CN111244954A - Non-invasive load identification method and device - Google Patents
Non-invasive load identification method and device Download PDFInfo
- Publication number
- CN111244954A CN111244954A CN202010207857.6A CN202010207857A CN111244954A CN 111244954 A CN111244954 A CN 111244954A CN 202010207857 A CN202010207857 A CN 202010207857A CN 111244954 A CN111244954 A CN 111244954A
- Authority
- CN
- China
- Prior art keywords
- load
- power
- time sequence
- characteristic
- active power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The application discloses a non-invasive load identification method and a non-invasive load identification device, wherein the method comprises the following steps: finding out a transient state stage of a time sequence according to the obtained time sequence at the electric power supply inlet, wherein the time sequence comprises an active power time sequence, a reactive power time sequence and a current time sequence; extracting load identification characteristic quantities of a transient state stage according to electric energy data at an electric power supply inlet, wherein the electric energy data comprise voltage, current and power, and the load identification characteristic quantities comprise steady-state power increment, active power characteristics, harmonic current increment and load time characteristics; and determining the load type according to the load identification characteristic quantity and a preset load library, wherein the preset load library has a corresponding relation between the load identification characteristic quantity and the load type. The technical problems that the steady-state characteristics of existing non-invasive load identification are limited and the identification accuracy is low under the condition that the actual working condition is complex are solved.
Description
Technical Field
The present disclosure relates to the field of power systems, and more particularly, to a non-invasive load identification method and apparatus.
Background
Non-invasive Load Monitoring (NILM) utilizes a measuring device installed at an electric power inlet to decompose and acquire the electricity consumption behavior of a user through signals such as voltage and current at the measuring inlet by an algorithm. In recent years, with the comprehensive development of science, technology and economy, household loads are more intelligentized and complicated, high-power electrical appliances are in a large number, and the influence of the load of residents on the peak-valley difference of a power grid is larger and larger, so that the requirements on the intelligent power utilization technology are more and more stringent, and the monitoring of the load of residents faces more severe challenges.
The load identification is based on the electrical characteristics of the electric loads during operation, and the electrical characteristics of each type of electric appliance are unique due to different working principles. The extraction of the electrical characteristic quantity and the load identification technology are the core content of the non-intrusive load identification technology. However, the existing non-invasive load identification methods are based on limited steady-state characteristic quantities to perform load identification, such as steady-state power, steady-state harmonic current and the like, and because electrical appliance load electrical appliances are more intelligent and the operation mode is more complicated in actual working conditions, the existing non-invasive load identification technology is not mature yet, and the actual identification accuracy is low.
Disclosure of Invention
The application provides a non-invasive load identification method and a non-invasive load identification device, which are used for solving the technical problems that the existing non-invasive load identification is limited in steady-state characteristics and low in identification accuracy under the condition of complex actual working conditions.
In view of the above, a first aspect of the present application provides a non-invasive load identification method, including:
finding out a transient state stage of the time sequence according to the acquired time sequence at the electric power supply inlet, wherein the time sequence comprises an active power time sequence, a reactive power time sequence and a current time sequence;
extracting load identification characteristic quantities of the transient stage according to electric energy data at the electric power supply inlet, wherein the electric energy data comprises voltage, current and power, and the load identification characteristic quantities comprise steady-state power increment, active power characteristic, harmonic current increment and load time characteristic;
and determining the load type according to the load identification characteristic quantity and a preset load library, wherein the preset load library stores the corresponding relation between the load identification characteristic quantity and the load type.
Preferably, the finding out the transient phase of the time series according to the acquired time series at the power supply inlet further includes:
acquiring electric quantity data of independent operation of various electrical appliances through a terminal;
calculating the steady-state power increment, the active power characteristic, the harmonic current increment and the load time characteristic of each electrical appliance according to each electrical quantity data;
and establishing the preset load library according to the steady-state power increment, the active power characteristic, the harmonic current increment and the load time characteristic.
Preferably, the finding out the transient phase of the time series according to the acquired time series at the power supply inlet includes:
respectively calculating the variable quantities of active power, reactive power and current in adjacent time periods;
and dividing the time series into a transient stage with load input or cut-off events and a steady stage without load input or cut-off events through the variable quantity.
Preferably, the determining the load type according to the load identification feature quantity and a preset load library includes:
determining a first load type according to the detection of the active power characteristic, wherein the first load type comprises a fluctuation load, a slow change load and a fixed frequency load;
and according to the first load type analysis, the load identification characteristic quantity and the matching identification of a preset load library determine a second load type, wherein the second load type comprises the starting or running of preset electric equipment.
Preferably, the determining the first load type according to the matching identification of the active power characteristics includes:
and determining the first load type according to the detection of the active power fluctuation and the active power slow change.
Preferably, the method further comprises the following steps:
and when the load type cannot be determined, the electric quantity data and the load identification characteristic quantity are sent to a master station, so that the master station determines the load type by adopting a semi-supervised learning clustering method according to the electric quantity data and the load identification characteristic quantity.
