A power user service demand prediction method based on big data analysis
By combining wavelet transform clustering and generative adversarial network models with electricity user data for electricity demand forecasting, the problem of low prediction accuracy in existing models is solved, and accurate prediction and visualized management of electricity user service demand are achieved.
Patent Information
- Application Number
- CN202111375506.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-11-19
- Publication Date
- 2026-02-13
- Estimated Expiration
- 2041-11-19
AI Technical Summary
Existing electricity demand forecasting models consider too many subjective factors, resulting in low accuracy of forecasts and an inability to effectively utilize big data for accurate predictions.
Electricity user data is collected, user categories are divided using wavelet transform clustering algorithm, a generative adversarial network model is built by combining historical consumption data for prediction, missing data is processed using K-nearest neighbor algorithm, and the results are visualized using EChart tool.
It enables accurate prediction and visualization of power user service needs, supporting refined management of power users.
Smart Images
Figure CN114239917B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of power user service demand prediction, and particularly relates to a power user service demand prediction method based on big data analysis. BACKGROUND
[0002] With the continuous improvement of the level of science and technology, people are more and more dependent on electricity, and the automation development of many industries also depends on electric power energy, and the power consumption of each region is increasing, and people's demand for electricity is also growing. The power grid customer service center is the external service window of the power grid enterprise, which needs to integrate various internal and external data resources, store and analyze massive customer service information. How to efficiently, reliably and cheaply store various data of the power grid enterprise, and quickly analyze and predict, is an important research topic at present.
[0003] Most of the prior art solves the demand prediction problem by combining artificial intelligence to establish a demand prediction model, but the existing power demand prediction model considers too subjective factors, thereby resulting in low prediction result accuracy, and cannot predict big data. SUMMARY
[0004] This section aims to summarize some aspects of the embodiments of the present application and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of the specification to avoid obscuring the purpose of this section, abstract and title, and such simplifications or omissions cannot be used to limit the scope of the present application.
[0005] In view of the above existing problems, the present application is proposed.
[0006] To solve the above technical problems, the present application provides the following technical scheme: collecting power user data and preprocessing the power user data; analyzing the preprocessed data using a wavelet transform clustering algorithm to classify power users; combining the power user categories and historical power consumption data to establish a power demand prediction model; predicting power user service demand through the power demand prediction model and visualizing the prediction results.
[0007] As a preferred scheme of the power user service demand prediction method based on big data analysis, the power user data includes user personal information and enterprise information; the user personal information includes gender, age, residence, income, expenditure, provident fund and social security information; and the enterprise information includes enterprise name, type, registered capital and legal person information.
[0008] As a preferred scheme of the power user service demand prediction method based on big data analysis, the preprocessing comprises: using a K nearest neighbor algorithm, selecting R sample instances closest to the information missing data as a class, removing the information missing data, and then counting the number of occurrences of each sample, and the highest frequency is used as replacement data, and the information missing data is replaced with the replacement data; and the power user data is normalized.
[0009] As a preferred scheme of the power user service demand prediction method based on big data analysis, the division of the power user categories comprises: establishing an i-dimensional quantization space, the quantization space is equally divided into n small intervals, each small interval corresponds to n units, and each data point in the preprocessed data is mapped to the quantization space; and the quantization space is convolved with a kernel function to complete data clustering.
[0010] As a preferred scheme of the power user service demand prediction method based on big data analysis, the kernel function comprises:
[0011]
[0012] Wherein, K is the kernel function, C is the complexity of wavelet transform, and T is the number of decomposition layers.
[0013] As a preferred scheme of the power user service demand prediction method based on big data analysis, the establishment of the power demand prediction model comprises: the power demand prediction model comprises a generator and a discriminator, the historical power consumption data is input into the generator, and the generator is used to obtain fake data; the fake data and the power user categories are input into the discriminator, and the discriminator is used to obtain a probability P(x); the loss value of the power demand prediction model is minimized to obtain an optimal probability, so as to optimize the power demand model.
[0014] As a preferred scheme of the power user service demand prediction method based on big data analysis, the loss value of the power demand prediction model comprises:
[0015]
[0016] Wherein, Loss is the loss value of the power demand prediction model, f is the objective function of the power demand prediction model, θ G is a sequence generated by the discriminator, θ D is a sequence generated by the generator, and M is the maximum number of iterations.
[0017] As a preferred scheme of the power user service demand prediction method based on big data analysis, the visualized prediction result comprises visualized display of the prediction result by using an EChart big data visualization tool.
[0018] The present application has the advantages that: by combining a clustering algorithm and a neural network, the present application can process massive data, accurately predict power user service demand, and visualize the prediction result, thereby realizing fine management of power users. BRIEF DESCRIPTION OF DRAWINGS
[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. Among them:
[0020] Figure 1 The flowchart of the power user service demand prediction method based on big data analysis according to the first embodiment of the present application. DETAILED DESCRIPTION
[0021] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.
