Non-invasive load monitoring method based on compressed sensing and mathematical optimization model

Abstract

The application provides a non-invasive load monitoring method based on compressed sensing and a mathematical optimization model, comprising the following steps: setting original load signal acquisition parameters and generating a binary sparse measurement matrix, and compressively collecting original load signals to obtain compressed signals; reconstructing the compressed signals according to the binary sparse measurement matrix, a sparse basis and a target reconstruction algorithm to obtain a sparse vector; determining a load analysis vector type according to an original load type, and forming a load analysis vector based on the sparse vector; generating a plurality of model parameter matrices for the mathematical optimization model according to load analysis vector sample values of each electrical equipment in a load sample library; establishing a plurality of mathematical optimization models according to the plurality of model parameter matrices and the load analysis vector, and obtaining a plurality of electrical equipment opening and closing state vectors by solving the mathematical optimization models. The application applies compressed sensing to solve data compression and analysis of load data in non-invasive load monitoring, and has the advantages of simple compression and low-frequency sampling.

Description

Technical Field

[0001] This invention relates to the field of non-intrusive load monitoring technology, and in particular to a non-intrusive load monitoring method based on compressed sensing and mathematical optimization models. Background Technology

[0002] Non-Intrusive Load Monitoring (NILM) collects electrical signals at the user's inlet and analyzes them to obtain information about the types and specific conditions of loads within the user's premises. Compared to traditional load monitoring methods, NILM has lower equipment installation and maintenance costs, higher operability, and greater user acceptance, making it a primary load monitoring method in future smart grids. It is better suited to the rapid growth in the number of grid load users and the demand for intelligent control of electrical equipment. NILM mainly includes data acquisition, data transmission, and load analysis. Among these, load analysis aims to achieve load identification, which is also the ultimate goal of NILM.

[0003] With the increasing scale and intelligence of power systems, the data collected by NILM (Non-Intrusive Load Monitoring) is growing explosively. Traditional data compression methods can address the massive data problem in NILM, but they suffer from drawbacks such as complexity and high-frequency sampling. In recent years, with the deepening research into the application of Compressed Sensing (CS) in power systems, CS can overcome the shortcomings of traditional compression methods. Compressed sensing is a novel sampling theory that combines signal acquisition and compression, featuring simple compression and low-frequency sampling. However, currently, there is no non-intrusive load monitoring technology based on compressed sensing, making it difficult to adapt to the future development of NILM. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a non-intrusive load monitoring method based on compressed sensing and a mathematical optimization model. By establishing a mathematical optimization model, non-intrusive load monitoring technology based on compressed sensing is realized, which solves the problems of high-frequency sampling, high compression cost, redundant storage at the sampling end, and inapplicability to monitoring equipment. It clarifies the technical route of compressed sensing in non-intrusive load monitoring and guides the construction of future non-intrusive load monitoring systems based on compressed sensing.

[0005] A first aspect of this invention provides a non-intrusive load monitoring method based on compressed sensing and a mathematical optimization model, comprising:

[0006] The original load signal acquisition parameters are set and a binary sparse measurement matrix is ​​generated. The original load signal is compressed and acquired to obtain a compressed signal. Based on the binary sparse measurement matrix, sparse basis, and target reconstruction algorithm, the compressed signal is reconstructed to obtain a sparse vector. The load analysis vector type is determined according to the original load type, and a load analysis vector is formed based on the sparse vector. A load sample library is established according to the sparse vector sample values, feature vector sample values, and load analysis vector sample values. Based on the load analysis vector sample values ​​of each electrical device in the load sample library, multiple model parameter matrices for mathematical optimization models are generated. Based on the multiple model parameter matrices and load analysis vectors, multiple mathematical optimization models are established, and multiple electrical device switching state vectors are obtained by solving the mathematical optimization models. Based on the multiple electrical device switching state vectors obtained by solving, the load scene identification result is output, and the reconstructed value of the original load signal is output.

[0007] In one possible implementation, the step of setting the original load signal acquisition parameters and generating a binary sparse measurement matrix, and compressing the original load signal to obtain a compressed signal, includes:

[0008] Set the type of the original load signal to either current waveform or instantaneous power;

[0009] The acquisition time is set to 1 second, the length of the original load signal is N = 2048, and the compression ratio is 0.4 to 0.7.

[0010] The measurement matrix size is determined based on the compression ratio and the length of the original load signal, and a zero matrix is ​​generated based on the measurement matrix size.

[0011] A predetermined number of elements are randomly selected from each column of the zero matrix and assigned the value 1 to form the generated binary sparse measurement matrix; wherein the predetermined number is less than the total number of elements in each column.

[0012] The compressed signal y is obtained according to y = Φx, where Φ is the binary sparse measurement matrix and x is the original load signal.

[0013] In one possible implementation, determining the load analysis vector type based on the original load type and forming the load analysis vector based on the sparse vector includes:

[0014] When the original load signal is instantaneous power, a sparse vector obtained through reconstruction is used as the load analysis vector;

[0015] When the original load signal is a current waveform, the fundamental current phasor value and the h-th harmonic current phasor value are obtained from the sparse vector and a 7-dimensional eigenvalue vector is formed as the load analysis vector; where h = 2, 3, 5, 7, 9, 11.

[0016] In one possible implementation, obtaining the fundamental current phasor value and the h-th harmonic current phasor value from the sparse vector and forming a 7-dimensional eigenvalue vector includes:

[0017] Search for the extrema of an N-dimensional sparse vector s and their position labels k. i ; where the position number k i Satisfy |s(k) i )|≥|s(k i +1)|and|s(k) i )|≥|s(k i -1)|;s(k i ), s(k i +1), s(k) i -1) represent the k-th digit of the N-dimensional sparse vector s. i The element, the kth element i +1 element, k-th element i -1 values ​​of elements, k i ∈[2,N]; i=1,2,3...;

[0018] Search sequentially for the condition hf-2≤(k) i The position label k of -1) / T≤hf+2 i And the filtered k i Put into set {k h}; where k h The spectral line designation represents the fundamental frequency or the h-th harmonic; set {k h There are 7 elements in total, h = 1, 2, 3, 5, 7, 9, 11, where h = 1 represents the spectral line number of the fundamental wave;

[0019] Following the sequence h = 1, 2, 3, 5, 7, 9, 11, find s(k) sequentially. h The larger element among the preceding and following elements is labeled. Where, when s(k h +1) <s(k h When -1), on the contrary

[0020] pass

[0021]

[0022] Calculate the correction amount α and the intermediate amount β;

[0023] pass

[0024]

[0025] Calculate the amplitude A of the h-th harmonic current. h and phase

[0026] Where h = 1 represents the fundamental wave, angle[s(k h +1)] represents the complex number s(k) h A complex angle of +1); h The current amplitudes are the fundamental frequency and each harmonic. For current harmonic phasors;

[0027] according to A 7-dimensional eigenvalue vector is formed.