A second aspect of the present application provides a non-invasive load identification apparatus, including:
the transient state module is used for finding out a transient state stage of the time sequence according to the acquired time sequence at the electric power supply inlet, wherein the time sequence comprises an active power time sequence, a reactive power time sequence and a current time sequence;
a characteristic extraction module, configured to extract load identification characteristic quantities of the transient stage according to electric energy data at the power supply inlet, where the electric energy data includes voltage, current, and power, and the load identification characteristic quantities include steady-state power increment, active power characteristics, harmonic current increment, and load time characteristics;
and the matching module is used for determining the load type according to the load identification characteristic quantity and a preset load library, and the preset load library stores the corresponding relation between the load identification characteristic quantity and the load type.
Preferably, the method further comprises the following steps: building a library module;
the database building module is used for acquiring electric quantity data of independent operation of various electric appliances through a terminal;
calculating the steady-state power increment, the active power characteristic, the harmonic current increment and the load time characteristic of each electrical appliance according to each electrical quantity data;
and establishing the preset load library according to the steady-state power increment, the active power characteristic, the harmonic current increment and the load time characteristic.
Preferably, the transient module comprises:
the transient submodule is used for respectively calculating the variable quantities of active power, reactive power and current in adjacent time periods;
and dividing the time series into a transient stage with load input or cut-off events and a steady stage without load input or cut-off events through the variable quantity.
Preferably, the matching module further comprises:
the matching submodule is used for determining a first load type according to the detection of the active power characteristic, and the first load type comprises a fluctuation load, a slow variation load and a fixed frequency load;
and determining a second load type according to the first load type analysis and the matching identification of the load identification characteristic quantity, wherein the second load type comprises the starting or running of preset electric equipment.
According to the technical scheme, the embodiment of the application has the following advantages:
the application provides a non-invasive load identification method, which comprises the following steps: finding out a transient state stage of a time sequence according to the obtained time sequence at the electric power supply inlet, wherein the time sequence comprises an active power time sequence, a reactive power time sequence and a current time sequence; extracting load identification characteristic quantities of a transient state stage according to electric energy data at an electric power supply inlet, wherein the electric energy data comprise voltage, current and power, and the load identification characteristic quantities comprise steady-state power increment, active power characteristics, harmonic current increment and load time characteristics; and determining the load type according to the load identification characteristic quantity and a preset load library, wherein the preset load library has a corresponding relation between the load identification characteristic quantity and the load type. According to the non-invasive load identification method, the characteristic of a time sequence is added for research, steady-state power increment, active power characteristics, harmonic current increment and load time characteristics of electric energy data at an electric power supply inlet are extracted at the transient stage of the time sequence, and non-invasive load identification is carried out on an electric power system in an actual working condition through the characteristics reflected by the time sequence, so that the requirements of the actual working condition can be met better, and the situation that the loads cannot be accurately identified due to the fact that the steady-state characteristics are close or overlapped is avoided; and transient characteristics and time characteristics break through steady state characteristic research limitations in the prior art. Therefore, the non-invasive load identification method solves the technical problems that the existing non-invasive load identification is limited in steady-state characteristics and low in identification accuracy under the condition of complex actual working conditions.
Drawings
Fig. 1 is a schematic flowchart illustrating an embodiment of a non-invasive load identification method according to the present application;
FIG. 2 is a schematic flowchart illustrating a non-invasive load recognition method according to another embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an embodiment of a non-invasive load identification apparatus provided in the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
For easy understanding, referring to fig. 1, an embodiment of a non-invasive load identification method provided in the present application includes:
The time sequence comprises an active power time sequence, a reactive power time sequence and a current time sequence.
Since the transient phase is a phase in which the load is put in or removed, the load putting in and removing operation in the power supply system can be accurately acquired and identified and studied by finding the transient phase in time series. And in order to find the transient state stage, acquiring an active power time sequence, a reactive power time sequence and a current time sequence at the power supply inlet, and reflecting the input and cut-off time of the load in the system through specific index information.
And 102, extracting load identification characteristic quantity of the transient stage according to the electric energy data at the electric power supply inlet.
Wherein the power data comprises voltage, current and power; the load identification characteristic quantity comprises steady-state power increment, active power characteristic, harmonic current increment and load time characteristic.
It should be noted that, the transient stage already defines the time period of the load input and the load removal in the power supply system, and the power system in the time period is subjected to targeted feature extraction, so that the load input and the load removal in the power supply system can be analyzed to the greatest extent according to the actual situation, and redundant information of load identification is considerably eliminated.
It should be noted that the steady-state power increment in the load identification characteristic quantity is mainly expressed by the steady-state active power increment and the steady-state reactive power increment of the power consumption equipment operating device power change, and because the steady-state active power increment and the steady-state reactive power increment are characteristics in a time sequence, the increment is obtained by performing difference operation on discrete steady-state active power and discrete steady-state reactive power in the time sequence.
The active power characteristics in the load identification characteristic quantity mainly refer to active power fluctuation, active power slow change and fixed frequency; the active power fluctuation is realized when some electric equipment runs along with severe power fluctuation, for example, a washing machine, the active power slow change is embodied in the transient process of the variable-frequency electric equipment, and the power characteristic except the active power fluctuation and the active power slow change is the fixed frequency.
Harmonic current increment in the load identification characteristic quantity can generate harmonic components in the operation process of the nonlinear load, wherein the amplitude of the third harmonic current is the largest relative to other frequency harmonics, and therefore the third harmonic current increment is taken as a main judgment basis for non-invasive identification.
