A method and system for establishing a discontinuous workload identification feature library

By extracting the features in the historical waveform data of discontinuous workloads, the problem of difficulty in establishing a discontinuous workload identification feature library in the prior art is solved, and the full-cycle feature extraction of discontinuous workloads and the completeness of the feature library is achieved, providing effective data support for load identification.

CN113486076BActive Publication Date: 2025-07-01STATE GRID SHANDONG ELECTRIC POWER CO MARKETING SERVICE CENT (MEASURING CENT) +4
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202110617450.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-05-28
Publication Date
2025-07-01
Estimated Expiration
2041-05-28

AI Technical Summary

Technical Problem

It is difficult to effectively establish a library of identification feature for discontinuous workloads, especially when processing historical waveform data of discontinuous workloads, it is difficult to extract stable and accurate features.

Method used

By obtaining the historical waveform data of the target workload, determine whether it belongs to the power load of the discontinuous work and has a steady-state output process, and extract its working mode characteristics, transient startup process characteristics, steady-state process characteristics and transient shutdown process characteristics to establish a corresponding identification feature library.

Benefits of technology

The full-cycle feature extraction of discontinuous workloads is realized, ensuring the completeness and accuracy of the feature library, and providing sufficient data support for subsequent load identification algorithm model training.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113486076B_ABST
    Figure CN113486076B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system suitable for establishing a discontinuous workload identification feature library, belonging to the technical field of power consumption monitoring and signal processing. The method of the present invention includes: for a target workload, obtaining historical waveform data of the target workload, and determining whether the target workload belongs to an electricity load with discontinuous operation and a steady-state output process according to the historical waveform data; when the target workload belongs to an electricity load with discontinuous operation and a steady-state output process, extracting the working mode features, transient start-up process features, steady-state process features, and transient shutdown process features of the target workload; establishing an identification feature library for continuous workloads according to the extracted working mode features, transient start-up process features, steady-state process features, and transient shutdown process features. The present invention can complete the extraction of main features in the full cycle of the transient start-up process, steady-state process, and transient shutdown process for the target load.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power consumption monitoring and signal processing, and more specifically, to a method and system suitable for establishing a discontinuous working load identification feature library. Background Art

[0002] The establishment of a load feature library is the prerequisite and core for realizing non-intrusive load identification. For industrial and commercial users in different industries, their power consumption loads are diverse. Based on a large amount of load start-stop waveform data, it is necessary to rely on an automated method to establish a relatively complete feature library. Summary of the Invention

[0003] In view of the above problems, the present invention proposes a method suitable for establishing a discontinuous working load identification feature library, including:

[0004] For a target working load, obtain historical waveform data of the target working load, and determine whether the target working load belongs to a power consumption load that is discontinuous and has a steady-state output process according to the historical waveform data;

[0005] When the target working load belongs to a power consumption load that is discontinuous and has a steady-state output process, extract the working mode characteristics, transient start-up process characteristics, steady-state process characteristics, and transient shutdown process characteristics of the target working load;

[0006] Establish an identification feature library for continuous working loads according to the extracted working mode characteristics, transient start-up process characteristics, steady-state process characteristics, and transient shutdown process characteristics.

[0007] Optionally, the extraction of the working mode feature library is performed according to the change of the three-phase current of the power consumption load, specifically including:

[0008] According to the start-up transient end time point T onb and the shutdown transient start time point T offa of the target working load, intercept the current waveform in the steady-state process [T onb , T offa , and calculate the mean value of the phase current of the current waveform. The formula is as follows:

[0009]

[0010]

[0011] Among them, formula (1) is used for calculating the mean value of the phase current of users with high-voltage supply and low-voltage metering, and formula (2) is used for calculating the mean value of the phase current of users with high-voltage supply and high-voltage metering. Supplementary parameter definitions are i at , i bt , i ctThey are the three-phase current sampling values collected in real time at the metering point of high-voltage supply and low-voltage metering users, respectively, i abt , i vbt They are the line current sampling values collected in real time at the metering point of high-voltage supply and high-voltage metering users, respectively;

[0012] The determination is made according to the following criteria:

[0013]

[0014]

[0015] Among them, K is the determination threshold. When the formula (3) or formula (4) is satisfied, the working mode characteristic of the target working load is a single-phase static electrical equipment, otherwise it is a three-phase rotating electrical equipment.