[0028] In one possible implementation, the plurality of mathematical optimization models include:

[0029] min||dD k a k

[0030]

[0031] Among them, D k Let be the k-th model parameter matrix; d is a U×1 dimensional vector, which is the load analysis vector formed based on sparse vectors; U is the vector length; when the original load signal is instantaneous power, U = 7; when the original load signal is instantaneous power, U = N; when the original load signal is instantaneous power, U = 7; when the original load signal is instantaneous power, U = N; a k Let a be an E×1 dimensional vector. k =[a k (1),a k (2)...a k (e)...a k [(E)] represents the on / off state of each electrical device; E is the total number of electrical devices; k = 1 to i E .

[0032] In one possible implementation, the step of generating multiple model parameter matrices for a mathematical optimization model based on the load analysis vector sample values ​​of each electrical device in the load sample library includes:

[0033] Based on the load analysis vector sample values ​​of each electrical device in the load sample library, determine the various parameter forms of each column vector of the model parameter matrix;

[0034] i is generated by combining different parameter forms of each column vector. E The model parameter matrix D k ;k=1~i E ; i represents the number of different parameter forms of the column vector.

[0035] In one possible implementation, establishing the load sample library according to sparse vector sample values, feature vector sample values, and load analysis vector sample values ​​includes:

[0036] The sparse vector of each original load sample value is obtained by sparse representation of the original load sample values, and then it is put into the load sample library as a sparse vector sample value.

[0037] Obtain the feature value vector of the original load sample values ​​of all individual electrical devices, form the feature vector sample values, and put them into the load sample library;

[0038] Based on sparse vector sample values ​​and feature vector sample values, load analysis vector sample values ​​are generated and placed into the load sample library.

[0039] In one possible implementation, the method further includes:

[0040] Obtain historical electrical signal data for all individual electrical devices, use them as raw load sample values, and store them in the load sample library.

[0041] In one possible implementation, the step of outputting the load scenario identification result and the reconstructed value of the original load signal based on the solved multiple electrical equipment disconnection state vectors includes:

[0042] Obtain i obtained by solving the multiple mathematical optimization models E A vector representing the on / off state of each electrical device; where i E The number of mathematical optimization models;

[0043] Determine i E The electrical equipment disconnection state vector that appears most frequently among the electrical equipment disconnection state vectors is taken as the target electrical equipment disconnection state vector, and the load scenario identification result is output based on the target electrical equipment disconnection state vector.

[0044] The reconstructed value of the original load signal is integrated based on the sparse vector output. in, Ψ and s are the original load signal reconstruction value, sparse basis, and sparse vector, respectively.

[0045] In one possible implementation, the target reconstruction algorithm is a gradient tracking algorithm or a convex optimization algorithm; the sparse basis is a Discrete Fourier Transform (DFT) basis.

[0046] A second aspect of the present invention provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the non-intrusive load monitoring method based on compressed sensing and mathematical optimization models as described above.

[0047] A third aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the non-intrusive load monitoring method based on compressed sensing and a mathematical optimization model as described above.

[0048] This invention provides a non-intrusive load monitoring method based on compressed sensing and a mathematical optimization model. First, it proposes an implementation framework for non-intrusive load monitoring based on compressed sensing and a mathematical optimization model. Leveraging the characteristic that sparse vectors under certain sparse bases in CS technology can characterize the feature values ​​of the original load signal, load analysis is achieved using intermediate signals from the reconstruction process. Second, it proposes a mathematical optimization model for load analysis and a solution approach based on the most frequently occurring optimal result. Third, it proposes a method for feature extraction from sparse vectors. Fourth, it proposes a method for feature extraction from sparse vectors to achieve load analysis. This invention solves problems such as high-frequency sampling, high compression costs, redundant storage at the sampling end, and unsuitability for monitoring electrical equipment. It enables the construction of a mathematical optimization model based on the load analysis vector sample values ​​of different devices in the sample library during data compression. This model can be solved using traditional artificial intelligence algorithms and 0-1 knapsack problem solving algorithms to obtain decision variables and determine the final result of the on / off state of electrical equipment based on these decision variables, thus completing the load analysis and obtaining the on / off state of each electrical device. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a technical schematic diagram of a non-intrusive load monitoring method based on compressed sensing and mathematical optimization model according to the present invention.

[0051] Figure 2 This is a schematic diagram illustrating the implementation process of a non-intrusive load monitoring method based on compressed sensing and a mathematical optimization model, according to an embodiment of the present invention.

[0052] Figure 3This is a schematic diagram illustrating the feature extraction process when the original signal is a current waveform, according to one embodiment of the present invention.

[0053] Figure 4 This is a diagram comparing the load identification rates of three load identification schemes.

[0054] Figure 5 A technical flowchart of a non-intrusive load monitoring method based on compressed sensing and mathematical optimization model, provided for another embodiment of the present invention;

[0055] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0056] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0057] NILM comprises key components such as data acquisition, data transmission, and load analysis, with load analysis being the core component. Load analysis primarily aims at load identification, which is also the ultimate goal of NILM. Load identification in NILM refers to determining which individual electrical signals from various electrical devices are included in the integrated electrical signal collected at the user's input point; in other words, determining the on / off status of all electrical devices. In NILM, integrated load data is first acquired using traditional sampling methods, and then this data is transmitted to data analysis equipment for load analysis.

