Methods for analyzing electrical load components, electronic equipment, readable media, and program products.

By performing differential calculations and appliance feature matching on historical power consumption data of household electricity consumption areas, combined with a mixed integer programming model, the high cost and low efficiency problems of household electricity load component analysis are solved, and fast and accurate identification and real-time analysis of electricity load components are achieved.

CN123068940APending Publication Date: 2026-11-10ECOFLOW INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202511968292.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-23
Publication Date
2026-11-10

AI Technical Summary

Technical Problem

Existing technologies for analyzing household electricity load components suffer from high costs, complex deployment, and low identification efficiency. In particular, non-intrusive load identification methods have high computational overhead and limited identification accuracy.

Method used

By performing differential calculations on historical power consumption data of the power consumption area, the target differential power features are extracted and matched with a preset electrical appliance feature knowledge base. Combined with a mixed integer programming model, the current electrical appliances and their status are identified, supporting the dynamic addition of new devices and the updating of the electrical appliance feature knowledge base.

Benefits of technology

It enables rapid and accurate identification of household electrical load components, improves analysis efficiency and accuracy, supports the identification of new devices, and meets the needs of real-time analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123068940A_ABST
    Figure CN123068940A_ABST
Patent Text Reader

Abstract

This application relates to the field of smart energy management technology, and provides a method, electronic device, readable medium, and program product for analyzing electricity load components. The method includes: acquiring historical electricity consumption data of an electricity consumption area within a preset time period; performing differential calculations on the historical electricity consumption data according to a preset time granularity to obtain target differential power features; matching the target differential power features with preset differential power features corresponding to each preset device in a preset electrical appliance feature knowledge base to determine candidate devices; acquiring current real-time electricity consumption data; and identifying devices based on electrical appliance feature data associated with candidate devices in the electrical appliance feature knowledge base to determine the currently operating electrical appliances and their current operating status in the electricity consumption area. This solution can quickly and accurately analyze the components of household electricity load.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application belongs to the field of energy intelligent management technology, and in particular relates to methods for analyzing the composition of electricity load, electronic equipment, readable media and program products. Background Technology

[0002] Home smart energy management can sense the composition of electricity load in a user's home, thereby clarifying information such as the electricity consumption of different electrical appliances in the user's home, and providing data support to guide the user's electricity consumption behavior to save electricity.

[0003] Currently, solutions for electricity load composition analysis are generally divided into two types: invasive load monitoring and non-invasive load monitoring (NILM). The former requires the deployment of dedicated measuring devices for each electrical appliance, resulting in high costs, complex deployment, and difficulty in widespread adoption. While the latter does not require measuring devices and can perform electricity load composition analysis based on data such as the total power or total current of household electricity meters, it suffers from high computational overhead, low identification efficiency, and limited identification accuracy.

[0004] Therefore, how to quickly and accurately analyze the components of household electricity load has become an urgent technical problem to be solved. Summary of the Invention

[0005] This application provides a method, electronic device, readable medium, and program product for analyzing the components of household electricity load, which can solve the problem of how to quickly and accurately analyze the components of household electricity load.

[0006] In a first aspect, embodiments of this application provide a method for analyzing the composition of electrical load, including: Obtain historical power consumption data for a power consumption area within a preset time period; The target differential power characteristics are obtained by performing differential calculations on historical power consumption data based on a preset time granularity. The target differential power features are matched with the preset differential power features corresponding to each preset device in the preset electrical feature knowledge base to determine candidate devices; Obtain the current real-time power consumption data; Based on the electrical feature data associated with candidate devices in the electrical feature knowledge base, the device identification is performed on the real-time power consumption data to determine the current electrical equipment currently in operation in the power consumption area and the current operating status of the current electrical equipment.

[0007] In some embodiments, differential operations are performed on historical power consumption data according to a preset time granularity to obtain target differential power characteristics, including: The dynamic window is determined based on a preset time granularity; A dynamic window is slid across historical power consumption data based on a preset step size. After each sliding of the dynamic window, a differential operation is performed on the historical power consumption data within the dynamic window to obtain the target differential power feature.

[0008] In some embodiments, matching the target differential power features with the preset differential power features corresponding to each preset device in a preset electrical feature knowledge base to determine candidate devices includes: Calculate the similarity between the target differential power characteristics and the preset differential power characteristics corresponding to each preset device in the preset electrical characteristic knowledge base; Preset devices with similarity scores greater than a preset similarity threshold are identified as candidate devices.

[0009] In some embodiments, based on electrical feature data associated with candidate devices in an electrical feature knowledge base, device identification is performed on real-time power consumption data to determine the currently operating electrical devices and their current operating status in the power consumption area, including: Based on the electrical feature data associated with candidate devices in the electrical feature knowledge base, a mixed integer programming model is constructed; Real-time power consumption data is input into a mixed integer programming model for optimization and solution to determine the current electrical equipment and its current operating status.

[0010] In some embodiments, the method further includes: Retrieve preset energy efficiency data for preset devices from a preset open-source appliance energy efficiency library; Based on the preset time granularity, the preset energy efficiency data is differentially processed to obtain the preset differential power characteristics; An electrical appliance feature knowledge base is constructed based on preset energy efficiency data and preset differential power characteristics of preset devices.

