CN113158446A - Non-invasive electric load identification method - Google Patents
Non-invasive electric load identification method Download PDFInfo
- Publication number
- CN113158446A CN113158446A CN202110372297.4A CN202110372297A CN113158446A CN 113158446 A CN113158446 A CN 113158446A CN 202110372297 A CN202110372297 A CN 202110372297A CN 113158446 A CN113158446 A CN 113158446A
- Authority
- CN
- China
- Prior art keywords
- initial state
- load
- power
- loads
- initial
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 239000013598 vector Substances 0.000 claims abstract description 21
- 239000002131 composite material Substances 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 238000001228 spectrum Methods 0.000 claims abstract description 6
- 238000005070 sampling Methods 0.000 claims description 21
- 230000002068 genetic effect Effects 0.000 claims description 16
- 230000005611 electricity Effects 0.000 claims description 6
- 230000035772 mutation Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 26
- 238000010586 diagram Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R21/00—Arrangements for measuring electric power or power factor
- G01R21/06—Arrangements for measuring electric power or power factor by measuring current and voltage
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Power Engineering (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a non-invasive electric load identification method, which comprises the steps of collecting load voltage data and current data and extracting total orthogonal current harmonic frequency spectrum characteristics; performing windowing pretreatment to obtain windowed power data; determining initial states of all the loads based on the generated initial state library; establishing a composite characteristic objective function model according to the windowed power data and the power characteristic vectors and harmonic characteristic vectors of all loads; and determining the initial parameter value of the composite characteristic objective function model based on the initial state of each load, and solving the composite characteristic objective function model to obtain the optimal solution of the power load. The invention effectively combines data preprocessing and recognition algorithm optimization, and utilizes the original data windowing preprocessing and initial state prejudgment to reduce the operation complexity; orthogonal current harmonic characteristics with large difference between loads are utilized, a characteristic model is optimized, and load identification accuracy in a power utilization scene is improved.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to a non-invasive electric load identification method.
Background
The non-invasive power load identification technology collects power utilization information through a monitoring device at an entrance of a power consumer, and then identifies the working states of various electric appliances of the user by analyzing information such as total current, total voltage and the like at the entrance. The technology can feed back an analysis result to the user, guide the power utilization behavior of the user, scientifically formulate a planning scheme and provide power utilization suggestions, and therefore energy conservation and consumption reduction are promoted to be achieved. Compared with the traditional invasive monitoring technology, the method reduces the equipment installation cost and the later maintenance consumption. The technology has very important use value and research significance for green, continuous and harmonious development of China and promotion of energy production and consumption revolution.
At present, with the increasing variety of the current household appliances, the load basic feature original data volume is larger, the identification processing process is more complicated, and the identification efficiency is reduced; load characteristics such as partial electric appliance power, current and the like are high in similarity, so that a characteristic overlapping phenomenon occurs, the identification effect is poor, in an actual power utilization scene, a situation that a high-power electric appliance and a low-power electric appliance run simultaneously usually exists, interference and noise influence of high-power non-stable load fluctuation exist, and low-power load identification accuracy is low. According to the current research situation of the non-invasive power load identification technology, the technology mainly establishes a power load model according to the electrical characteristics of the power load, and then utilizes pattern recognition and optimization technology to realize the decomposition of the power load, such as a clustering algorithm, a machine learning algorithm, an evolutionary algorithm and the like. However, the existing research of fuzzy clustering identification is established on the premise that the number and the type of loads, namely the clustering number, are known, and when the number and the type of the loads are unknown or multiple electric appliances run simultaneously, the types and the running states of the electric appliances cannot be accurately identified; the machine learning method has higher calculation efficiency, but the accuracy in load monitoring and identification is greatly influenced by a random initial result, a weight value and the like; the accuracy of the load identification result can be improved by the evolutionary algorithm through an iterative optimization mode, but the calculation efficiency is low. The method integrates the current research results, and is less related to a non-invasive load identification scheme for improving an identification algorithm and optimizing the operation efficiency.