[0058] Compressed sensing (CS) mainly comprises compressed measurement, data transmission, and signal reconstruction, with compressed measurement and signal reconstruction being the core components. CS is a data acquisition technology with compression and reconstruction capabilities, requiring no complex data encoding calculations, making it ideal for applications with limited encoding resources. CS compresses data simultaneously with signal acquisition, employing a low sampling frequency to reduce the amount of sampled data, saving storage space while still containing sufficient information. When the original signal needs to be recovered, a suitable reconstruction algorithm is used to restore it, thereby recovering sufficient data. The measurement matrix, sparse basis, and reconstruction algorithm are the three essential elements of compressed sensing.

[0059] This invention integrates the three core components of NILM with the three components of CS, proposing the basic idea of ​​a non-intrusive load monitoring method based on compressed sensing, and realizing load analysis based on compressed sensing and mathematical optimization models. Figure 1As shown in the figure, the data acquisition of NILM and the compressive measurement of CS are fused to perform a "compressive acquisition process" at the sampling end; the load analysis of NILM and the signal reconstruction of CS are fused to perform a "reconstruction and analysis process" at the data analysis end. Taking the minimum Euclidean distance between the load data of different electrical appliances in the load sample library and the original load data collected as the goal, a mathematical optimization model is established, the mathematical optimization model is solved, and the on-off state of each electrical appliance is obtained through the solution result with the most occurrences.

[0060] As Figure 1 shown, the basic process of the NILM method based on CS and scenario recognition is as follows: First, the measurement matrix Φ ∈ R M×N of CS is used to perform compressive acquisition on the original load signal x ∈ R N×1 to obtain the compressed signal y ∈ R M×1 (M << N); where, y = Φx = ΦΨs; Then, the compressed data y is reconstructed and analyzed. In the reconstruction and analysis process, first, the N×1-dimensional sparse vector s is obtained from y using the CS reconstruction algorithm, and load analysis is realized during the reconstruction process, and the reconstructed value of the original load signal is obtained Since the sparse vector s under certain sparse bases can represent the eigenvalue of the original load signal, load recognition can be realized without obtaining the reconstructed value . Load recognition is realized by establishing a mathematical optimization model and solving it. x ∈ R N×1 satisfying that the sparse vector s under a certain sparse basis Ψ ∈ R N×N has good sparsity is a prerequisite. The reconstruction algorithm needs to call the sparse basis during the reconstruction process. The number K of non-zero elements of the sparse vector s is called the sparsity of x under the sparse basis Ψ.

[0061] To illustrate the technical solution of the present invention, it will be described below through specific embodiments. The embodiments of the present invention aim to provide a non-intrusive load monitoring method based on compressive sensing and a mathematical optimization model. The solution provided by the embodiments of the present invention mainly includes two processes: compressive acquisition and reconstruction and analysis in the implementation process; and mainly includes three elements of CS and a load analysis method in terms of technical composition. The innovative ideas of the embodiments of the present invention are: First, an implementation framework for non-intrusive load monitoring based on compressive sensing is proposed, and load analysis is realized using the intermediate signal during the reconstruction process; Second, a mathematical optimization model for realizing load analysis and the solution result with the most occurrences is used as the optimal solution result; Third, various constructions of the model parameter matrix in the mathematical optimization model are proposed; Fourth, a method for feature extraction of the sparse vector is proposed to realize load analysis.

[0062] Embodiment 1

[0063] Figure 2This is a flowchart illustrating a non-intrusive load monitoring method based on compressed sensing and a mathematical optimization model, provided as an embodiment of the present invention. Figure 2 As shown, this embodiment includes the following steps:

[0064] S201, set the original load signal acquisition parameters and generate a binary sparse measurement matrix, and compress the original load signal to obtain a compressed signal.

[0065] In one possible implementation, the types of the original load signal include: current waveform and instantaneous power.

[0066] Specifically, the compression acquisition parameters and the type of the original load signal are set to generate an M×N dimensional binary sparse measurement matrix. The measurement matrix is ​​then used to compress and acquire the N×1 dimensional original load signal to obtain an M×1 dimensional compressed signal. The length of the original load signal is N, the length of the compressed signal is M, and the compression ratio is M / N.

[0067] Step S201 includes steps S2011 to S2014. Each step is as follows.

[0068] S2011, set the type of the original load signal to current waveform or instantaneous power.

[0069] In this embodiment of the invention, the type of the original load signal x is set to current waveform or instantaneous power. The type of the original load signal x is set to facilitate load analysis. In addition to being easy to obtain and compress, the selection of the original load signal should also follow two principles: First, it should have superposition, that is, the integrated electrical signal is the sum of all individual electrical signals; second, the sparse vector s under a certain sparse basis can be used for feature extraction, that is, there exists a sparse basis that can be used for feature extraction.

[0070] Based on the above principles, the original load signal is set as either a current waveform or instantaneous power. The current waveform is composed of the instantaneous current values ​​at the acquisition point within the acquisition time T, and includes 50 power frequency sine waves when T = 1s; the instantaneous power is composed of the instantaneous active power (the product of the instantaneous values ​​of current and voltage) at the acquisition point within the acquisition time T.

[0071] S2012, set the acquisition time length to 1s, the length of the original load signal to N=2048, and the compression ratio to 0.4~0.7.

[0072] The compression ratio is set based on the reconstruction accuracy and load identification accuracy of the environment. T is set to 1s; N satisfies N = 2fHT, where f is the frequency of the power system and H is the total number of harmonics to be identified. Therefore, optionally, the original load signal length N = 2048, in which case at least the 15th order and below of harmonics can be identified for the original load signal. The selection of the compression ratio M / N should consider the reconstruction accuracy and the effect of load analysis, and needs to be determined in specific implementation.

[0073] S2013 generates an M×N dimensional binary sparse measurement matrix Φ.

[0074] The measurement matrix is ​​one of the three essential elements of CS (Static Coding). To accurately reconstruct the original load signal, the measurement matrix must satisfy the constrained equidistant property, and a random measurement matrix can satisfy this condition. Currently, typical random measurement matrices include Gaussian random matrices, Bernoulli random matrices, partial Hadamard matrices, and binary sparse measurement matrices. Therefore, in this embodiment of the invention, typical random measurement matrices are all applicable to the technical solution of this embodiment.