Load event characteristics in the load identification characteristic quantity are different from load time characteristics of different electric equipment, the load can be divided into continuous operation load and intermittent operation load according to the working mode, the load time characteristics correspond to the working mode, and the load of the resident user is identified by combining non-electrical characteristic quantity such as the time characteristics of the load and electrical characteristic quantities such as power and harmonic component as the load identification characteristic quantity, so that the load identification accuracy in the actual engineering is improved.
And 103, determining the load type according to the load identification characteristic quantity and a preset load library, wherein the preset load library has a corresponding relation between the load identification characteristic quantity and the load type.
It should be noted that the load identification characteristic quantity includes steady-state power increment, active power characteristic, harmonic current increment and load time characteristic; different load types can be obtained according to different load identification characteristic quantities, and the load types can be divided into a fluctuation type load, a slowly-varying type load and a fixed-frequency type load according to the active power characteristics; various electrical devices can be specifically started and operated according to the electrical devices. In the classification process of the present embodiment, there will be classification according to power, but the final goal is to clearly identify a certain type of electric equipment to be used, started or operated.
According to the non-invasive load identification method provided by the embodiment, the characteristic of a time sequence is added for research, the steady-state power increment, the active power characteristic, the harmonic current increment and the load time characteristic of electric energy data at an electric power supply inlet are extracted at the transient stage of the time sequence, and the time characteristic reflected by the time sequence is used for carrying out non-invasive load identification on an electric power system in an actual working condition, so that the requirements of the actual working condition can be better met, and the situation that the loads cannot be accurately identified due to the fact that the steady-state characteristics are close or overlapped is avoided; and transient characteristics and time characteristics break through steady state characteristic research limitations in the prior art. Therefore, the non-invasive load identification method provided by the embodiment solves the technical problems that the existing non-invasive load identification is limited in steady-state characteristics and low in identification accuracy under the condition of complex actual working conditions.
For ease of understanding, referring to fig. 2, another embodiment of a non-invasive load identification method is provided in an embodiment of the present application, including:
And step 203, establishing a preset load library according to the steady-state power increment, the active power characteristic, the harmonic current increment and the load time characteristic.
It should be noted that, an acquisition terminal or an electric energy meter is installed at a user electric power main incoming line (for example, in an electric meter box of an electric power company), and the start-stop time and the electric energy consumption of a single electric appliance are identified by acquiring and analyzing the total current and the total voltage of the user, so that the electricity consumption behavior rules of residents are further obtained, the obtained electric quantity data can reflect the specific load change, and the established load characteristic library is more accurate and reliable.
And step 204, respectively calculating the variation of the active power, the reactive power and the current of the adjacent time periods at the power supply inlet.
And step 205, dividing the time series into a transient stage with load input or cutting-off events and a steady stage without load input or cutting-off events through the variation.
Since the transient phase is a phase in which the load is put in or removed, the load putting in and removing operation in the power supply system can be accurately acquired and identified and studied by finding the transient phase in time series. And if a transient state stage in the time sequence is to be found, acquiring an active power time sequence, a reactive power time sequence and a current time sequence at a power supply inlet, and respectively calculating the variation of active power, reactive power and current at adjacent time points or time periods, wherein the variation is compared with preset thresholds respectively corresponding to the active power, the reactive power and the current to judge whether the load is input or cut off in the power supply system, the moment when the load is input or cut off is the transient state stage, and the moment when the load is not input or cut off belongs to the steady state stage.
And step 206, extracting load identification characteristic quantity of the transient stage according to the electric energy data at the electric power supply inlet.
Wherein the power data comprises voltage, current and power; the load identification characteristic quantity comprises steady-state power increment, active power characteristic, harmonic current increment and load time characteristic.
It should be noted that the steady-state power increment in the load identification characteristic quantity is mainly expressed by the change of the power of the operating device of the electric equipment through a steady-state active power increment Δ P and a steady-state reactive power increment Δ Q, and because the steady-state power increment is a characteristic in a time sequence, the increment is obtained by performing difference operation on discrete steady-state active power and steady-state reactive power in the time sequence, and a specific calculation formula is as follows:
ΔPi＝Pi+j-Pi
ΔQi＝Qi+j-Qi
where i and j are the current time and time increment, respectively, Δ PiAnd Δ QiRespectively representing the current steady-state active power increment and the steady-state reactive power increment, Pi+j、Qi+jThe steady-state active power and the steady-state reactive power of the electric equipment at the moment (i + j) are obtained.
