A non-intrusive power load identification method and device

Abstract

The application relates to a non-intrusive power load identification method and device, which comprises the following steps: obtaining a total power load time domain signal of a historical identification period similar to a total power load time domain signal of a current identification period of an electric energy user, and power load time domain signals of various electric equipment corresponding to the total power load time domain signal; determining power load time domain signals of various electric equipment of the current identification period of the electric energy user according to the power load time domain signals of various electric equipment corresponding to the total power load time domain signal of the historical identification period. The non-intrusive power load identification method and device provided by the application can realize power load self-identification in the case of historical data and power load cross identification in the case of no historical data, and can reduce data acquisition and transmission cost, improve calculation efficiency and accuracy, and improve privacy protection.

Description

Technical Field

[0001] The present invention relates to the field of power load monitoring and load management, and in particular to a non-invasive power load identification method and device. Background Art

[0002] As load-side energy management continues to gain increasing attention both domestically and internationally, non-intrusive load identification technology is gaining increasing attention in both research and application. Non-intrusive load monitoring is defined as a technique designed to decompose the overall power signal of a home or building to derive power usage information at the device level for each electrical device. Device-level power usage information for various loads plays a vital role in smart grid and smart energy applications, including daily energy management, demand response programs, related commercial activities, and urban management.

[0003] Currently, some smart electrical devices are equipped with sensors that measure and transmit electrical signals for load monitoring. However, installing metering equipment on all electrical appliances in a building would be a significant investment. Therefore, a new method for non-invasive power load identification is needed. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a non-intrusive power load identification method and device, which can perform non-intrusive power load identification by only requiring low-frequency sampling data at the level of ordinary smart meters, thereby reducing data collection and transmission costs and improving computing efficiency.

[0005] The purpose of the present invention is achieved by adopting the following technical solutions:

[0006] The present invention provides a non-intrusive power load identification method, wherein the method comprises:

[0007] Obtaining a total power load time domain signal of a historical identification period similar to the total power load time domain signal of the current identification period of the power user, and corresponding power load time domain signals of various types of electrical equipment;

[0008] The power load time domain signals of various types of power consuming equipment in the current identification period of the power user are determined according to the power load time domain signals of various types of power consuming equipment corresponding to the total power load time domain signals of the historical identification period.

[0009] Preferably, the acquiring of a total power load time domain signal of a historical identification period similar to a total power load time domain signal of a current identification period of the power user comprises:

[0010] Obtaining frequency domain signals corresponding to the total power load time domain signals of each historical identification period of the power user and frequency domain signals corresponding to the total power load time domain signals of the current identification period;

[0011] Obtaining similarities between frequency domain signals corresponding to the total power load time domain signals of the current identification period of the electric energy user and frequency domain signals corresponding to the total power load time domain signals of each historical identification period, and adding the total power load time domain signals of the corresponding historical identification period whose similarity is less than a first preset value to the similarity set;

[0012] Obtain the similarity between the total power load time domain signal of the current identification period of the electric energy user and the total power load time domain signals of each historical identification period in the similarity set, and use the total power load time domain signal of the corresponding historical identification period whose similarity is less than a second preset value as the total power load time domain signal of the historical identification period similar to the total power load time domain signal of the current identification period of the electric energy user.

[0013] Furthermore, the obtaining of the frequency domain signal corresponding to the total power load time domain signal of each historical identification period of the power user and the frequency domain signal corresponding to the total power load time domain signal of the current identification period includes:

[0014] The frequency domain signal X corresponding to the kth sampling point in the total power load time domain signal of the electric energy user in the i-th historical identification period is determined as follows: i (k):

[0015]

[0016] The frequency domain signal Y corresponding to the kth sampling point in the total power load time domain signal of the current identification period of the electric energy user is determined by the following formula: r (k):

[0017]

[0018] In the above formula, x i (n) is the time domain signal corresponding to the nth sampling point in the total power load time domain signal of the electric energy user in the i-th historical identification period, y r (n) is the time domain signal corresponding to the nth sampling point in the total power load time domain signal in the current identification cycle, j is the imaginary part, k,n∈[0,N-1], N is the total number of sampling points in the current identification cycle and the historical identification cycle, i∈[1,T], T is the total number of total power load time domain signals in the historical identification cycle.

