Power customer behavior analysis method and system based on big data

Abstract

The invention relates to the technical field of power monitoring, in particular to a power customer behavior analysis method and system based on big data, and the method comprises the following steps: obtaining power consumption behavior data of customers in a park in real time based on the big data, and preprocessing the power consumption behavior data to obtain a power consumption time sequence; drawing a signal curve graph according to the electricity consumption time sequence to obtain two-dimensional signal data corresponding to different customer electricity consumption behaviors; according to the historical two-dimensional signal data, constructing dynamic baselines of different customer electricity consumption behaviors; analyzing the two-dimensional signal data at the current moment to obtain an abnormal power consumption factor; according to the dynamic base line and the abnormal power consumption factor, calculating a power consumption behavior abnormal index of the client at the current moment; and performing anomaly analysis according to the customer power consumption behavior anomaly index, and generating an analysis report. The method can meet the analysis requirements of a large amount of electric equipment, and accords with the actual situation of the park in the aspect of timeliness.

Description

Technical Field

[0001] The present invention relates to the technical field of power monitoring, and in particular to a method and system for analyzing power customer behavior based on big data. Background Art

[0002] As the scale of the park continues to expand and the production activities of various enterprises become increasingly complex, the operation and management of the power system in the park faces many challenges. The power consumption of various types of equipment under the name of many enterprises is complex and diverse. Their power consumption behavior is not only affected by the normal production and operation rhythm, but may also change abnormally due to various factors such as equipment failure.

[0003] Traditional power analysis methods often focus on collecting and roughly analyzing simple power data, which makes it difficult to comprehensively, real-timely and accurately capture subtle changes in equipment power consumption behavior and abnormal power consumption caused by equipment failures. For example, when analyzing a large amount of power consumption data, there is a lack of efficient and multi-dimensional methods to distinguish between normal and abnormal power consumption behavior, making it difficult to locate faulty equipment in a timely manner and accurately determine the scope of the fault. In addition, when analyzing the power consumption data of the park, due to the large number of enterprises in the park and the huge amount of power consumption data of power-consuming equipment, the previous methods are difficult to meet actual needs in terms of timeliness.

[0004] Therefore, how to accurately and quickly analyze the abnormal power consumption behavior of customers in the park and synchronously perform abnormal analysis on a large number of devices based on the abnormal power consumption behavior is an urgent problem to be solved in the park power detection. Summary of the invention

[0005] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a method and system for analyzing power customer behavior based on big data, which can accurately and quickly analyze the abnormal power consumption behavior of customers in the park, and realize synchronous abnormal analysis of a large number of devices according to the abnormal power consumption behavior.

[0006] In the first aspect, in order to solve the above technical problems, the basic concept of the technical solution adopted by the present invention is:

[0007] A method for analyzing electric power customer behavior based on big data, the method comprising the following steps:

[0008] Based on big data, the electricity consumption behavior data of customers in the park is obtained in real time, and the electricity consumption behavior data is preprocessed to obtain the electricity consumption time series;

[0009] Draw a signal curve graph according to the electricity consumption time series to obtain two-dimensional signal data corresponding to different customers' electricity consumption behaviors;

[0010] Constructing a dynamic baseline of different customers' electricity consumption behaviors based on the historical two-dimensional signal data;

[0011] Analyzing the two-dimensional signal data at the current moment to obtain an abnormal power consumption factor;

[0012] Calculate the abnormal power consumption behavior index of the customer at the current moment according to the dynamic baseline and the abnormal power consumption factor;

[0013] Perform anomaly analysis based on abnormal indicators of customers’ electricity usage behavior and generate an analysis report.

[0014] In any of the above solutions, it is preferred that the electricity consumption behavior data of customers in the park is obtained in real time based on big data, and the electricity consumption behavior data is preprocessed to obtain the electricity consumption time series, including:

[0015] Using a sliding window method to filter abnormal jump points in the electricity consumption behavior data, and interpolating and repairing missing values;

[0016] The interpolated and repaired electricity consumption behavior data is unified into a time series format and classified and stored according to customer and equipment type to obtain the equipment electricity consumption time series of each customer in the park.