[0011] In some embodiments, the method further includes: If no electrical appliance corresponding to the real-time power consumption data is identified, a confirmation message for adding electrical appliance feature entry will be displayed. In response to the user's consent to enter data, determine the type of new device corresponding to the real-time power consumption data; Differential calculations are performed on real-time power consumption data based on a preset time granularity to obtain the corresponding new differential power features; The electrical appliance feature knowledge base is updated based on real-time power consumption data, newly added equipment types, and newly added differential power features.

[0012] In some embodiments, the method further includes: Periodically access the open-source appliance energy efficiency library; When the open-source appliance energy efficiency database is updating data, the appliance feature knowledge base is updated based on the updated data.

[0013] In a second aspect, embodiments of this application provide an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it causes the electronic device to implement the method as described in any of the embodiments of the first aspect.

[0014] Thirdly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method as described in any of the embodiments of the first aspect.

[0015] Fourthly, embodiments of this application provide a computer program product, including a computer program, which, when run, causes the method as described in any embodiment of the first aspect to be performed.

[0016] The advantages of the embodiments in this application compared with related technologies are: By performing differential calculations on historical power consumption data of an electricity consumption area within a preset time period, based on a preset time granularity, the target differential power characteristics of existing electrical appliances in that area during that historical time period can be obtained. Furthermore, differential calculations on historical power consumption data can reveal the power characteristics of electrical appliances hidden at different time granularities. In this way, matching the target differential power characteristics with the preset differential power characteristics corresponding to each preset device in a preset electrical feature knowledge base allows for the accurate identification of potential electrical appliances in the electricity consumption area, i.e., candidate devices. The electrical feature data associated with candidate devices in the electrical feature knowledge base then constitutes the accurate electrical feature data of all possible electrical appliances in the electricity consumption area. Based on the identified candidate device electrical feature data, device identification is performed on the current real-time power consumption data of the electricity consumption area, significantly reducing the types and number of electrical appliances that need to be distinguished and identified, thereby greatly narrowing the appliance search range during device identification. Moreover, based on the accurate candidate device electrical feature data, information such as the power of different electrical appliances in the electricity consumption area under different operating states and possible power fluctuations when switching operating states can be accurately determined. In this way, by narrowing down the search scope for electrical appliances, the power consumption data of different candidate devices used in combination under different operating conditions can be quickly and accurately determined. This allows for the rapid and accurate acquisition of the electrical appliances and their operating status under the current real-time power consumption data. This not only improves the efficiency and accuracy of household electricity load component analysis but also enables real-time analysis of the electricity load component of an area based on the identified appliance characteristic data of candidate devices and device identification using real-time power consumption data. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or related technologies 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.

[0018] Figure 1 This is a schematic flowchart of a method for analyzing the components of electrical load provided in an embodiment of this application.

[0019] Figure 2 This is a flowchart illustrating another method for analyzing the composition of electrical load provided in this application.

[0020] Figure 3 This is an algorithm structure diagram of an application scenario power load component analysis method provided in an embodiment of this application.

[0021] Figure 4 This application provides an example of a cooperative application scenario. Figure 3 A flowchart illustrating the power load component analysis method based on the algorithm structure.

[0022] Figure 5 This is a flowchart of a component analysis system for an application scenario that is applicable to the method of analyzing the composition of electrical load, as provided in an embodiment of this application.

[0023] Figure 6 This is a schematic flowchart of another method for analyzing the composition of electrical load provided in an embodiment of this application.

[0024] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0025] Figure 8 This is a schematic diagram of the structure of an electrical load component analysis device provided in an embodiment of this application. Detailed Implementation

[0026] The technical solutions in the embodiments of this application will be described below with reference to the accompanying drawings.

[0027] Currently, NILM (Non-Induced Load Management) solutions for household electricity load component analysis typically fall into two categories: mathematical programming and artificial intelligence (AI). Mathematical programming directly encodes the physical characteristics (e.g., on / off states or power ranges) and operational logic (e.g., minimum operating time or state sequences) of household appliances into mathematical constraints (e.g., integer variables, continuous variables, or inequalities), transforming the load identification problem involved in load component analysis into a mathematical optimization problem, and then analyzing the load components based on the optimization results. AI, on the other hand, uses machine learning models to learn the steady-state (e.g., active or reactive power step) and / or transient characteristics (e.g., appliance IV curves) of appliances, thus failing to identify load components through models. However, the former requires pre-input of basic parameters for each appliance and is highly dependent on prior knowledge of the appliances; if appliances are updated or basic parameters are inaccurate, it cannot effectively identify the correct load components. The latter requires significant computational overhead, cannot achieve real-time identification on resource-constrained edge devices (such as smart meters), and cannot accurately identify newly added appliances.

[0028] To address the aforementioned issues, this application proposes a method for analyzing electricity load components, an electronic device, a readable medium, and a program product. It performs differential calculations on electricity power data of an area over a historical time period, based on a preset time granularity, to extract differential power characteristics of dynamic changes in electrical equipment within the historical time period. By matching these differential power characteristics with preset differential power characteristics corresponding to each preset device in a preset electrical feature knowledge base, the range of candidate devices is narrowed down, thereby reducing the computational load of subsequent load component analysis of the current real-time electricity power data. Furthermore, it can accurately identify electrical equipment involved in the real-time electricity power data based on the electrical feature data associated with the identified candidate devices. Simultaneously, it can support the dynamic addition of new devices through updates to the preset electrical feature knowledge base, improving the accuracy of identifying new devices.