The active power characteristics in the load identification characteristic quantity mainly refer to active power fluctuation, active power slow change and fixed frequency; the active power fluctuation is caused by severe power fluctuation when some electric equipment runs, for example, a washing machine, and the active power slow change is embodied in the transient process of the variable-frequency electric equipment, namely, the active power fluctuation and the active power slow change are removedThe power change other than the denaturation is constant frequency. The active power fluctuation calculation process comprises the following steps: build power sliding window W1[Pxk+1:Px(k+1)]The method is used for detecting an active power sequence, wherein x is the number of discrete active power points detectable by a single sliding of a sliding window, k is 0,1,2 and … …, the difference Dt of the maximum value of the active power points in the sliding window is calculated and recorded in a difference sequence D, and then the difference sliding window W is passed through to obtain the active power sequence1’[Dmq+1:Dm(q+1)]Wherein q is the number of discrete active power points detectable by single sliding of the difference sliding window, q is 0,1,2, …), and Dt is satisfied in the statistical sliding window>The number N of DTs, where DT is an active power fluctuation characteristic determination value, is predetermined if N>m/3, judging that the load has active power fluctuation characteristics. The active power creep calculation method comprises the following steps: construct the sliding window W2[Pyk+1:Py(k+1)]Where k is 0,1,2, … …, y is the number of discrete active power points detectable by a single sliding of the sliding window, and the average value of the y active power points in the sliding window is obtained, so as to obtain a new discrete active power sequence PNkIn the pair PNkThe sequences are differenced one by one to obtain active power conversion variable sequences delta P with the number of sliding windowsNk(ii) a If there is a continuation TNMore than one ofNkSatisfies Δ PNk>TPThen, the load is judged to have the active power slowly-changing characteristic, wherein TPThe active power slowly-varying characteristic judgment value is preset. The calculation and analysis of the constant-frequency characteristic of the active power are complex, and for a constant-frequency load, the absolute values of the step quantities of the active, reactive and third-order current harmonics of the load are basically equal when the load is put into and cut off, so that the load type when the load is cut off only needs to be judged, comparison and matching are carried out according to the characteristics that the power change values are equal when the load is put into and cut off, and other three characteristics in the load identification characteristic quantity are specifically required to be involved, and detailed description is carried out in the matching identification.
Harmonic current increment in the load identification characteristic quantity, harmonic components can appear in the nonlinear load in the operation process, wherein the amplitude of the third harmonic current is maximum relative to other frequency subharmonics, and therefore the harmonic current increment is takenThe third harmonic current increment is used as the main judgment basis for non-invasive identification, and the third harmonic current increment delta I3iIs calculated as Δ I3i＝I3(i+j)-I3iIn the formula, I3iFor third harmonic currents of electric devices at time I3(i+j)The third harmonic current of the consumer at time (i + j).
The load time characteristics in the load identification characteristic quantity are different from the load time characteristics of different electric equipment, the load can be divided into continuous operation load and intermittent operation load according to the working mode, the load time characteristics correspond to the working mode, and the embodiment combines non-electrical characteristic quantities such as the load time characteristics and the like with electrical characteristic quantities such as power, harmonic components and the like, so that the identification accuracy of the load of the resident user can be improved.
And step 207, determining a first load type according to the detection of the active power characteristic, wherein the first load type comprises a fluctuation load, a slow change load and a fixed frequency load.
And 208, determining a second load type according to the first load type analysis, the matching identification of the load identification characteristic quantity and the preset load library, wherein the second load type comprises the starting or running of the preset electric equipment.
It should be noted that, in the process of performing analysis or matching identification according to the load identification characteristic quantity to determine the load type, first, rough identification is performed, and a first load type is determined according to the active power characteristic, specifically, the first load type is determined according to the detection of the active power volatility and the active power creep property, that is, the fluctuating load, the creep load and the constant-frequency load are determined by the method described by the active power characteristic; after the three categories are divided, the specific load type can be obtained through matching and identification of the load identification characteristic quantity and the load characteristic library, or the specific load type is a certain type of electric equipment, or the certain type of electric equipment is started or operated.
And 209, when the load type cannot be determined, transmitting the electric quantity data and the load identification characteristic quantity to the master station, so that the master station determines the load type by adopting a semi-supervised learning clustering method according to the electric quantity data and the load identification characteristic quantity.
It should be noted that, for the identification data only capable of determining the load rough classification type and the electrical appliance identification data of the characteristics carried by the unknown novel user load, the master station uses the load characteristic library data containing all samples and adopts a clustering method of semi-supervised learning to realize the classification of the unknown load.
To facilitate understanding of the present embodiment, an application process of the present embodiment is illustrated and analyzed: if the load with larger active fluctuation exists, the total working time Tw of the load with larger fluctuation is calculated, and if the Tw is met>Tt, determining that the washing machine is operated for a Tw period, wherein Tt is a set threshold value; if the load starting of the active power gradual change is detected, the load starting time and the load ending time are recorded as Ta and Tb, and the reactive power increment delta Q is calculatedA＝QTa-QTbJudging the increment of the reactive power Delta QAWhether or not Δ Q is satisfiedA>ΔQT，ΔQTJudging a set reactive power increment judgment value for the operation of the variable frequency air conditioner and the electric cooker, judging that the variable frequency air conditioner is started if the condition is met, and otherwise judging that the electric cooker operates; if the fixed-frequency load is detected, setting a transient process power change threshold value PATIf the active power increment is larger than PATThen there is a load of power saving up, recording the time TuCalculating the total increment Pu of active power, and calculating the impact coefficient k according to a formulapThe formula is as follows:
kp＝ΔPpeak/ΔPstabilization
Wherein, Δ PpeakIs the peak value of the active power at the start of the load, Δ PStabilizationIs the increment of the active power after the load is started stably relative to the active power before the load is started, if kpGreater than a threshold value kpTJudging that the air conditioner is started normally; carrying out reactive power detection on the continuous working load, if Q is satisfiedd>QTJudging the load as an induction cooker; if not, detecting the third harmonic current component, and if the load simultaneously satisfies Qd<-QTAnd I3d<-I3TJudging the load is an air conditioner; if the power impact coefficient kpSatisfy kp>kpTIf the load is a fixed-frequency air conditioner, otherwise, the load is a variable-frequency air conditioner; if the reactive power increment and the harmonic component do not meet the conditions, distinguishing by using the load time characteristic, and if the total working time T of the loadWSatisfy TW>TmJudging whether the load running for a long time is an electric water heater or not, and judging whether the load running for a short time is an electric water heater or not, wherein T ismIs a set threshold; if the operation mode of the load conforms to the equal intermittent operation, judging through the reactive power increment and the third harmonic current increment, and if the delta Q is metd<-QT、ΔI3d<-I3TJudging as a microwave oven, otherwise, judging as an electric oven.
