appliance is identified for the first time or lacks a preset reference, its starting current and running energy efficiency parameter can be automatically recorded and the average value can be calculated as the initial reference value and stored in the database during the initial period when it is identified and confirmed to be running normally.

[0063] Step S502, real-time monitoring of the current starting current and current running energy efficiency parameter of the electrical appliance.

[0064] The current starting current refers to the maximum starting transient current value or characteristic value captured from the total current sampling data in the most recent detected electrical appliance starting event.

[0065] The current running energy efficiency parameter refers to an energy efficiency indicator calculated based on real-time voltage and current data after the electrical appliance enters a stable state during the latest running period.

[0066] In the embodiments of the present application, whenever the load identification result confirms that an electrical appliance is in operation, the smart meter can perform accurate analysis on the current waveform data before and after the event of starting the electrical appliance, extract the current starting current (usually the peak current in the starting transient process), and calculate the current operation energy efficiency parameter (such as power factor) based on the voltage and current data in a time window after the electrical appliance enters a stable operation state (such as 30 seconds after starting).

[0067] Step S503, comparing the current starting current with the reference starting current to obtain a first comparison result, and comparing the current operation energy efficiency parameter with the reference operation energy efficiency parameter to obtain a second comparison result.

[0068] In the embodiments of the present application, the smart meter can calculate the absolute difference or the relative percentage change of the current starting current and the reference starting current as the first comparison result, and calculate the difference or ratio of the current operation energy efficiency parameter and the reference operation energy efficiency parameter as the second comparison result. For example, the current starting current is 6.1A and the reference is 5A, so the first comparison result is that the current increases by 22%. The current power factor is 0.8 and the reference is 0.9, so the second comparison result is that the efficiency decreases by about 11%.

[0069] Step S504, when the first comparison result and / or the second comparison result exceeds the corresponding preset health warning threshold, generating device health state warning information.

[0070] In the embodiments of the present application, the smart meter can compare the first comparison result and the second comparison result with the preset health warning threshold (for example, the starting current increase threshold is set to 20% and the energy efficiency decrease threshold is set to 10%) respectively, if any comparison result or its combination (such as weighted score) exceeds the threshold, the warning generation logic is triggered, and a device health state warning information containing abnormal device ID, abnormal parameter (such as “starting current exceeds the standard”), exceeding amplitude, timestamp and recommended maintenance action is automatically created.

[0071] Step S505, incorporating the device health state warning information into the power consumption management report.

[0072] In the embodiments of the present application, the smart meter can add the generated device health state warning information as an independent chapter or a tag item to the data structure of the power consumption management report being generated or already existing, and then visualize the display through the local display of the smart meter, or send to the user's mobile phone APP, computer terminal, etc. via the communication module, so that the user can clearly check the specific warning content such as “the starting current of your master bedroom air conditioner is abnormally large, which may have aging risk, please contact maintenance”.

[0073] The embodiments of the present application can timely discover abnormalities in the early stage of slight degradation of device performance (such as an increase in starting resistance of a motor leading to an increase in current) or a decrease in operating efficiency (such as aging of a compressor leading to a decrease in energy efficiency), thereby generating accurate device health state early warnings and integrating the device health state early warnings into a power consumption report, so that users and operation and maintenance personnel can change from a traditional “post-fault maintenance” mode to a “pre-fault early warning” preventive maintenance mode, reduce the risk of power failure and economic losses caused by sudden device failure, and prolong the service life of the device.

[0074] In some specific embodiments of the present application, the electrical parameter data includes a voltage signal and a current signal, and the detection of the electrical appliance state change event based on the electrical parameter data can specifically include steps S601 to S604.

[0075] In step S601, total active power in a set time window is calculated according to the voltage signal and the current signal.

[0076] The set time window is a continuous data processing period, and the length thereof is configurable (for example, 1 second or 2 seconds).

[0077] The total active power refers to an average active power value calculated based on integration (or approximate summation) of products of instantaneous voltage signals and instantaneous current signals in the set time window, and can reflect real power consumed by a load in the window.