[0029] Figure 1 This is a schematic flowchart of a method for analyzing the composition of electrical load provided in an embodiment of this application, as shown below. Figure 1 The method shown includes the following steps: S101, Obtain historical power consumption data of the power consumption area within a preset time period.

[0030] The device recommendation method in this application embodiment can be applied to electronic devices. The electronic devices can be electronic devices carrying an EMS (Energy Management System) module (such as smart distribution boxes, home energy gateways, industrial energy gateways, energy storage devices, and smart charging piles), smart home central control devices or cloud back-end devices carrying a cloud EMS module, and the carrier of the smart home central control device or cloud back-end device can be a mobile phone, tablet computer, wearable device, laptop computer, or personal digital assistant (PDA), etc. This application embodiment does not impose any restrictions on the specific type of electronic device.

[0031] The electricity consumption area is the region where the meter can detect the power consumption. The meter communicates with electronic devices; for example, when the meter is installed at the main electrical inlet of a user's residence, it can detect the power consumption of all electrical appliances within the residence, meaning the electricity consumption area can be the user's residence.

[0032] The start time of the preset time period is earlier than the current time, and the end time of the preset time period can be earlier than or equal to the current time. For example, the preset time period can be three months, six months or one year before the current time. The specific settings can be based on the data period covered by the differential operation. No restrictions are imposed in this application embodiment.

[0033] Historical power consumption data includes at least one power consumption record collected by smart meters within a preset time period. The power consumption record includes the total power consumption value of the power consumption area at at least one moment. In other words, historical power consumption data includes at least one power consumption record arranged by time (or time sequence).

[0034] Electronic devices can read historical power consumption data within a preset time period from a smart meter that is connected to them for communication. Alternatively, electronic devices can record the power consumption data sent by the smart meter each time in chronological order, read the power consumption data within the preset time period from their own storage location, and use the read power consumption data as historical power consumption data within the preset time period. Alternatively, if the electronic device has already stored historical power consumption data within the preset time period in the same scenario, it can directly obtain it. Alternatively, the smart meter will send power values, current or voltage signals, and other power consumption information collected each time to the electronic device at a specified frequency, and the electronic device can filter out the historical power consumption data within the preset time period from the multiple power consumption information received.

[0035] S102, perform differential calculation on historical power consumption data according to the preset time granularity to obtain the target differential power characteristics.

[0036] The target differential power feature is used to represent the quantified power change index extracted through differential operations. For example, the target differential power feature may include the power change amount, state switching matrix, and switching category, etc., which are not specifically limited in this embodiment. The switching category is used to represent the switching event or state switching of the electrical equipment.

[0037] The preset time granularity is used to represent the smallest time unit during differential operations. The preset time granularity can be one or more granularities. When there is only one time granularity, the electronic device performs differential operations on the historical power consumption data based on that time granularity. When there are multiple time granularities, the electronic device performs differential operations on the historical power consumption data for each time granularity.

[0038] In the actual use of electrical appliances, power fluctuations (i.e., power changes) mainly originate from the switching (also known as switching events) or state transitions of these appliances (e.g., a dishwasher switching from sterilization mode to drying mode). Different appliances experience different power fluctuations due to switching events and state transitions. Therefore, differential calculations can dynamically capture the power changes caused by different appliances during switching events and / or state transitions. In other words, the target differential power characteristics obtained through differential calculations can serve as identification information for the dynamic power changes of existing appliances in the power consumption area within a preset time period, thereby enabling accurate identification of candidate devices within the power consumption area. Since switching events often cause power fluctuations within a very short time, while state transitions often cause power fluctuations over a slightly longer period, two preset time granularities of different sizes can be designed to accurately capture the different power changes caused by switching events and state transitions. In one embodiment, the time granularity corresponding to the switching event of the electrical device is used as the first time granularity. For example, 100ms can be used to capture the differential power during the transient change of the switch. The time granularity corresponding to the state switching event of the electrical device is used as the second time granularity. For example, 1s can be used to track the differential power during the mode switching. This application does not limit the setting of the time granularity.

[0039] In one implementation, the electronic device can perform time-series differential analysis on historical power consumption data according to a first time granularity using a differential algorithm to obtain a power change sequence of historical power consumption data at the first time granularity. Then, feature extraction operations such as state switching matrix and switching category are performed on this power change sequence to obtain differential power features of historical power consumption data at the first time granularity. Furthermore, the electronic device can perform time-series differential analysis on historical power consumption data according to a second time granularity using a differential algorithm to obtain a power change sequence of historical power consumption data at the second time granularity. Then, feature extraction operations such as state switching matrix and switching category are performed on this power change sequence to obtain differential power features of historical power consumption data at the second time granularity. The differential power features at both the first and second time granularities are used as the target power differential features.

[0040] In one implementation, differential operations are performed on historical power consumption data according to a preset time granularity to obtain target differential power features, including: determining a dynamic window based on the preset time granularity; sliding the dynamic window on the historical power consumption data based on a preset step size, and performing differential operations on the historical power consumption data within the dynamic window after each sliding of the dynamic window to obtain target differential power features.

[0041] The preset step size represents the movement interval between two adjacent dynamic windows each time the dynamic window is moved. It can be determined based on the time granularity, for example, the preset step size is 100%, 50%, or 30% of the time granularity.