[0075] Preferably, the embodiments of the present invention employ a binary sparse measurement matrix, which is both easy to implement and has good reconstruction performance from the random measurement matrix. The generation process of the binary sparse measurement matrix is ​​as follows:

[0076] The measurement matrix size M×N is determined based on the compression ratio and the length of the original load signal.

[0077] Generate an M×N dimensional zero matrix, i.e., all elements are zero;

[0078] Randomly select a set number of elements in each column of the zero matrix and assign them a value of 1, i.e., ɑM elements are assigned a value of 1, and update the zero matrix. The updated zero matrix is ​​the generated binary sparse measurement matrix.

[0079] The sparsity α can be flexibly set according to the specific environment, where α << 1, meaning the sparsity is much less than 1. Optionally, α can be less than 10%.

[0080] In one specific embodiment, when N = 1024 and the compression ratio is 0.5, then M = 512, and 5 elements are randomly selected from each column of the zero matrix, with the corresponding a ≈ 0.009; when N = 512 and the compression ratio is 0.5, then M = 256, and 2 elements are randomly selected from each column of the zero matrix, with the corresponding a ≈ 0.007.

[0081] S2014, Obtain the compressed signal y according to y = Φx; where Φ is the binary sparse measurement matrix generated in step S2013, and x is the original load signal.

[0082] S202, based on the binary sparse measurement matrix, as well as the sparse basis and target reconstruction algorithm, the compressed signal is reconstructed to obtain a sparse vector.

[0083] In order to ensure the sparse representation effect of the original load signal and improve the reconstruction accuracy, before step S202, it is necessary to call the measurement matrix and sparse basis, determine the target reconstruction algorithm, and then reconstruct the compressed signal based on the target reconstruction algorithm to obtain the sparse vector.

[0084] The sparse basis of CS directly affects the sparse representation of the original load signal. With the same measurement matrix and reconstruction algorithm, the lower the sparsity of the original load signal, the higher its reconstruction accuracy. CS sparse bases in power systems are represented by fixed orthogonal transform bases, including DFT bases, Discrete Cosine Transform (DCT) bases, and Discrete Wavelet Transform (DWT) bases. Fixed orthogonal transforms are simple to construct, easy to implement, and highly applicable to sinusoidal signals.

[0085] Preferably, in this embodiment of the invention, a DFT basis is used as the sparse basis. The original load signal has good sparsity under the DFT basis, and the obtained sparse vector can characterize the eigenvalues ​​of the original load.

[0086] The CS reconstruction algorithm solves equation (1) to obtain an N×1 dimensional sparse vector s from the M×1 dimensional compressed signal y. This process requires calling the measurement matrix and sparse basis. The CS reconstruction algorithm mainly includes greedy algorithms (lp=0) and convex optimization algorithms (lp=1). Greedy algorithms include orthogonal matching pursuit algorithm, compressed sampling matching pursuit algorithm, regularized orthogonal matching pursuit algorithm, gradient pursuit algorithm, etc. Convex optimization algorithms include gradient projection sparse reconstruction method, spectral projection gradient method, etc. These algorithms are all applicable to the technical solution of this embodiment.

[0087]

[0088] In this embodiment of the invention, the reconstruction algorithm aims to obtain sparse vectors with high accuracy or fast speed. Convex optimization algorithms have high reconstruction accuracy but slow computation speed, while greedy algorithms sacrifice reconstruction accuracy to improve computation speed, and the reconstruction accuracy meets the requirements in most cases.

[0089] Preferably, in this embodiment of the invention, a convex optimization algorithm or a gradient pursuit algorithm is used as the target reconstruction algorithm. When the reconstruction accuracy requirement is high or the original load signal is sparse, the convex optimization algorithm is selected; in most other cases, the gradient pursuit algorithm is selected.

[0090] S203, determine the load analysis vector type based on the original load type, and form a load analysis vector based on sparse vectors.

[0091] The load analysis vector is the foundation for establishing the mathematical optimization model and is influenced by the type of the original load signal; that is, the type of load analysis vector differs depending on the type of the original load signal. When the original load signal is a current waveform, the load analysis vector is the eigenvalue vector of the original load signal; when the original load signal is a current waveform, the load analysis vector is a sparse vector of the original load. The eigenvalues ​​of the original load are obtained by feature extraction from the sparse vector. Before obtaining the load eigenvalues, the load eigenvalue type needs to be set.

[0092] The load analysis vector type and eigenvalue type for different types of raw load signals are set as shown in Table 1.

[0093] Table 1

[0094]

[0095]

[0096] Based on this, step S203, which involves forming a load analysis vector based on sparse vectors, includes:

[0097] When the original load signal is a current waveform, load feature values ​​are obtained from the sparse vector according to the feature value extraction method, and a multi-dimensional feature value vector is formed to serve as the load analysis vector.

[0098] When the original load signal is instantaneous power, the sparse vector s obtained by reconstruction is used as the load analysis vector.

[0099] In one possible implementation, when the original load signal is a current waveform, load feature values ​​are obtained from a sparse vector using a feature value extraction method, forming a multi-dimensional feature value vector, including:

[0100] The fundamental current phasor value and the h-th harmonic current phasor value are obtained from the sparse vector and a 7-dimensional load characteristic vector is formed; where h = 2, 3, 5, 7, 9, 11.

[0101] In one specific implementation, the original load signal type is a current waveform, and it is necessary to extract the fundamental current phasor value and the h-th harmonic current phasor value (h=2,3,5,7,9,11). This step specifically includes steps S2031~S2036. Figure 3 The implementation process is illustrated in the diagram below, with each step as follows.

[0102] S2031, Search for the extrema of an N-dimensional sparse vector s and its position label k. i That is, the search satisfies |s(k) i )|≥|s(k i +1)|and|s(k) i )|≥|s(ki -1)| All position labels k i (i = 1, 2, 3...). Where s(k) i ), s(k i +1), s(k) i -1) represent the k-th digit of the N-dimensional sparse vector s. i The element, the kth element i +1 element, k-th element i -1 values ​​of elements, k i ∈[2,N].