[0019] Furthermore, the obtaining of the similarity between the frequency domain signal corresponding to the total power load time domain signal of the current identification period of the electric energy user and the frequency domain signal corresponding to the total power load time domain signal of each historical identification period includes:

[0020] The similarity between the frequency domain signal corresponding to the total power load time domain signal of the current identification period of the electric energy user and the frequency domain signal corresponding to the total power load time domain signal of the i-th historical identification period is determined by the following formula: ir ||:

[0021]

[0022] Where, X i =[X i (0),X i (1),…,X i (k),…,X i (N-1)] N , X i is the frequency domain signal corresponding to the total power load time domain signal of the i-th historical identification period, X i (k) is the frequency domain signal corresponding to the kth sampling point in the total power load time domain signal of the i-th historical identification period of the electric energy user, k∈[0,N-1], Y r =[Y r (0),Y r (1),…,Y r (k),…,Y r (N-1)] N , Y r The frequency domain signal corresponding to the total power load time domain signal of the current identification period, Y r (k) is the frequency domain signal corresponding to the kth sampling point in the total power load time domain signal of the current identification period of the electric energy user, and N is the total number of sampling points in the current identification period and the historical identification period.

[0023] Furthermore, the obtaining of the similarity between the total power load time domain signal of the current identification period of the electric energy user and the total power load time domain signals of each historical identification period in the similarity set includes:

[0024] The similarity between the total power load time domain signal of the current identification period of the power user and the total power load time domain signal of the qth historical identification period in the similarity set is determined by the following formula: qr ||:

[0025]

[0026] Where x q =[x q (0),x q (1),…,x q (n),…,x q (N-1)] N , x q is the total power load time domain signal of the qth historical identification period in the similarity set, yr =[y r (0),y r (1),…,y r (n),…,y r (N-1)] N ,y r is the total power load time domain signal of the current identification period, x q (n) is the time domain signal corresponding to the nth sampling point in the power load time domain signal of the qth historical identification period in the similarity set, y r (n) is the time domain signal corresponding to the nth sampling point in the total power load time domain signal in the current identification cycle, q∈[1,L1], L1 is the total number of historical identification cycles in the similarity set.

[0027] Preferably, the determining of the power load time domain signals of various types of electrical equipment in the current identification period of the electric energy user based on the power load time domain signals of various types of electrical equipment corresponding to the total power load time domain signals of the historical identification period includes:

[0028] Determine the power load time domain signals of various electrical equipment in the current identification period of the power user according to the following formula:

[0029]

[0030] Where y mr (n) is the power load time domain signal of the mth device at the nth sampling point in the current identification period of the power user, p∈[1,L2], L2 is the total number of total power load time domain signals in historical identification periods similar to the total power load time domain signal of the current identification period of the power user, x mp (n) represents the power load time domain signal of the mth device at the nth sampling point of the pth historical identification cycle in the historical identification cycle similar to the total power load time domain signal of the current identification cycle of the power user.

[0031] The present invention also provides a non-intrusive power load identification device, the improvement of which is that the device comprises:

[0032] An acquisition module is used to acquire a total power load time domain signal of a historical identification period similar to the total power load time domain signal of the current identification period of the power user, and the corresponding power load time domain signals of various types of electrical equipment;

[0033] The determination module is used to determine the power load time domain signals of various types of power equipment in the current identification period of the power user based on the power load time domain signals of various types of power equipment corresponding to the total power load time domain signals of the historical identification period.

[0034] Preferably, the acquisition module includes:

[0035] The first acquisition unit is used to acquire the frequency domain signal corresponding to the total power load time domain signal of each historical identification period of the electric energy user and the frequency domain signal corresponding to the total power load time domain signal of the current identification period;

[0036] a second acquisition unit, configured to acquire a similarity between a frequency domain signal corresponding to a total power load time domain signal of a current identification period of the electric energy user and a frequency domain signal corresponding to a total power load time domain signal of each historical identification period, and add the total power load time domain signal of the corresponding historical identification period whose similarity is less than a first preset value to a similarity set;

[0037] The third acquisition unit is used to obtain the similarity between the total power load time domain signal of the current identification period of the electric energy user and the total power load time domain signal of each historical identification period in the similarity set, and the total power load time domain signal of the corresponding historical identification period whose similarity is less than the second preset value is used as the total power load time domain signal of the historical identification period similar to the total power load time domain signal of the current identification period of the electric energy user.

