A load identification method, a load identification device and a computer storage medium

Abstract

The present application proposes a load identification method, a load identification device and a computer storage medium. The load identification method includes: in response to a trigger event instruction, obtaining the current aggregate current waveform data of the bus to which multiple loads are connected within the period where the trigger event is located; performing correlation matching on the current aggregate current waveform data and each maintenance aggregate current waveform data in the aggregate current waveform data set; in response to the existence of successfully matched target maintenance aggregate current waveform data, and the number is not 1, identifying and obtaining a candidate load type based on the current aggregate current waveform data; obtaining the periodic load type of the period where the previous trigger event is located; merging the candidate load type and the periodic load type to obtain the current load type. Through the above-mentioned load identification method, the current characteristics of multiple loads are adaptively collected, and the multiple load current characteristics are used to match the multiple load current characteristic library, so as to solve the problem of identification failure and improve the adaptability and accuracy of load identification.

Description

Technical Field

[0001] The present application relates to the technical field of load decomposition, and in particular to a load identification method, a load identification device and a computer storage medium. Background Art

[0002] With the development of society, people's living standards have improved, and the types of electrical appliances have become more and more abundant; some electrical appliances are prone to some safety hazards, such as heating appliances such as hair dryers, electric blankets and electric kettles, and large battery appliances such as electric vehicles and outdoor mobile power supplies. The corresponding violation scenarios are: using high-power heating appliances in campus dormitories and charging electric vehicles indoors.

[0003] Current load identification methods include malicious load detection technology based on load identification, and with the introduction of deep learning, the accuracy of load identification has been further improved; however, deep learning is highly dependent on training data, and a mapping relationship between total power consumption and all load power consumption needs to be established for multi-load environments. In addition, the types of electrical appliances involved in each usage environment are also basically different. With the addition of new loads, the number of such mapping relationships will also increase exponentially, which will lead to an increase in equipment maintenance costs. Summary of the invention

[0004] In order to solve the above technical problems, the present application proposes a load identification method, a load identification device and a computer storage medium.

[0005] In order to solve the above technical problems, the present application proposes a load identification method, which includes:

[0006] In response to a trigger event instruction, obtaining current aggregate current waveform data of a bus connected to a plurality of loads within a period where the trigger event occurs;

[0007] Correlation matching is performed between the current aggregate current waveform data and each maintenance aggregate current waveform data in the aggregate current waveform data set;

[0008] In response to the existence of successfully matched target maintenance aggregated current waveform data, and the number is not 1, identifying a candidate load type based on the current aggregated current waveform data;

[0009] Get the periodic load type of the period in which the last trigger event occurs;

[0010] The candidate load type and the periodic load type are combined to obtain a current load type.

[0011] In order to solve the above technical problems, the present application also proposes a load identification device, which includes:

[0012] In response to the trigger event instruction, the data acquisition module is used to acquire the current aggregate current waveform data of the bus connected to the multiple loads in the period where the trigger event occurs;

[0013] A data matching module, used for performing correlation matching between the current aggregate current waveform data and each maintenance aggregate current waveform data in the aggregate current waveform data set;

[0014] In response to the existence of successfully matched target maintenance aggregated current waveform data, and the number is not 1, a load identification module is used to identify a candidate load type based on the current aggregated current waveform data;

[0015] The load identification module is used to obtain the periodic load type of the period in which the last triggering event occurs;

[0016] The load identification module is used to combine the candidate load type and the periodic load type to obtain the current load type.

[0017] In order to solve the above technical problems, the present application also proposes a load identification device, which includes a memory and a processor coupled to the memory; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the load identification method as described above.

[0018] In order to solve the above technical problems, the present application also proposes a computer storage medium, wherein the computer storage medium is used to store program data, and when the program data is executed by a computer, it is used to implement the above load identification method.