[0042] Electronic devices can use a preset time granularity as the dynamic window for that granularity. For example, if the first time granularity is 50ms, the corresponding dynamic window is 50ms; if the second time granularity is 1s, the corresponding dynamic window is 1s. For each dynamic window of a preset time granularity, the electronic device can start from the earliest moment in the historical power consumption data, perform time-series differencing on the power consumption values ​​within that window, and continue performing time-series differencing on the power consumption values ​​within that window by sliding the dynamic window at a preset step size, until the end time of the sliding dynamic window is later than the latest moment in the historical power consumption data. The results of each time-series differencing under each dynamic window are combined as the differencing operation sequence for that time granularity. Differential power features are extracted from the combination of differencing operation sequences under each time granularity, and these differential power features are used as target differential power features. In this technical solution, the dynamic window is determined based on a preset time granularity, allowing for the targeted capture of transient or steady-state differential power features in historical power consumption data. Furthermore, by sliding a predetermined dynamic window across historical power consumption data with a preset step size, the differential calculation can ensure that the entire historical power consumption data is covered through the sliding of the window, reducing the possibility of missing data processing. The differential calculation results within each dynamic window are used together as the target differential power feature. This not only reduces the number of differential calculations on historical power consumption data, speeding up the differential calculation efficiency and thus accelerating the efficiency of power load component analysis, but also filters out noise in the data within the window through differential calculations on historical power consumption data within the dynamic window, making the target differential power feature more representative and thus improving the accuracy of subsequent candidate device determination.

[0043] In some embodiments, the extracted differential power features can be cleaned by setting a power fluctuation threshold and comparing the thresholds to remove differential power features that do not exhibit significant power fluctuations. This reduces the amount of data required for subsequent data matching and improves processing speed. For example, suppose a household has only one washing machine running, with a washing time of 40 minutes. The entire washing process consists of four stages: water filling, soaking, washing, and spin-drying. The power consumption of the washing machine changes due to variations in its operating mode at different stages, resulting in power fluctuations. If the differential power features of the washing machine's process are statistically analyzed at a 1-second time granularity, it can be found that significant power fluctuations only occur during the tens of seconds between different stages. No significant power fluctuations are observed at other times. Therefore, data cleaning of the differential power features during the washing process can remove most of the differential power features that do not exhibit power fluctuations, greatly reducing the amount of data required for subsequent data matching and effectively improving processing speed.

[0044] S103, Match the target differential power features with the preset differential power features corresponding to each preset device in the preset electrical feature knowledge base to determine the candidate devices.

[0045] The pre-defined electrical appliance feature knowledge base is a structured database containing electrical appliance feature data, including pre-defined differential power features, pre-defined basic features, and pre-defined state features. Pre-defined basic features represent the type of electrical appliance, while pre-defined state features represent the constraints during state switching. For example, pre-defined basic features may include the name, brand, model, or energy efficiency rating of the electrical appliance; pre-defined state features may include the number of states, state names, power of each state, and duration limits for each state. In other words, the electrical appliance feature knowledge base is a priori knowledge base that provides information such as differential power features, basic features, and state features for electricity load component analysis.

[0046] This appliance characteristic knowledge base can be pre-created based on information such as the name, brand, model, energy efficiency rating, and power consumption data under various test conditions of each appliance in publicly available open-source appliance energy efficiency databases and self-built private dynamic appliance databases. Alternatively, the appliance characteristic knowledge base can be obtained by periodically updating an existing prior knowledge base or by responding to user update requests.

[0047] In one implementation, the electronic device can analyze the differential power characteristics of different preset devices combined under different states based on the preset differential power characteristics corresponding to each preset device in the electrical feature knowledge base, and select the preset device in the combination that is most similar to the target differential power characteristics as the candidate device.

[0048] In one implementation, the target differential power feature is matched with the preset differential power features corresponding to each preset device in a preset electrical appliance feature knowledge base to determine candidate devices. This includes: calculating the similarity between the target differential power feature and the preset differential power features corresponding to each preset device in the preset electrical appliance feature knowledge base; and determining the preset devices corresponding to similarity scores greater than a preset similarity threshold as candidate devices. The similarity score can be cosine similarity or Euclidean distance, etc., and this application embodiment does not impose limitations. The preset similarity threshold can be 85%, 88%, 90%, or 95%, etc. For convenience, 90% is used as an example. In this technical solution, for each preset device corresponding to a preset differential power feature in the electrical appliance feature knowledge base, its similarity to the target differential power feature is calculated, and preset devices corresponding to similarity scores greater than a preset similarity threshold are selected as candidate devices. This allows for the rapid and accurate determination of electrical appliances, i.e., candidate devices, that may exist in a user area within a preset time period through similarity calculation and threshold filtering, thereby improving the efficiency of electricity load component analysis.

[0049] It is understandable that when the time granularity includes a first time granularity and a second time granularity, the target differential power features can include differential power features representing switching events and differential power features representing state transitions, respectively. Since switching events and state transitions may both be the power consumption behaviors of the same electrical device, the electronic device will perform similarity calculations on each differential power feature in the target differential power features to determine preset differential power features whose similarity is greater than a preset similarity threshold. Duplicate electrical devices will then be removed from all the electrical devices corresponding to the determined preset differential power features to obtain candidate devices.

[0050] S104, obtain the current real-time power consumption data.