For ease of understanding, please refer to fig. 3, an embodiment of a non-invasive load recognition apparatus is further provided, including:
the database building module 301 is used for acquiring electric quantity data of independent operation of various electrical appliances through a terminal;
calculating steady-state power increment, active power characteristics, harmonic current increment and load time characteristics of each electric appliance according to each electric quantity data;
and establishing a preset load library according to the steady-state power increment, the active power characteristic, the harmonic current increment and the load time characteristic.
The transient module 302 is configured to find a transient stage of a time sequence according to the obtained time sequence at the power supply inlet, where the time sequence includes an active power time sequence, a reactive power time sequence, and a current time sequence;
the characteristic extraction module 303 is configured to extract load identification characteristic quantities in a transient stage according to electric energy data at an electric power supply inlet, where the electric energy data includes voltage, current and power, and the load identification characteristic quantities include steady-state power increment, active power characteristics, harmonic current increment and load time characteristics;
and the matching module 304 is configured to determine the load type according to the load identification characteristic quantity and a preset load library, where the preset load library has a corresponding relationship between the load identification characteristic quantity and the load type.
Further, the air conditioner is provided with a fan,
the transient module 302 includes: the transient submodule 3021 is configured to calculate the variation of the active power, the reactive power, and the current in the adjacent time period respectively;
the time series is divided by the variance into a transient phase in which there is a load drop or shedding event and a steady phase in which there is no load drop or shedding event.
Further, the matching module 304 further includes: the matching submodule 3041 is configured to determine a first load type according to the detection of the active power characteristic, where the first load type includes a fluctuation type load, a slow variation type load, and a fixed frequency type load; and determining a second load type according to the first load type analysis, the matching identification of the load identification characteristic quantity and the preset load library, wherein the second load type comprises the starting or the running of the preset electric equipment.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for executing all or part of the steps of the method described in the embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device). And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A non-invasive load identification method, comprising:
finding out a transient state stage of the time sequence according to the acquired time sequence at the electric power supply inlet, wherein the time sequence comprises an active power time sequence, a reactive power time sequence and a current time sequence;
extracting load identification characteristic quantities of the transient stage according to electric energy data at the electric power supply inlet, wherein the electric energy data comprises voltage, current and power, and the load identification characteristic quantities comprise steady-state power increment, active power characteristic, harmonic current increment and load time characteristic;
and determining the load type according to the load identification characteristic quantity and a preset load library, wherein the preset load library stores the corresponding relation between the load identification characteristic quantity and the load type.
2. The method according to claim 1, wherein the step of finding the transient phase of the time sequence according to the obtained time sequence at the power supply inlet further comprises:
acquiring electric quantity data of independent operation of various electrical appliances through a terminal;
calculating the steady-state power increment, the active power characteristic, the harmonic current increment and the load time characteristic of each electrical appliance according to each electrical quantity data;
and establishing the preset load library according to the steady-state power increment, the active power characteristic, the harmonic current increment and the load time characteristic.
3. The method according to claim 1, wherein the finding the transient phase of the time sequence according to the acquired time sequence at the power supply inlet comprises:
respectively calculating the variable quantities of active power, reactive power and current in adjacent time periods;
and dividing the time series into a transient stage with load input or cut-off events and a steady stage without load input or cut-off events through the variable quantity.
4. The method of claim 1, wherein the determining the load type according to the load recognition feature quantity and a preset load library comprises:
determining a first load type according to the detection of the active power characteristic, wherein the first load type comprises a fluctuation load, a slow change load and a fixed frequency load;
and according to the first load type analysis, the load identification characteristic quantity and the matching identification of a preset load library determine a second load type, wherein the second load type comprises the starting or running of preset electric equipment.
5. The method of claim 4, wherein the identifying the first load type according to the matching of the active power characteristics comprises:
and determining the first load type according to the detection of the active power fluctuation and the active power slow change.
6. The method of claim 1, further comprising:
and when the load type cannot be determined, the electric quantity data and the load identification characteristic quantity are sent to a master station, so that the master station determines the load type by adopting a semi-supervised learning clustering method according to the electric quantity data and the load identification characteristic quantity.