[0038] Compared with the closest prior art, the present invention has the following beneficial effects:

[0039] The present invention proposes a non-invasive power load identification method and device. The present invention improves the similar day algorithm, which was originally only used for baseline load forecasting, and introduces it into the scenario of non-invasive power load identification for the first time. The present invention also designs the screening conditions and sequence of frequency domain and time domain features, thereby improving the computational efficiency and accuracy without reducing the accuracy of non-invasive charge load decomposition identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A flow chart of a non-intrusive power load identification method provided by the present invention;

[0041] Figure 2 This is a structural schematic diagram of a non-intrusive power load identification device provided by the present invention. DETAILED DESCRIPTION

[0042] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0044] The present invention provides a non-intrusive power load identification method, such as Figure 1 As shown, the method includes:

[0045] 101. Obtain a total power load time domain signal of a historical identification period similar to the total power load time domain signal of the current identification period of the power user, and corresponding power load time domain signals of various types of electrical equipment;

[0046] 102. Determine the power load time domain signals of various types of power consuming equipment in the current identification period of the power user based on the power load time domain signals of various types of power consuming equipment corresponding to the total power load time domain signals of the historical identification period;

[0047] Determine the power load time domain signals of various electrical equipment in the current identification period of the power user according to the following formula:

[0048]

[0049] Where y mr (n) is the power load time domain signal of the mth device at the nth sampling point in the current identification period of the power user, p∈[1,L2], L2 is the total number of total power load time domain signals in historical identification periods similar to the total power load time domain signal of the current identification period of the power user, x mp (n) represents the power load time domain signal of the mth device at the nth sampling point of the pth historical identification cycle in the historical identification cycle similar to the total power load time domain signal of the current identification cycle of the power user.

[0050] Specifically, step 101 includes:

[0051] 101.1. Obtain frequency domain signals corresponding to the total power load time domain signals of each historical identification period of the power user and frequency domain signals corresponding to the total power load time domain signals of the current identification period;

[0052] The frequency domain signal X corresponding to the kth sampling point in the total power load time domain signal of the electric energy user in the i-th historical identification period is determined as follows: i (k):

[0053]

[0054] The frequency domain signal Y corresponding to the kth sampling point in the total power load time domain signal of the current identification period of the electric energy user is determined by the following formula: r (k):

[0055]

[0056] In the above formula, x i(n) is the time domain signal corresponding to the nth sampling point in the total power load time domain signal of the i-th historical identification period of the electric energy user, y r (n) is the time domain signal corresponding to the nth sampling point in the total power load time domain signal in the current identification cycle, j is the imaginary part, k,n∈[0,N-1], N is the total number of sampling points in the current identification cycle and the historical identification cycle, i∈[1,T], T is the total number of total power load time domain signals in the historical identification cycle.

[0057] 101.2. Obtain similarity between a frequency domain signal corresponding to a total power load time domain signal of a current identification period of the electric energy user and a frequency domain signal corresponding to a total power load time domain signal of each historical identification period, and add the total power load time domain signal of the corresponding historical identification period having a similarity less than a first preset value to a similarity set;

[0058] The similarity between the frequency domain signal corresponding to the total power load time domain signal of the current identification period of the electric energy user and the frequency domain signal corresponding to the total power load time domain signal of the i-th historical identification period is determined by the following formula: ir ||:

[0059]

[0060] Where, X i =[X i (0),X i (1),…,X i (k),…,X i (N-1)] N , X i is the frequency domain signal corresponding to the total power load time domain signal of the i-th historical identification period, X i (k) is the frequency domain signal corresponding to the kth sampling point in the total power load time domain signal of the i-th historical identification period of the electric energy user, k∈[0,N-1], Y r =[Y r (0),Y r (1),…,Y r (k),…,Y r (N-1)] N , Y r The frequency domain signal corresponding to the total power load time domain signal of the current identification period, Y r (k) is the frequency domain signal corresponding to the kth sampling point in the total power load time domain signal of the current identification period of the electric energy user, N is the total number of sampling points in the current identification period and the historical identification period, i∈[1,T], T is the total number of total power load time domain signals in the historical identification period.