[0078] In the embodiments of the present application, the smart meter can read the synchronously sampled instantaneous voltage signal sequence and the instantaneous current signal sequence from the cache, multiply the instantaneous voltage value at the same time with the instantaneous current value to obtain an instantaneous power for each set time window (for example, 1 second in length, containing 4000 sampling points), then accumulate and average all instantaneous power values in the window to calculate the average total active power in the time window, and the calculation process is continuously rolled, and an active power value is obtained for each window, thereby forming a sequence of active power values changing with time, so as to convert the original voltage and current waveform data into a time sequence feature which can intuitively reflect overall load level and is easy to process.

[0079] In step S602, an absolute value of a total active power change amount between adjacent time windows is calculated according to the total active power.

[0080] The absolute value of the total active power change amount refers to an absolute value of a difference between total active power values of two adjacent set time windows, and can be used to capture power step changes caused by switching of an electrical appliance or mode switching.

[0081] In the embodiments of the present application, whenever a new total active power value of a time window is calculated, the smart meter can immediately obtain the total active power value of the previous time window from the cache, then calculate the difference between the two values and take the absolute value, thereby obtaining the absolute value of the total active power change between adjacent time windows, thereby converting the continuous active power sequence into a series of mutation data, highlighting the moments when the total load of the circuit changes significantly.

[0082] Step S603, comparing the absolute value of the total active power change with a preset event detection threshold.

[0083] In the embodiments of the present application, the smart meter can compare the absolute value of the power change with a preset event detection threshold (for example, 50 watts) to determine whether the absolute value of the power change is greater than the preset event detection threshold.

[0084] Step S604, when the absolute value of the active power change is greater than the event detection threshold, it is determined that an appliance state change event occurs.

[0085] In the embodiments of the present 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 "appliance state change event" flag signal, and mark the event with an accurate time stamp, record the time of the event, the size of the power change and the change direction (increase / decrease), and then the event signal will trigger the subsequent data upload process.

[0086] The embodiments of the present application utilize the voltage and current signals regularly collected by the smart meter, calculate the total active power in the set time window, and convert it into the power change between adjacent windows, and then compare it with a reasonably set threshold, thereby accurately capturing the state change events such as appliance start / stop or mode switching. The algorithm of the embodiments of the present application has low computational complexity, is very suitable for real-time execution on the smart meter with limited resources, avoids the continuous dependence on cloud computing resources, greatly reduces the amount of data to be uploaded (only when an event is detected), and significantly reduces the communication bandwidth demand and the overall power consumption of the system.

[0087] In some specific embodiments of the present application, the step of decomposing the power consumption information of the corresponding appliance from the total power consumption according to the identification result can specifically include steps S701 to S704.

[0088] Step S701, based on the identification result, obtaining the typical running power curve of the corresponding appliance from the pre-stored appliance feature database.

[0089] The typical operation power curve refers to a regular waveform or data sequence of active power of a specific type of electrical appliance changing with time under standard test conditions or typical working mode. The curve can be obtained through laboratory measurement or learning from a large amount of historical operation data, and is pre-stored in the electrical appliance feature database as a reference template for decomposing the power consumption of the electrical appliance. The features include start transient, steady-state operation power and shutdown curve.

[0090] In the embodiments of the present application, after receiving the load identification result, the smart meter can query the electrical appliance feature database locally cached or maintained in the cloud according to the electrical appliance type identifier (such as "air conditioner model ABC") determined in the identification result, retrieve and obtain the typical operation power curve data corresponding to the type of electrical appliance. The typical operation power curve data is usually stored in the form of time-power value array, covering the full cycle power change mode of the electrical appliance from start, steady-state operation to shutdown. If the electrical appliance is multi-mode operation (such as air conditioner cooling, air supply mode), the corresponding specific curve can be obtained according to the working mode information in the identification result.

[0091] Step S702, extracting the power sequence of the corresponding period from the total power consumption data according to the electrical appliance start-stop time in the identification result.