[0103] S2032, sequentially search for the condition hf-2≤(k) i -1) / T≤hf+2 of k i And the filtered k i Put into set {k h}. Where, k h The spectral line designation representing the fundamental wave or the h-th harmonic is set {k}. h There are 7 elements, namely h = 1, 2, 3, 5, 7, 9, 11, where h = 1 represents the spectral line number of the fundamental wave.

[0104] S2033, according to h = 1, 2, 3, 5, 7, 9, 11, sequentially search for s(k) h The larger element among the preceding and following elements is labeled. That is, when s(k) h +1) <s(k h When -1), on the contrary

[0105] S2034, calculate the correction amount α and the intermediate amount β using equation (2).

[0106]

[0107] S2035, calculate the amplitude A of the h-th harmonic current using equation (3). h and phase When h=1, it represents the fundamental wave, angle[s(k h +1)] represents the complex number s(k) h Complex angles of +1).

[0108]

[0109] S2036, A h The current amplitudes of the fundamental frequency and each harmonic are... For current harmonic phasors; according to Form a 7-dimensional eigenvalue vector I c .in, For a complex number, it can also be represented as

[0110] When the original load signal is a current waveform, the load analysis vector d is the 7-dimensional eigenvalue vector, i.e., d = I. c .

[0111] In another specific embodiment, when the original load signal is instantaneous power, the sparse vector s obtained by reconstruction is used as the load analysis vector, and feature extraction is not required.

[0112] When the original load signal is instantaneous power, the load analysis vector d is an N-dimensional sparse vector, i.e., d = s = [s1, s2, ... s]. i ,...s N ] T .

[0113] S204. Establish a load sample library based on sparse vector sample values, eigenvector sample values, and load analysis vector sample values.

[0114] A load sample library is formed based on the original load sample values, sparse vector sample values, and feature vector sample values ​​of each electrical device. Specifically, when the original load signal is a current waveform, the corresponding feature vector sample values ​​are stored as load analysis vector sample values; when the original load signal is a current waveform, the corresponding sparse vector sample values ​​are stored as load analysis vector sample values. The steps for forming the load sample library specifically include S2041 to S2044.

[0115] S2041, Obtain historical electrical signal data for all individual electrical devices, use them as raw load sample values, and store them in the load sample library.

[0116] S2042, obtain the sparse vector of each original load sample value by performing sparse representation on the original load sample value, and put it into the load sample library as a sparse vector sample value.

[0117] The electrical signals include the current waveforms and instantaneous power of each electrical device. The length and attributes of the original load sample values ​​are the same as those of the original load signals collected in S201; the length of the sparse vector sample values ​​is the same as the length of the original sample values, and the sparse vector sample values ​​are only applicable when the original load sample values ​​are instantaneous power.

[0118] Sparse vectors are obtained by sparsely representing the corresponding original load signals. In one possible implementation, the sparse vectors of the E electrical devices e in the load sample library include {s}. 1-i1 ,s 2-i2 ...s e-ie ...s E-iE}

[0119] Among them, s1-i1 ,s 2-i2 ...s e-ie ...s E-iE (e = 1, 2...E) represents the feature vector of electrical equipment e with instantaneous power as the original load signal, and is an N-dimensional column vector. Here, E represents the number of electrical equipment; i1 = 1, 2...W1, i2 = 1, 2...W2, ...ie = 1, 2...W e ..., iE = 1, 2...W E W1, W2...W e ...W E These represent the number of sparse vector sample values ​​for each electrical device.

[0120] S2043, obtain the feature value vector of the original load sample values ​​of all individual electrical devices, form the feature vector sample values, and put them into the load sample library.

[0121] The eigenvalue vector sample values ​​are only valid when the original load sample value is a current waveform. In one possible implementation, the load eigenvalue vectors of the E electrical devices in the load sample library include {I} 1-i1 ,I 2-i2 ...I e-ie ...I E-iE}

[0122] Among them, I e-ie (e = 1, 2...E) represents the feature vector sample values ​​of electrical equipment e, with the current waveform as the original load signal. These are all 7-dimensional column vectors, where each element is the phasor value of the h-th harmonic current (including the fundamental wave) (h = 1, 2, 3, 5, 7, 9, 11), calculated from the original load sample values. Here, E represents the number of electrical equipment; i1 = 1, 2...W1, i2 = 1, 2...W2, ...ie = 1, 2...W e ..., iE = 1, 2...W E W1, W2...W e ...W E These represent the number of feature vector sample values ​​for each electrical device.

[0123] S2044: Based on sparse vector sample values ​​and feature vector sample values, load analysis vector sample values ​​are formed and placed into the load sample library.

[0124] Load analysis vector sample values ​​are formed based on the sparse vector sample values ​​and eigenvector sample values ​​of each electrical device. When the original load signal is a current waveform, the eigenvector sample values ​​are used as the load analysis vector sample values; when the original load signal is instantaneous power, the sparse vector sample values ​​are used as the load analysis vector sample values.

[0125] S205, based on the load analysis vector sample values ​​of each electrical device in the load sample library, generates multiple model parameter matrices for mathematical optimization models.

[0126] Before generating multiple model parameter matrices for mathematical optimization models based on the load analysis vector sample values ​​of each electrical device in the load sample library, the process also includes: obtaining sparse vector sample values ​​and feature vector sample values ​​of different electrical devices in the load sample library.

[0127] The model parameter matrix D is a U×E dimensional matrix, and the column vectors represent the load analysis vectors of the applied electrical equipment in the load sample library, i.e., D=[d1,d2...d E ], where d e This represents the load analysis vector (e = 1, 2...E) corresponding to electrical equipment e in the load sample library. When the original load signal is a current waveform, d e The element in the middle represents the phasor value of the h-th harmonic current (h=1,2,3,5,7,9,11) and U=7, d e It consists of feature vector sample values ​​from the sample library; when the original load signal is instantaneous power, d e The elements in the middle represent the elements of a sparse vector and U = N, d e It consists of sparse vector sample values ​​from the sample library. Since the sample library contains a large number of sparse vectors and feature samples, d e The composition of the model parameter matrix D can be varied, thus generating multiple model parameter matrices D.