[0016] Optionally, the transient start-up process characteristics include transient time constant, transient power characteristic, transient voltage characteristic and transient current characteristic.

[0017] Optionally, the steady-state process characteristics include steady-state fluctuation period, steady-state power characteristic, steady-state voltage characteristic and steady-state current characteristic.

[0018] Optionally, the transient shutdown process characteristics include transient power characteristic, transient voltage characteristic and transient current characteristic. The transient power characteristic includes: power factor angle change characteristic, peak change characteristic and rising edge slope characteristic.

[0019] The present invention also proposes a system suitable for establishing an identification feature library for discontinuous working loads, including:

[0020] A data acquisition unit, for the target working load, obtains the historical waveform data of the target working load, and determines whether the target working load belongs to a discontinuous working and power output process existing electrical load according to the historical waveform data;

[0021] A feature extraction unit, when the target working load belongs to a discontinuous working and power output process existing electrical load, extracts the working mode characteristics, transient start-up process characteristics, steady-state process characteristics and transient shutdown process characteristics of the target working load;

[0022] A root feature library establishment unit, according to the extracted working mode characteristics, transient start-up process characteristics, steady-state process characteristics and transient shutdown process characteristics, establishes an identification feature library for continuous working loads.

[0023] Optionally, the extraction of the working mode feature library is carried out according to the change of the three-phase current of the electrical load, specifically including:

[0024] According to the start-up transient end time point T of the target working load onband the shutdown transient start time point T offa , intercept the current waveform during the steady-state process [T onb , T offa . Calculate the average value of the phase current for the current waveform. The formula is as follows:

[0025]

[0026]

[0027] Among them, Equation (1) is used to calculate the average value of the phase current for users with high-voltage supply and low metering, and Equation (2) is used to calculate the average value of the phase current for users with high-voltage supply and high metering. The supplementary parameter definitions are i at , i bt , i ct are the three-phase current sampling values collected in real time at the metering point of users with high-voltage supply and low metering, respectively, and i ab , i cbt are the line current sampling values collected in real time at the metering point of users with high-voltage supply and high metering, respectively;

[0028] Make a determination according to the following criteria:

[0029]

[0030]

[0031] Among them, K is the determination threshold. When Equation (3) or Equation (4) is satisfied, the working mode characteristic of the target workload is a single-phase static electrical equipment, otherwise it is a three-phase rotating electrical equipment.

[0032] Optionally, the transient start process characteristics include the transient time constant, transient power characteristics, transient voltage characteristics, and transient current characteristics.

[0033] Optionally, the steady-state process characteristics include the steady-state fluctuation period, steady-state power characteristics, steady-state voltage characteristics, and steady-state current characteristics.

[0034] Optionally, the transient shutdown process characteristics include the transient power characteristics, transient voltage characteristics, and transient current characteristics. The transient power characteristics include: power factor angle change characteristics, peak change characteristics, and rising edge slope characteristics.

[0035] The present invention can complete the extraction of the main characteristics in the full cycle of the transient start process, steady-state process, and transient shutdown process of the target load, realizing the complete retention of the identifiable characteristics, providing sufficient and effective sample data for the subsequent load identification algorithm model training, and providing a data basis for realizing the adaptive training and parameter adjustment of the load identification algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is the flowchart of the method of the present invention;

[0037] Figure 2 This is the waveform diagram of the time-domain current and voltage during the transient startup process of the method of the present invention;

[0038] Figure 3 This is the waveform diagram of the time-frequency domain characteristics during the transient startup process of the method of the present invention;

[0039] Figure 4 This is the waveform diagram of the time-domain current and voltage during the transient shutdown process of the method of the present invention.

[0040] Figure 5 This is the waveform diagram of the time-frequency domain characteristics during the transient shutdown process of the method of the present invention;

[0041] Figure 6 This is the structural diagram of the system of the present invention. Detailed implementation manners

[0042] Now, exemplary embodiments of the present invention will be described with reference to the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to disclose the present invention in detail and completely, and to fully convey the scope of the present invention to those skilled in the art. The terms in the exemplary embodiments shown in the drawings are not intended to limit the present invention. In the drawings, the same unit / element is denoted by the same reference numeral.