[0022] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the scope of the present application. Therefore, the present application is not limited to the specific embodiments disclosed below.
[0023] Secondly, the "one embodiment" or "embodiment" referred to herein can include specific features, structures or characteristics in at least one implementation of the present application. In this specification, "in one embodiment" appearing in different places does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.
[0024] The application is described in detail in combination with the schematic diagram. In the detailed description of the embodiments of the application, the cross-sectional view of the device structure is partially enlarged without the general proportion for the convenience of illustration, and the schematic diagram is only an example, which should not limit the scope of protection of the application herein. In addition, the three-dimensional spatial dimensions of length, width and depth should be included in actual production.
[0025] Meanwhile, in the description of the application, it should be noted that the terms "upper, lower, inner and outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the application. In addition, the terms "first, second or third" are only for descriptive purposes and cannot be understood as indicating or implying relative importance.
[0026] Unless otherwise specified and limited in the application, the terms "mounting, connection, connection" should be broadly understood, for example: it can be fixed connection, detachable connection or integral connection; it can also be mechanical connection, electrical connection or direct connection, it can also be indirectly connected through an intermediate medium, and it can also be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the application can be understood according to the specific circumstances.
[0027] Embodiment 1
[0028] Reference Figure 1 For the first embodiment of the application, the embodiment provides a power user service demand prediction method based on big data analysis, comprising:
[0029] S1: Collecting power user data and pre-processing the power user data.
[0030] The power user data includes user personal information and enterprise information;
[0031] The user personal information includes gender, age, residence, income, expenditure, provident fund and social security information; the enterprise information includes enterprise name, type, registered capital and legal person information.
[0032] Further, the power user data is pre-processed:
[0033] (1) Using K-Nearest Neighbor algorithm, selecting the R nearest sample instances of the information missing data as a class, and counting the number of occurrences of each sample after removing the information missing data;
[0034] (2) The highest frequency is used as the replacement data, and the information missing data is replaced with the replacement data;
[0035] (3) Normalizing the power user data.
[0036]
[0037] wherein X is the normalized data, x t is the tth feature component of the input data, x max and x min are the maximum and minimum values of the input data, respectively.
[0038] S2: Analyzing the preprocessed data using a wavelet transform clustering algorithm to divide the power user categories.
[0039] (1) Establishing an i-dimensional quantization space, which is equally divided into n small intervals, each corresponding to n cells, and mapping each data point in the preprocessed data to the quantization space;
[0040] wherein i>2.
[0041] (2) Convoluting the quantization space with a kernel function to complete data clustering.
[0042] The kernel function is:
[0043]
[0044] wherein K is the kernel function, C is the complexity of the wavelet transform, and T is the number of decomposition layers.
[0045] By convoluting the quantization space with the kernel function, C clusters, i.e., C power user categories, are generated.
[0046] S3: Establishing a power demand prediction model in combination with the power user categories and historical power consumption data.
[0047] This embodiment establishes a power demand prediction model based on a generative adversarial network, wherein the power demand prediction model includes a generator and a discriminator, specifically,
[0048] (1) Inputting the historical power consumption data into the generator to obtain fake data through the generator;
[0049] (2) Inputting the fake data and the power user categories into the discriminator to obtain a probability P(x) through the discriminator;
[0050] (3) Minimizing the loss value of the power demand prediction model to obtain an optimal probability to optimize the power demand model.
[0051] The loss value of the power demand prediction model is:
[0052]
[0053] Wherein, Loss is the loss value of the power demand prediction model, f is the objective function of the power demand prediction model, and θ G is the sequence generated by the discriminator, and θ D is the sequence generated by the generator, and M is the maximum number of iterations.
[0054] By minimizing the loss value of the power demand prediction model, the optimal probability is 0.9.
[0055] S4: Predict the power user service demand through the power demand prediction model, and visualize the prediction result.
[0056] The prediction result is visualized by using the EChart big data visualization tool, specifically,
[0057] (1) Introduce the dependent js library of echarts;
[0058] (2) Set the size of the data to be displayed;
[0059] (3) Initialize the instance;
[0060] (4) Specify the configuration items and data of the icon;
[0061] (5) Visualize the data.
[0062] Embodiment 2
[0063] In order to verify the technical effects adopted in the method, the traditional technical scheme and the method are compared and tested in this embodiment, and the test results are compared by scientific means to verify the real effect of the method.
[0064] In order to verify that the method has higher prediction accuracy than the traditional technical scheme, the traditional technical scheme and the method are used to predict the power consumption data (5 categories) of a certain area in this embodiment, and the prediction results are shown in Table 1.
[0065] Table 1: Comparison of power prediction results
[0066]
[0067] As shown in the above table, compared with the traditional technical scheme, the method can accurately predict the power consumption.