[0092] The electrical appliance start-stop time refers to the specific time stamp of the state change of the electrical appliance, including the start time (such as power surge) and the shutdown time (such as power drop).

[0093] The power sequence refers to the array of power values in a continuous time period arranged in time sequence, which is cut out from the total active power data continuously collected by the smart meter according to the electrical appliance start-stop time. The sequence reflects the detailed change of the total circuit power in the period.

[0094] In the embodiments of the present application, the smart meter can cut out all active power sampling values in the period from a short time before T_start (such as 0.5 seconds in advance to capture the start transient) to a short time after T_end (such as 0.5 seconds later to capture the shutdown transient) from the total active power historical data buffer cyclically stored by the smart meter according to the accurate start-stop time stamp (such as start time T_start and shutdown time T_end) carried in the identification result, to form a continuous power sequence. Since this power sequence may contain the power superposition of other parallel running electrical appliances, baseline correction or filtering preprocessing can be performed.

[0095] Step S703, matching and calculating the power sequence with the typical operation power curve to decompose the independent power consumption of the electrical appliance in the period.

[0096] In the embodiments of the present application, the smart meter can adopt a signal processing algorithm. Specifically, the smart meter can calculate the cross-correlation function of the actual power sequence and the typical power curve to find the best alignment point, and then estimate a scaling coefficient by least squares method, or minimize the difference between the actual sequence and the typical curve after scaling and translation, to calculate the proportion coefficient of the actual power sequence contributed by the typical curve representing the electrical appliance, so as to decompose the total power sequence into the power component of the electrical appliance and the power component of the remaining other electrical appliances, and finally integrate (i.e. sum) the power component of the electrical appliance in time to obtain the independent power consumption of the electrical appliance in the start-stop period.

[0097] In step S704, the power consumption information of the electrical appliance is generated according to the independent power consumption, and the power consumption information includes the power consumption and the running time.

[0098] In the embodiments of the present application, the smart meter can associate the calculated independent power consumption with the running time calculated according to the start-stop time difference to generate a structured power consumption record. The record can at least include the electrical appliance ID, power consumption, running time, period start timestamp, etc. fields, and can further calculate the average power, peak power and other derived indicators, and store them in the local database or send them to the user terminal.

[0099] The embodiments of the present application can effectively separate the power contribution of a specific electrical appliance from the mixed total load signal by using the pre-stored high-precision electrical appliance typical running power curve as a decomposition template and intelligently matching and calculating with the real-time collected total power sequence, so as to calculate the independent power consumption and running time of the electrical appliance. The embodiments of the present application adopt a decomposition method based on waveform matching, which has strong anti-interference ability and significantly improves the accuracy and reliability of non-intrusive load decomposition, and is especially suitable for distinguishing electrical appliances with similar power characteristics.

[0100] Figure 2 A flowchart of a power consumption information management method provided by an embodiment of the present application is shown. The method can be applied to a cloud server in a power consumption information management system based on load identification. The power consumption information management system based on load identification can also include a smart meter.

[0101] Specifically, the method can specifically include steps S801 to S803.

[0102] In step S801, the electrical parameter data uploaded by the smart meter is received.

[0103] In the embodiments of the present application, the cloud server can continuously monitor and receive data packets uploaded from the smart meter. The data packets can be compressed and encrypted. The cloud server can first unpack, decrypt and verify them to restore the valid electrical parameter data, which should include complete timestamp information and voltage and current instantaneous value sequences or preliminary processed power data collected by the smart meter. The received data will be stored in the real-time database or message queue of the cloud, waiting for subsequent processing.

[0104] In step S802, feature extraction is performed on the electrical parameter data to obtain electrical features, including steady-state features, transient-state features and noise features.

[0105] The steady-state features are the features of the electrical appliance in the stable operation state, such as steady-state active power, reactive power, current total harmonic distortion (THD) and the amplitudes and phases of each harmonic (such as 3rd and 5th harmonics).