[0051] Electronic devices can read real-time power consumption data collected at the current moment from a smart meter that is connected to them for communication, or electronic devices can also receive real-time power consumption data sent by the smart meter at the current moment.

[0052] S105, based on the electrical feature data associated with candidate devices in the electrical feature knowledge base, perform device identification on real-time power consumption data to determine the current electrical equipment currently operating in the power consumption area and the current operating status of the current electrical equipment.

[0053] Among them, the operating status of electrical equipment is used to indicate whether the electrical equipment is in a specified state or whether the electrical equipment has switched from one state to another.

[0054] In one implementation, the electronic device can simulate the power consumption data of different numbers of candidate devices combined under different states based on electrical feature data associated with candidate devices in an electrical feature knowledge base. This yields simulated power consumption data for multiple reference device combinations. The reference device combination with the smallest difference between the simulated power consumption data and the real-time power consumption data is selected as the target device combination. The electronic device then identifies each candidate device in this target device combination as the currently operating electrical device in the power consumption area, and the operating state of each candidate device in the target device combination is taken as the current operating state of the current electrical device.

[0055] In one implementation, combining Figure 2 Based on the electrical feature data associated with candidate devices in the electrical feature knowledge base, the real-time power consumption data is used to identify the devices and determine the current electrical devices currently operating in the power consumption area and the current operating status of the current electrical devices, including the following S201 to S202.

[0056] S201. Based on the electrical feature data associated with candidate devices in the electrical feature knowledge base, a mixed integer programming model is constructed.

[0057] Electronic devices can construct model constraints and objective functions based on the electrical feature data associated with each candidate device, thereby obtaining a Mixed Integer Programming (MIP) model.

[0058] The objective function indicates that the goal of the model is to minimize the estimation error and the state transition cost. The objective function can be expressed as shown in Equation 1: Formula 1 in, Indicates the state transition cost weight. This represents the finite number of states of the i-th electrical device. Indicates whether the i-th electrical device transitions from finite state s to finite state s at time t. next Boolean variable, Let T represent the state transition cost matrix of the i-th electrical device, T represent the preset time period, and N represent the total number of candidate devices. represents the estimation error between the actual power at time t (i.e., the power value at time t in historical power consumption data) and the estimated power, and is a continuous variable greater than or equal to 0, where i is a positive integer.

[0059] Constraints can be set according to the actual scenario. For example, constraints may include estimation error balance constraints, state uniqueness constraints, state transition uniqueness constraints, and maximum state running time constraints. The estimation error balance constraint indicates that the estimation error equals the difference between the actual power and the estimated power, as shown in Equation 2: Formula 2 in, This represents the power value at time t. A Boolean variable representing whether the i-th electrical device is in a finite state s at time t. The power consumption of the i-th electrical device in finite state s.

[0060] The state uniqueness constraint is used to indicate that each electrical device is in at most one finite state at any given time, as shown in Equation 3: Formula 3 The state transition uniqueness constraint is used to indicate that each electrical device can only transition to one state and can only transition from one state during each state transition, as shown in Equations 4 and 5: Formula 4 Formula 5 in, Indicates whether the i-th electrical device is in finite state s at time t+1. next Boolean variable.

[0061] The maximum running time constraint for a state is used to indicate that the duration of time each electrical device is in each state cannot exceed the maximum and minimum values, as shown in Formulas 6 and 7: Formula 6 Formula 7 in, This represents the maximum number of operating times for the i-th electrical device under finite state s. This represents the minimum number of operating times for the i-th electrical device in finite state s. It should be noted that the i-th electrical device mentioned in formulas 1 to 7 above is the i-th candidate device among all candidate devices determined in S102, and the finite state can also be called a state.

[0062] S202, input the real-time power consumption data into the mixed integer programming model for optimization and solution, and determine the current electrical equipment and its current operating status.

[0063] Electronic devices input real-time power consumption data into a pre-built MIP model. The MIP model then uses an open-source solver or heuristic method to optimize and solve the real-time power consumption data, outputting the solution results. The electronic devices can then determine the current electrical equipment and its current operating status from the solution results. Because candidate devices are pre-screened before optimization, the scale of the problem to be solved by the MIP model is greatly reduced, allowing the optimization process to be completed in seconds or even milliseconds, meeting users' real-time requirements for power load component analysis.

[0064] The input parameters of the MIP model include: , , , , , , , and ,in, This represents the state transition matrix of the i-th electrical device. This represents the state transition cost matrix of the i-th electrical device. It can be understood that when the electronic device inputs real-time power consumption data into the MIP model, it will input the electrical feature data associated with all candidate devices determined in S102, along with the data involved in the aforementioned objective function and model constraints, into the MIP model for optimization. The output parameters of the MIP model include... , and .

[0065] In this technical solution, a mixed integer programming model containing integer variables is constructed by using electrical feature data associated with candidate devices in an electrical feature knowledge base. This transforms the device identification problem for electricity load component analysis into an optimization solution process for the mixed integer programming model. This not only accurately identifies each currently operating electrical device and its specific operating status in real-time power consumption data based on the created model, but also ensures the global optimality and consistency of the identification results through optimization, thereby significantly improving the identification accuracy and reliability, enhancing the accuracy of electricity load component analysis in the electricity consumption area, and providing strong data support for efficient management and energy-saving analysis of the electricity consumption area.

