Temperature regulation electric quantity prediction method, system and equipment based on support vector machine, and medium

Abstract

The invention belongs to the technical field of power grid electric quantity prediction, and discloses a temperature regulation electric quantity prediction method, system and equipment based on a support vector machine, and a medium, so as to solve the problem of temperature regulation electric quantity prediction. The method comprises the following steps: acquiring historical temperature data, historical daily electricity consumption data and a preset temperature time window of a target industry in a predicted target area, and performing moving weighted average based on the historical temperature data, the historical daily electricity consumption data and the preset temperature time window so as to respectively obtain an accumulated highest temperature, an accumulated lowest temperature and an accumulated average temperature; after abnormal data in the historical daily electricity consumption data are removed, polynomial regression models are sequentially constructed by combining the accumulated highest temperature, the accumulated lowest temperature and the accumulated average temperature for fitting, so that a corresponding polynomial regression model fitting curve and corresponding historical temperature adjustment electricity consumption data are obtained; and using support vector machine regression to predict the future temperature regulation electric quantity of the target industry in the target region. According to the method, the defect that nonlinear characteristics are neglected during data processing in the prior art is overcome, and more accurate prediction of the temperature regulation electric quantity is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid electricity prediction, and specifically relates to a temperature control electricity prediction method, system, equipment and medium based on a support vector machine. Background Art

[0002] The consumption of electric power in various industries shows a certain periodic law, especially in summer and winter, due to the combined effect of multiple factors such as climate, the power consumption usually shows an upward trend. The present invention defines this part of the increased power as "temperature control power". Accurately predicting the temperature control power is of great significance for power grid companies to fully grasp and reasonably allocate summer power supply demand and ensure the smooth and orderly production activities of various industries. However, due to the lack of special metering equipment, the specific value of the temperature control power is difficult to accurately calculate. To solve this problem, the invention patent CN201510056866.9 discloses a method for predicting daily power consumption of power grids based on temperature fluctuations. The method uses a linear time trend regression equation to decompose the temperature control power, and uses the ARMA algorithm to predict the model. However, it is worth noting that this method does not fully consider the nonlinear characteristics of the data during data processing. Therefore, if the method of the invention patent CN201510056866.9 is directly adopted, it will be difficult to effectively solve the problem of nonlinear data prediction. Summary of the invention

[0003] Based on the above-mentioned shortcomings and deficiencies in the prior art, one of the objects of the present invention is to at least solve one or more of the above-mentioned problems in the prior art. In other words, one of the objects of the present invention is to provide a temperature control power prediction method, system, equipment and medium based on a support vector machine that meets one or more of the aforementioned needs, aiming to achieve accurate prediction of temperature control power and provide solid technical support for power dispatching and resource optimization allocation of power grid enterprises.

[0004] In order to achieve the above-mentioned object of the invention, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for predicting temperature control power based on a support vector machine, comprising the steps of: S1. Obtain historical temperature data and historical daily electricity consumption data of the target industry in the forecast target area; S2. Obtain a preset temperature time window, and based on this, perform a moving weighted average on the daily maximum temperature, daily minimum temperature, and daily average temperature in the historical temperature data to obtain a cumulative maximum temperature, a cumulative minimum temperature, and a cumulative average temperature, respectively; S3, after removing abnormal data in the historical daily power consumption data, construct a polynomial regression model in sequence based on the cumulative maximum temperature, the cumulative minimum temperature and the cumulative average temperature for fitting, so as to obtain a corresponding polynomial regression model fitting curve; S4. Obtain the corresponding historical temperature control power based on the polynomial regression model fitting curve, thereby obtaining historical temperature control power data and using a support vector machine to perform regression prediction to obtain predicted temperature control power data.

[0005] As a preferred solution, the temperature time window is four days; The calculation formula of the cumulative maximum temperature is: , where Indicates the cumulative maximum temperature, , , , , Respectively represent the maximum temperature of each day within the temperature time window; The calculation formula of the cumulative minimum temperature is: , where Indicates the cumulative maximum temperature, , , , , Respectively represent the lowest temperature of each day within the temperature time window; The calculation formula of the cumulative average temperature is: , where represents the cumulative average temperature, , , , , Respectively represent the average temperature of each day in the temperature time window.