7. A non-invasive load identifying device, comprising:
the transient state module is used for finding out a transient state stage of the time sequence according to the acquired time sequence at the electric power supply inlet, wherein the time sequence comprises an active power time sequence, a reactive power time sequence and a current time sequence;
a characteristic extraction module, configured to extract load identification characteristic quantities of the transient stage according to electric energy data at the power supply inlet, where the electric energy data includes voltage, current, and power, and the load identification characteristic quantities include steady-state power increment, active power characteristics, harmonic current increment, and load time characteristics;
and the matching module is used for determining the load type according to the load identification characteristic quantity and a preset load library, and the preset load library stores the corresponding relation between the load identification characteristic quantity and the load type.
8. The non-invasive load identifying device according to claim 7, further comprising: building a library module;
the database building module is used for acquiring electric quantity data of independent operation of various electric appliances through a terminal;
calculating the steady-state power increment, the active power characteristic, the harmonic current increment and the load time characteristic of each electrical appliance according to each electrical quantity data;
and establishing the preset load library according to the steady-state power increment, the active power characteristic, the harmonic current increment and the load time characteristic.
9. The apparatus according to claim 7, wherein the transient module comprises:
the transient submodule is used for respectively calculating the variable quantities of active power, reactive power and current in adjacent time periods;
and dividing the time series into a transient stage with load input or cut-off events and a steady stage without load input or cut-off events through the variable quantity.
10. The apparatus of claim 7, wherein the matching module further comprises:
the matching submodule is used for determining a first load type according to the detection of the active power characteristic, and the first load type comprises a fluctuation load, a slow variation load and a fixed frequency load;
and determining a second load type according to the first load type analysis and the matching identification of the load identification characteristic quantity, wherein the second load type comprises the starting or running of preset electric equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010207857.6A CN111244954B (en) | 2020-03-23 | 2020-03-23 | Non-invasive load identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010207857.6A CN111244954B (en) | 2020-03-23 | 2020-03-23 | Non-invasive load identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111244954A true CN111244954A (en) | 2020-06-05 |
| CN111244954B CN111244954B (en) | 2022-01-21 |
Family
ID=70880603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010207857.6A Active CN111244954B (en) | 2020-03-23 | 2020-03-23 | Non-invasive load identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111244954B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107525964A (en) * | 2017-10-23 | 2017-12-29 | 云南电网有限责任公司电力科学研究院 | A kind of recognition methods of non-intrusion type load and device based on fusion decision-making |
| CN112035793A (en) * | 2020-08-20 | 2020-12-04 | 国网湖南省电力有限公司 | Non-intrusive identification method and system for electric appliances based on discrete second-order derivative |
| CN112346349A (en) * | 2020-10-22 | 2021-02-09 | 珠海格力电器股份有限公司 | Control method and device of intelligent equipment, electronic equipment and storage medium |
| CN112395348A (en) * | 2020-10-21 | 2021-02-23 | 中国电力科学研究院有限公司 | Method and system for identifying non-intervention load |
| CN112434799A (en) * | 2020-12-18 | 2021-03-02 | 宁波迦南智能电气股份有限公司 | Non-invasive load identification method based on full convolution neural network |
| CN112560889A (en) * | 2020-11-06 | 2021-03-26 | 云南电网有限责任公司电力科学研究院 | Power load identification method |
| CN112924779A (en) * | 2021-01-25 | 2021-06-08 | 河北科技大学 | Non-invasive load identification method and device and terminal equipment |
| CN112924790A (en) * | 2021-01-29 | 2021-06-08 | 上海逐鲨智能科技有限公司 | Fourier transform-based non-invasive load identification device and method thereof |
| CN112952827A (en) * | 2021-04-08 | 2021-06-11 | 任亚星 | Non-invasive full-load identification technology for accurately identifying charging of electric bicycle |
| CN113054747A (en) * | 2021-04-13 | 2021-06-29 | 国网福建省电力有限公司 | Non-invasive detection method for nonlinear load of power distribution station |
| CN113219268A (en) * | 2021-03-26 | 2021-08-06 | 国电南瑞科技股份有限公司 | Non-invasive identification method and device for multi-state electric appliance |
| CN113285442A (en) * | 2021-04-21 | 2021-08-20 | 广东工业大学 | Single electric equipment identification method and device based on non-invasive load characteristics |
| CN113326296A (en) * | 2021-02-25 | 2021-08-31 | 中国电力科学研究院有限公司 | Load decomposition method and system suitable for industrial and commercial users |
| CN113408481A (en) * | 2021-07-13 | 2021-09-17 | 国网江苏省电力有限公司营销服务中心 | Multi-class typical load characteristic analysis and extraction method |
| CN113655337A (en) * | 2021-07-27 | 2021-11-16 | 上海千居智科技有限公司 | Non-invasive electric equipment operation sequence identification method and identification system |
| CN113687140A (en) * | 2021-08-26 | 2021-11-23 | 天津大学 | Unsupervised non-invasive television identification method based on current space trajectory |
| CN113723806A (en) * | 2021-08-30 | 2021-11-30 | 南京智睿能源互联网研究院有限公司 | Method for establishing electric load characteristic image for load identification |
| CN116780537A (en) * | 2023-08-24 | 2023-09-19 | 国网天津市电力公司宝坻供电分公司 | Non-invasive load monitoring method, device and storage medium |
| CN116800165A (en) * | 2023-08-21 | 2023-09-22 | 江苏和亿智能科技有限公司 | Automatic frequency conversion energy-saving speed regulation control system |
| CN117349639A (en) * | 2023-12-04 | 2024-01-05 | 国网江西省电力有限公司供电服务管理中心 | Identification method and device for charging behavior of electric bicycle |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110213739A1 (en) * | 2009-12-16 | 2011-09-01 | Robert Bosch Gmbh | Non-intrusive load monitoring system and method |
| CN105186693A (en) * | 2015-09-28 | 2015-12-23 | 南方电网科学研究院有限责任公司 | Non-invasive electrical load identification system and method |
| CN106646026A (en) * | 2016-11-11 | 2017-05-10 | 华北电力大学 | Non-intrusive household appliance load identification method |
| CN109492667A (en) * | 2018-10-08 | 2019-03-19 | 国网天津市电力公司电力科学研究院 | A kind of feature selecting discrimination method for non-intrusive electrical load monitoring |
| CN110516788A (en) * | 2019-08-07 | 2019-11-29 | 深圳供电局有限公司 | Bi-LSTM algorithm-based non-invasive load detection method and system |
| CN110672934A (en) * | 2019-08-23 | 2020-01-10 | 北京中电飞华通信股份有限公司 | Non-invasive load identification method, terminal and system |
-
2020
- 2020-03-23 CN CN202010207857.6A patent/CN111244954B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110213739A1 (en) * | 2009-12-16 | 2011-09-01 | Robert Bosch Gmbh | Non-intrusive load monitoring system and method |
| CN105186693A (en) * | 2015-09-28 | 2015-12-23 | 南方电网科学研究院有限责任公司 | Non-invasive electrical load identification system and method |
| CN106646026A (en) * | 2016-11-11 | 2017-05-10 | 华北电力大学 | Non-intrusive household appliance load identification method |
| CN109492667A (en) * | 2018-10-08 | 2019-03-19 | 国网天津市电力公司电力科学研究院 | A kind of feature selecting discrimination method for non-intrusive electrical load monitoring |
| CN110516788A (en) * | 2019-08-07 | 2019-11-29 | 深圳供电局有限公司 | Bi-LSTM algorithm-based non-invasive load detection method and system |
| CN110672934A (en) * | 2019-08-23 | 2020-01-10 | 北京中电飞华通信股份有限公司 | Non-invasive load identification method, terminal and system |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107525964A (en) * | 2017-10-23 | 2017-12-29 | 云南电网有限责任公司电力科学研究院 | A kind of recognition methods of non-intrusion type load and device based on fusion decision-making |
| CN107525964B (en) * | 2017-10-23 | 2023-11-21 | 云南电网有限责任公司电力科学研究院 | Non-invasive load identification method and device based on fusion decision |
| CN112035793A (en) * | 2020-08-20 | 2020-12-04 | 国网湖南省电力有限公司 | Non-intrusive identification method and system for electric appliances based on discrete second-order derivative |
| CN112035793B (en) * | 2020-08-20 | 2023-11-10 | 国网湖南省电力有限公司 | Non-intrusive identification method and system for motor electric appliances based on discrete second derivative |
| CN112395348A (en) * | 2020-10-21 | 2021-02-23 | 中国电力科学研究院有限公司 | Method and system for identifying non-intervention load |
| CN112346349A (en) * | 2020-10-22 | 2021-02-09 | 珠海格力电器股份有限公司 | Control method and device of intelligent equipment, electronic equipment and storage medium |
| CN112560889A (en) * | 2020-11-06 | 2021-03-26 | 云南电网有限责任公司电力科学研究院 | Power load identification method |
| CN112434799B (en) * | 2020-12-18 | 2022-07-05 | 宁波迦南智能电气股份有限公司 | Non-invasive load identification method based on full convolution neural network |
| CN112434799A (en) * | 2020-12-18 | 2021-03-02 | 宁波迦南智能电气股份有限公司 | Non-invasive load identification method based on full convolution neural network |
| CN112924779A (en) * | 2021-01-25 | 2021-06-08 | 河北科技大学 | Non-invasive load identification method and device and terminal equipment |
| CN112924790A (en) * | 2021-01-29 | 2021-06-08 | 上海逐鲨智能科技有限公司 | Fourier transform-based non-invasive load identification device and method thereof |
| CN113326296A (en) * | 2021-02-25 | 2021-08-31 | 中国电力科学研究院有限公司 | Load decomposition method and system suitable for industrial and commercial users |
| CN113326296B (en) * | 2021-02-25 | 2024-06-07 | 中国电力科学研究院有限公司 | Load decomposition method and system suitable for industrial and commercial users |
| CN113219268A (en) * | 2021-03-26 | 2021-08-06 | 国电南瑞科技股份有限公司 | Non-invasive identification method and device for multi-state electric appliance |
| CN112952827A (en) * | 2021-04-08 | 2021-06-11 | 任亚星 | Non-invasive full-load identification technology for accurately identifying charging of electric bicycle |
| CN113054747B (en) * | 2021-04-13 | 2022-06-07 | 国网福建省电力有限公司 | Non-invasive detection method for nonlinear load of power distribution station |
| CN113054747A (en) * | 2021-04-13 | 2021-06-29 | 国网福建省电力有限公司 | Non-invasive detection method for nonlinear load of power distribution station |