[0061] 101.3 Obtaining a similarity between a total power load time domain signal of a current identification period of the electric energy user and a total power load time domain signal of each historical identification period in the similarity set, and determining a total power load time domain signal of a corresponding historical identification period having a similarity less than a second preset value as a total power load time domain signal of a historical identification period similar to the total power load time domain signal of the current identification period of the electric energy user;

[0062] The similarity between the total power load time domain signal of the current identification period of the power user and the total power load time domain signal of the qth historical identification period in the similarity set is determined by the following formula: qr ||:

[0063]

[0064] Where x q =[x q (0),x q (1),…,x q (n),…,x q (N-1)] N , x q is the total power load time domain signal of the qth historical identification period in the similarity set, y r =[y r (0),y r (1),…,y r (n),…,y r (N-1)] N ,y r is the total power load time domain signal of the current identification period, x q (n) is the time domain signal corresponding to the nth sampling point in the power load time domain signal of the qth historical identification period in the similarity set, y r (n) is the time domain signal corresponding to the nth sampling point in the total power load time domain signal in the current identification cycle, q∈[1,L1], L1 is the total number of total power load time domain signals in the historical identification cycle in the similarity set.

[0065] In the embodiment provided by the present invention, during the execution of step 101, the data source for obtaining the total power load time domain signal of a historical identification period similar to the total power load time domain signal of the current identification period of the power user and the corresponding power load time domain signals of various types of power consumption equipment is preferentially selected from the total power load signal data of the historical identification period of the power user itself and the corresponding power load time domain signals of various types of power consumption equipment, and secondly, the total power load signal data of the historical identification period of power users similar to the power user and the corresponding power load time domain signals of various types of power consumption equipment;

[0066] The process of determining electric energy users is similar to that of electric energy users and is as follows:

[0067] Step 1): Based on the existing user data set with historical data on the power load of various types of electrical equipment, a user identification database is established. When establishing the database, priority should be given to users located in the same area as the target users, because these users often have stronger external conditions similarity (including environmental, weather, holidays, etc.) and stronger user power consumption behavior similarity with the target user load to be decomposed.

[0068] Step 2): The key to cross-prediction using the user identification database is to select households most similar to the target user to improve cross-prediction accuracy. The method for selecting similar users is as follows: First, load cross-identification is performed between users in the user identification database who have historical power load data for various types of electrical devices. The cross-identification accuracy result is regressed using the similarity of external conditions between each group of users as the independent variable.

[0069] The main purposes of regression are twofold: A. to identify the most important correlated factors among the user's own characteristics that affect the accuracy of cross-identification; B. to propose a similarity index to quantify the similarity between two users and use this similarity index to filter out the users in the user identification database who are most similar to the target user.

[0070] The cross-identification accuracy prediction value was selected as the dependent variable Y, and six independent variables X1-X6 (or "predictors") were selected, representing different user characteristics under external conditions. Multiple regression analysis was used to assess the impact of each variable on the prediction accuracy. The selected independent variables are described as follows: X1 is the age of the house, X2 is the total area of ​​the house, X3 is the number of floors in the unit, X4 is the total number of devices, X5 is the number of devices shared by two users, and X6 is the average user load. X1-X6 are calculated as follows:

[0071]

[0072]

[0073] Among them, P and Q are two different users in the user identification database, represents the maximum house age among h users, Ag represents the minimum house age among h users. P and Ag Q Represents the house age of users P and Q respectively, Sf P and Sf QDenote the house areas of users P and Q, respectively. Similarly, X3-X6 can be calculated. Let the similarity feature vector be X = (X1, X2, X3, X4, X5, X6). The greater the similarity between the external conditions of different users, the closer the elements in the vector are to 0. The parameters in the regression formula Y(X) are derived based on the characteristic variables of the similarity between each user in the user identification database. The matching user in the user identification database that is most similar to the target user is obtained based on the characteristic variables of the similarity between the target user to be identified and each user in the user identification database. The user in the user identification database with the highest cross-identification accuracy is considered the matching user that is most similar to the target user. Regression results on an actual data set show that factors X2 and X6 have a significant impact on cross-identification accuracy. The most significant factor influencing similarity is the average load per user, X6. X2 and X6 pass the t-test and F-test, respectively, with a confidence coefficient of 99%. Therefore, based on factors X2 and X6, the similarity index between users can be calculated and used as a reference for selecting similar users: On the one hand, when selecting similar users in the user identification database for the target user to be identified, the first consideration is to select houses with similar total average loads. In addition, the total area of ​​the house will also affect the results. On the other hand, the number of devices in common between two users, the number of floors, the total number of devices, and the age of the house are relatively unimportant in determining the similarity of user electricity usage behavior. In summary, ranked by their importance level, the two most important predictive factors for user similarity in cross-identification are average load and total area. When screening similar users for cross-prediction, only information from these two factors is needed.