[0019] Compared with the prior art, the beneficial effects of the present application are as follows: the load identification device responds to the existence of successfully matched target maintenance aggregated current waveform data, and the number is not 1, and obtains the candidate load type based on the current aggregated current waveform data; obtains the periodic load type of the period in which the previous trigger event is located; and merges the candidate load type and the periodic load type to obtain the current load type. Through the above load identification method, the current characteristics of multiple loads are adaptively collected, and the multiple load current characteristics are used to match the multiple load current characteristic library, so as to solve the problem of identification failure and improve the adaptability and accuracy of load identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0021] Figure 1It is a schematic diagram of the application scenario of indoor charging monitoring of electric battery vehicles provided by this application;

[0022] Figure 2 is a flow chart of the first embodiment of the load identification method provided by the present application;

[0023] Figure 3 It is a technical implementation flow diagram of the adaptive load decomposition method provided by this application;

[0024] Figure 4 is a flow chart of a second embodiment of a load identification method provided by the present application;

[0025] Figure 5 yes Figure 2 The specific flow chart of step S15 of the load identification method is shown;

[0026] Figure 6 is a schematic diagram of the multi-load identification process provided by this application;

[0027] Figure 7 is a flow chart of a third embodiment of a load identification method provided by the present application;

[0028] Figure 8 is a schematic diagram of the data structure of the aggregated current waveform data set provided by the present application;

[0029] Fig. 9 is a flow chart of a fourth embodiment of a load identification method provided by the present application;

[0030] Fig.10 It is a structural schematic diagram of an embodiment of a load identification device provided by the present application;

[0031] Fig.11 is a structural schematic diagram of another embodiment of the load identification device provided by the present application;

[0032] Fig.12 It is a structural diagram of an embodiment of a computer storage medium provided by the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can, for example, be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] In order to solve the current load identification technology, the present application provides an adaptive load decomposition method and device, which is suitable for Figure 1 The battery vehicle charging monitoring application scenario shown in the figure. Figure 1 In the application scenario, the battery vehicle is an illegal electrical appliance, that is, a malicious load. It should be noted that the adaptive load decomposition method of the present application is also applicable to other multi-load identification application scenarios, which are not listed here one by one.

[0036] Please refer to Figure 2 and Figure 3 , Figure 2 is a flow chart of the first embodiment of the load identification method provided by the present application, Figure 3 It is a schematic diagram of the technical implementation flow of the adaptive load decomposition method provided in this application.

[0037] The load identification method of the present application is applied to a load identification device, wherein the load identification device of the present application can be a server, a terminal device, or a system in which a server and a terminal device cooperate with each other. Accordingly, the various parts included in the load identification device, such as various units, subunits, modules, and submodules, can all be set in the server, can all be set in the terminal device, or can be set in the server and the terminal device respectively.

[0038] Furthermore, the above-mentioned server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules, such as software or software modules used to provide distributed servers, or it can be implemented as a single software or software module, which is not specifically limited here.

[0039] like Figure 2 As shown, the specific steps are as follows:

[0040] Step S11: in response to a trigger event instruction, obtaining current aggregate current waveform data of a bus to which multiple loads are connected within a period where the trigger event occurs.

[0041] In the embodiment of the present application, the load identification device determines the identification period of the trigger event of the connected load according to the trigger event instruction. The load identification device obtains the current aggregate current waveform data of the bus connected to multiple loads in the period of the trigger event. Figure 1 As shown, in Figure 1 In the monitoring application scenario shown, all electrical appliances are connected to the bus. Therefore, the load identification device directly collects the aggregated current waveform data of the bus to obtain the identification data of multiple loads.

[0042] Specifically, the generation process of the trigger event instruction in the above process can be found in Figure 4 , Figure 4 It is a flow chart of the second embodiment of the load identification method provided in this application.

[0043] like Figure 4 As shown, the specific steps are as follows:

[0044] Step S21: Obtaining current aggregate voltage and current waveform data of the current cycle.

