CN117878905A

CN117878905A - Power grid load prediction method, device, equipment and medium based on white noise signals

Info

Publication number: CN117878905A
Application number: CN202311862575.XA
Authority: CN
Inventors: 刘喆; 张春葵; 钟志聪; 谢皓彬; 冼心培; 许悦; 张建锋; 李佛阳; 漆小涛; 马浩平; 丁关柱; 郑瑶; 冯浩; 徐鹏雷
Original assignee: Guangdong Power Grid Co Ltd; Huizhou Power Supply Bureau of Guangdong Power Grid Co Ltd
Current assignee: Guangdong Power Grid Co Ltd; Huizhou Power Supply Bureau of Guangdong Power Grid Co Ltd
Priority date: 2023-12-29
Filing date: 2023-12-29
Publication date: 2024-04-12

Abstract

The invention discloses a power grid load prediction method, device, equipment and medium based on white noise signals. The power grid load prediction method based on the white noise signal comprises the following steps: acquiring the historical grid load of the grid in at least one historical period, and predicting meteorological data of a target period to be predicted to obtain target meteorological data; performing feature extraction on the target meteorological data based on the white noise signals to obtain target meteorological feature information; and predicting the target meteorological characteristic information and the historical grid load by adopting a grid load prediction model based on a bagging algorithm to obtain at least two candidate grid prediction results of the grid, and determining the target grid load of the grid according to the at least two candidate grid prediction results. By the technical scheme, the reliability of the prediction model is improved, and meanwhile, the accuracy of the model in outputting the prediction result is improved.

Description

Power grid load prediction method, device, equipment and medium based on white noise signals

Technical Field

The invention relates to the technical field of power systems, in particular to a power grid load prediction method, device, equipment and medium based on white noise signals.

Background

In the operation, control and planning management of the power system, the load prediction determines the reasonable arrangement of power generation, transmission and distribution, and is not only an important component of the power system planning, but also one of important factors for improving the economic benefit of power enterprises and promoting the national economic development.

Because electric energy cannot be stored in large quantities, the power system must be kept in balance at any time and provide reliable and standard electric energy to various users as much as possible to meet their demands for loads. Therefore, in order to ensure safe and economical operation of the power system, it is necessary to grasp the change rule of the load and the future change trend. Therefore, a highly reliable power grid load prediction method is needed.

Disclosure of Invention

The invention provides a power grid load prediction method, device, equipment and medium based on a white noise signal so as to improve the reliability of a power grid load prediction result.

According to an aspect of the present invention, there is provided a power grid load prediction method based on a white noise signal, the method comprising:

acquiring the historical grid load of the grid in at least one historical period, and predicting meteorological data of a target period to be predicted to obtain target meteorological data; wherein the target weather data includes at least one of annual average air temperature data, annual highest air temperature data, annual lowest air temperature data, and annual sunlight duration data;

performing feature extraction on the target meteorological data based on a white noise signal to obtain target meteorological feature information;

the method comprises the steps of adopting a power grid load prediction model, predicting the target meteorological characteristic information and the historical power grid load based on a bagging algorithm to obtain at least two candidate power grid prediction results of a power grid, and determining the target power grid load of the power grid according to the at least two candidate power grid prediction results; the power grid load prediction model is an extreme learning machine model integrating a bagging algorithm.

According to another aspect of the present invention, there is provided a power grid load prediction apparatus based on a white noise signal, the apparatus comprising:

the data acquisition module is used for acquiring the historical grid load of the grid in at least one historical period, and carrying out meteorological data prediction on a target period to be predicted to obtain target meteorological data; wherein the target weather data includes at least one of annual average air temperature data, annual highest air temperature data, annual lowest air temperature data, and annual sunlight duration data;

the feature extraction module is used for carrying out feature extraction on the target meteorological data based on the white noise signal to obtain target meteorological feature information;

the prediction module is used for predicting the target meteorological characteristic information and the historical power grid load quantity based on a bagging algorithm to obtain at least two candidate power grid prediction results of the power grid, and determining the target power grid load quantity of the power grid according to the at least two candidate power grid prediction results; the power grid load prediction model is an extreme learning machine model integrating a bagging algorithm.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the white noise signal based grid load prediction method of any one of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the white noise signal based grid load prediction method according to any one of the embodiments of the present invention when executed.