[0128] In this embodiment, d e It can be obtained from all samples or from a portion of the samples, forming i kinds of d. e The form (i≥2). The parameter matrix D = [d1, d2...d... E Each column vector in the equation represents any term from the i-th type of parameterized row expression, constructing i... E The model parameter matrix D is given. The original load signal type is either a current waveform or instantaneous power, and the i-th type of d... e The construction approach is the same, but d e The number and meaning of the elements in them are different.

[0129] In one specific embodiment, the number of electrical devices E = 3, d e The number of forms i = 2, that is: each column vector in the model parameter matrix D corresponds to a certain electrical device, and each column vector has two parameter forms to choose from. The number of model parameter matrices D constructed is i. E =8 types. Let p and q represent d respectively. e The two parameter forms, corresponding to the eight model parameter matrices D1 to D8, are as follows:

[0130] D1=[ppp], D2=[ppq], D3=[pqp], D4=[qpp], D5=[pqq], D6=[q pq], D7=[qqp], D8=[qqq].

[0131] In one specific embodiment, the number of electrical devices E = 4, d e The formal quantity i = 2, denoted by p and q respectively for d e There are two parameter forms. Each column vector in the model parameter matrix D corresponds to a specific electrical device, and each column vector has two parameter forms to choose from. Based on this, the constructed model parameter matrix D has 16 elements, corresponding to model parameter matrices D1 to D2. 16 as follows:

[0132] D1=[pppp], D2=[pppq], D3=[ppqp], D4=[pqpp], D5=[qppp], D6=[ppqq], D7=[pqpq], D8=[pqqp], D9=[qppq], D 10 =[pqpq], D 11 =[q qp p], D 12 =[pqqq],D 13 =[qpqq], D 14 =[qqpq], D 15 =[qqqp], D 16 =[qqqq].

[0133] S206. Based on multiple model parameter matrices and load analysis vectors, multiple mathematical optimization models are established, and multiple electrical equipment switching state vectors are obtained by solving the mathematical optimization models.

[0134] This step includes S2061 to S2062.

[0135] S2061, according to different model parameter matrices D k (k=1~i E ), i is established through equation (4) and equation (5) respectively. E A mathematical optimization model.

[0136] min||dD k a k || (4)

[0137]

[0138] Where d is a U×1 dimensional vector, which is the vector composed of the analysis basis of the actual collected load signal, obtained by step S203, and U is the vector length; E×1 dimensional vector a k =[a k (1),a k (2)...a k (e)...a k [E] represents the on / off state of each electrical device, k = 1 ~ i E E represents the total number of electrical devices; model parameter matrix It is a U×E dimensional matrix, and each column is obtained from the load analysis vector corresponding to the electrical equipment e in the load sample library (e=1~E), that is, obtained from step S205.

[0139] In one embodiment, when the original load signal is a current waveform, d, All are the current phasor values ​​of the h-th harmonic (h=1,2,3,5,7,9,11), and when U=7 and h=1, they represent the fundamental current phasor values.

[0140] In another embodiment, when the original load signal is instantaneous power, d = s, The average value is calculated from the sparse vector sample values ​​in step S2041, and U = N.

[0141] S2062 solves multiple mathematical optimization models to obtain multiple on / off state vectors of electrical equipment.

[0142] Optionally, according to k = 1, 2...i E The 0-1 knapsack problem solution algorithm is used sequentially to solve all i. E Solve the mathematical optimization model to obtain i E The switching state vector of a single electrical device a k (k=1~i E ).

[0143] In the specific calculation process, d is the vector composed of the actual collected load signals. The mathematical optimization model is constructed according to the above formulas (4) and (5), and based on d and the corresponding selected i E Model parameter matrix D k Solve separately to obtain i E A vector representing the on / off state of an electrical device (i.e., the vector set {a}) k}, k = 1~2 E ).

[0144] S207, based on the solved multiple electrical equipment switching state vectors, outputs the load scenario identification result and the reconstructed value of the original load signal.

[0145] Specifically, obtain i obtained by solving the multiple mathematical optimization models. E A vector representing the on / off state of each electrical device; where i E The number of mathematical optimization models. Determine i. E The electrical equipment interruption state vector that appears most frequently among the electrical equipment interruption state vectors is taken as the target electrical equipment interruption state vector. Based on the target electrical equipment interruption state vector, the load scenario identification result is used, and the reconstructed values ​​of the target electrical equipment interruption state vector and the original load signal are output.

[0146] Where i is calculated E The switching state vector of a single electrical device a k (k=1~i E If there are identical values, the result that appears most frequently is determined by counting and becomes the on / off state vector of the target electrical equipment.

[0147] In one embodiment, the number of electrical devices E = 3, d e The formal quantity i = 2, corresponding to the selection of i E When calculating the model parameter matrix, the resulting 8 electrical equipment on / off state vectors are {a}. k}(k=1~i E In the electrical equipment on / off state vector a = [a1, a2, a3, a4], the elements a1 to a4 take values ​​of 0 or 1. A value of 0 indicates the electrical equipment is off, and a value of 1 indicates the electrical equipment is on. When the calculated 8 electrical equipment on / off state vectors a include multiple instances of a = [1, 1, 0], and the number of repetitions is the highest, then the target electrical equipment on / off state vector is a = [1, 1, 0].

[0148] In another embodiment, d e Given that the number of forms i = 2 and the number of electrical devices E = 4, select i accordingly. E Taking a model parameter matrix of 16 as an example, it includes the on / off state vectors of 16 electrical devices. k as follows:

[0149] a1 = [1, 1, 0, 0] T a2 = [0,1,0,0] T a3 = [0, 1, 1, 0] T a4 = [1,1,0,0] T a5 = [1,1,0,0] T a6 = [1, 1, 1, 0] T a7 = [1,1,0,0] T a8 = [0, 1, 1, 0] T a9 = [0,1,0,0] Ta 10 =[1,1,0,0] T a 11 =[1,1,0,0] T a 12 =[1,1,0,0] T a 13 =[1,1,1,0] T a 14 =[0,1,1,0] T a 15 =[1,1,0,0] T a 16 =[1,1,0,0] T .