[0017] In any of the above solutions, preferably, a signal curve graph is drawn according to the electricity consumption time series to obtain two-dimensional signal data corresponding to different customers' electricity consumption behaviors, including:

[0018] With the horizontal axis representing time and the vertical axis representing power value, a corresponding signal curve graph is generated based on the equipment power consumption time series;

[0019] The equipment power consumption time series is expanded into a two-dimensional matrix through a sliding window;

[0020] The two-dimensional matrix is ​​interpolated and scaled to generate a two-dimensional signal image with a fixed resolution.

[0021] In any of the above solutions, preferably, a dynamic baseline of different customers' electricity consumption behaviors is constructed based on the historical two-dimensional signal data, including:

[0022] Detect edge points of the two-dimensional signal image by using an edge detection algorithm to obtain an edge point set;

[0023] Calculate the average power value corresponding to each element in the edge point set to obtain the dynamic mean μ t ;

[0024] Calculate the variation range between the elements in the edge point set to obtain the dynamic standard deviation σ t ;

[0025] According to the dynamic mean μ t and dynamic standard deviation σ t Get the dynamic baseline (μ t , σt ).

[0026] In any of the above solutions, preferably, analyzing the two-dimensional signal data at the current moment to obtain the abnormal power consumption factor includes:

[0027] Perform edge point detection on the two-dimensional signal image at the current moment, obtain the edge detection result, and calculate the gradient amplitude G of each edge point t ;

[0028] The edge detection result is subjected to a two-dimensional discrete cosine transform to extract the amplitude R of the main frequency component t ;

[0029] The two-dimensional signal image after edge point detection is divided into multiple small blocks, and the distribution of gradient direction in each small block is counted to obtain the feature vector H t , each component corresponds to a statistical value of the gradient direction.

[0030] In any of the above solutions, preferably, calculating the abnormal power consumption behavior index of the customer at the current moment according to the dynamic baseline and the abnormal power consumption factor includes:

[0031] By formula: Calculate the abnormal score A of the customer's electricity consumption behavior at the current moment t ; where α is the weight coefficient; x t is the power at the current moment; μ t is the dynamic mean; σ t is the dynamic standard deviation; N is the total number of edge points in the edge detection result; is the gradient amplitude of the i-th edge point; is the average gradient amplitude of edge points in edge detection results; R t is the amplitude of the main frequency component at the current moment; is the mean of the historical spectrum characteristics; σ R is the standard deviation of the historical spectrum characteristics; H ref is the preset reference vector.

[0032] In any of the above solutions, preferably, an abnormality analysis is performed based on the abnormal indicators of the customer's electricity consumption behavior, and an analysis report is generated, including:

[0033] Set the abnormal threshold T A , if A t >T A , then it is determined that the device corresponding to the two-dimensional signal data at the current moment is abnormal;

[0034] Record the customers and time points mentioned in the abnormal equipment, summarize the number of abnormal equipment and abnormal time periods of all customers in the park, and obtain an abnormal power consumption analysis report for each customer in the park.

[0035] Second, a power customer behavior analysis system based on big data, including:

[0036] An acquisition module is used to acquire the electricity consumption behavior data of customers in the park in real time based on big data, and pre-process the electricity consumption behavior data to obtain an electricity consumption time series;

[0037] A drawing module, used to draw a signal curve graph according to the power consumption time series to obtain two-dimensional signal data corresponding to different customers' power consumption behaviors;

[0038] A construction module, used to construct a dynamic baseline of different customers' electricity consumption behaviors based on the historical two-dimensional signal data;

[0039] An analysis module, used for analyzing the two-dimensional signal data at the current moment to obtain an abnormal power consumption factor;

[0040] A calculation module, used to calculate the abnormal power consumption behavior index of the customer at the current moment according to the dynamic baseline and the abnormal power consumption factor;

[0041] The generation module is used to perform abnormal analysis based on abnormal indicators of customer electricity consumption behavior and generate an analysis report.