| CN113285442A (en) * | 2021-04-21 | 2021-08-20 | 广东工业大学 | Single electric equipment identification method and device based on non-invasive load characteristics |
| CN113408481A (en) * | 2021-07-13 | 2021-09-17 | 国网江苏省电力有限公司营销服务中心 | Multi-class typical load characteristic analysis and extraction method |
| CN113408481B (en) * | 2021-07-13 | 2024-06-07 | 国网江苏省电力有限公司营销服务中心 | Multi-category typical load characteristic analysis and extraction method |
| CN113655337A (en) * | 2021-07-27 | 2021-11-16 | 上海千居智科技有限公司 | Non-invasive electric equipment operation sequence identification method and identification system |
| CN113655337B (en) * | 2021-07-27 | 2024-05-14 | 上海千居智科技有限公司 | Non-invasive electric equipment operation sequence identification method and identification system |
| CN113687140A (en) * | 2021-08-26 | 2021-11-23 | 天津大学 | Unsupervised non-invasive television identification method based on current space trajectory |
| CN113687140B (en) * | 2021-08-26 | 2023-11-17 | 天津大学 | Non-supervision non-invasive television identification method based on current space track |
| CN113723806A (en) * | 2021-08-30 | 2021-11-30 | 南京智睿能源互联网研究院有限公司 | Method for establishing electric load characteristic image for load identification |
| CN116800165A (en) * | 2023-08-21 | 2023-09-22 | 江苏和亿智能科技有限公司 | Automatic frequency conversion energy-saving speed regulation control system |
| CN116780537A (en) * | 2023-08-24 | 2023-09-19 | 国网天津市电力公司宝坻供电分公司 | Non-invasive load monitoring method, device and storage medium |
| CN117349639A (en) * | 2023-12-04 | 2024-01-05 | 国网江西省电力有限公司供电服务管理中心 | Identification method and device for charging behavior of electric bicycle |
| CN117349639B (en) * | 2023-12-04 | 2024-03-08 | 国网江西省电力有限公司供电服务管理中心 | Identification method and device for charging behavior of electric bicycle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111244954B (en) | 2022-01-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111244954B (en) | Non-invasive load identification method and device | |
| CN106786534B (en) | A kind of non-intrusive electrical load transient process discrimination method and system | |
| CN110672934A (en) | Non-invasive load identification method, terminal and system | |
| CN110514889A (en) | A kind of method and system of non-intrusion type household electricity remained capacity | |
| CN111564842B (en) | Method for statistical estimation of medium-and-long-term energy consumption in non-invasive electric load monitoring | |
| CN105067966B (en) | The low-voltage alternating-current fault arc detection method of feature based modal components energy spectrometer | |
| CN108021736A (en) | A kind of load switching action monitoring method based on sliding window Remanent Model | |
| CN110488112A (en) | Classification metering method non-intrusion type load identification and its realized based on recognition result | |
| CN106443244A (en) | Electric equipment type identification method and system | |
| Girmay et al. | Simple event detection and disaggregation approach for residential energy estimation | |
| CN109782086B (en) | Non-intrusive load identification method based on multi-dimensional signal analysis | |
| CN112396007A (en) | Non-invasive three-threshold detection method and system for load sudden change event of residents | |
| CN113567794A (en) | Electric bicycle indoor charging identification method and system based on dynamic time warping | |
| CN115456034A (en) | Automatic identification and monitoring method and system for electric bicycle charging | |
| CN118395365B (en) | Power box with function of monitoring abnormal metering data and monitoring method | |
| CN113887912A (en) | Non-invasive load identification method for deeply learning downward embedded equipment | |
| Nardello et al. | A low-cost smart sensor for non intrusive load monitoring applications | |
| Chen et al. | Non-intrusive load monitoring based on feature extraction of change-point and xgboost classifier | |
| CN115758234A (en) | Battery car load identification method based on multi-feature fusion and related device thereof | |
| CN112949563B (en) | Non-invasive load identification method based on variable point detection and improved KNN algorithm | |
| Cannas et al. | NILM techniques applied to a real-time monitoring system of the electricity consumption | |
| WO2024069466A1 (en) | Method for anomaly detection in electric appliances, corresponding system and computer program product | |
| Cannas et al. | Real-time monitoring system of the electricity consumption in a household using NILM techniques | |
| CN115578217A (en) | Non-invasive load monitoring method and monitoring system based on decision tree model | |
| Yang et al. | Mining the big data of residential appliances in the smart grid environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: Room 501-503, annex building, Huaye building, No.1-3 Chuimao new street, Xihua Road, Yuexiu District, Guangzhou City, Guangdong Province 510000 Applicant after: China Southern Power Grid Power Technology Co.,Ltd. Address before: Room 501-503, annex building, Huaye building, No.1-3 Chuimao new street, Xihua Road, Yuexiu District, Guangzhou City, Guangdong Province 510000 Applicant before: GUANGDONG ELECTRIC POWER SCIENCE RESEARCH INSTITUTE ENERGY TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |