A system and method for monitoring abnormal power consumption based on topological structure
By building a topology structure for household variation relationships and calculating line loss and voltage volatility, the problem of inaccurate monitoring of electricity consumption abnormalities in the existing technology is solved, and more efficient identification and monitoring of electricity consumption abnormalities is achieved.
Patent Information
- Application Number
- CN202311836317.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-28
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2043-12-28
AI Technical Summary
The existing power consumption abnormality monitoring methods fail to make full use of user-variable relationship topological structure information, resulting in inaccurate monitoring.
By obtaining user electricity consumption data, transformer data and geographical location, building a topology of household variation relationships, calculating line loss and voltage volatility, dividing potential electricity consumption abnormalities and marking abnormal nodes, improving the accuracy of electricity consumption abnormalities monitoring.
It improves the accuracy of power consumption abnormality monitoring and the timeliness of building topological structures, can more effectively identify power consumption abnormalities and reduce the rate of misjudgment.
Smart Images

Figure CN117874459B_ABST
Abstract
Description
Background Art
[0002] Abnormal power consumption is the main cause of non-technical losses in the distribution network, which directly causes huge economic losses to the power grid and endangers the smooth operation of the power grid. At the same time, with the gradual increase in the number of power grid equipment, users in the low-voltage distribution network are frequently expanded, modified, and connected, which greatly increases the pressure of identifying the topological structure of the household-transformer relationship.
[0003] For example, a Chinese patent with authorization announcement number CN109164319B discloses a method for determining abnormal electricity consumption of building users, which relates to the field of power management technology. The method includes: constructing a circuit model, compiling a mathematical model, calculating the impedance of feeder branch lines, and determining abnormal electricity consumption behavior of users; first, establishing a circuit model based on the topological structure of the low-voltage distribution network; then establishing a linear mathematical model based on the circuit model; calculating the impedance of the feeder branch lines based on the measured data and the impedance correction function; calculating the user loop impedance based on the user's home section impedance and the feeder branch line impedance; comparing the user loop impedances calculated by different users at the same node, or comparing them with the abnormal electricity consumption judgment threshold respectively, to determine whether the user has abnormal electricity consumption behavior.
[0004] A Chinese patent with authorization announcement number CN115575754B discloses a method and system for identifying abnormal electricity consumption information in a smart industrial park. The method includes: splitting the park circuit topology diagram to generate a line distribution tree diagram; determining the line load distribution tree diagram based on the model information and location information of the power-consuming equipment, traversing the line load distribution tree diagram according to the output power gradient interval and the electric power parameter for feature calibration, and constructing an abnormal electricity consumption identification module; uploading real-time electricity consumption information through the power monitoring device, inputting it into the abnormal electricity consumption identification module, and generating abnormal power consumption lines.
[0005] The above patents all have the problem raised by this background technology: the existing power consumption abnormality monitoring method fails to fully utilize the household transformer relationship topology structure information to effectively monitor abnormal power consumption. Summary of the invention
[0006] In order to overcome the defects and shortcomings of the prior art, the present invention provides a system and method for monitoring abnormal power consumption based on a topological structure, which improves the accuracy of abnormal power consumption monitoring by constructing a household-transformer relationship topological structure.
[0007] In order to achieve the above object, the present invention adopts the following technical solutions:
[0008] The present invention provides a method for monitoring abnormal power consumption based on a topological structure, comprising the following steps:
[0009] Obtain user power consumption data, transformer data, user geographic location and transformer geographic location. User power consumption data includes voltage data, current data and power consumption data;
[0010] Preprocess the user's electricity consumption data, including missing data filling and data standardization;
[0011] Construct the user-transformer relationship topology structure through electricity user data and transformer data;
[0012] Calculate the line loss of adjacent nodes in the household-to-substation topology structure, and classify areas with line loss higher than the average line loss as potential power consumption abnormal areas;
[0013] By calculating the voltage fluctuation rate in potential power consumption abnormal areas, abnormal power consumption nodes are marked.
[0014] As a preferred technical solution, the missing data filling is expressed by the following formula:
[0015]
[0016] Where X i Indicates the missing voltage data, current data and power consumption data at the time of collection, X i-1 Indicates the voltage data, current data and power consumption data at the time of collection before the missing data, X i+1 Indicates the voltage data, current data and power consumption data at the time of collection after the missing data.