[0043] Unless otherwise specified, the terms (including scientific and technical terms) used herein have the ordinary meaning understood by those skilled in the art. In addition, it can be understood that the terms defined in the commonly used dictionary should be understood to have a meaning consistent with the context of their related fields, and should not be understood as having an idealized or overly formal meaning.

[0044] The present invention will be further described below in conjunction with the embodiments and the accompanying drawings:

[0045] The present invention proposes a method applicable to establishing a discontinuous workload identification feature library, as Figure 1 shown, including:

[0046] For the target workload, obtain the historical waveform data of the target workload, and determine whether the target workload belongs to a non-continuous workload and an electrical load with a steady-state output process according to the historical waveform data;

[0047] When the target workload belongs to a non-continuous workload and an electrical load with a steady-state output process, extract the working mode characteristics, transient startup process characteristics, steady-state process characteristics, and transient shutdown process characteristics of the target workload;

[0048] Establish an identification feature library for continuous workloads based on the extracted working mode characteristics, transient start-up process characteristics, steady-state process characteristics, and transient shutdown process characteristics.

[0049] Specifically, it includes:

[0050] Step 1: Determine whether the target load belongs to an electrical load with discontinuous operation and a steady-state output process. If the condition is met, proceed with subsequent feature extraction;

[0051] Step 2: Extract the working mode characteristics of the target load according to the changes in three-phase current;

[0052] Step 3: Determine the transient start-up process of the target load. For electrical equipment with a mechanical power part, the cut-in transient process lasts for a relatively long time, and there are obvious transient changes in both its electrical and mechanical characteristics. Extract the transient start-up process characteristics of the target load, including transient time constant, transient power characteristics, transient voltage characteristics, and transient current characteristics;

[0053] Step 4: Determine the steady-state process of the target load and extract the steady-state process characteristics of the target load, including steady-state fluctuation period, steady-state power characteristics, steady-state voltage characteristics, and steady-state current characteristics;

[0054] Step 5: There are obvious differences in the characteristics of the transient start-up process and the transient shutdown process of electrical equipment. The transient shutdown process is mainly a mechanical transient process. Since the power supply is mostly cut off directly during the cut-out process, the electrical characteristics of the cut-out transient process shown externally are all mutations of relevant characteristic quantities. Extract the transient shutdown process characteristics of the target load, including transient power characteristics, transient voltage characteristics, and transient current characteristics;

[0055] Step 6: Establish a complete feature library for the target load.

[0056] Among them, Step 1 includes the following steps:

[0057] Step 1.1:

[0058] According to the historical waveform data of the target load, set the base state window, monitoring window, and steady-state window, and determine the start transient opening time point T ona , shutdown transient opening time point T offa , start transient end time point T onb and shutdown transient end time point T offb based on the improved CUSUM method;

[0059] Step 1.2:

[0060] If the four types of time points cannot be effectively extracted, the target load does not belong to an electrical load with discontinuous operation and a steady-state output process, and waveform data replacement is required;

[0061] Further, the said step 2 includes the following steps:

[0062] Step 2.1:

[0063] According to the matched starting transient end time point T onb and shutdown transient start time point T offa , intercept the current waveform in the steady state process [T onb , T offa , and perform the calculation of the average value of the phase-separated current:

[0064]

[0065]

[0066] Among them, formula (1) is applicable to users with high-voltage power supply and low-voltage metering. i at , i bt , i ct are the three-phase current sampling values collected in real time at the metering point of users with high-voltage power supply and low-voltage metering. Formula (2) is applicable to users with high-voltage power supply and high-voltage metering. i abt , i cbt are the line current sampling values collected in real time at the metering point of users with high-voltage power supply and high-voltage metering;

[0067] Step 2.2:

[0068] Judge whether the device is a single-phase static power consumption device or a three-phase rotating power consumption device according to the average value of the phase-separated current. Considering the background noise and the unbalance degree of the three phases, adjust the value of the judgment threshold K:

[0069]

[0070]

[0071] When formula (3) or formula (4) is satisfied, the target device is a single-phase static power consumption device, otherwise it is a three-phase rotating power consumption device.