[0150] In this embodiment, [1,1,0,0] T This occurred 9 times, therefore the target electrical equipment's on / off state vector is a = [1,1,0,0]. T That is, devices 1 and 2 are in an "open" state, while devices 3 and 4 are in a "closed" state.

[0151] The reconstructed value of the original load signal is based on The reconstructed value of the original load signal is calculated. Ψ and s are the original load signal reconstruction value, sparse basis, and sparse vector, respectively.

[0152] In Example 1, the switching status of all electrical devices in the NILM was obtained through steps S201 to S207. In this example, load analysis is performed using a mathematical optimization model to obtain load identification results. Simultaneously, during the implementation of the mathematical optimization model, an i... E A mathematical optimization model is used to obtain multiple device on / off state vectors to improve load identification.

[0153] In addition to the embodiments of the present invention, there are two ways to achieve load identification: The first is the traditional identification method, which does not use a mathematical optimization model for load analysis. That is, the original load signal x is compressed and acquired through the CS measurement matrix to obtain the compressed signal y, and then reconstructed to obtain the reconstructed value of the original load signal. According to traditional methods The first method involves traditional load identification to obtain load identification results. The second method uses a single mathematical model, employing a mathematical optimization model with a single model parameter matrix for load analysis. Specifically, in S205, only one model parameter matrix D is constructed, and in S206, only one mathematical optimization model is constructed and a single solution result is determined.

[0154] like Figure 4The diagram shows a comparison of load identification rates for three load identification schemes. The three schemes are the one provided in this embodiment, the traditional method described above, and the single mathematical model method. As shown, the load identification results of this embodiment are more accurate than those of the traditional method and the single mathematical model method. In this embodiment, d... e The following example illustrates the configuration with a quantity of form i = 2, a quantity of electrical equipment E = 4, and a compression ratio M / N = 0.4 to 0.6.

[0155] This invention provides a non-intrusive load monitoring method based on compressed sensing and a mathematical optimization model. First, it proposes an implementation framework for non-intrusive load monitoring based on compressed sensing and a mathematical optimization model. Leveraging the characteristic that sparse vectors under certain sparse bases in CS technology can characterize the feature values ​​of the original load signal, load analysis is achieved using the intermediate signals from the reconstruction process. Second, it proposes a mathematical optimization model for load analysis and a solution approach based on the most frequently occurring optimal result. Third, it proposes a method for feature extraction from sparse vectors. Fourth, it proposes a method for feature extraction from sparse vectors to achieve load analysis. Specifically, CS is applied to solve load data analysis in NILM, transforming load analysis into solving a mathematical optimization model. The essence of the mathematical optimization model is a 0-1 mathematical optimization problem, which is relatively simple to solve and can be solved using traditional artificial intelligence algorithms, 0-1 knapsack problem solving algorithms, etc., to obtain the decision variable 'a'. The most frequently occurring 'a' among the multiple sets of 'a' obtained is taken as the final result of the on / off state of the electrical equipment, and then the state result can be used to determine the decision variable 'd'. e The average value is approximately considered as the result of load decomposition for different electrical devices.

[0156] Example 2

[0157] Figure 5 This paper presents a theoretical block diagram for load analysis without obtaining reconstructed values. The aim is to construct a model parameter matrix from load analysis vector sample values ​​of various electrical devices in a sample library under different device switching states, and then build a mathematical optimization model based on this matrix. The device switching state scheme is determined by combining the mathematical optimization model with the actual acquired load signals, and this determination serves as the load identification result. Figure 5 As shown, the process includes the following steps S501 to S506.

[0158] S501, establish a load sample library based on sparse vector sample values, eigenvector sample values, and load analysis vector sample values.

[0159] S502 generates multiple model parameter matrices for mathematical optimization models based on the load analysis vector sample values ​​of each electrical device in the load sample library.

[0160] S503 uses an M×N dimensional binary sparse measurement matrix to compress and acquire the N×1 dimensional original load signal x to obtain the M×1 dimensional compressed signal y.

[0161] S504, the compressed signal y is reconstructed based on the binary sparse measurement matrix, sparse basis and target reconstruction algorithm to obtain the sparse vector s.

[0162] S505: Based on the sparse vector s and multiple model parameter matrices, multiple mathematical optimization models are established, and multiple electrical equipment on / off state vectors are obtained by solving the mathematical optimization models.

[0163] S506 outputs the most frequently occurring equipment on / off state scheme as the load scenario identification result, and also outputs the reconstructed value of the original load signal. in, Ψ and s are the original load signal reconstruction value, sparse basis, and sparse vector, respectively.

[0164] Example 3

[0165] This invention also provides a schematic diagram of the structure of an electronic device. For example... Figure 6 As shown, the electronic device 6 of this embodiment includes: a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and executable on the processor 60. When the processor 60 executes the computer program 62, it implements the steps in the various embodiments of the non-intrusive load monitoring method based on compressed sensing and mathematical optimization models described above. Alternatively, when the processor 60 executes the computer program 62, it implements the functions of each module / unit in the various device embodiments described above.

[0166] For example, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 62 in the electronic device 6.

[0167] The electronic device 6 can be a desktop computer, laptop, handheld computer, or cloud server, etc. The electronic device 6 may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 6 This is merely an example of electronic device 6 and does not constitute a limitation on electronic device 6. It may include more or fewer components than shown, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0168] The processor 60 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0169] The memory 61 can be an internal storage unit of the electronic device 6, such as a hard disk or memory. The memory 61 can also be an external storage device of the electronic device 6, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 61 can include both internal and external storage units of the electronic device 6. The memory 61 is used to store the computer program and other programs and data required by the electronic device. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0170] Example 4

[0171] This invention also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the steps in various embodiments of the non-intrusive load monitoring method based on compressed sensing and mathematical optimization models, for example... Figure 2 Steps S202 to S207 are shown.