[0042] In a third aspect, a device for analyzing electricity customer behavior based on big data is provided, comprising: one or more processors; a storage system for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any of the above-mentioned methods for analyzing electricity customer behavior based on big data.

[0043] In a fourth aspect, a computer-readable storage medium stores a program, which, when executed by a processor, implements any of the above-mentioned methods for analyzing electricity customer behavior based on big data.

[0044] Compared with the prior art, the big data-based electricity customer behavior analysis method of the embodiment of the present application can comprehensively, real-time and accurately capture the subtle changes in the electricity consumption behavior of enterprise equipment in the park, efficiently distinguish between normal and abnormal electricity consumption behaviors, timely locate faulty equipment and accurately determine its impact range, while meeting the analysis needs for a large number of power-consuming equipment. In terms of timeliness, it is in line with the actual situation of the park, and effectively solves the difficult problems of accurately and quickly analyzing abnormal electricity consumption behaviors in the park's power detection and simultaneously performing abnormal analysis on a large number of equipment, thereby helping to stabilize the operation of the park's power system and the orderly development of enterprise production activities.

[0045] The specific implementation modes of the present invention are further described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. Some specific embodiments of the present application will be described in detail in an illustrative and non-restrictive manner with reference to the drawings. The same reference numerals in the drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the drawings:

[0047] Figure 1 This is a flow chart of a method for analyzing electric power customer behavior based on big data according to an embodiment of the present application;

[0048] Figure 2 This is a module diagram of the power customer behavior analysis system based on big data according to an embodiment of the present application.

[0049] It should be noted that these drawings and text descriptions are not intended to limit the conceptual scope of the present invention in any way, but to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. The elements in the drawings are schematic and not drawn to scale. DETAILED DESCRIPTION

[0050] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0051] It should be noted that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0052] The following embodiment of the present application takes the power customer behavior analysis method based on big data as an example to explain the scheme of the present application in detail, but this embodiment cannot limit the scope of protection of the present application.

[0053] like Figure 1As shown, the present invention provides a method for analyzing electric power customer behavior based on big data, the method comprising the following steps:

[0054] Step 1: acquiring electricity consumption behavior data of customers in the park in real time based on big data, and preprocessing the electricity consumption behavior data to obtain an electricity consumption time series;

[0055] Step 2, drawing a signal curve graph according to the electricity consumption time series to obtain two-dimensional signal data corresponding to different customers' electricity consumption behaviors;

[0056] Step 3, constructing a dynamic baseline of different customers' electricity consumption behaviors based on the historical two-dimensional signal data;

[0057] Step 4, analyzing the two-dimensional signal data at the current moment to obtain an abnormal power consumption factor;

[0058] Step 5, calculating the abnormal power consumption behavior index of the customer at the current moment according to the dynamic baseline and the abnormal power consumption factor;

[0059] Step 6: Perform an abnormal analysis based on the abnormal indicators of the customer's electricity consumption behavior and generate an analysis report.

[0060] In the power customer behavior analysis method based on big data described in an embodiment of the present invention,.

[0061] In the above embodiment, the step 1, based on big data, real-time acquisition of electricity consumption behavior data of customers in the park, and pre-processing of the electricity consumption behavior data to obtain an electricity consumption time series, includes:

[0062] Step 11, using a sliding window method to filter abnormal jump points in the electricity consumption behavior data, and interpolating and repairing missing values;

[0063] Step 12: unify the interpolated and repaired electricity consumption behavior data into a time series format, and classify and store them according to the customer and equipment type to obtain the equipment electricity consumption time series of each customer in the park.

[0064] In the big data-based electricity customer behavior analysis method described in an embodiment of the present invention, customers within the park can be distinguished based on company name, company number, etc., and the electricity consumption behavior data includes real-time electricity consumption data, historical data and environmental data of equipment under each company.