[0066] In one application scenario, combined with Figures 3 to 5Taking an electronic device integrated with a component analysis system as an example, the working process of the power load component analysis method in this application embodiment is explained. First, in Step 1, the component analysis system performs data processing operations based on information such as the name, brand, model, energy efficiency level, and power consumption data under various test conditions of each electrical appliance in the open-source (electrical appliance) energy efficiency library and the private dynamic electrical appliance library. This creates an electrical characteristic knowledge base that includes differential power characteristics of multiple household appliances (an example of preset differential power characteristics of preset devices). Then, in Step 2, the component analysis system collects the total historical power consumption of a user's household (an example of an electricity consumption area) within one year or six months (an example of historical power consumption data within a preset time period) at the data acquisition layer or synthesis layer. At the differential processing layer, it performs window sliding and differential processing on the total historical power consumption of the household through different differential time resolutions (an example of time granularity). The system captures transient abrupt changes in the total historical electricity consumption of a household within a 100ms window (an example of a dynamic window) and gradual abrupt changes within a 1s window (another example of a dynamic window) at the feature library layer, obtaining the actual differential power characteristics of the user's household (an example of target differential power characteristics). At the matching layer, lightweight matching rules (or a lightweight matching engine) are used to calculate the similarity between the differential power characteristics of household appliances in the appliance feature knowledge base and the actual differential power characteristics. Differential power characteristics with a similarity greater than 90% are selected, and it is identified whether they correspond to switching events or state transitions. The selected household appliances corresponding to these differential power characteristics are then merged to obtain a household appliance filter set (an example of S103). The household appliances in the filter set are the candidate devices. In Step 4, the current total household electricity consumption (an example of current real-time electricity consumption data) is obtained at the data acquisition layer or synthesis layer. In Step 5, at the model algorithm layer, the appliance feature data of the household appliances in the household appliance filter set is obtained from the appliance feature knowledge base. The real-time total power consumption of the household appliances and the obtained appliance feature data are input into the constructed MIP model so that the start-up and operation status of each appliance can be identified through the MIP model. This enables intelligent scheduling optimization (such as controllable load scheduling or demand response) at the application layer and recommendations to users to guide their electricity consumption behavior and save users' electricity costs.

[0067] It should be noted that the aforementioned power consumption data and appliance characteristic data can only be obtained with the user's authorization. For example, when a user enters the relevant electricity consumption query page, the page enters an interactive state, prompting the user with a question asking "Do you authorize the user's household electricity consumption information?" The user can then refuse or authorize the access to electricity consumption information. Generally, if the user does not authorize, information indicating insufficient permissions to query can be displayed.

[0068] In this embodiment, by performing differential calculations on historical power consumption data of an electricity consumption area within a preset time period based on a preset time granularity, the target differential power characteristics of existing electrical devices in the electricity consumption area within the historical time period can be obtained. Furthermore, differential calculations on historical power consumption data can yield the power characteristics of electrical devices hidden within the power data at different time granularities. In this way, by matching the target differential power characteristics with the preset differential power characteristics corresponding to each preset device in a preset electrical feature knowledge base, the electrical devices that may exist in the electricity consumption area, i.e., candidate devices, can be accurately determined. Therefore, the electrical feature data associated with candidate devices in the electrical feature knowledge base constitutes the accurate electrical feature data of all possible electrical devices in the electricity consumption area. Based on the determined electrical feature data of candidate devices, device identification is performed on the current real-time power consumption data of the electricity consumption area. This limits the type and number of electrical devices corresponding to the real-time power consumption data from the outset, thereby significantly reducing the search scope during device identification. Furthermore, based on the accurate electrical feature data of candidate devices, information such as the power of different electrical devices in the electricity consumption area under different operating states and possible power fluctuations when switching operating states can be accurately identified. In this way, by narrowing down the search scope for electrical appliances, the power consumption data of different candidate devices used in combination under different operating conditions can be quickly and accurately determined. This allows for the rapid and accurate acquisition of the electrical appliances and their operating status under the current real-time power consumption data. This not only improves the efficiency and accuracy of household electricity load component analysis but also enables real-time analysis of the electricity load component of an area based on the identified appliance characteristic data of candidate devices and device identification using real-time power consumption data.

[0069] Figure 6 This is yet another method for analyzing the composition of electrical load provided in the embodiments of this application, such as... Figure 6 The method shown includes the following steps.

[0070] S301 If no current electrical appliance corresponding to the real-time power consumption data is identified, a confirmation message for adding electrical appliance feature entry will be displayed.

[0071] If, based on the electrical feature data associated with candidate devices in the electrical feature knowledge base, the electronic device fails to identify the current electrical device corresponding to the real-time power consumption data, the electronic device can determine that a new electrical device exists in the power consumption area, and the electrical feature data of this new electrical device is not in the electrical feature knowledge base, meaning an unknown electrical device exists. In this case, the electronic device outputs a prompt for confirmation of the new electrical device's feature input via voice, text, or image, to inform the user that a new electrical device exists in the power consumption area and that the user needs to input the type of the relevant electrical device.

[0072] S302, in response to the user's consent entry operation, determines the new device type corresponding to the real-time power consumption data.

[0073] The newly added equipment types can include information such as the name, brand, model, or energy efficiency rating of the electrical equipment.

[0074] If the user agrees to input the data, the user can enter the device type of the relevant electrical appliance in the electronic device, such as a new brand of air purifier or electric oven. The electronic device will use the device type entered by the user as the new device type corresponding to the real-time power consumption data.

[0075] S303 performs differential calculations on real-time power consumption data according to a preset time granularity to obtain the corresponding newly added differential power features.

[0076] When electronic devices determine the presence of unknown electrical equipment in a power consumption area, they perform differential calculations on the acquired real-time power consumption data to obtain corresponding new differential power characteristics. The specific process is as follows... Figure 1 S102 in the illustrated embodiment is similar and will not be described in detail here.

[0077] S304 updates the electrical appliance feature knowledge base based on real-time power consumption data, newly added equipment types, and newly added differential power features.

[0078] Electronic devices determine new state characteristics based on real-time power consumption data and newly added differential power characteristics, and determine new basic characteristics based on the new device type. The new differential power characteristics, new state characteristics, and new basic characteristics are then stored as new electrical appliance characteristic data in the electrical appliance characteristic knowledge base. This process continues... Figure 5 By enabling open feature input, online effect-driven updates to the electrical appliance feature knowledge base can be achieved.

[0079] In one implementation, the method further includes: obtaining preset energy efficiency data of preset devices from a preset open-source electrical energy efficiency library; performing differential operations on the preset energy efficiency data according to a preset time granularity to obtain preset differential power features; and constructing an electrical feature knowledge base based on the preset energy efficiency data and preset differential power features of the preset devices.

[0080] The preset energy efficiency data includes at least several preset devices' applied power data, appliance names, brands, models, and energy efficiency ratings under various test conditions. Electronic devices can perform differential operations on the power consumption data in the preset energy efficiency data based on a preset time granularity to obtain preset differential power characteristics. Based on the power consumption data under each test condition and the determined preset differential power characteristics, preset state characteristics are determined, and preset basic characteristics are determined based on the appliance name, brand, model, and energy efficiency rating. The preset differential power characteristics, preset state characteristics, and preset basic characteristics of each preset device are combined to construct an appliance characteristic knowledge base. In this way, by integrating data from authoritative open-source appliance energy efficiency libraries and combining differential operations to extract identifiable differential power characteristics, an accurate and reliable appliance characteristic knowledge base can be constructed, thereby improving the reliability of electricity load component analysis.

[0081] In some implementations, the method further includes: periodically accessing an open-source appliance energy efficiency database; and updating the appliance feature knowledge base based on updated data when the open-source appliance energy efficiency database contains updated data. Electronic devices can periodically (e.g., daily, weekly, or monthly) access the open-source appliance energy efficiency database via an Application Programming Interface (API) to detect the presence of updated data. If updated data is found, preset energy efficiency data is updated based on the updated data, and the updated preset energy efficiency data undergoes the same processing operations as described in the aforementioned implementation to obtain new appliance feature data, thereby updating the appliance feature knowledge base. In this way, by periodically accessing the open-source appliance energy efficiency database and automatically updating the appliance feature knowledge base, the accuracy and timeliness of electricity load component analysis are ensured.

[0082] In this embodiment, when no current electrical device corresponding to the real-time power consumption data is identified, not only will a prompt to add electrical device features be output, but the type of new device will also be determined in a timely manner based on the content entered by the user. The electrical feature knowledge base will be automatically updated according to the real-time power consumption data, the type of new device, and the new differential power features, so as to realize the dynamic and accurate expansion of the electrical feature knowledge base, thereby adapting to the new electrical devices in the power consumption area. This can reduce the situation of poor identification of new electrical devices in traditional solutions and improve the system's adaptability and long-term identification accuracy.

[0083] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 7 As shown, the electronic device 6 of this embodiment includes: at least one processor 60 ( Figure 7(Only one is shown in the diagram) a processor, a memory 61, and a computer program 62 stored in the memory 61 and executable on the at least one processor 60, wherein the processor 60 executes the computer program 62 to implement the steps in any of the above method embodiments.

[0084] The electronic device 6 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. This electronic device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 7 This is merely an example of electronic device 6 and does not constitute a limitation on electronic device 6. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0085] The processor 60 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0086] In some embodiments, the memory 61 may be an internal storage unit of the electronic device 6, such as a hard disk or memory of the electronic device 6. In other embodiments, the memory 61 may be an external storage device of the electronic device 6, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 6. Furthermore, the memory 61 may include both internal and external storage units of the electronic device 6. The memory 61 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0087] Corresponding to the electricity load component analysis method described in the above embodiments, Figure 8A structural block diagram of the electrical load component analysis device provided in the embodiments of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0088] Reference Figure 8 The device includes: The acquisition module 810 is used to acquire historical power consumption data of the power consumption area within a preset time period; The differential module 820 is used to perform differential calculations on historical power consumption data according to a preset time granularity to obtain the target differential power characteristics. The matching module 830 is used to match the target differential power features with the preset differential power features corresponding to each preset device in the preset electrical feature knowledge base to determine the candidate devices; The acquisition module 810 is also used to acquire the current real-time power consumption data; The identification module 840 is used to identify devices based on electrical feature data associated with candidate devices in the electrical feature knowledge base, and to determine the current electrical devices currently operating in the power consumption area and the current operating status of the current electrical devices.

[0089] In some embodiments, the differential module is further configured to: The dynamic window is determined based on a preset time granularity; A dynamic window is slid across historical power consumption data based on a preset step size. After each sliding of the dynamic window, a differential operation is performed on the historical power consumption data within the dynamic window to obtain the target differential power feature.

[0090] In some embodiments, the matching module is also used for: Calculate the similarity between the target differential power characteristics and the preset differential power characteristics corresponding to each preset device in the preset electrical characteristic knowledge base; Preset devices with similarity scores greater than a preset similarity threshold are identified as candidate devices.

[0091] In some embodiments, the identification module is further configured to: Based on the electrical feature data associated with candidate devices in the electrical feature knowledge base, a mixed integer programming model is constructed; Real-time power consumption data is input into a mixed integer programming model for optimization and solution to determine the current electrical equipment and its current operating status.

[0092] In some embodiments, the acquisition module is further configured to acquire preset energy efficiency data of a preset device from a preset open-source electrical appliance energy efficiency library; The differential module is also used to perform differential operations on preset energy efficiency data according to preset time granularity to obtain preset differential power characteristics; The matching module is also used to build an appliance feature knowledge base based on preset energy efficiency data and preset differential power characteristics of preset devices.

[0093] In some embodiments, the identification module is further configured to: If no electrical appliance corresponding to the real-time power consumption data is identified, a confirmation message for adding electrical appliance feature entry will be displayed. In response to the user's consent to enter data, determine the type of new device corresponding to the real-time power consumption data; Differential calculations are performed on real-time power consumption data based on a preset time granularity to obtain the corresponding new differential power features; The electrical appliance feature knowledge base is updated based on real-time power consumption data, newly added equipment types, and newly added differential power features.

[0094] In some embodiments, the identification module is further configured to: Periodically access the open-source appliance energy efficiency library; When the open-source appliance energy efficiency database is updating data, the appliance feature knowledge base is updated based on the updated data.

[0095] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0096] 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.

[0097] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0098] This application provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps described in the above-described method embodiments.

[0099] If the integrated 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 of this application can 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 at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0100] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0101] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0102] Furthermore, in the description of this application and the appended claims, the terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized. 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.

[0103] 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 each specific application, but such implementation should not be considered beyond the scope of this application.

[0104] In the embodiments provided in this application, it should be understood that the disclosed apparatus, computer equipment, and methods can be implemented in other ways. For example, the apparatus and computer equipment embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple 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 apparatuses or units may be electrical, mechanical, or other forms.

[0105] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. 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. Such 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 analyzing the components of electrical load, characterized in that, include: Obtain historical power consumption data for a power consumption area within a preset time period; The historical power consumption data is differentially processed according to a preset time granularity to obtain the target differential power characteristics; The target differential power feature is matched with the preset differential power features corresponding to each preset device in the preset electrical feature knowledge base to determine the candidate device; Obtain the current real-time power consumption data; Based on the electrical feature data associated with the candidate devices in the electrical feature knowledge base, the real-time power consumption data is used to identify the current electrical devices currently operating in the power consumption area and the current operating status of the current electrical devices.

2. The method as described in claim 1, characterized in that, The step of performing differential calculations on the historical power consumption data according to a preset time granularity to obtain target differential power characteristics includes: The dynamic window is determined based on a preset time granularity; The dynamic window is slid across the historical power consumption data based on a preset step size, and after each slid of the dynamic window, a differential operation is performed on the historical power consumption data within the dynamic window to obtain the target differential power feature.

3. The method as described in claim 2, characterized in that, The step of matching the target differential power feature with the preset differential power features corresponding to each preset device in a preset electrical feature knowledge base to determine candidate devices includes: Calculate the similarity between the target differential power feature and the preset differential power feature corresponding to each preset device in the preset electrical feature knowledge base; The preset devices corresponding to similarity scores greater than a preset similarity threshold are determined as the candidate devices.

4. The method as described in claim 3, characterized in that, The step of identifying devices based on electrical feature data associated with the candidate devices in the electrical feature knowledge base, and determining the currently operating electrical devices and their current operating status in the electricity consumption area, includes: Based on the electrical feature data associated with the candidate device in the electrical feature knowledge base, a mixed integer programming model is constructed; The real-time power consumption data is input into the mixed integer programming model for optimization and solution to determine the current electrical equipment and its current operating status.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Obtain the preset energy efficiency data of the preset device from the preset open-source electrical appliance energy efficiency library; The preset energy efficiency data is differentially processed according to the preset time granularity to obtain the preset differential power characteristics; Based on the preset energy efficiency data and preset differential power characteristics of the preset device, the electrical appliance feature knowledge base is constructed.

6. The method as described in claim 5, characterized in that, The method further includes: If no current electrical device corresponding to the real-time power consumption data is identified, a confirmation message for adding electrical device feature entry will be displayed. In response to the user's consent to enter the data, the type of new device corresponding to the real-time power consumption data is determined; The real-time power consumption data is differentially processed according to a preset time granularity to obtain the corresponding new differential power features; The electrical appliance feature knowledge base is updated based on the real-time power consumption data, the newly added device type, and the newly added differential power feature.

7. The method as described in claim 5, characterized in that, The method further includes: Periodically access the aforementioned open-source appliance energy efficiency library; When the open-source appliance energy efficiency database is updating data, the appliance feature knowledge base is updated according to the updated data.

8. An electronic device, characterized in that, The device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, the electronic device performs the method as described in any one of claims 1-7.

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

10. A computer program product, characterized in that, Includes a computer program, which, when run, causes the method as described in any one of claims 1-7 to be performed.