[0006] As a preferred solution, the step S3 of removing abnormal data from the historical daily power consumption data includes the following steps: Get the preset power time window; Eliminate the daily electricity consumption data during holidays within the electricity time window.

[0007] As a preferred solution, the calculation formula of the polynomial regression model fitting curve is:

[0008] In the formula, represents the polynomial order, Represents the parameters to be fitted.

[0009] As a preferred solution, the step S4 of obtaining the corresponding historical temperature control power based on the polynomial regression model fitting curve includes the following steps: Obtain the lowest points corresponding to the polynomial regression model fitting curve and the cumulative maximum temperature, the cumulative minimum temperature, and the cumulative average temperature, and calculate the historical basic electricity based on this; When the daily maximum temperature is greater than the corresponding minimum point, or the daily minimum temperature is less than the corresponding minimum point, the difference between the daily maximum temperature and its corresponding minimum point, or the difference between the daily minimum temperature and its corresponding minimum point, is recorded as the historical temperature control power.

[0010] As a preferred solution, the calculation formula of the historical basic electricity is: , In the formula, represents the lowest point corresponding to the cumulative maximum temperature in the polynomial regression model fitting curve, represents the lowest point corresponding to the cumulative minimum temperature in the polynomial regression model fitting curve, It represents the lowest point corresponding to the cumulative average temperature in the polynomial regression model fitting curve.

[0011] As a preferred solution, the step S4 uses a support vector machine to perform regression prediction to obtain predicted temperature control power data, including the steps of: Normalizing the historical temperature control power data; Get the preset kernel function and its parameters; Building an SVR model based on the normalized historical temperature control power data, and obtaining a fault tolerance parameter C and a fitting accuracy ε of the SVR model; Based on the kernel function and its parameters, the SVR model is trained on the basis of the fault tolerance parameter C and the fitting accuracy ε; The predicted temperature control power data is obtained based on the trained SVR model prediction.

[0012] In a second aspect, the present invention provides a temperature control power prediction system based on a support vector machine, which is used to implement the temperature control power prediction method as described in the first aspect.

[0013] In a third aspect, the present invention provides an electronic device, wherein the computer device includes a memory, a processor, and a computer program, and when the computer program is executed by the processor, the temperature control power prediction method as described in the first aspect is implemented.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the temperature control power prediction method as described in the first aspect.

[0015] Compared with the prior art, the present invention has the following beneficial effects: In view of the lack of dedicated measurement equipment for thermostatic power consumption and the difficulty in accurate statistics, the present invention uses historical temperature data and historical daily power consumption data after moving weighted average processing to construct a polynomial regression model for fitting processing. On this basis, the present invention further uses the acquired nonlinear historical thermostatic power consumption data and processes it through a regression prediction method, which effectively makes up for the defect of the prior art that ignores nonlinear characteristics when processing data, thereby achieving a more accurate prediction of thermostatic power consumption.

[0016] Further or more detailed beneficial effects will be described in detail in conjunction with specific examples in the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of the temperature control power prediction method described in an embodiment of the present invention.

[0019] Figure 2 It is a structural diagram of an electronic device described in an embodiment of the present invention.

[0020] Figure Number: 200. Electronic equipment; 201, processor; 202, communication bus; 203, user interface; 204, network interface; 205, memory. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0022] In the following description, multiple embodiments of the present invention are provided, and different embodiments may be replaced or combined, so the present invention may also be considered to include all possible combinations of the same and / or different embodiments described. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present invention should also be considered to include embodiments containing one or more of A, B, C, and D, all other possible combinations, even though the embodiment may not be clearly described in the following text.

[0023] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present invention. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the described order, and various steps may be added, omitted or combined. In addition, the features described in some examples may be combined in other examples.

[0024] In order to facilitate a better understanding of the embodiments of the present invention, before explaining the specific implementation modes of the present invention in detail, its application scenarios are first described.

[0025] The temperature control power prediction method described in the embodiments of this specification is applied to power management and dispatching processes. In these scenarios, the application of the temperature control power prediction method is intended to achieve accurate prediction of temperature control power and provide solid technical support for power dispatching and resource optimization allocation of power grid companies.