[0172] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0173] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A non-intrusive load monitoring method based on compressed sensing and mathematical optimization models, characterized in that, include: Set the original load signal acquisition parameters and generate a binary sparse measurement matrix. Compress the original load signal to obtain a compressed signal. Based on the binary sparse measurement matrix, and the sparse basis and target reconstruction algorithm, the compressed signal is reconstructed to obtain a sparse vector; the load analysis vector type is determined according to the original load type, and a load analysis vector is formed based on the sparse vector; a load sample library is established according to the sparse vector sample values, feature vector sample values, and load analysis vector sample values; multiple model parameter matrices for mathematical optimization models are generated based on the load analysis vector sample values ​​of each electrical device in the load sample library; multiple mathematical optimization models are established based on the multiple model parameter matrices and the load analysis vector, and multiple electrical device switching state vectors are obtained by solving the mathematical optimization models; based on the solved multiple electrical device switching state vectors, the load scene identification result is output, and the reconstructed value of the original load signal is output.

2. The non-intrusive load monitoring method based on compressed sensing and mathematical optimization model according to claim 1, characterized in that, The process of setting the original load signal acquisition parameters and generating a binary sparse measurement matrix, and then compressing the original load signal to obtain a compressed signal includes: Set the type of the original load signal to either current waveform or instantaneous power; Set the data collection time length to 1. s The length of the original load signal is N =2048 and compression ratio of 0.4~0.7; The measurement matrix size is determined based on the compression ratio and the length of the original load signal, and a zero matrix is ​​generated based on the measurement matrix size. A predetermined number of elements are randomly selected from each column of the zero matrix and assigned the value 1 to form the generated binary sparse measurement matrix; wherein the predetermined number is less than the total number of elements in each column. according to Acquire compressed signal ,in, The binary sparse measurement matrix is... This refers to the original load signal.

3. The non-intrusive load monitoring method based on compressed sensing and mathematical optimization model according to claim 2, characterized in that, The step of determining the load analysis vector type based on the original load type and forming the load analysis vector based on the sparse vector includes: When the original load signal is instantaneous power, the sparse vector obtained from reconstruction is used as the load analysis vector; When the original load signal is a current waveform, the fundamental current phasor value and the first current phasor value are obtained from the sparse vector. The phasor values ​​of the second harmonic currents are used to form a 7-dimensional eigenvalue vector, which serves as the load analysis vector; among them, =2,3,5,7,9,11.

4. The non-intrusive load monitoring method based on compressed sensing and mathematical optimization model according to claim 3, characterized in that, The fundamental current phasor value and the first obtained from the sparse vector. The phasor values ​​of the second harmonic current are used to form a 7-dimensional eigenvalue vector, including: search N 2D sparse vector Extreme values ​​and their position labels Among them, the position number ki satisfy and ; , , They are respectively N 2D sparse vector The Middle The element, the first The element, the first The value of each element, ; Search for the satisfied one by one Location label And the filtered Add to collection ;in, Indicates the fundamental wave or the first Spectral line labels of subharmonics; set There are 7 elements in total. =1,2,3,5,7,9,11 =1 indicates the spectral line number of the fundamental wave; where, Where T is the frequency of the power system, and T is the acquisition time; according to =1,2,3,5,7,9,11, search sequentially The larger element among the preceding and following elements is labeled. Among them, when hour, ;on the contrary ; pass Calculate the correction amount α and intermediate quantity β ; pass Calculate the first Amplitude of subharmonic current and phase ; in, =1 indicates the fundamental frequency. Representing complex numbers Complex angles; The current amplitudes are the fundamental frequency and each harmonic. For current harmonic phasors; according to A 7-dimensional eigenvalue vector is formed.

5. The method according to claim 4, characterized in that, The plurality of mathematical optimization models include: in, For the first k A model parameter matrix; d for U A ×1 dimensional vector is a load analysis vector formed based on sparse vectors; U The vector length; when the original load signal is a current waveform. U= 7; When the original load signal is instantaneous power, U=N ; for E A 1-dimensional vector This indicates the on / off status of each electrical device; E This represents the total number of electrical devices. .

6. The method according to claim 5, characterized in that, The process involves generating multiple model parameter matrices for mathematical optimization models based on the load analysis vector sample values ​​of each electrical device in the load sample library, including: Based on the load analysis vector sample values ​​of each electrical device in the load sample library, determine the various parameter forms of each column vector of the model parameter matrix; Generate based on the different parameter combinations of each column vector Model parameter matrix ; ; The number of various parameter forms of the column vector.

7. The method according to any one of claims 1 to 6, characterized in that, The process of establishing a load sample library based on sparse vector sample values, eigenvector sample values, and load analysis vector sample values ​​includes: The sparse vector of each original load sample value is obtained by sparse representation of the original load sample values, and then it is put into the load sample library as a sparse vector sample value. Obtain the feature value vector of the original load sample values ​​of all individual electrical devices, form the feature vector sample values, and put them into the load sample library; Based on sparse vector sample values ​​and feature vector sample values, load analysis vector sample values ​​are generated and placed into the load sample library.

8. The method according to claim 1, characterized in that, The step of outputting load scenario identification results and reconstructing values ​​of the original load signals based on the solved multiple electrical equipment disconnection state vectors includes: Obtain the results of solving the multiple mathematical optimization models. A vector representing the on / off state of each electrical device; where... The number of mathematical optimization models; Sure The electrical equipment disconnection state vector that appears most frequently among the electrical equipment disconnection state vectors is taken as the target electrical equipment disconnection state vector, and the load scenario identification result is output based on the target electrical equipment disconnection state vector. The reconstructed value of the original load signal is integrated based on the sparse vector output. ;in, , , The original load signal reconstructed values, sparse basis, and sparse vector are given.

9. The non-intrusive load monitoring method based on compressed sensing and mathematical optimization model according to claim 1, characterized in that, The target reconstruction algorithm is a gradient tracking algorithm or a convex optimization algorithm; the sparse basis is a discrete Fourier transform basis.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the non-intrusive load monitoring method based on compressed sensing and mathematical optimization model as described in any one of claims 1 to 9.

11. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the non-intrusive load monitoring method based on compressed sensing and mathematical optimization model as described in any one of claims 1 to 9.

Images