[0106] The transient-state features are the features exhibited by the electrical appliance in the transition process during the opening, closing or power switching moment, such as the peak value, rise time and duration of the starting current.

[0107] The noise features are the spectral distribution characteristics of the high-frequency noise in the current signal in a specific frequency band (such as 2kHz-150kHz). Different electrical appliances will produce unique noise fingerprints due to different working modes of internal power electronic components.

[0108] In the embodiments of the present application, after the cloud server takes out the electrical parameter data from the cache, it can call the built-in feature extraction algorithm module to first perform preprocessing on the current and voltage waveform data, such as denoising, filtering and calibration, and then perform multi-dimensional feature calculation in parallel or series, for example, calculating the mean and variance of active / reactive power through a sliding window to obtain steady-state features, capturing the parameters of power mutation points through edge detection and waveform analysis to obtain transient-state features, and applying 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, these parameters revealing the running characteristics of the electrical appliance from different dimensions are combined into a high-dimensional feature vector, so as to convert the original waveform data into a set of mathematical features that can effectively distinguish different types of electrical appliances.

[0109] In step S803, load identification is performed on the electrical features according to the electrical appliance feature database to obtain an identification result.

[0110] In the embodiments of the present application, the cloud server can input the feature vector into a pre-trained machine learning classification model (such as a deep learning neural network, a support vector machine SVM, or a gradient boosting decision tree, etc.), which is trained on a large number of known electric appliance feature sample libraries (i.e. electric appliance feature database). The model can perform similarity calculation or probability classification on the input feature vector and the feature templates of various electric appliances stored in the library, and finally output one or more most possible electric appliance types and their confidence, thereby obtaining the recognition result.

[0111] The embodiments of the present application make full use of the powerful computing power and storage space of the cloud server, run very complex feature extraction algorithms (such as deep neural networks) and compare a large number of electric appliance feature template libraries, thereby greatly improving the accuracy of load identification and the range of electric appliances that can be identified, overcoming the bottleneck of complex calculations on the local smart meter with limited resources. At the same time, the cloud solution reduces the requirement for the hardware computing power of the terminal smart meter, helps to control the terminal cost and power consumption, and centralized processing is also conducive to deeper aggregation analysis of regional power consumption data.

[0112] In some specific embodiments of the present application, the load identification of the electric appliance features according to the electric appliance feature database to obtain the recognition result can specifically include steps S901 to S906.

[0113] Step S901, performing feature vectorization processing on the electric appliance features to generate a standardized feature vector.

[0114] In the embodiments of the present application, the cloud server can first perform data cleaning on the electric appliance 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 dimension influence. Then, a dimension unification technique (such as principal component analysis PCA) can be used to reduce high-dimensional features to a fixed dimension (such as 50 dimensions) to generate a standardized feature vector as the input for subsequent similarity calculation.

[0115] Step S902, calculating the similarity between the standardized feature vector and a plurality of pre-stored typical feature vectors in the electric appliance feature database to obtain a set of similarity values.

[0116] In the embodiments of the present application, the cloud server can use a cosine similarity algorithm to calculate the similarity between the input vector and each template vector. Specifically, the cloud server can first regard the vectors as points in space and calculate the cosine value of their included angle. Then, all templates in the database are traversed to obtain a set of similarity values, forming a set of similarity values.

[0117] Step S903, filtering out the maximum similarity value from the set of similarity values, and determining the corresponding appliance type as the candidate recognition result.

[0118] In embodiments of the present application, the cloud server can identify the maximum similarity value by traversing the set using a maximum value finding algorithm (such as linear scan or sorting), and then map the corresponding appliance type in the appliance feature database according to the index of the value in the set (such as the maximum similarity value corresponding to index 0 for air conditioner and index 1 for refrigerator) as the candidate recognition result, including the appliance type (such as "air conditioner") and the maximum similarity value.

[0119] Step S904, comparing the maximum similarity value with a pre-set confidence threshold.