[0026] The following is a brief explanation of the support vector machine, temperature control power, polynomial regression model, kernel function, and SVR model involved in multiple embodiments of this specification: Support vector machine is a supervised learning algorithm, especially suitable for classification and regression analysis. It classifies data by finding an optimal hyperplane, which is called the "maximum margin hyperplane" because it can maximize the distance between data points of different categories and the plane, thus providing stronger generalization ability and better classification effect. In regression problems, a variant of SVM is called Support Vector Regression (SVR).

[0027] Temperature control power refers to the power consumed to adjust the ambient temperature (such as heating or cooling). In the power system, temperature control power is an important load component, and its changes are often affected by many factors such as weather, season, and user behavior. Accurate prediction of temperature control power helps the power grid better understand and allocate summer power demand to ensure that production activities in various industries can proceed normally.

[0028] A polynomial regression model is a form of regression analysis in which the regression function is a polynomial of the input variables. Compared to linear regression, polynomial regression is able to capture nonlinear relationships between variables, thus providing more accurate predictions.

[0029] The kernel function is a key concept in support vector machines, which allows the algorithm to calculate in high-dimensional space without explicitly calculating high-dimensional features. By using the kernel function, SVM is able to process non-linearly separable data sets and map them into a high-dimensional space, making the data linearly separable in the high-dimensional space.

[0030] The SVR model is an application of support vector machines in regression problems. Similar to SVM, the SVR model also attempts to find an optimal hyperplane (or decision boundary), but this hyperplane is not used to classify data points, but to minimize the error between the predicted value and the actual value. By introducing an error metric called the ε-insensitive loss function, the SVR model can provide accurate predictions of nonlinear relationships while maintaining the simplicity of the model.

[0031] Embodiment 1: like Figure 1 As shown, the present embodiment provides a method for predicting thermostat power based on a support vector machine, comprising the steps of: S1, obtaining historical temperature data and historical daily power consumption data of a target industry in a prediction target area; S2, obtaining a preset temperature time window, and based on this, performing a moving weighted average on the daily maximum temperature, daily minimum temperature and daily average temperature in the historical temperature data to obtain the cumulative maximum temperature, the cumulative minimum temperature and the cumulative average temperature, respectively; S3, after eliminating abnormal data in the historical daily power consumption data, a polynomial regression model is sequentially constructed in combination with the cumulative maximum temperature, the cumulative minimum temperature and the cumulative average temperature for fitting, so as to obtain a corresponding polynomial regression model fitting curve; S4, obtaining the corresponding historical thermostat power based on the polynomial regression model fitting curve, thereby obtaining the historical thermostat power data and using the support vector machine for regression prediction to obtain the predicted thermostat power data.

[0032] It is understandable that when forecasting the daily electricity consumption of a regional power grid, in view of the significant differences in electricity consumption characteristics of various industries, it is necessary to use the distribution network ledger information to conduct detailed electricity decomposition and forecasting by industry classification in order to improve the accuracy of the forecast. With the continuous accumulation of multi-source data such as historical electricity data and meteorological data in various industries, the use of big data and machine learning technology to conduct in-depth analysis of the electricity consumption characteristics of various industries and their influencing factors can significantly improve the forecast accuracy of industry electricity, thereby optimizing the effect of short-term power and electricity forecasting. The thermostatic electricity prediction method proposed in this embodiment uses a support vector machine to perform regression prediction on the nonlinear data of the target industry in the target area, which effectively makes up for the deficiency of the existing technology that ignores the nonlinear characteristics of the data. In addition, the method has a wide range of applicability and can be flexibly applied to thermostatic electricity prediction in different regions and industries.

[0033] Specifically, this embodiment provides a preferred implementation, the temperature time window is four days; the calculation formula of the cumulative maximum temperature is , where Indicates the cumulative maximum temperature, , , , , Respectively represent the highest temperature of each day in the temperature time window; the calculation formula of the cumulative minimum temperature is: , where Indicates the cumulative maximum temperature, , , , , Respectively represent the lowest temperature of each day in the temperature time window; the calculation formula of the cumulative average temperature is: , where represents the cumulative average temperature, , , , , Respectively represent the average temperature of each day in the temperature time window.

[0034] Specifically, this embodiment provides a preferred implementation of step S3, wherein the removal of abnormal data in the historical daily electricity consumption data comprises the steps of: obtaining a preset electricity time window; and removing daily electricity consumption data on holidays within the electricity time window.