[0045] In an embodiment of the present application, the load identification device obtains aggregated current waveform data and aggregated voltage data of a valid cycle collected by the metering chip, where the aggregated data refers to the voltage and current waveform data collected at the bus. Among them, one cycle in the present application can be 128 points, and the data collection frequency is 6.4kHz. In other embodiments, the metering chip can also directly collect aggregated voltage and current waveform data of a valid cycle, that is, merge the voltage data and current waveform data into a data set.

[0046] Step S22: Based on the current aggregated voltage and current waveform data, obtain the current aggregated power of the current cycle.

[0047] In the embodiment of the present application, the load identification device calculates the aggregate power P(t) consumed in the current cycle, and subtracts it from the cycle power P(t-1) when the previous event is triggered to obtain Pd. The aggregate power can be obtained by multiplying the aggregate voltage and the aggregate current.

[0048] Step S23: In response to the power difference between the current aggregate power and the period aggregate power of the period in which the last trigger event is located being greater than a preset power threshold, a trigger event instruction is generated.

[0049] In the embodiment of the present application, the load identification device compares the absolute value of the power difference calculated in step S22, |Pd|, with the set power threshold. If |Pd| is greater than the set power threshold, it is determined that an event has occurred, and a trigger event instruction is generated. The cycle at this time is the cycle where the trigger event is located. If |Pd| is less than or equal to the set power threshold, it is determined that no event has occurred, and the above steps are continued for monitoring.

[0050] It should be noted that the triggering event of the present application is essentially the connection of one or more loads to the bus, which causes changes in the aggregated voltage data and aggregated current waveform data on the bus.

[0051] Step S12: performing correlation matching between the current aggregated current waveform data and each maintenance aggregated current waveform data in the aggregated current waveform data set.

[0052] In an embodiment of the present application, the load identification device traverses a pre-maintained aggregate current waveform data set Agg based on the current aggregate current waveform data of the period in which the current trigger event is located. The aggregate current waveform data set Agg is mainly used to perform adaptive load identification according to the user's electricity usage habits, and pre-stores the correspondence between a number of aggregate current waveform data and load types.

[0053] Specifically, the load identification device performs correlation analysis on the current aggregate current waveform data and each maintenance aggregate current waveform data in the aggregate current waveform data set Agg, wherein the correlation analysis algorithm may adopt Pearson correlation analysis. When there is a positive or negative correlation relationship between the maintenance aggregate current waveform data and the current aggregate current waveform data, it is considered that the two have successfully completed the correlation matching, and the process proceeds to step S13.

[0054] Step S13: In response to the existence of successfully matched target maintenance aggregated current waveform data, and the number is not 1, a candidate load type is identified based on the current aggregated current waveform data.

[0055] In response to the existence of the successfully matched target maintenance aggregated current waveform data, a current load type of the current aggregated current waveform data is determined based on the maintenance load type corresponding to the target maintenance aggregated current waveform data.

[0056] In the embodiment of the present application, there is successfully matched target maintenance aggregate current waveform data, that is, the current trigger event basically meets the user's daily electricity consumption behavior. Therefore, the load identification device can use the target maintenance aggregate current waveform data to pre-store the corresponding maintenance load type and determine the current load type of the current aggregate current waveform data. Among them, the load identification device can use the maintenance load type as the basic load type of the current load type, that is, the current load type at least includes the maintenance load type, and then analyze other newly added load types.

[0057] Furthermore, the present application adopts different load identification schemes based on the number of successfully matched maintenance aggregated current waveform data, so as to adapt to different load access scenarios.

[0058] For example, when the number of successfully matched maintenance aggregated current waveform data is greater than one, the following steps S14 and S15 are performed.

[0059] Step S14: Obtain the periodic load type of the period in which the last triggering event occurs.

[0060] In the embodiment of the present application, the load identification device obtains the periodic load type when the last event is triggered.

[0061] Step S15: Merge the candidate load type and the periodic load type to obtain the current load type.