[0072] Further, the said step 3 includes the following steps:

[0073] Step 3.1:

[0074] First, calculate the transient time constant. According to the change of the transient current characteristics of the device, the transient time constant τ on when the device starts to enter the steady state through the transient can be obtained:

[0075] τ on = T onb - T ona (5)

[0076] Step 3.2:

[0077] Calculate transient power-related features, including the change in power factor angle θ, peak change P peak1 and the rising edge slope K p1 :

[0078]

[0079]

[0080]

[0081] In Equation (6), K is the number of sampling points per cycle, x and y are the positions of the zero-crossing points (Δ>0) in the periodic sequences of phase voltage and phase current respectively, is the active power value at the transient start time, p max is the maximum active power during the transient start-up process.

[0082] Step 3.3:

[0083] Calculate the transient voltage feature, mainly calculate the change rate of the transient voltage of the device ΔU:

[0084]

[0085] In the formula, U0 is the minimum value (peak value) of the transient voltage, and U is the average value of the steady-state voltage.

[0086] Step 3.4:

[0087] The current characteristics of different types of devices are rich. Electrical equipment with different starting methods has different degrees of impact components during the transient start-up process. Use the transient current peak I p to characterize it, and its discretized calculation formula is as follows:

[0088] I p = max(i(k)), 0 < k < N (10)

[0089] In the formula, i(k) is the maximum value of the current amplitude per cycle during the transient start-up process.

[0090] For linear loads such as electric furnaces, their current waveforms are approximately sinusoidal curves. For non-linear loads such as lighting lamps, converters, and motors (including frequency converters), the current waveforms have obvious distortions, and the current waveforms are significantly different. The peak characteristics extracted from the current waveforms have large differences. Therefore, different types of loads can be effectively identified.

[0091] In addition, due to different structures and processes, different electrical loads have different degrees of non-linearity and thus different harmonic contents. By analyzing the harmonic currents of different loads in the frequency domain and extracting the frequency characteristics of the harmonic currents through fast Fourier transform or wavelet transform, the accuracy of load identification can be improved. The total harmonic distortion rate of current is as follows:

[0092]

[0093] where I i is the amplitude of the i-th harmonic of the current in the frequency domain, and h is the order of the highest harmonic.

[0094] Furthermore, step 4 includes the following steps:

[0095] Step 4.1:

[0096] First, extract the steady-state fluctuation period characteristics. For some power mechanical equipment, since the mechanical work output is periodic, there are corresponding certain fluctuation laws in the electrical characteristics of the equipment, which are usually characterized by the characteristic quantity of the steady-state fluctuation period time constant T0:

[0097]

[0098] where p a and are the active powers at time points a and a + Nt0 respectively.

[0099] Step 4.2:

[0100] Calculate the steady-state power-related characteristics. Using the step change of active power or the step change of active power and reactive power as the characteristic quantity for load decomposition, high-power loads with obvious power consumption characteristics are easy to identify. Considering the situation that some equipment has a steady-state fluctuation period, the maximum value p max , minimum value p min of the steady-state active power and the power factor angle are used as identification characteristics:

[0101]

[0102] where u kt and i kt are the sampled values of voltage and current collected in real time, U rmst and I rmst are the effective values of voltage and current respectively, and S t is the apparent power value.

[0103] Step 4.3:

[0104] During the operation in different states, different electrical devices will introduce voltage noise with their characteristics into the main line. By analyzing the frequency-domain components of the noise, the type of unknown electrical devices can be identified. In the steady-state operation, the voltage noise of the electrical device can be characterized by the voltage fluctuation rate. Calculate the steady-state voltage fluctuation rate of the device:

[0105]

[0106] In the formula, Umax is the minimum steady-state voltage (peak value), Umax is the maximum steady-state voltage (peak value), and U is the average steady-state voltage.

[0107] Step 4.4:

[0108] Calculate the steady-state current-related characteristics, including the current peak value, root mean square value, and total harmonic distortion rate. The calculation of the peak value and total harmonic distortion rate refers to Equation (10) and Equation (11). The discretized calculation formula for the root mean square value is as follows:

[0109]

[0110] In the formula, i(n) is the current sampling value during the steady-state process.