Disclosure of Invention
The invention aims to provide an efficient and accurate non-invasive charge identification method, which reduces the operation complexity of a load identification algorithm and improves the accuracy and the anti-interference capability.
In order to achieve the technical purpose, the invention adopts the following technical scheme.
The invention provides a non-intrusive power load identification method, which comprises the following steps:
acquiring load voltage data and current data and extracting load power characteristics and total orthogonal current harmonic frequency spectrum characteristics; performing windowing preprocessing based on the load voltage data, the current data and the load power characteristics to obtain windowed power data;
determining initial states of all the loads based on the generated initial state library;
establishing a composite characteristic objective function model according to the windowed power data and the power characteristic vectors and harmonic characteristic vectors of all loads; and determining the initial parameter value of the composite characteristic objective function model based on the initial state of each load, and solving the composite characteristic objective function model to obtain the optimal solution of the power load.
Further, the total quadrature current harmonic frequency signature h (k) is expressed as follows:
where U (t) is the load voltage at sampling time t, i (t) is the load current at sampling time t, UrmsThe root mean square voltage of the voltage u (T), N is the total number of loads in the power utilization scene, N is the serial number of the loads in the power utilization scene, and T is the sampling time period.
Further, the expression for windowing preprocessing the collected voltage data, current data and orthogonal current harmonic frequency characteristics is as follows:
where P (t) is the total load power at the sampling instant t, Pm(t) is power data obtained after windowing preprocessing of the load power P (t) at the sampling time t; w (T) is a window function, D is the total number of windows, TwIs the window width, beta, of the window functioniIs the window overlap ratio.
Further, the method of determining the initial states of all the loads based on the generated initial state library is as follows:
step a, randomly generating an initial State base State0 ═ S at the time t0_1，S0_2,…,S0_Q}， S0_j＝{δ0_j1,δ0_j2,,…,δ0_jN}，j＝1,2,…,Q，S0_jRepresenting the jth operation initial state of all loads in the initial state library, wherein Q is the total number of states in the initial state library; delta0_jiE {0,1}, i 1,2, …, N is the total number of loads in the electricity usage scenario, δ0_jiRepresents the jth initial State of the ith load in the initial State library State0,
step b: calculating the distance difference between each initial State in the initial State library State0 at the time t and power data obtained after windowing preprocessing of load power P (t) at the sampling time t, and determining the minimum distance difference delta, wherein the minimum distance difference delta is represented as follows:
wherein delta0_jiE {0,1}, i 1,2, …, N is the total number of loads in the electricity usage scenario, δ0_jiJ represents the j initial state of the ith load in the initial state library, wherein j is 1,2, …, Q, and Q is the total number of the initial states in the initial state library; p is a radical ofjiIs the power of a certain load in the jth initial state;
step c: determining an initial state S corresponding to the minimum value of the distance difference0_min；
Step d: judging whether the delta is less than or equal to the epsilon, if so, updating the epsilon value, wherein the epsilon is a threshold value; otherwise, the initial state is generated again at random to replace the initial state S determined in the step c0_min；
Step e: initial state S to be determined0_minAs an initial state of all loads.
Still further, the composite-feature objective function model is represented as follows:
wherein D (j, t) representsAn objective function related to the sampling time t and the initial state; pm(t) is power data obtained after windowing preprocessing of the load power P (t) of the original sampling time t; h (k) is a total harmonic load characteristic value at the sampling time t; load state S0_jPower characteristic vector P ═ P for all loads at the bottomj1,pj2,…,pjN]Harmonic feature vector H ═ H for all loadsj1,hj2,…,hjN]ω represents a weight value of the model with emphasis on power characteristics, and ω' represents a weight value of the model with emphasis on orthogonal current harmonic characteristics.