[0017] As a preferred technical solution, the data standardization is expressed by the following formula:
[0018]
[0019] Where X i Indicates the collected voltage data, current data and power consumption data, X mean Indicates the average value of voltage data, current data and power consumption data, X std represents the standard deviation of voltage data, current data and power consumption data, and X′ represents the standardized voltage data, current data and power consumption data.
[0020] As a preferred technical solution, the specific steps of constructing the household change relationship topological structure include:
[0021] Based on the geographical location of users and transformers, a preliminary topological structure of the relationship between users and transformers in non-overlapping areas is constructed;
[0022] Calculate the similarity of current data of electricity users and adjacent transformers in the overlapping area through current data;
[0023] If the current data similarity is greater than or equal to a preset threshold, it is determined that the electricity user belongs to the transformer. If the current data similarity is less than the preset threshold, the user-transformer relationship of the electricity user is manually verified. The preset threshold is determined by technical personnel in this field based on a large number of experiments.
[0024] As a preferred technical solution, the line loss is expressed by the following formula:
[0025]
[0026] In the formula, W p (j) represents the power data of transformer p at the jth acquisition moment, W q (j) represents the electricity consumption data of the qth electricity user at the jth collection time, N represents the number of collections, μ j Represents the line loss at the jth acquisition moment.
[0027] As a preferred technical solution, the calculation process of the voltage fluctuation rate is expressed by the following formula:
[0028]
[0029] Where T represents the number of voltage collection points, L t represents the voltage data collected at the tth voltage collection point, and σ represents the voltage fluctuation rate.
[0030] As a preferred technical solution, the specific steps of judging the abnormal power consumption node include:
[0031] The voltage fluctuation curve is drawn by the voltage fluctuation rate. If the voltage fluctuates positively and exceeds the preset fluctuation threshold, the power consumption anomaly occurs on the power user side. If the voltage fluctuates negatively and exceeds the preset fluctuation threshold, the power consumption anomaly occurs on the transformer side. The preset fluctuation threshold is determined by technical personnel in this field based on a large number of experiments.
[0032] As a preferred technical solution, the calculation process of the current data similarity is expressed by the following formula:
[0033]
[0034] Where I A,k represents the transformer current data collected at the kth moment, I B,k represents the current data of the electricity user collected at the kth moment, K represents the number of current collection times, and R represents the similarity of the current data.
[0035] The present invention also provides a power consumption anomaly monitoring system based on a topological structure, comprising:
[0036] A data acquisition module is used to obtain user power consumption data, transformer data, user geographic location and transformer geographic location. User power consumption data includes voltage data, current data and power consumption data;
[0037] A data preprocessing module is used to preprocess the user's electricity consumption data, including missing data filling and data standardization;
[0038] A topology structure building module is used to build a user-transformer relationship topology structure through electricity user data and transformer data;
[0039] The line loss calculation module is used to calculate the line loss of adjacent nodes in the household-to-substation topology structure, and classify areas with line loss higher than the average line loss as potential power consumption abnormal areas;
[0040] The voltage fluctuation rate calculation module is used to mark the power consumption abnormal nodes by calculating the voltage fluctuation rate of the potential power consumption abnormal area.
[0041] A computer-readable storage medium of the present invention stores a computer program, and when the computer program is executed by a processor, a method for monitoring abnormal power consumption based on a topological structure is implemented.
[0042] A controller of the present invention comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to implement a method for monitoring power consumption anomalies based on a topological structure when executing the computer program.
[0043] Compared with the prior art, the present invention has the following advantages and beneficial effects:
[0044] (1) The present invention divides potential power consumption abnormality areas by calculating the line losses of adjacent nodes in the household-to-substation relationship topology structure, and marks power consumption abnormality nodes by calculating the voltage fluctuation rate in the potential power consumption abnormality areas, thereby improving the accuracy of power consumption abnormality monitoring.
[0045] (2) The present invention preliminarily constructs a household-transformer relationship topology structure in a non-overlapping area based on the user's geographic location and the transformer's geographic location. At the same time, the similarity of current data between electricity users and adjacent transformers in the overlapping area is calculated, thereby improving the timeliness and accuracy of the household-transformer relationship topology structure construction. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:
[0047] Figure 1 It is a schematic diagram of the overall process of a method for monitoring abnormal power consumption based on a topological structure of the present invention;
[0048] Figure 2The schematic diagram is a structural diagram of a power consumption anomaly monitoring system based on a topological structure according to the present invention. DETAILED DESCRIPTION
[0049] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.
[0050] Example 1
[0051] like Figure 1 As shown, this embodiment provides a method for monitoring abnormal power consumption based on a topological structure, which specifically includes the following steps:
[0052] S1: Obtain user power consumption data, transformer data, user geographic location and transformer geographic location. User power consumption data includes voltage data, current data and power consumption data.
[0053] S2: Preprocessing the user's electricity consumption data, including missing data filling and data standardization;
[0054] Missing data filling is expressed as follows:
[0055]
[0056] Where X i Indicates the missing voltage data, current data and power consumption data at the time of collection, X i-1 Indicates the voltage data, current data and power consumption data at the time of collection before the missing data, X i+1 Indicates the voltage data, current data and power consumption data at the time of collection after the missing data;
[0057] Data standardization is expressed as follows:
[0058]
[0059] Where X i Indicates the collected voltage data, current data and power consumption data, X mean Indicates the average value of voltage data, current data and power consumption data, X std represents the standard deviation of voltage data, current data and power consumption data, and X′ represents the standardized voltage data, current data and power consumption data.
[0060] S3: Construct the user-transformer relationship topology structure through the electricity user data and transformer data;
[0061] The specific steps of constructing the household change relationship topological structure include:
[0062] Based on the user's geographical location and the transformer's geographical location, a preliminary topological structure of the user-transformer relationship between electricity users and transformers in non-overlapping areas is constructed. Non-overlapping areas refer to users whose geographical location is only within the coverage of one transformer.
[0063] Calculate the similarity of current data of electricity users and adjacent transformers in the overlapping area through current data;
[0064] If the current data similarity is greater than or equal to the preset threshold, it is determined that the electricity user belongs to the transformer. If the current data similarity is less than the preset threshold, the user-transformer relationship of the electricity user is manually verified;
[0065] The calculation process of current data similarity is expressed as follows:
[0066]
[0067] Where I A,k represents the transformer current data collected at the kth moment, I B,k represents the current data of the electricity user collected at the kth moment, K represents the number of current collection times, and R represents the similarity of the current data.
[0068] S4: Calculate the line loss of adjacent nodes in the household-to-substation relationship topology structure, and classify the area where the line loss is higher than the average line loss as a potential abnormal power consumption area;
[0069] The line loss is expressed as follows:
[0070]
[0071] In the formula, W p (j) represents the power data of transformer p at the jth acquisition moment, W q (j) represents the electricity consumption data of the qth electricity user at the jth collection time, N represents the number of collections, μ j Represents the line loss at the jth acquisition moment.
[0072] S5: Calculate the voltage fluctuation rate of the potential power consumption abnormal area and mark the power consumption abnormal nodes;
[0073] The calculation process of voltage fluctuation rate is expressed as follows:
[0074]
[0075] Where T represents the number of voltage collection points, L t represents the voltage data collected at the t-th voltage collection point, and σ represents the voltage fluctuation rate;
[0076] The specific steps for determining abnormal power consumption nodes include:
[0077] The voltage fluctuation curve is drawn by the voltage fluctuation rate. If the voltage fluctuates positively and exceeds the preset fluctuation threshold, the power consumption anomaly occurs on the power user side. If the voltage fluctuates negatively and exceeds the preset fluctuation threshold, the power consumption anomaly occurs on the transformer side.
[0078] Example 2
[0079] like Figure 2 As shown, this embodiment provides a power consumption anomaly monitoring system based on a topology structure, including:
[0080] The data acquisition module 21 is used to obtain user power consumption data, transformer data, user geographic location and transformer geographic location. The user power consumption data includes voltage data, current data and power consumption data.
[0081] A data preprocessing module 22 is used to preprocess the user's electricity consumption data, and the preprocessing includes missing data filling and data standardization;
[0082] A topology structure building module 23 is used to build a user-transformer relationship topology structure through power user data and transformer data;
[0083] The line loss calculation module 24 is used to calculate the line loss of adjacent nodes in the household transformer relationship topology structure, and classify the area where the line loss is higher than the average line loss as a potential abnormal power consumption area;
[0084] The voltage fluctuation rate calculation module 25 is used to mark the power consumption abnormal nodes by calculating the voltage fluctuation rate of the potential power consumption abnormal area.