[0111] Furthermore, Step 5 includes the following steps:

[0112] Step 5.1:

[0113] Calculate the power characteristics during the transient shutdown process. Usually, the maximum power change value and the power factor angle change value are used to characterize the power change differences of different devices during the transient shutdown process;

[0114] Step 5.2:

[0115] Calculate the voltage and current characteristics during the transient shutdown process, mainly represented by the transient voltage change rate, current peak-to-peak value, and current harmonic content change rate. The calculation refers to Equation (9), Equation (10), and Equation (11).

[0116] In Step 6, taking a three-phase asynchronous motor and a small heating furnace of a certain brand as examples, a feature library as shown in Table 1 is formed. Taking the transient startup and shutdown processes of a typical variable-frequency motor as an example, the waveform diagram is as Figures 2 - 5 shown.

[0117] Table 1

[0118]

[0119] The present invention also proposes a system 200 suitable for establishing a discontinuous working load identification feature library, as Figure 6 shown, including:

[0120] The data acquisition unit 201 obtains the historical waveform data of the target workload for the target workload, and determines whether the target workload belongs to an electrical load with discontinuous operation and a steady-state output process according to the historical waveform data;

[0121] The feature extraction unit 202 extracts the working mode features, transient start-up process features, steady-state process features, and transient shutdown process features of the target workload when the target workload belongs to an electrical load with discontinuous operation and a steady-state output process;

[0122] The root feature library establishment unit 203 establishes an identification feature library for continuous working loads based on the extracted working mode features, transient start-up process features, steady-state process features, and transient shutdown process features.

[0123] Among them, the extraction of the working mode feature library is carried out according to the change of the three-phase current of the electrical load, specifically including:

[0124] According to the transient start-up end time point T of the target workload onb and the transient shutdown start time point T offa , intercept the current waveform in the steady-state process [T onb , T offa , calculate the average value of the phase current of the current waveform, and the formula is as follows:

[0125]

[0126]

[0127] Among them, formula (1) is used to calculate the average value of the phase current of users with high supply and low metering, and formula (2) is used to calculate the average value of the phase current of users with high supply and high metering. The supplementary parameter definitions i at , i bt , i ct are the three-phase current sampling values collected in real time at the metering point of users with high supply and low metering, respectively, and i abt , i cbt are the line current sampling values collected in real time at the metering point of users with high supply and high metering;

[0128] The determination is made according to the following criteria:

[0129]

[0130]

[0131] Among them, K is the determination threshold. When formula (3) or formula (4) is satisfied, the working mode feature of the target workload is a single-phase static electrical device, otherwise it is a three-phase rotating electrical device.

[0132] Among them, the transient startup process characteristics include transient time constant, transient power characteristics, transient voltage characteristics, and transient current characteristics.

[0133] Among them, the steady-state process characteristics include steady-state fluctuation period, steady-state power characteristics, steady-state voltage characteristics, and steady-state current characteristics.

[0134] Among them, the transient shutdown process characteristics include transient power characteristics, transient voltage characteristics, and transient current characteristics. The transient power characteristics include: power factor angle change characteristics, peak change characteristics, and rising edge slope characteristics.

[0135] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages. For example, object-oriented programming languages such as Java and interpreted scripting languages such as JavaScript.

[0136] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0137] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0138] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable apparatus to generate a computer-implemented process, thereby providing instructions for implementing the process Figure 1 in one process or more processes and / or blocks Figure 1 or steps for implementing the functions specified in one block or more blocks.