[0062] In the embodiment of the present application, the load identification device obtains the current load type by directly analyzing the current aggregate current waveform data, and extracts the periodic load type when the previous event is triggered. By combining the two load types, the load identification device needs to further distinguish the specific real access load type of the multi-load access scenario.

[0063] To better distinguish the scenarios where multiple appliances are connected at the same time, please refer to Figure 5 and Figure 6 , Figure 5 yes Figure 2 The specific flow chart of step S15 of the load identification method is shown in FIG. Figure 6 It is a schematic diagram of the multi-load identification process provided by this application.

[0064] like Figure 5 As shown, the specific steps are as follows:

[0065] Step S151: In response to the existence of successfully matched target maintenance aggregated current waveform data, and the number is not 1, a matching counting step is performed based on the current aggregated current waveform data.

[0066] In the embodiments of the present application, Figure 6 As shown, after the load identification device performs current signal similarity analysis and determines that there are multiple matching aggregate currents, it maintains a reference count Cnt for each matching aggregate current waveform data and executes a matching counting step, namely, step S152.

[0067] Step S152: Identify candidate load types based on the current aggregate current waveform data; obtain the periodic load type of the period in which the previous trigger event is located; merge the candidate load type and the periodic load type to obtain the search load type; based on the search load type, search for aggregate current waveform data that matches the load in the successfully matched target maintenance aggregate current waveform data and record the number of matches plus 1.

[0068] In an embodiment of the present application, the load identification device directly inputs the current aggregate current waveform data into a deep neural network, and directly obtains the candidate load type through model identification. The load identification device obtains the periodic load type of the cycle in which the previous trigger event is located, and then merges the periodic load type with the candidate load type to obtain the search load type of the current cycle. The load identification device extracts the corresponding load type of the successfully matched maintenance aggregate current waveform data, and then matches it with the search load type until the maintenance aggregate current waveform data matching the load is searched, and its Cut value is increased by 1.

[0069] Step S153: Continue to obtain the aggregation current waveform data of the next cycle, and repeat the matching counting step until the number of matches of one of the target maintenance aggregation current waveform data is greater than the preset number threshold, and use one of the target maintenance aggregation current waveform data as the final aggregation current waveform data.

[0070] In the embodiment of the present application, the load identification device continues to monitor the subsequent multiple cycles of key aggregate current waveform data, and repeats the above step S152 directly until a Cut value of the maintenance aggregate current waveform data appears to be greater than the preset number threshold Tcnt. At this time, it can be determined that the maintenance aggregate current waveform data that accurately corresponds to this application scenario is the target aggregate current waveform data.

[0071] Step S154: The target load type corresponding to the final aggregated current waveform data is used as the current load type.

[0072] In the embodiment of the present application, the load identification device uses the target load type corresponding to the target aggregate current waveform data as the current load type of the current aggregate current waveform data.

[0073] The load identification method of the present application can adaptively collect current characteristics of multiple loads, and utilizes multi-load current characteristic matching combined with single load identification of a neural network model to solve the problem of identification failure, save the cost of collecting multi-load training data, and can automatically adjust the multi-load current characteristic library according to the user's electricity usage habits.

[0074] In the present application, the load identification device responds to the existence of successfully matched target maintenance aggregated current waveform data, and the number is not 1, identifies the candidate load type based on the current aggregated current waveform data; obtains the periodic load type of the period in which the previous trigger event is located; and merges the candidate load type and the periodic load type to obtain the current load type. Through the above load identification method, the current characteristics of multiple loads are adaptively collected, and the multiple load current characteristics are used to match the multiple load current characteristic library, so as to solve the problem of identification failure and improve the adaptability and accuracy of load identification.

[0075] Please refer to Figure 7 , Figure 7 It is a flow chart of the third embodiment of the load identification method provided in this application.