[0085] In this embodiment, the data preprocessing module 22 is used to preprocess the user's electricity consumption data, and the preprocessing includes missing data filling and data standardization, wherein the missing data filling is expressed by the following formula:
[0086]
[0087] Where X i Indicates the missing voltage data, current data and power consumption data at the time of collection, X i-1 Indicates the voltage data, current data and power consumption data at the time of collection before the missing data, X i+1 Indicates the voltage data, current data and power consumption data at the time of collection after the missing data.
[0088] In this embodiment, the topology structure construction module 23 is used to construct a household-transformer relationship topology structure through electricity user data and transformer data, wherein the specific steps of constructing the household-transformer relationship topology structure include:
[0089] Based on the geographical location of users and transformers, a preliminary topological structure of the relationship between users and transformers in non-overlapping areas is constructed;
[0090] Calculate the similarity of current data of electricity users and adjacent transformers in the overlapping area through current data;
[0091] If the current data similarity is greater than or equal to the preset threshold, it is determined that the electricity user belongs to the transformer. If the current data similarity is less than the preset threshold, the user-transformer relationship of the electricity user is manually verified;
[0092] The calculation process of current data similarity is expressed as follows:
[0093]
[0094] Where I A,k represents the transformer current data collected at the kth moment, I B,k represents the current data of the electricity user collected at the kth moment, K represents the number of current collection times, and R represents the similarity of the current data.
[0095] In this embodiment, the line loss calculation module 24 is used to calculate the line loss of adjacent nodes in the household transformer relationship topology structure, and classify the area where the line loss is higher than the average line loss as a potential abnormal power consumption area, wherein the line loss is expressed by the following formula:
[0096]
[0097] In the formula, W p (j) represents the power data of transformer p at the jth acquisition moment, W q (j) represents the power consumption data of the qth power user at the jth collection time, N represents the number of collections, μ j Represents the line loss at the jth acquisition moment.
[0098] In this embodiment, the voltage fluctuation rate calculation module 25 is used to mark the power consumption abnormality node by calculating the voltage fluctuation rate of the potential power consumption abnormality area, wherein the calculation process of the voltage fluctuation rate is expressed by the following formula:
[0099]
[0100] Where T represents the number of voltage collection points, L t represents the voltage data collected at the t-th voltage collection point, and σ represents the voltage fluctuation rate;
[0101] The specific steps for determining abnormal power consumption nodes include:
[0102] The voltage fluctuation curve is drawn by the voltage fluctuation rate. If the voltage fluctuates positively and exceeds the preset fluctuation threshold, the power consumption anomaly occurs on the power user side. If the voltage fluctuates negatively and exceeds the preset fluctuation threshold, the power consumption anomaly occurs on the transformer side.
[0103] The above-mentioned parameters and steps for each unit module to implement corresponding functions in a power consumption abnormality monitoring system based on a topological structure of the present invention can refer to the parameters and steps in the embodiment of a power consumption abnormality monitoring method based on a topological structure above, and will not be repeated here.
[0104] Example 3
[0105] A computer-readable storage medium according to an embodiment of the present invention stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for monitoring abnormal power consumption based on a topological structure is implemented. It should be noted that all computer programs of the method for monitoring abnormal power consumption based on a topological structure are implemented in Python language, wherein the data preprocessing module, the topological structure building module, the line loss calculation module and the voltage fluctuation rate calculation module are all controlled by a remote server; the CPU of the remote server is Intel Xeon Gold 5118, the GPU is NVIDIA GTX 2080Ti 11GB, the operating system is Ubuntu 18.04.2, the deep learning framework is PyTorch1.7.0, the CUDA version is 10.2, and cuDNN7.6.5 is used for accelerated reasoning; Intel Xeon Gold 5118 includes a memory and a processor, wherein the memory is used to store the computer program; the processor is used to execute the computer program, so that Intel Xeon Gold 5118 executes and implements a method for monitoring abnormal power consumption based on a topological structure.
[0106] Those skilled in the art will appreciate that the present invention may be implemented as a system, method or computer program product.
[0107] Therefore, the present disclosure may be specifically implemented in the following forms, namely: it may be completely hardware, it may be completely software (including firmware, resident software, microcode, etc.), or it may be a combination of hardware and software, generally referred to herein as a "circuit", "module" or "system". In addition, in some embodiments, the present invention may also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.
[0108] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.
[0109] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.
Claims
1. A method for monitoring abnormal power consumption based on topological structure, characterized in that: The steps include: Obtain user power consumption data, transformer data, user geographic location and transformer geographic location. User power consumption data includes voltage data, current data and power consumption data; Preprocess the user's electricity consumption data, including missing data filling and data standardization; Construct the user-transformer relationship topology structure through electricity user data and transformer data; Calculate the line loss of adjacent nodes in the household-to-substation topology structure, and classify areas with line loss higher than the average line loss as potential power consumption abnormal areas; By calculating the voltage fluctuation rate in potential power consumption abnormal areas, abnormal power consumption nodes are marked; The specific steps of constructing the household change relationship topological structure include: Based on the geographical location of users and transformers, a preliminary topological structure of the relationship between users and transformers in non-overlapping areas is constructed; Calculate the similarity of current data of electricity users and adjacent transformers in the overlapping area through current data; If the current data similarity is greater than or equal to the preset threshold, it is determined that the electricity user belongs to the transformer. If the current data similarity is less than the preset threshold, the user-transformer relationship of the electricity user is manually verified; The calculation process of the current data similarity is expressed by the following formula: Where I A,k represents the transformer current data collected at the kth moment, I B,k represents the current data of the electricity user collected at the kth moment, K represents the number of current collection times, and R represents the similarity of current data; The line loss is expressed as follows: In the formula, W p (j) represents the power data of transformer p at the jth acquisition moment, W q (j) represents the electricity consumption data of the qth electricity user at the jth collection time, N represents the number of collections, μ j represents the line loss at the jth acquisition moment; The calculation process of the voltage fluctuation rate is expressed by the following formula: Where T represents the number of voltage collection points, L t represents the voltage data collected at the t-th voltage collection point, and σ represents the voltage fluctuation rate; The specific steps of judging the abnormal power consumption node include: The voltage fluctuation curve is drawn by the voltage fluctuation rate. If the voltage fluctuates positively and exceeds the preset fluctuation threshold, the power consumption anomaly occurs on the power user side. If the voltage fluctuates negatively and exceeds the preset fluctuation threshold, the power consumption anomaly occurs on the transformer side.
2. The method for monitoring abnormal power consumption based on topological structure according to claim 1, characterized in that: The missing data filling is expressed by the following formula: Where X i Indicates the missing voltage data, current data and power consumption data at the time of collection, X i-1 Indicates the voltage data, current data and power consumption data at the time of collection before the missing data, X i+1 Indicates the voltage data, current data and power consumption data at the time of collection after the missing data.
3. A power consumption anomaly monitoring system based on topological structure, which is implemented based on a power consumption anomaly monitoring method based on topological structure according to any one of claims 1-2, characterized in that: The system comprises: A data acquisition module is used to obtain user power consumption data, transformer data, user geographic location and transformer geographic location. User power consumption data includes voltage data, current data and power consumption data; A data preprocessing module is used to preprocess the user's electricity consumption data, including missing data filling and data standardization; A topology structure building module is used to build a user-transformer relationship topology structure through electricity user data and transformer data; The line loss calculation module is used to calculate the line loss of adjacent nodes in the household-to-substation topology structure, and classify areas with line loss higher than the average line loss as potential power consumption abnormal areas; The voltage fluctuation rate calculation module is used to mark the power consumption abnormal nodes by calculating the voltage fluctuation rate of the potential power consumption abnormal area.
4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for monitoring abnormal power consumption based on a topological structure described in any one of claims 1 to 2 is implemented.
5. A controller, comprising a memory and a processor, wherein the memory is used to store a computer program, characterized in that: The processor is used to implement a method for monitoring abnormal power consumption based on a topology structure as described in any one of claims 1-2 when executing the computer program.
Citation Information
Patent Citations
A method for determining abnormal electricity consumption in building users
CN109164319B
A method and system for identifying abnormal electricity consumption information in a smart industrial park
CN115575754B
An algorithm and a system for judging household change relationship of a station area based on power consumption information and geographical position
CN109034585A
Power grid district line loss abnormity cause diagnosis method and device, computer equipment and storage medium
CN110134708A
Abnormal power consumption data detection method, system and device, and storage medium
CN110503570A