[0074] Step 3): To help identify the households most similar to the verified user, the regression formula is used to quantify the similarity between users. Once the regression formula parameters are obtained, the degree of similarity between groups of users, i.e., the load cross-identification accuracy of any two users, can be obtained. Therefore, the result of this formula can be defined as the similarity index of the two houses. A high index indicates good cross-prediction results between the two users, with a high degree of similarity in load composition and usage. Conversely, a low index indicates significant differences in the electricity usage behavior of the two users, making them unsuitable for cross-identification. Finally, the user in the user identification database with the highest similarity index Y is selected as the most similar matching user to the target user for cross-identification, thus obtaining the load identification results for users without historical data.

[0075] Based on the same concept of the above control method, the present invention also provides a non-intrusive power load identification device, such as Figure 2 As shown, the device includes:

[0076] An acquisition module is used to acquire a total power load time domain signal of a historical identification period similar to the total power load time domain signal of the current identification period of the power user, and the corresponding power load time domain signals of various types of electrical equipment;

[0077] The determination module is used to determine the power load time domain signals of various types of power equipment in the current identification period of the power user based on the power load time domain signals of various types of power equipment corresponding to the total power load time domain signals of the historical identification period.

[0078] Preferably, the acquisition module includes:

[0079] The first acquisition unit is used to acquire the frequency domain signal corresponding to the total power load time domain signal of each historical identification period of the electric energy user and the frequency domain signal corresponding to the total power load time domain signal of the current identification period;

[0080] a second acquisition unit, configured to acquire a similarity between a frequency domain signal corresponding to a total power load time domain signal of a current identification period of the electric energy user and a frequency domain signal corresponding to a total power load time domain signal of each historical identification period, and add the total power load time domain signal of the corresponding historical identification period whose similarity is less than a first preset value to a similarity set;

[0081] The third acquisition unit is used to obtain the similarity between the total power load time domain signal of the current identification period of the electric energy user and the total power load time domain signal of each historical identification period in the similarity set, and the total power load time domain signal of the corresponding historical identification period whose similarity is less than the second preset value is used as the total power load time domain signal of the historical identification period similar to the total power load time domain signal of the current identification period of the electric energy user.

[0082] Furthermore, the first acquiring unit includes:

[0083] The first determining subunit is used to determine the frequency domain signal X corresponding to the kth sampling point in the total power load time domain signal of the electric energy user in the i-th historical identification period according to the following formula: i (k):

[0084]

[0085] The second determining subunit is used to determine the frequency domain signal Y corresponding to the kth sampling point in the total power load time domain signal of the current identification period of the power user according to the following formula: r (k):

[0086]

[0087] In the above formula, x i (n) is the time domain signal corresponding to the nth sampling point in the total power load time domain signal of the electric energy user in the i-th historical identification period, y r(n) is the time domain signal corresponding to the nth sampling point in the total power load time domain signal in the current identification cycle, j is the imaginary part, k,n∈[0,N-1], N is the total number of sampling points in the current identification cycle and the historical identification cycle, i∈[1,T], T is the total number of total power load time domain signals in the historical identification cycle.