Still further, the method for solving the composite-feature objective function model is as follows:
initial State library State0 was used as the genetic initial population S0_1，S0_2,…,S0_QN-dimensional binary vector S for each state0_j(ii) a Setting genetic iteration parameters; according to the determined initial state S of all loads0_minDetermining initial parameter values of the composite characteristic objective function model according to the corresponding power characteristic vectors of all loads, the harmonic characteristic vectors of all loads and the initial states of all loads;
calculating the fitness of the population according to the objective function, determining the optimal value in the population, judging whether the maximum genetic algebra is reached, if the maximum genetic algebra is not reached, performing selection, crossing and mutation operations to generate a new initial next generation population, and repeatedly calculating the fitness of the population according to the objective function; and when the maximum genetic algebra is reached, selecting the individual with the highest fitness from the optimal individuals of each generation, and outputting the individual as the optimal solution of the algorithm.
Based on the above technical scheme, still include: updating the initial State library State0, wherein the updating method comprises the following steps: replacing the State S corresponding to the maximum value of the distance difference in the initial State library State0 with the State with the highest frequency of occurrence in the selected identification period0_maxA new initial State library State0 is constructed.
Further, the method of updating the threshold value ε is as follows: the median value of the distance difference in each state in the initial state library is used to replace the original threshold value epsilon.
The invention has the following beneficial technical effects:
the invention effectively combines data preprocessing and recognition algorithm optimization, and utilizes the original data windowing preprocessing and initial state prejudgment to reduce the operation complexity; orthogonal current harmonic characteristics with large difference between loads are utilized, a characteristic model is optimized, and load identification accuracy in a power utilization scene is improved. The method solves the problem of poor identification effect when the load active and reactive power characteristics are close in the prior art, and also solves the problem of significant increase of operation time caused in the algorithm optimization process;
the invention preprocesses each coincident initial state, optimizes the initial state of each load, improves the identification efficiency of the non-intrusive power load identification method, and ensures that the method is converged more quickly.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a schematic structural diagram of a non-intrusive power load identification method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a non-intrusive power load identification method according to an embodiment of the present invention;
FIG. 3 is a block diagram of a collection device used in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram of load feature raw data windowing pre-processing in an embodiment of the invention
FIG. 5 is a graph of window width, overlap ratio and operating time according to an embodiment of the present invention
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The first embodiment provides a non-intrusive power load identification method, which includes the following steps, and a schematic structural diagram of the method provided by the present embodiment is shown in fig. 1:
step 1: load voltage data and current data are collected. In this embodiment, an intelligent non-invasive load characteristic acquisition device as shown in fig. 2 is used to obtain the basic characteristics of the load voltage and current signals. The intelligent non-invasive load characteristic acquisition device is shown in fig. 3 and comprises three parts, namely monitoring equipment, data acquisition equipment and peripheral equipment. The monitoring equipment comprises an intelligent monitor, a concentrator, a controller and the like, the data acquisition equipment comprises a communication bus, a master control module, a storage unit and the like, and the peripheral equipment comprises a display module and input equipment. The device is used for acquiring signals such as voltage, current and the like of the electric appliance.
Step 2: and (2) extracting load characteristics such as power, current harmonic and the like of the electrical appliance based on the basic characteristic data in the step (1), wherein the load characteristics such as power, current harmonic and the like of the electrical appliance (namely the load) and the total orthogonal current harmonic spectrum characteristics are extracted.
The orthogonal current harmonic frequency domain characteristics of different loads have larger difference, which is beneficial to improving the load identification accuracy, so that in addition to the power characteristics, the orthogonal current harmonic frequency spectrum H (k) extracted in the step 2 is as follows:
wherein the load voltage and current are respectively expressed as U (t) and i (t), UrmsIs the root mean square voltage of the voltage u (t), and N is the total number of loads in the power consumption scene.