[0065] In the big data-based electricity customer behavior analysis method described in the embodiment of the present invention, by using the sliding window method to filter the abnormal jump points caused by equipment failure, it is possible to effectively identify sudden changes in electricity consumption caused by the failure (such as instantaneous electricity consumption surge or zero), and at the same time smooth the noise interference, extract the real electricity consumption characteristics of the equipment failure, and reduce false alarms and missed reports; the time series discontinuities caused by data missing during the equipment failure are filled with high quality through interpolation repair technology, the complete electricity consumption curve is restored, and the electricity consumption trend characteristics during the equipment failure are retained, providing real and continuous data support for subsequent analysis; through the unification of the time series format and classified storage by customer and equipment type, it supports the rapid positioning of abnormal electricity consumption behavior of specific customers or equipment, facilitates multi-dimensional analysis of the causes and impact scope of equipment failures, and improves fault diagnosis efficiency.

[0066] In the above embodiment, the step 2, drawing a signal curve graph according to the power consumption time series to obtain two-dimensional signal data corresponding to different customers' power consumption behaviors, includes:

[0067] Step 21, with the horizontal axis representing time and the vertical axis representing power value, a corresponding signal curve graph is generated according to the time series of power consumption of the equipment;

[0068] Step 22, expanding the equipment power consumption time series into a two-dimensional matrix through a sliding window;

[0069] Step 23: interpolate and scale the two-dimensional matrix to generate a two-dimensional signal image with a fixed resolution.

[0070] In the big data-based electricity customer behavior analysis method described in the embodiment of the present invention, by converting the equipment power consumption time series into a signal curve graph, a two-dimensional matrix, and a two-dimensional signal image with a fixed resolution, the power consumption of the enterprise equipment in the park can be intuitively presented in a visual manner, which is convenient for timely discovery of power consumption anomalies caused by equipment failures. Through multi-dimensional processing and visual conversion of power consumption data, an efficient and intuitive analysis method is provided for power consumption monitoring of park equipment, which can quickly locate equipment that may have faults, improve the efficiency of equipment fault troubleshooting and power consumption anomaly detection, contribute to the stable operation of the park power system and the normal development of enterprise production, and reduce production losses and safety risks caused by equipment failures.

[0071] In the above embodiment, the step 3, constructing a dynamic baseline of different customers' electricity consumption behaviors based on the historical two-dimensional signal data, includes:

[0072] Step 31, detecting edge points of the two-dimensional signal image by an edge detection algorithm to obtain an edge point set;

[0073] Step 32, calculate the average power value corresponding to each element in the edge point set to obtain a dynamic mean μt ;

[0074] Step 33, calculate the variation range between the elements in the edge point set to obtain the dynamic standard deviation σ t ;

[0075] Step 34, according to the dynamic mean μ t and dynamic standard deviation σ t Get the dynamic baseline (μ t , σ t ).

[0076] In the power customer behavior analysis method based on big data described in the embodiment of the present invention, by converting the power mutation characteristics in the time series into the "edge detection problem" in image processing, volatility and drastic changes can be quickly captured, and large-scale power consumption data in the park can be quickly analyzed to improve practicality and efficiency. The dynamic baseline is obtained through the edge detection algorithm and related calculations, and the baseline can be dynamically generated according to the real-time data of the power consumption of the enterprise equipment in the park, accurately capturing the normal range and fluctuation of the power consumption of the equipment. When the equipment has abnormal power consumption due to a fault, the dynamic baseline can quickly and accurately reflect the deviation of parameters such as power value, so as to timely discover the abnormal power consumption caused by the equipment failure, and provide a reliable basis for the real-time monitoring and fault warning of the park power system, which helps to improve the intelligent level of power management in the park, reduce production interruptions and safety hazards caused by equipment failure, and ensure the stable operation and production efficiency of enterprises in the park.

[0077] In the above embodiment, the step 4, analyzing the two-dimensional signal data at the current moment to obtain the abnormal power consumption factor, includes:

[0078] Step 41, perform edge point detection on the two-dimensional signal image at the current moment, obtain edge detection results, and calculate the gradient amplitude G of each edge point t ;

[0079] Step 42: Perform a two-dimensional discrete cosine transform on the edge detection result to extract the amplitude R of the main frequency component. t ;

[0080] Step 43, divide the two-dimensional signal image after edge point detection into multiple small blocks, count the gradient direction distribution in each small block, and obtain the feature vector H t , each component corresponds to a statistical value of the gradient direction.

[0081] In the big data-based electricity customer behavior analysis method described in the embodiment of the present invention, by performing edge point detection, discrete cosine transform and gradient direction distribution statistical operations on the two-dimensional signal image, the characteristic information of the electricity consumption data of enterprise equipment in the park can be deeply mined from multiple dimensions; the subtle changes and potential laws of the equipment power consumption pattern can be captured more accurately, and the normal power consumption state can be effectively distinguished from the abnormal power consumption state caused by equipment failure, providing richer and more targeted feature basis for fault diagnosis and early warning of the park power system, thereby realizing early detection and accurate positioning of abnormal equipment power consumption, improving the refinement of the park power management and fault response capabilities, ensuring the continuity and stability of the production of park enterprises, and reducing the economic losses and safety risks caused by equipment failures.

[0082] In the above embodiment, the step 5, calculating the abnormal index of the customer's electricity consumption behavior at the current moment according to the dynamic baseline and the abnormal electricity consumption factor, includes:

[0083] Step 51, by formula:

[0085] Calculate the abnormal score A of the customer's electricity consumption behavior at the current moment t ; where α is the weight coefficient; x t is the power at the current moment; μ t is the dynamic mean; σ t is the dynamic standard deviation; N is the total number of edge points in the edge detection result; is the gradient amplitude of the i-th edge point; is the average gradient amplitude of edge points in edge detection results; R t is the amplitude of the main frequency component at the current moment; is the mean of the historical spectrum characteristics; σ R is the standard deviation of the historical spectrum characteristics; H ref is the preset reference vector.

[0086] In the power customer behavior analysis method based on big data described in the embodiment of the present invention, in the above formula, It can reflect the degree to which the real-time power deviates from the dynamic baseline; It can reflect the degree of deviation between the real-time edge gradient amplitude and the normal fluctuation range; It can reflect the deviation degree between the main component amplitude of the real-time spectrum and the normal amplitude; 1-cos_simH t ,H ref ) can reflect the similarity between the real-time gradient direction distribution and the reference distribution.

[0087] In the big data-based electricity customer behavior analysis method described in the embodiment of the present invention, the customer's electricity consumption behavior anomaly score is calculated by comprehensively considering multiple factors such as real-time power, dynamic baseline, edge gradient amplitude, spectrum main component amplitude, and gradient direction distribution. It can comprehensively and accurately evaluate the electricity consumption status of enterprise equipment in the park, quantify the degree and characteristics of equipment power consumption anomalies from multiple dimensions, and effectively capture various subtle changes in electricity consumption caused by equipment failures. It provides a scientific and reliable quantitative basis for timely detection of equipment failures, accurate positioning of faulty equipment, and prediction of potential failures, greatly improving the monitoring capability and early warning accuracy of the park's power system for equipment failures, helping to ensure the stability of the park's power supply and the normal operation of enterprise production, and reducing economic losses and safety risks caused by equipment failures.

[0088] In the above embodiment, the step 6, performing abnormal analysis based on the abnormal indicators of the customer's electricity usage behavior and generating an analysis report, includes:

[0089] Step 61, setting the abnormal threshold T A , if A t >T A , then it is determined that the device corresponding to the two-dimensional signal data at the current moment is abnormal;

[0090] Step 62, record the customer and time point of the abnormal equipment, summarize the number of abnormal equipment and abnormal time period of all customers in the park, and obtain an abnormal power consumption analysis report for each customer in the park.

[0091] In the big data-based electricity customer behavior analysis method described in the embodiment of the present invention, an abnormal power consumption analysis report is generated by setting abnormal thresholds for judgment and recording relevant information, and a clear abnormal judgment standard and a systematic monitoring mechanism are established for the power consumption of enterprise equipment in the park. It can accurately and timely identify abnormal power consumption caused by equipment failure, and fully grasp the abnormal conditions and time period distribution of each customer's equipment, providing intuitive and detailed data support for the park's power operation and maintenance management, facilitating rapid response and handling of faults, and ensuring the stable operation of the park's power system and the orderly development of enterprise production activities.

[0092] like Figure 2 As shown, the present invention also provides a power customer behavior analysis system based on big data, comprising:

[0093] The acquisition module 10 is used to acquire the electricity consumption behavior data of customers in the park in real time based on big data, and pre-process the electricity consumption behavior data to obtain the electricity consumption time series;

[0094] A drawing module 20, used to draw a signal curve graph according to the power consumption time series to obtain two-dimensional signal data corresponding to different customers' power consumption behaviors;

[0095] A construction module 30, for constructing a dynamic baseline of different customers' electricity consumption behaviors according to the historical two-dimensional signal data;

[0096] The analysis module 40 is used to analyze the two-dimensional signal data at the current moment to obtain an abnormal power consumption factor;

[0097] A calculation module 50, configured to calculate an abnormal power consumption behavior index of a customer at a current moment according to the dynamic baseline and the abnormal power consumption factor;

[0098] The generating module 60 is used to perform abnormal analysis based on the abnormal indicators of the customer's electricity consumption behavior and generate an analysis report.

[0099] The power customer behavior analysis device based on big data can also communicate with one or more external devices (such as keyboards, pointing devices, displays, etc.), and can also communicate with one or more devices that enable users to interact with the power customer behavior analysis device based on big data, and / or communicate with any device that enables the power customer behavior analysis device based on big data to communicate with one or more other computing devices (such as network cards, modems, etc.). This communication can be carried out through an input / output (I / O) interface. In addition, the power customer behavior analysis device based on big data can also communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs) and / or public networks, such as the Internet) through a network adapter. The network adapter communicates with other modules of the power customer behavior analysis device based on big data through a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the power customer behavior analysis device based on big data, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage devices.

[0100] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor device, device or component, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media 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 of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution device, a device or a device or used in combination with it.

[0101] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution device, apparatus, or device.

[0102] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0103] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for analyzing power customer behavior based on big data, characterized in that: The method comprises the following steps: Based on big data, the electricity consumption behavior data of customers in the park is obtained in real time, and the electricity consumption behavior data is preprocessed to obtain the electricity consumption time series; Draw a signal curve graph according to the electricity consumption time series to obtain two-dimensional signal data corresponding to different customers' electricity consumption behaviors; Constructing a dynamic baseline of different customers' electricity consumption behaviors based on the historical two-dimensional signal data; Analyzing the two-dimensional signal data at the current moment to obtain an abnormal power consumption factor; Calculate the abnormal power consumption behavior index of the customer at the current moment according to the dynamic baseline and the abnormal power consumption factor; Perform anomaly analysis based on abnormal indicators of customers’ electricity usage behavior and generate an analysis report.

2. The method for analyzing electricity customer behavior based on big data according to claim 1 is characterized in that: Based on big data, the electricity consumption behavior data of customers in the park is obtained in real time, and the electricity consumption behavior data is preprocessed to obtain the electricity consumption time series, including: Using a sliding window method to filter abnormal jump points in the electricity consumption behavior data, and interpolating and repairing missing values; The interpolated and repaired electricity consumption behavior data is unified into a time series format and classified and stored according to customer and equipment type to obtain the equipment electricity consumption time series of each customer in the park.

3. The method for analyzing electricity customer behavior based on big data according to claim 2 is characterized in that: A signal curve graph is drawn according to the electricity consumption time series to obtain two-dimensional signal data corresponding to different customers' electricity consumption behaviors, including: With the horizontal axis representing time and the vertical axis representing power value, a corresponding signal curve graph is generated based on the equipment power consumption time series; The equipment power consumption time series is expanded into a two-dimensional matrix through a sliding window; The two-dimensional matrix is ​​interpolated and scaled to generate a two-dimensional signal image with a fixed resolution.

4. The method for analyzing electricity customer behavior based on big data according to claim 3 is characterized in that: Based on the historical two-dimensional signal data, a dynamic baseline of different customers' electricity consumption behaviors is constructed, including: Detect edge points of the two-dimensional signal image by using an edge detection algorithm to obtain an edge point set; Calculate the average power value corresponding to each element in the edge point set to obtain the dynamic mean μ t ; Calculate the variation range between the elements in the edge point set to obtain the dynamic standard deviation σ t ; According to the dynamic mean μ t and dynamic standard deviation σ t Get the dynamic baseline (μ t , σ t ).

5. The method for analyzing electric power customer behavior based on big data according to claim 4 is characterized in that: Analyze the two-dimensional signal data at the current moment to obtain abnormal power consumption factors, including: Perform edge point detection on the two-dimensional signal image at the current moment, obtain the edge detection result, and calculate the gradient amplitude G of each edge point t ; The edge detection result is subjected to a two-dimensional discrete cosine transform to extract the amplitude R of the main frequency component t ; The two-dimensional signal image after edge point detection is divided into multiple small blocks, and the distribution of gradient direction in each small block is counted to obtain the feature vector H t , each component corresponds to a statistical value of the gradient direction.

6. The method for analyzing electric power customer behavior based on big data according to claim 5 is characterized in that: According to the dynamic baseline and the abnormal power consumption factor, the abnormal power consumption behavior index of the customer at the current moment is calculated, including: By formula: Calculate the abnormal score A of the customer's electricity consumption behavior at the current moment t ; where α is the weight coefficient; x t is the power at the current moment; μ t is the dynamic mean; σ t is the dynamic standard deviation; N is the total number of edge points in the edge detection result; is the gradient amplitude of the i-th edge point; is the average gradient amplitude of edge points in edge detection results; R t is the amplitude of the main frequency component at the current moment; is the mean of the historical spectrum characteristics; σ R is the standard deviation of the historical spectrum characteristics; H ref is the preset reference vector.

7. The method for analyzing electricity customer behavior based on big data according to claim 6 is characterized in that: Perform abnormal analysis based on abnormal indicators of customer electricity consumption behavior and generate analysis reports, including: Set the abnormal threshold T A , if A t >T A , then it is determined that the device corresponding to the two-dimensional signal data at the current moment is abnormal; Record the customers and time points mentioned in the abnormal equipment, summarize the number of abnormal equipment and abnormal time periods of all customers in the park, and obtain an abnormal power consumption analysis report for each customer in the park.

8. A power customer behavior analysis system based on big data, characterized in that: include: An acquisition module is used to acquire the electricity consumption behavior data of customers in the park in real time based on big data, and pre-process the electricity consumption behavior data to obtain an electricity consumption time series; A drawing module, used to draw a signal curve graph according to the power consumption time series to obtain two-dimensional signal data corresponding to different customers' power consumption behaviors; A construction module, used to construct a dynamic baseline of different customers' electricity consumption behaviors based on the historical two-dimensional signal data; An analysis module, used for analyzing the two-dimensional signal data at the current moment to obtain an abnormal power consumption factor; A calculation module, used to calculate the abnormal power consumption behavior index of the customer at the current moment according to the dynamic baseline and the abnormal power consumption factor; The generation module is used to perform abnormal analysis based on abnormal indicators of customer electricity consumption behavior and generate an analysis report.

9. A power customer behavior analysis device based on big data, characterized in that: include: one or more processors; A storage system for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the big data-based electricity customer behavior analysis method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which, when executed by a processor, implements the big data-based electricity customer behavior analysis method as described in any one of claims 1 to 7.

Images