[0120] In embodiments of the present application, the cloud server can perform numerical comparison, and if the maximum similarity value ≥ the pre-set confidence threshold, it is marked as high confidence, otherwise it is marked as low confidence. Thus a Boolean flag (true or false) is obtained to drive the subsequent branch.

[0121] Step S905, if the maximum similarity value is greater than or equal to the pre-set confidence threshold, output the candidate recognition result as the recognition result.

[0122] In embodiments of the present application, if the maximum similarity value is greater than or equal to the pre-set confidence threshold, the cloud server can directly output the candidate appliance type as the final recognition result without additional calculation. At the same time, the cloud server can record the result in the log and prepare to send it back to the smart meter.

[0123] Step S906, if the maximum similarity value is less than the pre-set confidence threshold, input the standardized feature vector into the machine learning recognition model for load identification, and output the recognition result.

[0124] In embodiments of the present application, if the maximum similarity value is less than the pre-set 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 "air conditioner" probability 0.7 and "refrigerator" probability 0.3, and finally select "air conditioner".

[0125] Embodiments of the present application unify the feature scale through feature vectorization processing, avoid calculation bias caused by dimensional differences, and combine similarity calculation and threshold verification to accurately match known appliances and reduce misjudgment. Secondly, the machine learning auxiliary path is used as a backup and automatically enabled when the similarity matching is insufficient, so that the system can adapt to new appliances or complex operating modes and enhance robustness.

[0126] The embodiment of the present application provides a power consumption information management system based on load identification, which comprises a smart meter and a cloud server. The smart meter is used for collecting electrical parameter data of a user's total circuit. The smart meter is further used for detecting an electrical appliance state change event based on the electrical parameter data. The smart meter is further used for uploading the electrical parameter data to the cloud server in response to the detection of the electrical appliance state change event. The cloud server is used for receiving the electrical parameter data uploaded by the smart meter. The cloud server is further used for extracting features from the electrical parameter data to obtain electrical features, wherein the electrical features comprise steady-state features, transient-state features and noise features. The cloud server is further used for performing load identification on the electrical features according to an electrical appliance feature database to obtain an identification result. The smart meter is further used for receiving the identification result obtained by the cloud server after performing load identification on the electrical parameter data, wherein the identification result is used for representing a type of electrical appliance that has a state change. The smart meter is further used for decomposing power consumption information of an electrical appliance corresponding to the identification result from total power consumption according to the identification result. The smart meter is further used for generating a power consumption management report according to the power consumption information.

[0127] As shown in Figure 3 Fig. 3 is a schematic diagram of a smart meter provided by the embodiment of the present application. The smart meter 3 can comprise a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301, for example, a power consumption information management program based on load identification. The processor 301 implements the steps in the above various power consumption information management embodiments based on load identification when executing the computer program 303, for example, steps S101-S106 shown in Figure 1 Fig. 3.

[0128] The computer program can be divided into one or more modules / units, which are stored in the memory 302 and executed by the processor 301 to complete the present application. One or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the smart meter.

[0129] The smart meter can comprise, but is not limited to, the processor 301 and the memory 302. Those skilled in the art can understand that Figure 3This 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] like Figure 4 The 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.

[0134] Specifically, the collection terminal can be deployed in a power distribution area (such as a cell power distribution room) as a core hub device connecting an upper layer master station system and a lower layer of numerous user side smart meters. The collection terminal can collect and manage data of dozens to hundreds of smart meters in its subordinate area. It is a more powerful edge computing node with stronger processing capability, storage capacity and communication capability.

[0135] The computer program can be divided into one or more modules / units, one or more modules / units are stored in the memory 402 and executed by the processor 401 to complete the present application. One or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which is used to describe the execution process of the computer program in the collection terminal.

[0136] The collection terminal can include, but is not limited to, the processor 401, the memory 402. Those skilled in the art can understand that, Figure 4 The collection terminal is only an example and does not constitute a limitation on the collection terminal, and can include more or fewer components than the illustration, or combine certain components, or different components, for example, the collection terminal can also include input / output devices, network access devices, buses, etc.