[0068] It should be appreciated that embodiments of the present application can be realized by computer hardware, a combination of hardware and software, or by computer instructions stored on a non-transitory computer-readable storage medium. The methods can be implemented in a computer program using standard programming techniques— including non-transitory computer-readable storage media configured with a computer program to implement the methods in which the storage media so configured causes a computer to operate in a specific and predefined manner— according to the methods described in the detailed embodiments and drawings. Each program can be implemented in a high level procedural or object-oriented programming language to communicate with a computer system. However, the programs can be implemented in assembly or machine language, if desired. In any case, the language can be a compiled or interpreted language. Also, the programs can be able to run on standalone systems or in conjunction with other programs or in a distributed computing environment, or any combination thereof. Further, the programs can be stored in any pure or mixed mode execution environment.
[0069] Further, the operations of the processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and / or combinations thereof) can be performed under the control of one or more computer systems configured with executable instructions (e.g., computer programs, one or more computer programs, or one or more applications) to perform the processes, by hardware, or combinations thereof. The computer programs include processor-executable instructions that are stored on a non-transitory computer-readable storage medium.
[0070] Further, the methods can be implemented in any suitable type of computing platform operably connected to, including but not limited to, a personal computer, mini-computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platforms, or in communication with charged particle tools or other imaging devices, and the like. Aspects of the present application can be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated to the computing platform, such as a hard disk, optical read and / or write storage media, RAM, ROM, and the like, such that it can be read by a programmable computer to configure and operate the computer to perform the processes described herein. Further, the machine-readable code, or portions thereof, can be transmitted over wired or wireless networks. The present application described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs to implement the steps described above in conjunction with a microprocessor or other data processor. The present application also includes the computer itself when programmed according to the methods and techniques described herein. The computer programs are able to apply to input data to perform the functions described herein, thereby transforming the input data to generate output data that is stored to non-volatile memory. The output information can also be applied to one or more output devices, such as a display. In the preferred embodiments of the present application, the transformed data represents physical and tangible objects, including specific visual depictions of physical and tangible objects produced on a display.
[0071] As used in this application, the terms "component," "module," "system" and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and / or a computer. By way of illustration, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and / or thread of execution and a component can be localized, partially and / or entirely, in one computer or distributed between two or more computers. Also, these components can execute from various computer-readable media having various data structures stored thereon. The components can communicate by way of local and / or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and / or across a network such as the Internet with other systems via the signal).
[0072] It should be noted that the above-mentioned embodiments are only used to illustrate but not to limit the technical solutions of the present application, and although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalent replaced without departing from the spirit and scope of the technical solutions of the present application, and all of them should be covered in the scope of the claims of the present application.
Claims
1. A method for predicting power consumer service demand based on big data analysis, characterized in that: The method comprises the following steps: Collecting power user data and preprocessing the power user data; Using a wavelet transform clustering algorithm to analyze the preprocessed data to divide power user categories; Establishing a power demand prediction model in combination with the power user categories and historical power consumption data; Predicting power user service demand through the power demand prediction model and visualizing the prediction results; The division of power user categories comprises the following steps: Establishing an i-dimensional quantization space, which is equally divided into n small intervals, each small interval corresponding to n units, and mapping each data point in the preprocessed data to the quantization space; Convolving the quantization space with a kernel function to complete data clustering; The establishment of the power demand prediction model comprises the following steps: The power demand prediction model comprises a generator and a discriminator, the historical power consumption data is input into the generator, and the generator is used to obtain fake data; The fake data and power user categories are input into the discriminator, and the discriminator is used to obtain a probability P(x); Minimizing the loss value of the power demand prediction model to obtain an optimal probability to optimize the power demand model; The loss value of the power demand prediction model comprises the following steps: Wherein, Loss is the loss value of the power demand prediction model, f is the objective function of the power demand prediction model, a sequence generated for the discriminator, a sequence generated for the generator, and M is the maximum number of iterations. The kernel function is as follows: Wherein, K is the kernel function, C is the complexity of wavelet transform, and T is the number of decomposition layers.
2. The big data analytics based power consumer service demand prediction method as claimed in claim 1, wherein: The power user data comprises user personal information and enterprise information; The user personal information comprises gender, age, residence, income, expenditure, provident fund and social security information; The enterprise information comprises enterprise name, type, registered capital and legal person information. 3.The big data analysis based power consumer service demand forecasting method according to claim 1 or 2, characterized in that: The preprocessing comprises the following steps: Using a K-nearest neighbor algorithm, selecting R nearest sample instances of information missing data as a class, counting the number of occurrences of each sample after removing the information missing data, and selecting the highest frequency as the replacement data, and replacing the information missing data with the replacement data; Normalizing the power user data.
4. The big data analytics based power consumer service demand prediction method as claimed in claim 3, wherein: The visualization of the prediction results comprises the following steps: Using an EChart big data visualization tool to visualize the prediction results.