[0076] like Figure 7 As shown, the specific steps are as follows:

[0077] Step S31: In response to the existence of successfully matched target maintenance aggregated current waveform data, and the number is 1, the maintenance load type corresponding to the target maintenance aggregated current waveform data is obtained.

[0078] In the embodiments of this application, please combine Figure 3 , when the number of the maintenance aggregated current waveform data successfully matched by the load identification device in the aggregated current waveform data set Agg is 1, based on the following Figure 8 The aggregated current waveform data set data structure shown extracts the corresponding maintenance load type, namely Figure 8 “Refrigerator”, “LED light”, “kettle”, “electric fan”.

[0079] At this time, the load identification device can determine that the current application scenario is the user's accustomed electricity usage scenario, and it can be considered that only one load is connected, and enters step S32.

[0080] Step S32: All load types in the maintenance load type are taken as the current load type.

[0081] In an embodiment of the present application, the load identification device directly obtains all load types in the maintenance load type as the current load type of the current aggregated current waveform data to correspond to the user's electricity usage habits.

[0082] Please refer to Fig. 9 , Fig. 9 It is a flow chart of the fourth embodiment of the load identification method provided in this application.

[0083] like Fig. 9 As shown, the specific steps are as follows:

[0084] Step S41: in response to the absence of successfully matched maintenance aggregated current waveform data, acquiring the periodic aggregated current waveform data of the period where the last trigger event is located.

[0085] In the embodiments of this application, please combine Figure 3 When the load identification device does not have successfully matched maintenance aggregated current waveform data in the aggregated current waveform data set Agg, it indicates that this triggering event is not the user's electricity usage habit. Therefore, the load identification device needs to identify the new electricity usage behavior.

[0086] Specifically, the load identification device obtains the periodic aggregated current waveform data of the period in which the last trigger event is located. The periodic aggregated current waveform data and the current aggregated current waveform data have a certain correlation, and the change between the two is caused by the new power consumption behavior. The load identification device can accurately identify the new power consumption behavior by distinguishing the two.

[0087] Step S42: obtaining a polymerization current difference based on the periodic polymerization current waveform data and the current polymerization current waveform data.

[0088] In an embodiment of the present application, the load identification device calculates the aggregate current difference dc between the current aggregate current and the periodic aggregate current. Based on the superposition of the currents, the present application can determine that the aggregate current difference dc is the current waveform data of the currently connected load.

[0089] Step S43: Identify the newly added load type based on the aggregate current difference.

[0090] In an embodiment of the present application, the load identification device can directly input the aggregated current difference into a deep neural network model for identification to obtain a newly added load type.

[0091] Furthermore, the load identification device can also construct a VI trajectory feature using the aggregate current difference dc and the input voltage of the bus, and this VI trajectory feature can represent the currently connected load. It should be noted that the input voltage of the input bus can be an AC voltage of 220V. The load identification device inputs the VI trajectory feature into the deep neural network model for identification to obtain a newly added load type.

[0092] Step S44: Obtain the periodic load type corresponding to the periodic aggregated current waveform data.

[0093] Step S45: Combine the newly added load type and the periodic load type into the current load type.

[0094] In an embodiment of the present application, the load identification device extracts the periodic load type corresponding to the periodic aggregated current waveform data from the aggregated current waveform data set Agg, and then merges the newly added load type obtained in step S43 with the periodic load type to obtain all load types of the current trigger event.

[0095] For example, all load types in the previous trigger event are refrigerators, LED lights, and kettles, and the deep neural network result in this trigger event is a hair dryer. Then all load types corresponding to the aggregated current waveform data this time are refrigerators, LED lights, kettles, and hair dryers.

[0096] Furthermore, since the current aggregate current does not exist in the set Agg, after obtaining the current aggregate current and all the load types mapped by it, the present application will maintain this data in the set Agg. When the combination is encountered again next time, it will be directly identified by the aggregate current similarity without the need for deep neural network identification.