[0137] The processor 401 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0138] The memory 402 can be an internal storage unit of the collection terminal, such as a hard disk or memory of the collection terminal. The memory 402 can also be an external storage device of the collection terminal, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the collection terminal. Further, the memory 402 can include both the internal storage unit and the external storage device of the collection terminal. The memory 402 is used to store computer programs and other programs and data required by the collection terminal. The memory 402 can also be used to temporarily store data that has been output or will be output.

[0139] It should be noted that, for the convenience and brevity of description, the structure of the collection terminal can also refer to the specific description of the structure in the method embodiments, which will not be repeated here.

[0140] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific name of each functional unit and module is only for easy distinction, and does not limit the protection scope of the present application. The specific working process of the unit and module in the system can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0141] The embodiment of the present application also provides a computer readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the power consumption information management method described above can be realized.

[0142] The embodiment of the present application provides a computer program product, when the computer program product is run on a mobile terminal, so that the mobile terminal executes the steps of the power consumption information management method described above.

[0143] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0144] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware or in a combination of computer software and electronic hardware. Whether the functions are performed 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 implementation should not be considered beyond the scope of the present application.

[0145] In the embodiments of the present application, it should be understood that the disclosed device / smart meter and method can be implemented in other manners. For example, the described device / smart meter embodiments are merely schematic. For example, the division of the modules or units is merely logical function division. There can be another division manner for actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, can be indirect couplings or communication connections through some interfaces, devices or units.

[0146] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they can be located in one place, or distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0147] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0148] The integrated module / unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by computer programs instructing related hardware, and the computer programs can be stored in a computer readable storage medium. When the processor executes the computer programs, the steps of the above-mentioned various method embodiments can be implemented. The computer programs include computer program codes, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium can include any entity or device capable of carrying the computer program codes, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the computer readable medium can include appropriate contents according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0149] The above-described embodiments are merely used to illustrate the technical solutions of the present application, but not to limit the same. Although the present application is described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some of the technical features can be replaced equivalently. The modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A power utilization information management method characterized by comprising: The method is applied to a smart meter in a load identification-based power consumption information management system, the load identification-based power consumption information management system further comprising a cloud server, and the method comprises: collecting electrical parameter data of a user's total circuit; detecting an electrical appliance state change event based on the electrical parameter data; uploading the electrical parameter data to the cloud server in response to detecting the electrical appliance state change event; receiving an identification result obtained by the cloud server after load identification based on the electrical parameter data, the identification result being used to represent the type of electrical appliance that has undergone a state change; based on the identification result, decomposing power consumption information of the electrical appliance corresponding to the identification result from total power consumption; generating a power consumption management report based on the power consumption information.

2. The method of electricity utilization information management as claimed in claim 1, characterized in that, After the power consumption management report is generated based on the power consumption information, the method further comprises: determining whether the identification result corresponds to an electrical appliance type that cannot be identified; if it is determined that the identification result corresponds to an electrical appliance type that cannot be identified, sending a device information input request to the user end, the device information input request including a prompt for the user to input the type identification of the electrical appliance; receiving device information returned by the user end, the device information including the type of electrical appliance confirmed by the user; associating the device information with electrical parameter data corresponding to the electrical appliance state change event, to generate self-learning sample data; sending the self-learning sample data to the cloud server to update an electrical appliance feature database in the cloud server.

3. The method of electricity utilization information management as claimed in claim 1, characterized in that, After the identification result obtained by the cloud server after load identification based on the electrical parameter data is received, the method further comprises: obtaining a reference starting current and a reference running energy efficiency parameter of the electrical appliance corresponding to the identification result; real-time monitoring of a current starting current and a current running energy efficiency parameter of the electrical appliance; comparing the current starting current with the reference starting current to obtain a first comparison result, and comparing the current running energy efficiency parameter with the reference running energy efficiency parameter to obtain a second comparison result; generating device health state warning information when the first comparison result and / or the second comparison result exceeds a corresponding preset health warning threshold; including the device health state warning information in the power consumption management report.

4. The method of electricity utilization information management as claimed in claim 1, characterized in that, The electrical parameter data includes voltage signals and current signals, and the detection of the electrical appliance state change event based on the electrical parameter data comprises: calculating total active power in a set time window based on the voltage signals and the current signals; calculating the absolute value of the total active power change between adjacent time windows based on the total active power; comparing the absolute value of the total active power change with a preset event detection threshold; when the absolute value of the active power change is greater than the event detection threshold, it is determined that an electrical appliance state change event has occurred.

5. The method of electricity utilization information management as claimed in claim 1, characterized in that, The decomposition of the power consumption information of the electrical appliance corresponding to the identification result from the total power consumption based on the identification result comprises: based on the identification result, obtaining a typical running power curve of the corresponding electrical appliance from a pre-stored electrical appliance feature database; According to the appliance start-stop time in the identification result, a power sequence of a corresponding period is extracted from total power consumption data; The power sequence is matched with the typical operation power curve for calculation, and independent power consumption of the appliance in the period is decomposed; According to the independent power consumption, power consumption information of the appliance is generated, which includes power consumption and operation time length.

6. A power utilization information management method characterized by comprising: The method is applied to a cloud server in a power consumption information management system based on load identification, and the power consumption information management system based on load identification further includes a smart meter, and the method includes: Receiving electrical parameter data uploaded by the smart meter; Extracting features from the electrical parameter data to obtain electrical features, including steady-state features, transient-state features, and noise features; According to the electrical feature database, the electrical features are identified to obtain an identification result.

7. The method of electricity utilization information management as claimed in claim 6, characterized in that, The electrical features are subjected to feature vectorization processing to generate a standardized feature vector; The similarity between the standardized feature vector and a plurality of typical feature vectors pre-stored in the electrical feature database is calculated to obtain a similarity value set; The maximum similarity value is selected from the similarity value set, and the corresponding electrical appliance type is determined as a candidate identification result; The maximum similarity value is compared with a preset confidence threshold value; If the maximum similarity value is greater than or equal to the preset confidence threshold value, the candidate identification result is output as the identification result; If the maximum similarity value is less than the preset confidence threshold value, the standardized feature vector is input into a machine learning identification model for load identification, and the identification result is output. The system includes a smart meter and a cloud server; 8. A power utilization information management system characterized by comprising: The smart meter is used to collect electrical parameter data of a user's total circuit; The smart meter is also used to detect electrical appliance state change events based on the electrical parameter data; The smart meter is also used to upload the electrical parameter data to the cloud server in response to detecting the electrical appliance state change event; The cloud server is used to receive the 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, including steady-state features, transient-state features, and noise features; The cloud server is also used to identify the electrical features according to an electrical feature database to obtain an identification result; The smart meter is also used to receive the identification result obtained by the cloud server after identifying the electrical parameter data, which is used to represent the type of electrical appliance that has changed state; The smart meter is also used to decompose power consumption information of the corresponding electrical appliance from total power consumption according to the identification result; The smart meter is also used to generate a power consumption management report according to the power consumption information. ​ 9. An intelligent electric meter comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the electric information management method according to any one of claims 1 to 5 when executing the computer program.

10. A collection terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the collection terminal is applied to an electric information management system, the electric information management system based on load identification further comprises a cloud server, and the collection terminal is configured to: collect electric parameter data of a user's total circuit; detect an electric appliance state change event based on the electric parameter data; upload the electric parameter data to the cloud server in response to detecting the electric appliance state change event; receive an identification result obtained by the cloud server after load identification based on the electric parameter data, the identification result being used to represent a type of electric appliance that has a state change; decompose electric information of the electric appliance corresponding to the identification result from total power consumption according to the identification result; and generate an electric management report according to the electric information. ​ ​ ​ ​ ​ ​

Images