[0035] Specifically, this embodiment provides a preferred implementation, and the calculation formula of the polynomial regression model fitting curve is:

[0036] In the formula, represents the polynomial order, Represents the parameters to be fitted.

[0037] Specifically, this embodiment provides a preferred implementation of step S4, wherein the corresponding historical temperature control power is obtained based on the polynomial regression model fitting curve, including the steps of: obtaining the lowest points corresponding to the polynomial regression model fitting curve and the cumulative maximum temperature, the cumulative minimum temperature, and the cumulative average temperature, respectively, and calculating the historical basic power based on this; when the daily maximum temperature is greater than the corresponding minimum point, or the daily minimum temperature is less than the corresponding minimum point, the difference between the daily maximum temperature and its corresponding minimum point, or the difference between the daily minimum temperature and its corresponding minimum point, is recorded as the historical temperature control power.

[0038] Specifically, this embodiment provides a preferred implementation method, and the calculation formula of the historical basic electricity is: , where represents the lowest point corresponding to the cumulative maximum temperature in the polynomial regression model fitting curve, represents the lowest point corresponding to the cumulative minimum temperature in the polynomial regression model fitting curve, It represents the lowest point corresponding to the cumulative average temperature in the polynomial regression model fitting curve.

[0039] Specifically, this embodiment provides a preferred implementation of step S4, and uses a support vector machine to perform regression prediction to obtain predicted thermostat power data, including the steps of: normalizing the historical thermostat power data; obtaining a preset kernel function and its parameters; constructing an SVR model based on the normalized historical thermostat power data, and obtaining the fault tolerance parameter C and fitting accuracy ε of the SVR model; training the SVR model based on the kernel function and its parameters on the basis of the fault tolerance parameter C and fitting accuracy ε; and predicting the predicted thermostat power data based on the trained SVR model.

[0040] Embodiment 2: This embodiment provides a temperature control power prediction system based on a support vector machine, which is used to implement the temperature control power prediction method as described in the first embodiment.

[0041] Embodiment three: like Figure 2 As shown, this embodiment provides an electronic device, which may include: at least one processor, at least one network interface, a user interface, a memory, and at least one communication bus.

[0042] The communication bus can be used to realize the connection and communication among the above-mentioned components.

[0043] The user interface may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0044] The network interface may include but is not limited to a Bluetooth module, an NFC module, a Wi-Fi module, etc.

[0045] Among them, the processor may include one or more processing cores. The processor uses various interfaces and lines to connect the various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory, and calling data stored in the memory. Optionally, the processor can be implemented in at least one hardware form of DSP, FPGA, and PLA. The processor can integrate one or a combination of CPU, GPU, modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display; the modem is used to handle wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor, but may be implemented separately through a chip.

[0046] Among them, the memory may include RAM or ROM. Optionally, the memory includes a non-transitory computer-readable medium. The memory can be used to store instructions, programs, codes, code sets or instruction sets. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory may also be at least one storage device located away from the aforementioned processor. The memory as a computer storage medium may include an operating system, a network communication module, a user interface module, and a thermostat power prediction application. The processor can be used to call the thermostat power prediction application stored in the memory and execute the thermostat power prediction steps mentioned in the above-mentioned embodiments.

[0047] Embodiment 4: This embodiment provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is executed on a computer or a processor, the computer or the processor executes the above-mentioned Figure 1 One or more steps in the illustrated embodiment. If the components of the electronic device described above are implemented in the form of software functional units and sold or used as independent products, they can be stored in the computer-readable storage medium.

[0048] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of this specification is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state drive (SSD)).

[0049] A person of ordinary skill in the art can understand that all or part of the processes in the method of the first embodiment can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. The aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes. In the absence of conflict, the technical features in this embodiment and the implementation scheme can be combined arbitrarily.

[0050] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0051] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0052] The above is only an exemplary embodiment of the present invention and cannot be used to limit the scope of the present invention. That is, any equivalent changes and modifications made according to the teachings of the present invention are still within the scope of the present invention. After considering the specification and practicing the disclosure here, it will be easy for those skilled in the art to think of the implementation scheme of the present invention. The present invention is intended to cover any modification, use or adaptation of the present invention, which follows the general principles of the present invention and includes common knowledge or customary technical means in the art that are not recorded in the present invention. The description and examples are only regarded as exemplary, and the scope and spirit of the present invention are defined by the claims.