[0097] In addition, because the power threshold-based judgment event may result in misjudgment, such as: multiple appliances are connected at the same time, and there are multiple appliances that are instantaneous start appliances (the instantaneous current waveform data reaches a stable state when connected to the socket), the multiple appliances connected will be identified as one appliance, so the load type mapped by the aggregate signal is wrong. At this time, the number of successfully matched maintenance aggregate current waveform data in the aggregate current waveform data set Agg may not be 1, that is, there are multiple aggregate current waveform data that can be successfully matched.

[0098] For the above scenario, the load identification device can directly input the current aggregate current waveform data into the deep neural network to identify the candidate load type; then, obtain the periodic load type of the period in which the previous trigger event is located; finally, merge the candidate load type and the periodic load type to obtain the current load type.

[0099] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0100] In order to implement the above load identification method, this application also proposes a load identification device, please refer to Fig.10 , Fig.10 It is a structural schematic diagram of an embodiment of a load identification device provided in the present application.

[0101] The load identification device 500 of this embodiment includes:

[0102] In response to the trigger event instruction, the data acquisition module 51 is used to acquire the current aggregate current waveform data of the bus connected to multiple loads within the period where the trigger event occurs.

[0103] The data matching module 52 is used to perform correlation matching between the current aggregated current waveform data and each maintenance aggregated current waveform data in the aggregated current waveform data set.

[0104] In response to the existence of successfully matched target maintenance aggregated current waveform data and the number is not 1, the load identification module 53 is used to identify and obtain candidate load types based on the current aggregated current waveform data.

[0105] The load identification module 53 is used to obtain the periodic load type of the period in which the last triggering event occurs.

[0106] The load identification module 53 is used to combine the candidate load type and the periodic load type to obtain the current load type.

[0107] In order to implement the above load identification method, this application also proposes another load identification device, please refer to Fig.11 , Fig.11 It is a structural schematic diagram of another embodiment of the load identification device provided in the present application.

[0108] The load identification device 400 of this embodiment includes a processor 41 , a memory 42 , an input / output device 43 , and a bus 44 .

[0109] The processor 41 , the memory 42 , and the input / output device 43 are respectively connected to the bus 44 . The memory 42 stores program data. The processor 41 is used to execute the program data to implement the load identification method described in the above embodiment.

[0110] In the embodiment of the present application, the processor 41 may also be referred to as a CPU (Central Processing Unit). The processor 41 may be an integrated circuit chip having the ability to process signals. The processor 41 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or the processor 41 may also be any conventional processor, etc.

[0111] This application also provides a computer storage medium, please continue to refer to Fig.12 , Fig.12 It is a structural diagram of an embodiment of a computer storage medium provided in the present application. The computer storage medium 600 stores a computer program 61. When the computer program 61 is executed by a processor, it is used to implement the load identification method of the above embodiment.

[0112] When the embodiments of the present application are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0113] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A load identification method, characterized in that: The load identification method comprises: In response to a trigger event instruction, obtaining current aggregate current waveform data of a bus connected to a plurality of loads within a period where the trigger event occurs; Correlation matching is performed between the current aggregate current waveform data and each maintenance aggregate current waveform data in the aggregate current waveform data set; In response to the existence of successfully matched target maintenance aggregated current waveform data, and the number is not 1, identifying a candidate load type based on the current aggregated current waveform data; Get the periodic load type of the period in which the last trigger event occurs; Combining the candidate load type and the periodic load type to obtain a current load type; The step of combining the candidate load type and the periodic load type to obtain the current load type includes: In response to the existence of successfully matched target maintenance aggregate current waveform data, and the number is not 1, a matching counting step is performed based on the current aggregate current waveform data: Based on the current aggregate current waveform data, a candidate load type is identified; the periodic load type of the period in which the last trigger event is located is obtained; the candidate load type and the periodic load type are combined to obtain a search load type; based on the search load type, the aggregate current waveform data matching the load is searched in the successfully matched target maintenance aggregate current waveform data and the matching number is recorded plus 1; Continue to obtain the aggregation current waveform data of the next cycle, and repeat the matching counting step until the number of matches of one of the target maintenance aggregation current waveform data is greater than a preset number threshold, and use the one of the target maintenance aggregation current waveform data as the final aggregation current waveform data; The target load type corresponding to the final aggregate current waveform data is used as the current load type.