And step 3: performing windowing pretreatment on the collected voltage data, current data and orthogonal current harmonic frequency characteristics to obtain windowed power data;
determining initial states of all the loads based on the generated initial state library; in the step 2, the original data is preprocessed based on the load characteristics, so that the operation efficiency is improved.
3.1 windowing pretreatment.
The original data is preprocessed by windowing, so that the effective data is not lost, the data volume is reduced, and the operation complexity is reduced. In a fixed power utilization scene, the load state change is usually periodic, the period value can be judged and obtained through the original data acquisition and analysis, then effective data are extracted by adding a time window to the load power characteristic data in the full time period range, and the windowing mode is shown in fig. 4. Important parameters related to the windowing pretreatment process comprise a windowing position, a windowing size and efficiency amplification, wherein the windowing position is a position with sudden change or fluctuation of a characteristic value; the initial window size is larger, the subsequent window size is decreased progressively, and the window length can be further reduced through long-time data accumulation; the efficiency increase is related to the window size and the window overlap ratio. The windowed load power signature data can be expressed as:
where P (T) is the total power at sampling time T, w (T) is a window function, D is the total number of windows added, T is the window width, and β is the window overlap ratio. As shown in fig. 5, the larger the overlap ratio, that is, the higher the window overlap ratio, the longer the operation time.
3.2 initial state prejudgment, namely, determining the initial state of all the loads based on the generated initial state library. The estimated initial state is used as the input of the next recognition algorithm, so that the subsequent processing time can be reduced.
The estimated initial state is used as the input of the next step, so that the subsequent processing time can be reduced. For non-intrusive load identification, the initial state of operation of all appliances can be represented as S0＝{δ01,δ02,…,δ0N}，δ0iE {0,1}, i ═ 1,2, …, N. Outputting the initial state S of each load through the single-power target characteristic value delta and the preset threshold epsilon according to the data subjected to the windowing preprocessing in the step 3.10The estimation method comprises the following steps:
step a, randomly generating an initial State base State0 ═ S at the time t0_1，S0_2,…,S0_Q}， S0_j＝{δ0_j1,δ0_j2,,…,δ0_jN}，j＝1,2,…,Q，S0_jRepresenting the jth operation initial state of all loads in the initial state library, wherein Q is the total number of states in the initial state library; delta0_jiE {0,1}, i 1,2, …, N is the total number of loads in the electricity usage scenario, δ0_jiA jth initial State representing the ith load in the initial State library State 0;
step b: calculating the distance difference between each initial State in the initial State library State0 at the time t and power data obtained after windowing preprocessing of load power P (t) at the sampling time t, and determining the minimum distance difference delta, wherein the minimum distance difference delta is represented as follows:
wherein p isjiFor the power of a certain electric appliance in the jth state, the larger the value of Q is, the higher the complexity of data preprocessing is, but the lower the complexity of subsequent identification processing is. Delta0_jiE {0,1}, i 1,2, …, N is the total number of loads in the electricity usage scenario, δ0_jiJ represents the j initial state of the ith load in the initial state library, wherein j is 1,2, …, Q, and Q is the total number of the initial states in the initial state library; p is a radical ofjiIs the power of a certain load (i-th load) in the j initial state;
step c: determining an initial state S corresponding to the minimum value of the distance difference0_min；
Step d: judging whether the delta is less than or equal to the epsilon, if so, updating the epsilon value, wherein the epsilon is a threshold value; otherwise, the initial state is generated again at random to replace the initial state S determined in the step c0_min；
Step e: initial state S to be determined0_minAs an initial state of all loads.
And 4, step 4: establishing a composite characteristic objective function model according to the windowed power data and the power characteristic vectors and harmonic characteristic vectors of all loads; and determining the initial parameter value of the composite characteristic objective function model based on the initial state of each load, and solving the composite characteristic objective function model to obtain the optimal solution of the power load.