[0088] Furthermore, the second acquiring unit includes:

[0089] The third determining subunit is used to determine the similarity between the frequency domain signal corresponding to the total power load time domain signal of the current identification period of the power user and the frequency domain signal corresponding to the total power load time domain signal of the i-th historical identification period according to the following formula || ef ir ||:

[0090]

[0091] Where, X i =[X i (0),X i (1),…,X i (k),…,X i (N-1)] N , X i is the frequency domain signal corresponding to the total power load time domain signal of the i-th historical identification period, X i (k) is the frequency domain signal corresponding to the kth sampling point in the total power load time domain signal of the i-th historical identification period of the electric energy user, k∈[0,N-1], Y r =[Y r (0),Y r (1),…,Y r (k),…,Y r (N-1)] N , Y r The frequency domain signal corresponding to the total power load time domain signal of the current identification period, Y r (k) is the frequency domain signal corresponding to the kth sampling point in the total power load time domain signal of the current identification period of the electric energy user, and N is the total number of sampling points in the current identification period and the historical identification period.

[0092] Furthermore, the third obtaining unit includes:

[0093] The fourth determining subunit is used to determine the similarity between the total power load time domain signal of the current identification period of the power user and the total power load time domain signal of the qth historical identification period in the similarity set according to the following formula || e qr ||:

[0094]

[0095] Where xq =[x q (0),x q (1),…,x q (n),…,x q (N-1)] N , x q is the total power load time domain signal of the qth historical identification period in the similarity set, y r =[y r (0),y r (1),…,y r (n),…,y r (N-1)] N ,y r is the total power load time domain signal of the current identification period, x q (n) is the time domain signal corresponding to the nth sampling point in the power load time domain signal of the qth historical identification period in the similarity set, y r (n) is the time domain signal corresponding to the nth sampling point in the total power load time domain signal in the current identification cycle.

[0096] Preferably, the determining module includes:

[0097] The fifth determining subunit is used to determine the power load time domain signals of various types of electrical equipment in the current identification period of the power user according to the following formula:

[0098]

[0099] Where y mr (n) is the power load time domain signal of the mth device at the nth sampling point in the current identification period of the power user, p∈[1,L2], L2 is the total number of total power load time domain signals in historical identification periods similar to the total power load time domain signal of the current identification period of the power user, x mp (n) represents the power load time domain signal of the mth device at the nth sampling point of the pth historical identification cycle in the historical identification cycle similar to the total power load time domain signal of the current identification cycle of the power user.

[0100] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0101] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0102] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A non-intrusive power load identification method, characterized in that: The method comprises: Obtaining a total power load time domain signal of a historical identification period similar to the total power load time domain signal of the current identification period of the power user, and corresponding power load time domain signals of various types of electrical equipment; Determine the power load time domain signals of various types of electrical equipment in the current identification period of the electric energy user based on the power load time domain signals of various types of electrical equipment corresponding to the total power load time domain signals of the historical identification period; The acquiring of a total power load time domain signal of a historical identification period similar to a total power load time domain signal of a current identification period of the power user includes: Obtaining frequency domain signals corresponding to the total power load time domain signals of each historical identification period of the power user and frequency domain signals corresponding to the total power load time domain signals of the current identification period; Obtaining similarities between frequency domain signals corresponding to the total power load time domain signals of the current identification period of the electric energy user and frequency domain signals corresponding to the total power load time domain signals of each historical identification period, and adding the total power load time domain signals of the corresponding historical identification period whose similarity is less than a first preset value to the similarity set; Obtain the similarity between the total power load time domain signal of the current identification period of the electric energy user and the total power load time domain signals of each historical identification period in the similarity set, and use the total power load time domain signal of the corresponding historical identification period whose similarity is less than a second preset value as the total power load time domain signal of the historical identification period similar to the total power load time domain signal of the current identification period of the electric energy user.

2. The method according to claim 1, wherein The obtaining of the frequency domain signal corresponding to the total power load time domain signal of each historical identification period of the power user and the frequency domain signal corresponding to the total power load time domain signal of the current identification period includes: The frequency domain signal X corresponding to the kth sampling point in the total power load time domain signal of the electric energy user in the i-th historical identification period is determined as follows: i (k): The frequency domain signal Y corresponding to the kth sampling point in the total power load time domain signal of the current identification period of the electric energy user is determined by the following formula: r (k): In the above formula, x i (n) is the time domain signal corresponding to the nth sampling point in the total power load time domain signal of the i-th historical identification period of the electric energy user, y r (n) is the time domain signal corresponding to the nth sampling point in the total power load time domain signal in the current identification cycle, j is the imaginary part, k,n∈[0,N-1], N is the total number of sampling points in the current identification cycle and the historical identification cycle, i∈[1,T], T is the total number of total power load time domain signals in the historical identification cycle.

3. The method according to claim 1, wherein The obtaining of the similarity between the frequency domain signal corresponding to the total power load time domain signal of the current identification period of the electric energy user and the frequency domain signal corresponding to the total power load time domain signal of each historical identification period includes: The similarity between the frequency domain signal corresponding to the total power load time domain signal of the current identification period of the electric energy user and the frequency domain signal corresponding to the total power load time domain signal of the i-th historical identification period is determined by the following formula: ir ||: Where, X i =[X i (0),X i (1),…,X i (k),…,X i (N-1)] N , X i is the frequency domain signal corresponding to the total power load time domain signal of the i-th historical identification period, X i (k) is the frequency domain signal corresponding to the kth sampling point in the total power load time domain signal of the i-th historical identification period of the electric energy user, k∈[0,N-1], Y r =[Y r (0),Y r (1),…,Y r (k),…,Y r (N-1)] N , Y r The frequency domain signal corresponding to the total power load time domain signal of the current identification period, Y r (k) is the frequency domain signal corresponding to the kth sampling point in the total power load time domain signal of the current identification period of the electric energy user, and N is the total number of sampling points in the current identification period and the historical identification period.

4. The method according to claim 1, wherein The obtaining of the similarity between the total power load time domain signal of the current identification period of the electric energy user and the total power load time domain signal of each historical identification period in the similarity set includes: The similarity between the total power load time domain signal of the current identification period of the power user and the total power load time domain signal of the qth historical identification period in the similarity set is determined by the following formula: qr ||: Where x q =[x q (0),x q (1),…,x q (n),…,x q (N-1)] N , x q is the total power load time domain signal of the qth historical identification period in the similarity set, y r =[y r (0),y r (1),…,y r (n),…,y r (N-1)] N ,y r is the total power load time domain signal of the current identification period, x q (n) is the time domain signal corresponding to the nth sampling point in the power load time domain signal of the qth historical identification period in the similarity set, y r (n) is the time domain signal corresponding to the nth sampling point in the total power load time domain signal in the current identification cycle, q∈[1,L1], L1 is the total number of historical identification cycles in the similarity set.

5. The method according to claim 1, wherein The determining of the power load time domain signals of various types of power consuming equipment in the current identification period of the power user according to the power load time domain signals of various types of power consuming equipment corresponding to the total power load time domain signals of the historical identification period includes: Determine the power load time domain signals of various electrical equipment in the current identification period of the power user according to the following formula: Where y mr (n) is the power load time domain signal of the mth device at the nth sampling point in the current identification period of the power user, p∈[1,L2], L2 is the total number of total power load time domain signals in historical identification periods similar to the total power load time domain signal of the current identification period of the power user, x mp (n) represents the power load time domain signal of the mth device at the nth sampling point of the pth historical identification cycle in the historical identification cycle similar to the total power load time domain signal of the current identification cycle of the power user.

6. A non-intrusive power load identification device, characterized in that: The device comprises: An acquisition module is used to acquire a total power load time domain signal of a historical identification period similar to the total power load time domain signal of the current identification period of the power user, and the corresponding power load time domain signals of various types of electrical equipment; The determination module is used to determine the power load time domain signals of various types of power equipment in the current identification period of the power user based on the power load time domain signals of various types of power equipment corresponding to the total power load time domain signals of the historical identification period. The acquisition module includes: The first acquisition unit is used to acquire the frequency domain signal corresponding to the total power load time domain signal of each historical identification period of the electric energy user and the frequency domain signal corresponding to the total power load time domain signal of the current identification period; a second acquisition unit, configured to acquire a similarity between a frequency domain signal corresponding to a total power load time domain signal of a current identification period of the electric energy user and a frequency domain signal corresponding to a total power load time domain signal of each historical identification period, and add the total power load time domain signal of the corresponding historical identification period whose similarity is less than a first preset value to a similarity set; The third acquisition unit is used to obtain the similarity between the total power load time domain signal of the current identification period of the electric energy user and the total power load time domain signal of each historical identification period in the similarity set, and the total power load time domain signal of the corresponding historical identification period whose similarity is less than the second preset value is used as the total power load time domain signal of the historical identification period similar to the total power load time domain signal of the current identification period of the electric energy user.

Images