2. The load identification method according to claim 1, characterized in that: The load identification method further includes: Obtain the current aggregate voltage and current waveform data of the current cycle; Based on the current aggregated voltage and current waveform data, obtaining the current aggregated power of the current cycle; In response to the power difference between the current aggregate power and the period aggregate power of the period in which the last trigger event is located being greater than a preset power threshold, the trigger event instruction is generated.

3. The load identification method according to claim 1, characterized in that: The load identification method further includes: In response to the existence of successfully matched target maintenance aggregated current waveform data, and the number is 1, obtaining the maintenance load type corresponding to the target maintenance aggregated current waveform data; All load types in the maintenance load type are used as the current load type.

4. The load identification method according to claim 1, characterized in that: The load identification method further includes: In response to the absence of successfully matched maintenance aggregated current waveform data, acquiring period aggregated current waveform data of the period in which the last trigger event is located; Based on the periodic polymerization current waveform data and the current polymerization current waveform data, obtaining a polymerization current difference; Based on the aggregate current difference, identifying a newly added load type; Obtaining a periodic load type corresponding to the periodic aggregated current waveform data; The newly added load type and the periodic load type are combined into the current load type.

5. The load identification method according to claim 4, characterized in that: The identifying the newly added load type based on the aggregated current difference includes: Using the aggregated current difference and preset voltage data, constructing voltage and current trajectory characteristics; The newly added load type is obtained based on the voltage and current trajectory characteristics.

6. The load identification method according to claim 4, characterized in that: After the newly added load type and the periodic load type are combined into the current load type, the load identification method further includes: The current aggregate current waveform data and the current load type are recorded into the aggregate current waveform data set.

7. A load identification device, characterized in that: The load identification device comprises: In response to the trigger event instruction, the data acquisition module is used to acquire the current aggregate current waveform data of the bus connected to the multiple loads in the period where the trigger event occurs; A data matching module, used for performing correlation matching between the current aggregate current waveform data and each maintenance aggregate current waveform data in the aggregate current waveform data set; In response to the existence of successfully matched target maintenance aggregated current waveform data, and the number is not 1, a load identification module is used to identify a candidate load type based on the current aggregated current waveform data; The load identification module is used to obtain the periodic load type of the period in which the last triggering event occurs; The load identification module is used to combine the candidate load type and the periodic load type to obtain the current load type; The load identification module is used to respond to the existence of successfully matched target maintenance aggregated current waveform data, and the number is not 1, and perform a matching counting step based on the current aggregated current waveform data: identify and obtain a candidate load type based on the current aggregated current waveform data; obtain the periodic load type of the period in which the previous trigger event is located; merge the candidate load type and the periodic load type to obtain a search load type; search for load-matching aggregated current waveform data in the successfully matched target maintenance aggregated current waveform data based on the search load type and record the number of matches plus 1; continue to obtain the aggregated current waveform data of the next period, and repeat the matching counting step until the number of matches of one of the target maintenance aggregated current waveform data is greater than a preset number threshold, and use one of the target maintenance aggregated current waveform data as the final aggregated current waveform data; and use the target load type corresponding to the final aggregated current waveform data as the current load type.

8. A load identification device, characterized in that: The load identification device includes a memory and a processor coupled to the memory; The memory is used to store program data, and the processor is used to execute the program data to implement the load identification method according to any one of claims 1 to 6.

9. A computer storage medium, characterized in that The computer storage medium is used to store program data, and when the program data is executed by a computer, it is used to implement the load identification method according to any one of claims 1 to 6.

Images