And 4, improving and optimizing the single objective function on the basis of the traditional genetic algorithm, and establishing a composite characteristic objective function model by comprehensively utilizing the load power characteristic and the orthogonal current harmonic characteristic. And then obtaining an optimal solution through genetic iteration based on a composite characteristic objective function model according to the load characteristic data and the initial state obtained after the preprocessing.
Because the frequency domain characteristics of the orthogonal current harmonics of different loads have larger difference, the orthogonal current harmonic characteristics are introduced in the step to enhance the difference between the load characteristics and improve the identification accuracy and the anti-interference performance. The load power characteristics and the orthogonal current harmonic characteristics are synthesized, and an objective function model based on the composite characteristics is established as follows:
representing an objective function related to the sampling time t and the initial state by D (j, t); the initial state library randomly generated in the step 3 is used as a genetic initial population { S }0_1，S0_2,…,S0_QN-dimensional binary vector S for each state0_j＝{δ0_j1,δ0_j2,,…,δ0_jN}; state S generated in step 30_minDetermines the parameter delta0_ji、pjiAnd hjiOf the initial parameter value, i.e. delta0_jiInitial value is the state S corresponding to the ith load0_minValue of (a), pjiTakes the ith load in its first state S0_minA lower power value; h isjiTakes the initial value of the ith load in its first state S0_minThe lower harmonic (i.e., the quadrature current harmonic spectrum);
the total power and the total harmonic load characteristic values monitored and extracted at a certain moment are respectively expressed as P after being preprocessedm(t) and Hk(t); state S0_jPower characteristic vector P ═ P for all loads at the bottomj1,pj2,…,pjN]Harmonic feature vector H ═ H for all electrical appliancesj1,hj2,…,hjN]The values of ω and ω 'represent whether the model is focused on power characteristics or orthogonal current harmonic characteristics, ω represents a weight value of the model focused on power characteristics, and ω' represents a weight value of the model focused on orthogonal current harmonic characteristics.
Performing multi-target optimization according to the model, and performing multiple iterations to obtain an optimal individual: (1) according to the target function model D (j, t), substituting according to the initial state S0_minSetting genetic iteration parameters according to the determined parameter initial value; (2) calculating the fitness of the population according to the target function, recording the optimal value in the population, judging whether the maximum genetic algebra is reached, if so, executing (4), and if not, continuing; (3) carrying out selection, crossing and mutation operations to generate a new next generation population, and repeatedly executing the step (2); (4) and selecting the individual with the highest fitness from the optimal individuals of each generation, and outputting the individual as the optimal solution of the algorithm.
In a second embodiment, on the basis of the first embodiment, in order to adaptively adjust the value of the update threshold epsilon, so that the set threshold can adapt to the change of the initial state and is more reasonable, the embodiment further includes: replacing the original threshold epsilon with the median value of the distance difference in each state in the initial state library, wherein the calculation formula of the distance difference in each state in the initial state library is as follows:
the third embodiment further includes, on the basis of the above embodiments: updating the initial State library State0, wherein the updating method comprises the following steps: replacing the State S corresponding to the maximum value of the distance difference in the initial State library State0 with the State with the highest frequency of occurrence in the selected identification period0_maxA new initial State library State0 is constructed.
For example, in step a of the initial state prejudging in step 3.2, after the initial state library is randomly generated, the method provided in this embodiment is adopted to update the randomly generated initial state library, and the updated initial state library of each load is used as the initial state library of the next round of identification, thereby further improving the identification efficiency and the convergence rate.
In addition, if the initial population adopts the randomly generated initial state library of each load in the process of solving the composite characteristic objective function model in the step 4, the steps in the embodiment can be adopted to update the initial population, so that the identification efficiency and the convergence speed are further improved. The schematic flow chart of the method provided by the embodiment is shown in fig. 2.
In the above embodiments, the steps are numbered for convenience of description, and the order of executing the steps is not to be construed as limited.