According to the technical scheme, the characteristic extraction is carried out on the target meteorological data based on the white noise signals to determine the target meteorological characteristic information, the limit learning machine model based on the set bagging algorithm predicts the target meteorological characteristic information and the historical power grid load, the target power grid load of the power grid to-be-predicted period is output, the reliability of the prediction model is improved, and meanwhile the accuracy of the prediction result output by the model is improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a power grid load prediction method based on a white noise signal according to a first embodiment of the present invention;

fig. 2 is a flowchart of a power grid load prediction method based on a white noise signal according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of a power grid load prediction device based on a white noise signal according to a third embodiment of the present invention;

fig. 4 is a schematic structural diagram of an electronic device implementing a method for predicting a power grid load based on a white noise signal according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1 is a flowchart of a method for predicting a load amount of a power grid according to an embodiment of the present invention, where the method may be performed by a power grid load predicting device based on a white noise signal, and the power grid load predicting device based on a white noise signal may be implemented in hardware and/or software, and the power grid load predicting device based on a white noise signal may be configured in various general-purpose computing devices. As shown in fig. 1, the method includes:

s110, acquiring the historical grid load of the grid in at least one historical period, and predicting the meteorological data of the target period to be predicted to obtain target meteorological data.

The historical period may take years as a period, and the historical period may refer to historical years; the historical grid load may refer to a grid load used by the grid during a historical period, and may be used to represent a power consumption of the grid during the historical period.

The target period may be a period of years, and may refer to a historical year for which a prediction of grid load is to be made.

The target weather data may be used to represent weather information of an area where the power grid is located in the target period, and may include at least one of average air temperature data, highest air temperature data, lowest air temperature data, and solar duration data.

Specifically, the historical power grid load of the power grid in at least one historical period can be obtained, the weather data of the target period to be predicted is predicted, the target weather data is obtained, and therefore the power consumption condition of the historical year of the power grid and the weather data of the year of the power grid to be subjected to load prediction are determined.

Optionally, predicting the meteorological data for the target period to be predicted to obtain target meteorological data, including: taking the historical period as an independent variable and the historical meteorological data in the historical period as a dependent variable, carrying out regression analysis on the historical period and the historical meteorological data in the historical period based on a unitary linear regression analysis method, and determining a unitary linear regression equation about the historical period and the historical meteorological data; and predicting the meteorological data in the target period based on the unitary linear regression equation and the target period to obtain the target meteorological data.

TABLE 1

Historical year	Average air temperature	Minimum air temperature	Maximum air temperature	Number of sunshine hours
					2016	13.8	-15.2	37.8	2502.1
2017	14.2	-10.1	38.5	2479.2
					2018	13.6	-13.9	39.9	2475.4
2019	13.8	-14.4	38	2542.3
					2020	13.8	-12.8	37.8	2441.4
2021	13.6	-19.6	37.2	2285
					2022	13.38	-12	39	2579.1

The historical meteorological data may refer to meteorological information of an area where the power grid is located in a historical period. For example, the historical meteorological data in the historical period can be shown in table 1, and as can be seen from table 1, the data fluctuation of each item of historical meteorological data in the historical year is stable, and the same historical meteorological data in different years only fluctuates in a small range. Accordingly, in the embodiment of the invention, each item of historical meteorological data in the historical period can be used as an independent variable by taking the historical period (historical year) as an independent variable, regression analysis is performed on the historical period and the historical meteorological data in the historical period based on a unified linear regression analysis method, a unified linear regression equation corresponding to each item of historical meteorological data in the historical period is built, and each item of meteorological data in the target period can be predicted by inputting the target period into the built unified linear regression equation, so that the target meteorological data can be obtained. Alternatively, the unitary linear regression equation may be determined by the least squares method.

Optionally, in the embodiment of the present invention, in the process of obtaining the historical grid load in the historical period, the obtained historical grid load may be preprocessed in advance, and exemplary preprocessing operations may include low-frequency outlier rejection, missing data filling, and so on.

And S120, carrying out feature extraction on the target meteorological data based on the white noise signals to obtain target meteorological feature information.

The target weather feature information is used for representing data feature information of the target weather data.

Specifically, a white noise signal can be added to the target meteorological data in the process of extracting the characteristics of the target meteorological data, so that target meteorological characteristic information corresponding to the target meteorological data is obtained, the influence of noise on the target meteorological characteristic information is reduced, and the accuracy of a target meteorological characteristic information result is improved. Alternatively, the target weather characteristic information may be represented in a matrix form.

S130, a power grid load prediction model is adopted, target weather feature information and historical power grid load are predicted based on a bagging algorithm to obtain at least two candidate power grid prediction results of the power grid, and the target power grid load of the power grid is determined according to the at least two candidate power grid prediction results.

The power grid load prediction model can be an extreme learning machine model integrating a bagging algorithm;

the candidate power grid prediction results can refer to at least two prediction results generated by a power grid load prediction model based on a bagging algorithm; the target prediction result may refer to a prediction result finally output by the power grid load prediction model.

Specifically, a power grid load model may be adopted, input variables formed by target feature information and historical power grid load amounts under at least two historical periods are predicted based on a bagging algorithm to obtain at least two candidate power grid prediction results of the power grid, and the target power grid load amount of the power grid is determined through the at least two candidate power grid prediction results. Alternatively, the number of historical grid loads in the input variable may be adaptively set according to one skilled in the art, and exemplary, the historical grid loads in the input variable may be historical grid loads of six historical periods adjacent to the target period. Alternatively, the input variables may be in the form of a matrix.

Alternatively, in an embodiment of the present invention, the grid load prediction model may include at least two weak learners generated based on a bagging algorithm. Wherein the weak learner may refer to an extreme learning machine.

Optionally, a power grid load prediction model is adopted, target weather feature information and historical power grid load are predicted based on a bagging algorithm to obtain at least two candidate power grid prediction results of the power grid, and the target power grid load of the power grid is determined according to the at least two candidate power grid prediction results, including: predicting target meteorological information characteristics and at least one historical power grid load by adopting at least two weak learners included in a power grid load prediction model to obtain at least two candidate power grid prediction results of a power grid; and determining the average value of the prediction results of the at least two candidate grids as the target grid load.

Specifically, at least two weak learners included in the power grid load model are adopted to respectively predict input variables formed by the target weather information characteristics and at least one historical power grid load quantity, at least two candidate power grid prediction results are obtained, and the average value of the at least two candidate power grid prediction results is used as the target power grid load quantity finally output by the power grid load model.

The bagging algorithm is selected as an integration strategy, the extreme learning machine is used as a weak learner, and a plurality of weak learners are combined into one strong learner to be used as a power grid load prediction model, so that the accuracy of model prediction is improved.

Optionally, in the training process of the initial power grid load prediction model, the number of input neurons, the number of output neurons and the number of hidden neurons of each weak learner in the initial power grid load prediction model may be preset. By way of example, the number of input neurons may be used to represent the dimension of a parameter in an input variable, e.g., the number of input neurons may be set to 10 (target weather feature information and historical grid load for six historical cycles); the number of the output neurons can be set to be 1, and the number is used for representing the number of parameters output by the model; the number of bank neurons can be set to 35 for reducing errors and calculation of the model during training.

Optionally, in the training process of the initial power grid load prediction model, the historical meteorological data of the area where the power grid is located and the historical power grid load of the power grid can be used as sample data, the initial power grid load prediction model is trained, and the training sample of each weak learner in the initial power grid load prediction model can be set to be a preset multiple, for example, 0.6 times of the sample data, so that the phenomenon of fitting excessively in the training process is avoided.

Example two

Fig. 2 is a flowchart of a power grid load prediction method based on a white noise signal, which is provided in the second embodiment of the present invention, and is further refined based on the foregoing embodiment, and specific steps of extracting characteristics of target meteorological data based on the white noise signal to obtain target meteorological characteristic information are provided. It should be noted that, in the embodiments of the present invention, the details of the description of other embodiments may be referred to, and will not be described herein. As shown in fig. 2, the method includes:

s210, acquiring the historical grid load of the grid in at least one historical period, and predicting the meteorological data of the target period to be predicted to obtain target meteorological data.

S220, generating weather noise data based on the white noise signal and the target weather data.

The weather noise data may be target weather data carrying a white noise signal.

Specifically, the white noise signal may be added to the target weather data based on the white noise signal and the target weather data to generate weather noise data.

Optionally, generating weather noise data based on the white noise signal and the target weather data includes: at least one set of white noise signals of the same amplitude and opposite signs are added to the target weather data to generate at least one set of weather noise data.

The weather noise data may refer to weather data carrying white noise signals, and may include two weather noise data with opposite signs.

Specifically, at least one group of two white noise signals with the same amplitude and opposite signs can be added to each piece of weather data in the target weather data, at least one group of weather noise data with opposite signs is generated, and a weather noise sequence corresponding to the target weather data is formed. Alternatively, each item of weather data in the target weather data may correspond to the presence of a weather noise sequence.

Optionally, the weather noise data is determined by the following formula:

wherein y is _i (t) is the ith meteorological noise data,and->Weather noise data carrying white noise signals with opposite signs are carried in the weather noise data; x (t) is target meteorological data, +.>And->Is two white noise signals with the same amplitude and opposite signs.

By adding at least one group of two white noise signals with the same amplitude and opposite signs to each item of weather data in the target weather data, the influence of irrelevant noise on the target weather data can be reduced, and the data quality of the target weather data can be improved.

S230, empirical mode decomposition is carried out on the meteorological noise data, and at least two signal components corresponding to the meteorological noise data are determined.

Among them, empirical mode decomposition (Empirical Mode Decomposition, EMD) is a data processing method commonly used for signal analysis, decomposing into a plurality of natural mode functions (Intrinsic Mode Function, IMF). The target meteorological data belongs to the meteorological data, a plurality of complex factors are coupled, certain noise exists, and the traditional empirical mode decomposition method cannot directly conduct characteristic decomposition on the target meteorological data to obtain the target meteorological characteristic information, so that a group of complementary white noise signals are required to be added to the target meteorological data in advance, and the influence of noise in the target meteorological data in the characteristic information obtaining process is reduced.

The signal component may refer to an IMF component generated by empirical mode decomposition of the weather noise data.

Specifically, data processing may be performed on weather noise data of opposite sign based on empirical mode decomposition to generate at least two signal components. Optionally, the number of signal components corresponding to positive-sign weather noise is the same as the number of signal components corresponding to negative-sign weather noise data.

Alternatively, the signal component may be represented by the following formula:

where n represents the number of signal components,and->The ith signal component of the weather noise data with the opposite sign white noise signal of the jth item in the weather noise sequence is represented, respectively.

S240, generating target weather characteristic information according to at least two signal components corresponding to the weather noise data.

Specifically, the target weather feature information may be generated by at least two signal components obtained by empirical mode decomposition of weather noise data and a residual sequence.

Optionally, generating the target weather feature information according to at least two signal components corresponding to the weather noise data includes: determining an average signal component of the meteorological noise data according to at least two signal components corresponding to the meteorological noise data; the target weather feature information is generated based on the average signal component of the weather noise data.

Specifically, an average value of at least two signal components corresponding to weather noise data with opposite signs corresponding to the target weather data may be calculated, and the average signal component is determined, and the target weather characteristic information of the target weather data is determined according to the average signal component and the residual sequence.

Alternatively, the target weather characteristic information may be determined by the following formula

Wherein, IMF _j The method comprises the steps that the average signal component of the j-th item of meteorological data in target meteorological data is represented by 2n, the number of the signal components is represented by A, the target meteorological characteristic information is represented by m, the number of the meteorological noise data in a meteorological noise sequence is represented by m, and the residual sequence is represented by R (t).

By determining the characteristic information of the target meteorological data based on the meteorological noise data with the white noise signals with opposite signs and the residual sequence, the influence of irrelevant noise on the characteristic information is reduced, and the accuracy of the characteristic information is improved.

S250, a power grid load prediction model is adopted, target weather feature information and historical power grid load are predicted based on a bagging algorithm to obtain at least two candidate power grid prediction results of the power grid, and the target power grid load of the power grid is determined according to the at least two candidate power grid prediction results.

According to the technical scheme, the meteorological noise data corresponding to the target meteorological data are generated based on the white noise signals, the meteorological noise data are subjected to empirical mode decomposition to determine at least two signal components, the target meteorological characteristic information is determined through the at least two signal components, interference of irrelevant noise in the complex meteorological data is reduced, accuracy of the target meteorological characteristic information is improved, and accuracy of a prediction result obtained according to the target meteorological characteristic information is further improved.

Example III

Fig. 3 is a schematic structural diagram of a power grid load prediction device based on a white noise signal according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes:

the data acquisition module 310 is configured to acquire a historical grid load of the grid in at least one historical period, and perform weather data prediction on a target period to be predicted to obtain target weather data; the target meteorological data comprise at least one of annual average air temperature data, annual highest air temperature data, annual lowest air temperature data and annual sunshine duration data;

the feature extraction module 320 is configured to perform feature extraction on the target meteorological data based on the white noise signal, so as to obtain target meteorological feature information;

the prediction module 330 is configured to predict, using a power grid load prediction model, the target weather feature information and the historical power grid load based on a bagging algorithm to obtain at least two candidate power grid prediction results of the power grid, and determine the target power grid load of the power grid according to the at least two candidate power grid prediction results; the power grid load prediction model is an extreme learning machine model integrating a bagging algorithm.

Optionally, the feature extraction module 320 includes:

the signal sequence determining unit is used for determining a white noise signal sequence corresponding to the target meteorological data based on the white noise signal and the target meteorological data;

the signal component determining unit is used for respectively performing empirical mode decomposition on at least one white noise signal in the white noise signal sequence and determining at least one signal component corresponding to the white noise signal;

and the characteristic generating unit is used for updating the target meteorological data according to at least one signal component corresponding to the white noise signal to generate target meteorological characteristic information.

Alternatively, the signal sequence determining unit may be specifically configured to: and adding at least one group of white noise signals with the same amplitude and opposite signs to the target meteorological data, and generating a white noise signal sequence corresponding to the target meteorological data.

Alternatively, the feature generation unit may be specifically configured to: determining an average signal component of the white noise signal according to at least one signal component corresponding to the white noise signal; and updating the target meteorological data according to the average signal component of at least one white noise signal to generate target meteorological characteristic information.

Alternatively, the grid load prediction model may include at least two weak learners generated based on a bagging algorithm.

Optionally, the prediction module 330 may be specifically configured to predict the target weather information feature and the at least one historical grid load by using at least two weak learners included in the grid load prediction model, so as to obtain at least two candidate grid prediction results of the grid; and determining the average value of the prediction results of the at least two candidate grids as the target grid load.

Optionally, the data acquisition module 310 further includes:

an equation determining unit for determining a unitary linear regression equation for the historical period and the historical weather data based on regression analysis of the historical period and the historical weather data in the historical period by using the historical period as an independent variable and the historical weather data in the historical period as a dependent variable;

the data acquisition unit is used for predicting the meteorological data in the target period based on the unitary linear regression equation and the target period to obtain target meteorological data.

The power grid load prediction device based on the white noise signal provided by the embodiment of the invention can execute the power grid load prediction method based on the white noise signal provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Example IV

Fig. 4 shows a schematic diagram of an electronic device 410 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 4, the electronic device 410 includes at least one processor 411, and a memory, such as a Read Only Memory (ROM) 412, a Random Access Memory (RAM) 413, etc., communicatively connected to the at least one processor 411, wherein the memory stores computer programs executable by the at least one processor, and the processor 411 may perform various suitable actions and processes according to the computer programs stored in the Read Only Memory (ROM) 412 or the computer programs loaded from the storage unit 418 into the Random Access Memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 may also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other through a bus 414. An input/output (I/O) interface 415 is also connected to bus 414.

Various components in the electronic device 410 are connected to the I/O interface 415, including: an input unit 416 such as a keyboard, a mouse, etc.; an output unit 417 such as various types of displays, speakers, and the like; a storage unit 418, such as a magnetic disk, optical disk, or the like; and a communication unit 419 such as a network card, modem, wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

The processor 411 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 411 performs the various methods and processes described above, such as a grid load prediction method based on white noise signals.

In some embodiments, the white noise signal based grid load prediction method may be implemented as a computer program tangibly embodied on a computer readable storage medium, such as storage unit 418. In some embodiments, some or all of the computer program may be loaded and/or installed onto the electronic device 410 via the ROM 412 and/or the communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the white noise signal based grid load prediction method described above may be performed. Alternatively, in other embodiments, the processor 411 may be configured by any other suitable means (e.g. by means of firmware) to perform a white noise signal based grid load prediction method.

Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A white noise signal-based power grid load prediction method, comprising:

acquiring the historical grid load of the grid in at least one historical period, and predicting meteorological data of a target period to be predicted to obtain target meteorological data; the target meteorological data comprise at least one of average air temperature data, highest air temperature data, lowest air temperature data and sunshine duration data;

2. The method of claim 1, wherein the performing feature extraction on the target weather data based on the white noise signal to obtain target weather feature information includes:

generating weather noise data based on the white noise signal and the target weather data; the meteorological noise data are target meteorological data carrying white noise signals;

performing empirical mode decomposition on the meteorological noise data to determine at least two signal components corresponding to the meteorological noise data;

and generating target weather characteristic information according to at least two signal components corresponding to the weather noise data.

3. The method of claim 2, wherein the generating weather noise data based on the white noise signal and the target weather data comprises:

at least one set of white noise signals with the same amplitude and opposite signs are added to the target meteorological data, and at least one set of meteorological noise data is generated.

4. The method of claim 2, wherein generating the target weather feature information from the at least two signal components corresponding to the weather noise data comprises:

determining an average signal component of the meteorological noise data according to at least two signal components corresponding to the meteorological noise data;

and generating target weather characteristic information based on the average signal component of the weather noise data.

5. The method of claim 1, wherein the grid load prediction model comprises at least two weak learners generated based on a bagging algorithm; correspondingly, the predicting the target weather feature information and the historical power grid load by adopting a power grid load predicting model based on a bagging algorithm to obtain at least two candidate power grid predicting results of the power grid, and determining the target power grid load of the power grid according to the at least two candidate power grid predicting results, including:

predicting the target meteorological information characteristics and at least one historical power grid load by adopting at least two weak learners included in a power grid load prediction model to obtain at least two candidate power grid prediction results of a power grid;

and determining the average value of the prediction results of the at least two candidate grids as a target grid load.

6. The method according to claim 1, wherein the predicting the weather data for the target period to be predicted to obtain the target weather data includes:

taking the historical period as an independent variable, taking historical meteorological data in the historical period as a dependent variable, carrying out regression analysis on the historical period and the historical meteorological data in the historical period based on a unitary linear regression analysis method, and determining a unitary linear regression equation about the historical period and the historical meteorological data;

and predicting the meteorological data in the target period based on the unitary linear regression equation and the target period to obtain target meteorological data.

7. A white noise signal-based power grid load prediction apparatus, comprising:

8. The apparatus of claim 7, wherein the feature extraction module comprises:

a signal component determining unit, configured to perform empirical mode decomposition on at least one white noise signal in the white noise signal sequence, and determine at least one signal component corresponding to the white noise signal;

9. An electronic device, the electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the white noise signal based grid load prediction method of any one of claims 1-6.

10. A computer readable storage medium storing computer instructions for causing a processor to implement the white noise signal based grid load prediction method of any one of claims 1-6 when executed.