Claims

1. A method for predicting temperature control power based on support vector machine, characterized in that: Includes steps: S1. Obtain historical temperature data and historical daily electricity consumption data of the target industry in the forecast target area; S2. Obtain a preset temperature time window, and based on this, perform a moving weighted average on the daily maximum temperature, daily minimum temperature, and daily average temperature in the historical temperature data to obtain a cumulative maximum temperature, a cumulative minimum temperature, and a cumulative average temperature, respectively; S3, after removing abnormal data in the historical daily power consumption data, construct a polynomial regression model in sequence based on the cumulative maximum temperature, the cumulative minimum temperature and the cumulative average temperature for fitting, so as to obtain a corresponding polynomial regression model fitting curve; S4. Obtain the corresponding historical temperature control power based on the polynomial regression model fitting curve, thereby obtaining historical temperature control power data and using a support vector machine to perform regression prediction to obtain predicted temperature control power data.

2. The method for predicting temperature control power based on support vector machine according to claim 1, characterized in that: The temperature time window is four days; The calculation formula of the cumulative maximum temperature is: , where Indicates the cumulative maximum temperature, , , , , Respectively represent the maximum temperature of each day within the temperature time window; The calculation formula of the cumulative minimum temperature is: , where Indicates the cumulative maximum temperature, , , , , Respectively represent the lowest temperature of each day within the temperature time window; The calculation formula of the cumulative average temperature is: , where represents the cumulative average temperature, , , , , Respectively represent the average temperature of each day in the temperature time window.

3. The method for predicting temperature control power based on support vector machine according to claim 2, characterized in that: Step S3 of eliminating abnormal data in the historical daily power consumption data includes the following steps: Get the preset power time window; Eliminate the daily electricity consumption data during holidays within the electricity time window.

4. The method for predicting temperature control power based on support vector machine according to claim 3, characterized in that: The calculation formula of the polynomial regression model fitting curve is: In the formula, represents the polynomial order, Represents the parameters to be fitted.

5. The method for predicting temperature control power based on support vector machine according to claim 4, characterized in that: The step S4 of obtaining the corresponding historical temperature adjustment power based on the polynomial regression model fitting curve includes the following steps: Obtain the lowest points corresponding to the polynomial regression model fitting curve and the cumulative maximum temperature, the cumulative minimum temperature, and the cumulative average temperature, and calculate the historical basic electricity based on this; When the daily maximum temperature is greater than the corresponding minimum point, or the daily minimum temperature is less than the corresponding minimum point, the difference between the daily maximum temperature and its corresponding minimum point, or the difference between the daily minimum temperature and its corresponding minimum point, is recorded as the historical temperature control power.

6. The method for predicting temperature control power based on support vector machine according to claim 5, characterized in that: The calculation formula of the historical basic electricity is: ， In the formula, represents the lowest point corresponding to the cumulative maximum temperature in the polynomial regression model fitting curve, represents the lowest point corresponding to the cumulative minimum temperature in the polynomial regression model fitting curve, It represents the lowest point corresponding to the cumulative average temperature in the polynomial regression model fitting curve.

7. The method for predicting temperature control power based on support vector machine according to claim 6, characterized in that: Step S4 uses a support vector machine to perform regression prediction to obtain predicted temperature control power data, including the following steps: Normalizing the historical temperature control power data; Get the preset kernel function and its parameters; Building an SVR model based on the normalized historical temperature control power data, and obtaining a fault tolerance parameter C and a fitting accuracy ε of the SVR model; Based on the kernel function and its parameters, the SVR model is trained on the basis of the fault tolerance parameter C and the fitting accuracy ε; The predicted temperature control power data is obtained based on the trained SVR model prediction.

8. A temperature control power prediction system based on support vector machine, characterized in that: Used to implement the temperature control power prediction method as described in any one of claims 1 to 7.

9. A computer device, comprising a memory, a processor and a computer program, characterized in that: When the computer program is executed by a processor, the temperature control power prediction method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the temperature control power prediction method according to any one of claims 1 to 7 is implemented.

Images