The invention relates to a high-efficiency and accurate non-invasive power load identification method, which adopts an intelligent non-invasive load characteristic acquisition device to acquire and store voltage and current signals in a power utilization scene, and can efficiently and accurately acquire a load identification result through key steps of data windowing pretreatment, initial state generation, identification algorithm analysis, genetic iteration and the like.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (8)
1. A method of non-intrusive electrical load identification, comprising the steps of:
acquiring load voltage data and current data and extracting load power characteristics and total orthogonal current harmonic frequency spectrum characteristics;
performing windowing preprocessing based on the load voltage data, the current data and the load power characteristics to obtain windowed power data;
determining initial states of all the loads based on the generated initial state library;
establishing a composite characteristic objective function model according to the windowed power data and the power characteristic vectors and harmonic characteristic vectors of all loads; and determining the initial parameter value of the composite characteristic objective function model based on the initial state of each load, and solving the composite characteristic objective function model to obtain the optimal solution of the power load.
2. A non-intrusive electrical load identification method as defined in claim 1, wherein the total quadrature current harmonic frequency signature h (k) is expressed as follows:
where U (t) is the load voltage at sampling time t, i (t) is the load current at sampling time t, UrmsThe root mean square voltage of the voltage u (T), N is the total number of loads in the power utilization scene, N is the serial number of the loads in the power utilization scene, and T is the sampling time period.
3. A non-intrusive electrical load identification method as defined in claim 1, wherein the expression for windowing preprocessing the collected voltage data, current data and quadrature current harmonic frequency characteristics is as follows:
where P (t) is the total load power at the sampling instant t, Pm(t) is power data obtained after windowing preprocessing of the load power P (t) at the sampling time t; w (T) is a window function, D is the total number of windows, TwIs the window width, beta, of the window functioniAs windowsMouth overlap ratio.
4. A non-intrusive electrical load identification method as defined in claim 1, wherein the method of determining the initial state of all loads based on the generated initial state library is as follows:
step a, randomly generating an initial State base State0 ═ S at the time t0_1，S0_2,…,S0_Q}，S0_j＝{δ0_j1,δ0_j2,,…,δ0_jN}，j＝1,2,…,Q，S0_jRepresenting the jth operation initial state of all loads in the initial state library, wherein Q is the total number of states in the initial state library; delta0_jiE {0,1}, i 1,2, …, N is the total number of loads in the electricity usage scenario, δ0_jiRepresents the jth initial State of the ith load in the initial State library State0,
step b: calculating the distance difference between each initial State in the initial State library State0 at the time t and power data obtained after windowing preprocessing of load power P (t) at the sampling time t, and determining the minimum distance difference delta, wherein the minimum distance difference delta is represented as follows:
wherein delta0_jiE {0,1}, i 1,2, …, N is the total number of loads in the electricity usage scenario, δ0_jiJ represents the j initial state of the ith load in the initial state library, wherein j is 1,2, …, Q, and Q is the total number of the initial states in the initial state library; p is a radical ofjiIs the power of a certain load in the jth initial state;
step c: determining an initial state S corresponding to the minimum value of the distance difference0_min；
Step d: judging whether the delta is less than or equal to the epsilon, if so, updating the epsilon value, wherein the epsilon is a threshold value; otherwise, the initial state is generated again at random to replace the initial state S determined in the step c0_min；
Step e: initial state S to be determined0_minAs an initial state of all loads.
5. The method of non-intrusive electrical load identification (PMD) of claim 4, wherein the composite signature objective function model is represented as follows:
wherein D (j, t) represents an objective function related to the sampling time t and the initial state; pm(t) is power data obtained after windowing preprocessing of the load power P (t) of the original sampling time t; h (k) is a total harmonic load characteristic value at the sampling time t; load state S0_jPower characteristic vector P ═ P for all loads at the bottomj1,pj2,…,pjN]Harmonic feature vector H ═ H for all loadsj1,hj2,…,hjN]ω represents a weight value of the model with emphasis on power characteristics, and ω' represents a weight value of the model with emphasis on orthogonal current harmonic characteristics.
6. A non-intrusive electrical load identification method as defined in claim 5, wherein the method of solving the composite signature objective function model is as follows:
initial State library State0 was used as the genetic initial population S0_1，S0_2,…,S0_QN-dimensional binary vector S for each state0_j(ii) a Setting genetic iteration parameters; according to the determined initial state S of all loads0_minDetermining initial parameter values of the composite characteristic objective function model according to the corresponding power characteristic vectors of all loads, the harmonic characteristic vectors of all loads and the initial states of all loads;
calculating the fitness of the population according to the objective function, determining the optimal value in the population, judging whether the maximum genetic algebra is reached, if the maximum genetic algebra is not reached, performing selection, crossing and mutation operations to generate a new initial next generation population, and repeatedly calculating the fitness of the population according to the objective function; and when the maximum genetic algebra is reached, selecting the individual with the highest fitness from the optimal individuals of each generation, and outputting the individual as the optimal solution of the algorithm.
7. A non-intrusive electrical load identification method as defined in any of claims 4 to 6, further comprising: updating the initial State library State0, wherein the updating method comprises the following steps: replacing the State S corresponding to the maximum value of the distance difference in the initial State library State0 with the State with the highest frequency of occurrence in the selected identification period0_maxA new initial State library State0 is constructed.
8. A method of non-intrusive electrical load identification as defined in claim 4, wherein the method of updating the threshold ε is as follows:
the median value of the distance difference in each state in the initial state library is used to replace the original threshold value epsilon.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110372297.4A CN113158446B (en) | 2021-04-07 | 2021-04-07 | Non-invasive electrical load identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110372297.4A CN113158446B (en) | 2021-04-07 | 2021-04-07 | Non-invasive electrical load identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113158446A true CN113158446A (en) | 2021-07-23 |
| CN113158446B CN113158446B (en) | 2024-06-11 |
Family
ID=76888574
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110372297.4A Active CN113158446B (en) | 2021-04-07 | 2021-04-07 | Non-invasive electrical load identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113158446B (en) |
Cited By (1)
| 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 |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104777383A (en) * | 2015-04-16 | 2015-07-15 | 武汉阿帕科技有限公司 | Non-invasive electrical load monitoring and load decomposing device |
| CN105429135A (en) * | 2015-12-08 | 2016-03-23 | 河南许继仪表有限公司 | Distinguishing and decision-making method and system for noninvasive power load decomposition |
| CN106022645A (en) * | 2016-06-07 | 2016-10-12 | 李祖毅 | Non-intruding type on-line and real-time electric power load identification method and identification system |
| CN106655160A (en) * | 2016-10-27 | 2017-05-10 | 国家电网公司 | Non-intrusion electric power load decomposition identification decision method and system |
| CN106786534A (en) * | 2016-12-28 | 2017-05-31 | 天津求实智源科技有限公司 | A kind of non-intrusive electrical load transient process discrimination method and system |
| CN109541346A (en) * | 2018-11-23 | 2019-03-29 | 四川长虹电器股份有限公司 | A kind of non-intrusion type electrical load under steady state condition identifies method for improving |
| CN110866214A (en) * | 2019-11-07 | 2020-03-06 | 昆明理工大学 | Non-invasive load decomposition based on improved differential evolution algorithm |
| CN112101110A (en) * | 2020-08-13 | 2020-12-18 | 西安理工大学 | Non-invasive load identification method for user side of power system |
-
2021
- 2021-04-07 CN CN202110372297.4A patent/CN113158446B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104777383A (en) * | 2015-04-16 | 2015-07-15 | 武汉阿帕科技有限公司 | Non-invasive electrical load monitoring and load decomposing device |