[0139] Although the preferred embodiments of the present application have been described, additional changes and modifications can be made to these embodiments by those skilled in the art once they learn of the basic creative concept. Therefore, the appended claims are intended to be construed to cover the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0140] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A method applicable to establishing an identification feature library for discontinuous workloads, the method comprising: For a target workload, obtaining historical waveform data of the target workload, and determining whether the target workload belongs to an electricity load with discontinuous operation and a steady-state output process according to the historical waveform data; When the target workload belongs to an electricity load with discontinuous operation and a steady-state output process, extracting the working mode features, transient startup process features, steady-state process features, and transient shutdown process features of the target workload; Establishing an identification feature library for continuous workloads according to the extracted working mode features, transient startup process features, steady-state process features, and transient shutdown process features; The extraction of the working mode features is performed according to the change of the three-phase current of the electricity load, and specifically includes: According to the start transient end time point T of the target workload onb and the shutdown transient start time point T offa , intercept the current waveform in the steady-state process [T onb , T offa , calculate the average value of the phase-separated current of the current waveform, and the formula is as follows: Among them, Equation (1) is used for calculating the average value of the phase currents of users with high-voltage power supply and low-voltage metering, and Equation (2) is used for calculating the average value of the phase currents of users with high-voltage power supply and high-voltage metering. The supplementary parameter definitions i at , i bt , i ct are the three-phase current sampling values collected in real time at the metering point of users with high-voltage power supply and low-voltage metering, respectively, and i abt , i cbt are the line current sampling values collected in real time at the metering point of users with high-voltage power supply and high-voltage metering, respectively; Making a determination according to the following criterion: where K is a determination threshold. When Equation (3) or Equation (4) is satisfied, the working mode feature of the target workload is a single-phase static electrical device; otherwise, it is a three-phase rotating electrical device.

2. The method according to claim 1, wherein the transient startup process features include a transient time constant, a transient power feature, a transient voltage feature, and a transient current feature.

3. The method according to claim 1, wherein the steady-state process features include a steady-state fluctuation period, a steady-state power feature, a steady-state voltage feature, and a steady-state current feature.

4. The method according to claim 1, wherein the transient shutdown process characteristics include transient power characteristics, transient voltage characteristics, and transient current characteristics, and the transient power characteristics include: Power factor angle change feature, peak change feature, and rising edge slope feature.

5. A system applicable to establishing an identification feature library for discontinuous workloads, the system comprising: A data acquisition unit, which, for a target workload, obtains historical waveform data of the target workload, and determines whether the target workload belongs to an electricity load with discontinuous operation and a steady-state output process according to the historical waveform data; A feature extraction unit, which, when the target workload belongs to an electricity load with discontinuous operation and a steady-state output process, extracts the working mode features, transient startup process features, steady-state process features, and transient shutdown process features of the target workload; A feature library establishment unit, which establishes an identification feature library for continuous workloads according to the extracted working mode features, transient startup process features, steady-state process features, and transient shutdown process features. The extraction of the working mode features is performed according to the change of the three-phase current of the electricity load, and specifically includes: According to the start transient end time point T of the target workload onb and the shutdown transient start time point T offa , intercept the current waveform in the steady-state process [T onb , T offa , calculate the average value of the phase-separated current for the current waveform, and the formula is as follows: Among them, Equation (1) is used for calculating the average value of phase currents of users with high-voltage supply and low-voltage metering, and Equation (2) is used for calculating the average value of phase currents of users with high-voltage supply and high-voltage metering. The supplementary parameter definitions are i at , i bt , i ct are respectively the three-phase current sampling values collected in real time at the metering point of users with high-voltage supply and low-voltage metering, and i abt , i cbt are respectively the line current sampling values collected in real time at the metering point of users with high-voltage supply and high-voltage metering; Making a determination according to the following criterion: where K is a determination threshold. When Equation (3) or Equation (4) is satisfied, the working mode feature of the target workload is a single-phase static electrical device; otherwise, it is a three-phase rotating electrical device.

6. The system according to claim 5, wherein the transient startup process features include a transient time constant, a transient power feature, a transient voltage feature, and a transient current feature.

7. The system according to claim 5, wherein the steady-state process features include a steady-state fluctuation period, a steady-state power feature, a steady-state voltage feature, and a steady-state current feature.

8. The system according to claim 5, wherein the transient shutdown process characteristics include transient power characteristics, transient voltage characteristics, and transient current characteristics, and the transient power characteristics include: Power factor angle change feature, peak change feature, and rising edge slope feature.

Citation Information

Patent Citations

  • Non-intrusive mode electrical load identification system and method

    CN105186693A

  • Non-invasion load identification method for user side

    CN107025365A