| CN105429135A (en) * | 2015-12-08 | 2016-03-23 | 河南许继仪表有限公司 | Distinguishing and decision-making method and system for noninvasive power load decomposition |
| CN106022645A (en) * | 2016-06-07 | 2016-10-12 | 李祖毅 | Non-intruding type on-line and real-time electric power load identification method and identification system |
| CN106655160A (en) * | 2016-10-27 | 2017-05-10 | 国家电网公司 | Non-intrusion electric power load decomposition identification decision method and system |
| CN106786534A (en) * | 2016-12-28 | 2017-05-31 | 天津求实智源科技有限公司 | A kind of non-intrusive electrical load transient process discrimination method and system |
| CN109541346A (en) * | 2018-11-23 | 2019-03-29 | 四川长虹电器股份有限公司 | A kind of non-intrusion type electrical load under steady state condition identifies method for improving |
| CN110866214A (en) * | 2019-11-07 | 2020-03-06 | 昆明理工大学 | Non-invasive load decomposition based on improved differential evolution algorithm |
| CN112101110A (en) * | 2020-08-13 | 2020-12-18 | 西安理工大学 | Non-invasive load identification method for user side of power system |
Non-Patent Citations (2)
| Title |
|---|
| 张玲玲;: "非侵入式电力负荷分解算法综述", 安徽电子信息职业技术学院学报, no. 01 * |
| 陈于锋;: "基于竞争聚集和神经网络的非侵入式负载监测方法", 江苏通信, no. 06 * |
Cited By (2)
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113158446B (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108616120B (en) | Non-invasive power load decomposition method based on RBF neural network | |
| CN110956220B (en) | Non-invasive household appliance load identification method | |
| CN111160798B (en) | Non-invasive household appliance load identification method based on bee colony algorithm | |
| CN103400052A (en) | Combined method for predicting short-term wind speed in wind power plant | |
| CN109633301B (en) | Non-invasive electrical appliance load identification method based on quantum genetic optimization | |
| Zhou et al. | Non-intrusive load monitoring using a CNN-LSTM-RF model considering label correlation and class-imbalance | |
| Shao et al. | Hybrid model for short-term wind power forecasting based on singular spectrum analysis and a temporal convolutional attention network with an adaptive receptive field | |
| CN111563827A (en) | Load decomposition method based on electrical appliance physical characteristics and residential electricity consumption behaviors | |
| CN114444539A (en) | Power load identification method, apparatus, device, medium, and program product | |
| CN113158446B (en) | Non-invasive electrical load identification method | |
| CN113762355B (en) | User abnormal electricity behavior detection method based on non-invasive load decomposition | |
| CN113887912A (en) | Non-invasive load identification method for deeply learning downward embedded equipment | |
| CN114358367A (en) | Non-invasive load decomposition method and device | |
| CN111898694B (en) | Non-invasive load identification method and device based on random tree classification | |
| Jiang et al. | A new method for recognition and classification of power quality disturbances based on IAST and RF | |
| Wang et al. | A non-intrusive method of industrial load disaggregation based on load operating states and improved grey wolf algorithm | |
| Feng et al. | Identification of disturbance sources based on random forest model | |
| CN113036754A (en) | Non-invasive load identification method based on improved DAG-SVMS | |
| CN113010985A (en) | Non-invasive load identification method based on parallel AANN | |
| CN117315434A (en) | Non-invasive load identification method based on time sequence imaging and deep learning | |
| CN115343959B (en) | Self-adaptive control method, device, equipment and medium for electric heating load | |
| CN112070625A (en) | User electricity consumption behavior pattern recognition method and system | |
| CN113595242B (en) | Non-invasive load identification method based on depth CNN-HMM | |
| CN114741943A (en) | Energy storage capacity configuration optimization method based on particle swarm optimization | |
| CN115828091A (en) | Non-invasive load identification method and system based on end-cloud cooperation |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |