CN114626636A

CN114626636A - Power grid load prediction method and device, modeling method, computer equipment and medium

Info

Publication number: CN114626636A
Application number: CN202210354777.2A
Authority: CN
Inventors: 周丹; 邓旭; 邓美玲; 罗钰娇; 李嘉杰
Original assignee: Guangdong Power Grid Co Ltd; Shaoguan Power Supply Bureau Guangdong Power Grid Co Ltd
Current assignee: Guangdong Power Grid Co Ltd; Shaoguan Power Supply Bureau Guangdong Power Grid Co Ltd
Priority date: 2022-04-06
Filing date: 2022-04-06
Publication date: 2022-06-14

Abstract

The invention discloses a power grid load prediction method, a power grid load prediction device, a modeling method, computer equipment and a medium, wherein the prediction method comprises the following steps: acquiring net load original data of a power grid; carrying out data preprocessing on the net load original data to obtain a gray generation sequence; determining a target gray prediction model according to the gray generation sequence, wherein the target gray prediction model is a discrete gray prediction model established based on a target fluctuation coefficient; and determining a net load predicted value according to the target gray prediction model. According to the method, the improved grey prediction model is constructed by introducing the parameters representing the load fluctuation, the improved grey prediction model is adopted to predict the power grid load, the prediction precision is high, and the economic dispatching and safe operation performance of the power grid can be improved.

Description

Power grid load prediction method, device, modeling method, computer equipment and medium

Technical Field

The invention relates to the technical field of load prediction of power systems, in particular to a power grid load prediction method, a power grid load prediction device, a modeling method, computer equipment and a medium.

Background

With the access of renewable energy sources such as hydropower and photovoltaic to the power grid, the fluctuation and randomness of the power grid are increased, and the economic dispatching and stable operation of the power grid face greater challenges. The net load is used as a difference value between the micro-grid load and the renewable energy output, and accurate prediction of the net load is a key for ensuring economic dispatching and safe operation of the micro-grid.

In the prior art, a common load prediction method includes: according to a traditional grey prediction Model (GM) prediction method and a Discrete grey prediction Model (GM) prediction method, the grey prediction Model can predict a small amount of net load data sequences with low data integrity and reliability.

However, the existing prediction method has the following problems that a certain error exists in the differential steering differential solving process of the traditional grey prediction model; the volatility and the randomness of load data after the renewable energy is accessed are not fully considered by the discrete gray prediction model, the two models are applied to the renewable energy micro-grid system, the prediction results have certain deviation, the prediction precision of the load data is low, and the safe operation and the economic dispatching of a power grid can be influenced.

Disclosure of Invention

The invention provides a power grid load prediction method, a power grid load prediction device, a modeling method, computer equipment and a medium, aiming at improving a gray prediction model by introducing parameters representing load fluctuation and achieving high prediction precision.

According to an aspect of the present invention, there is provided a power grid load prediction method, including:

acquiring net load original data of a power grid;

carrying out data preprocessing on the net load original data to obtain a gray generation sequence;

determining a target gray prediction model according to the gray generation sequence, wherein the target gray prediction model is a discrete gray prediction model established based on a target fluctuation coefficient;

and determining a net load predicted value according to the target gray prediction model.

Optionally, the functional expression of the target gray prediction model is:

x⁽¹⁾(k+1)＝μ₁×x⁽¹⁾(k)^α+μ₂

wherein alpha is a fluctuation coefficient, x⁽¹⁾(k +1) is the (k +1) th data in the gray generation sequence, x⁽¹⁾(k) Generating the kth data in sequence, μ for the gray color₁To develop the coefficient, mu₂The amount is gray.

According to another aspect of the present invention, there is provided a power grid load prediction model modeling method, used in the above load prediction method, the modeling method including:

acquiring net load original data of a power grid;

creating a discrete grey prediction model containing fluctuation coefficients;

determining a target fluctuation coefficient, a development coefficient and a gray action quantity of the discrete gray prediction model according to a gray generation sequence;

and creating a target gray prediction model according to the target fluctuation coefficient, the development coefficient and the gray effect quantity.

According to another aspect of the present invention, there is provided a power grid load prediction apparatus for performing the above power grid load prediction method, the apparatus including: the system comprises an original data acquisition unit, a data processing unit and a data processing unit, wherein the original data acquisition unit is used for acquiring net load original data of a power grid; the data processing unit is used for carrying out data preprocessing on the net load original data to obtain a gray generation sequence; the model correction unit is used for determining a target grey prediction model according to the grey generation sequence, and the target grey prediction model is a discrete grey prediction model established based on a target fluctuation coefficient; and the prediction execution unit is used for determining a net load prediction value according to the target gray prediction model.

According to another aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the grid load prediction method as described above when executing the program; alternatively, the modeling method described above is implemented.

According to another aspect of the present invention, there is provided a computer readable storage medium, on which a computer program is stored, which program, when executed by a processor, implements a grid load prediction method as described above; alternatively, the modeling method described above is implemented.

According to the technical scheme, a gray generation sequence is obtained by preprocessing the net load original data, a target gray prediction model is determined according to the gray generation sequence, the target gray prediction model is a discrete gray prediction model established based on a target fluctuation coefficient, a net load prediction value is determined according to the target gray prediction model, the problem that the existing renewable energy micro-grid load prediction precision is low is solved, the gray prediction model is improved by introducing the fluctuation coefficient representing the load data change degree, the prediction precision is improved, and the economic dispatching and safe operation performance of the renewable energy micro-grid are improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of a method for predicting a load of a power grid according to an embodiment of the present invention;

fig. 2 is a flowchart of another grid load prediction method according to an embodiment of the present invention;

fig. 3 is a flowchart of another power grid load prediction method according to an embodiment of the present invention;

fig. 4 is a flowchart of a modeling method of a power grid load prediction model according to a second embodiment of the present invention;

fig. 5 is a schematic structural diagram of a power grid load prediction apparatus according to a third embodiment of the present invention;

fig. 6 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, shall fall within the protection scope of the present invention.

It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present invention and the above-described drawings, 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 one

Fig. 1 is a flowchart of a power grid load prediction method according to an embodiment of the present invention, which is applicable to an application scenario in which a renewable energy microgrid performs load prediction, where the renewable energy microgrid may be a hydroelectric microgrid, a photovoltaic microgrid, or a wind power generation microgrid. The method may be performed by a grid load prediction device, which may be implemented in hardware and/or software, and may be configured in a grid dispatching system.

As shown in fig. 1, the power grid load prediction method specifically includes the following steps:

step S1: and acquiring the net load raw data of the power grid.

The net load original data is calculated by subtracting the renewable energy output original data from the power grid load original data; the load original data of the power grid is the sum of the consumed electric power of various electric equipment born by the power grid at any moment; the raw data of the output of the renewable energy source is the power generation output power of the renewable energy source power generation system, and typically, the renewable energy source power generation system can be a hydroelectric power generation system.

In this step, the method for acquiring the net load original data of the power grid specifically includes the following steps: the method comprises the steps of obtaining a sampling period and a sampling step length, recording power grid load original data and renewable energy output original data of a plurality of continuous sampling nodes based on the sampling step length and the sampling period, and calculating the net load original data of each sampling node according to the power grid load original data and the renewable energy output original data.

Wherein the sampling period is a period of time before a target period of the payload prediction.

For example, if the number of data in the payload raw data is defined as N, the payload raw data sequence may be represented as: x⁽⁰⁾＝{x⁽⁰⁾(1)，x⁽⁰⁾(2)，......，x⁽⁰⁾(N) }, in which, X⁽⁰⁾Representing the payload raw data sequence, x⁽⁰⁾(1) Representing the payload raw data, x, of the 1 st sampling node⁽⁰⁾(2) Representing the payload raw data of the 2 nd sampling node, … …, x⁽⁰⁾(N) represents the payload raw data of the Nth sampling node.

Step S2: and carrying out data preprocessing on the net load original data to obtain a gray generation sequence.

The gray generation sequence is a data sequence which is established according to the net load original data and has load change regularity, the net load original data has high volatility and stability in a microgrid with renewable energy, and the influence of randomness of the net load original data on model training can be reduced by taking the gray generation sequence as model training data.

Optionally, the data preprocessing may include an accumulation generation operation, the gray generation sequence including: the payload accumulation generates a sequence.

For example, if the number of data in the payload raw data is defined as N, the gray generation sequence can be represented as X⁽¹⁾＝{x⁽¹⁾(1)，x⁽¹⁾(2)，……，x⁽¹⁾(N) }, in which, X⁽¹⁾Representing a payload accumulation generating sequence, x⁽¹⁾(1) Representing the payload accumulated data, x, of the 1 st sampling node⁽¹⁾(2) Payload accumulation data representing the 2 nd sampling node, … …, c⁽¹⁾(N) payload accumulated data for the nth sampling node, the payload accumulated data satisfying, with the payload raw data:

x⁽¹⁾(k) representing payload accumulated data, x, of the kth sampling node⁽⁰⁾(i) Representing the payload raw data of the ith sampling node, k and i being positive integers greater than or equal to 1. Based on the foregoing formula, x⁽¹⁾(1) Equal to the payload raw data of the 1 st sampling node, x⁽¹⁾(2) Equal to the cumulative sum of the payload raw data of the 1 st sampling node to the payload raw data of the 2 nd sampling node, … …, x⁽¹⁾(N) is equal to the cumulative sum of the payload raw data of the 1 st sampling node to the payload raw data of the Nth sampling node.

Step S3: and determining a target gray prediction model according to the gray generation sequence, wherein the target gray prediction model is a discrete gray prediction model established based on the target fluctuation coefficient.

The target gray prediction model can be a first-order univariate discrete gray model comprising three parameters, and the three parameters of the model comprise a fluctuation coefficient, a development coefficient and a gray effect quantity, wherein the fluctuation coefficient is a parameter representing the change degree of the net load original data, and the target fluctuation coefficient is a target value of the fluctuation coefficient calculated based on specific data in a gray generation sequence; the development coefficient is a parameter for representing the development trend of the grey generation sequence predicted value; the amount of gray effect is a parameter of the relationship of the change in the response data.

Alternatively, the functional expression of the target gray prediction model may be:

x⁽¹⁾(k+1)＝μ₁×x⁽¹⁾(k)^α+μ₂(formula one)

Wherein, alpha is a fluctuation coefficient, x⁽¹⁾(k +1) is the (k +1) th data in the gray generation sequence, x⁽¹⁾(k) Generating the kth data in sequence, μ, for gray₁To develop the coefficient, mu₂The grey effect is indicated.

With reference to equation one, substituting k-1, 2, 3, … …, N-1 into equation one results in the simultaneous equation:

introducing a matrix vector notation:

in the step, the fluctuation coefficient alpha can be calculated by an assigning method and an error analysis method, and the development coefficient mu can be calculated by a least square method₁And amount of Grey effect μ₂The calculated target fluctuation coefficient alpha₁Coefficient of development mu₁And amount of Grey action μ₂Substituting the formula I to obtain the final target gray colorAnd (6) measuring the model.

Step S4: and determining a net load predicted value according to the target gray prediction model.

In this step, data in the gray generation sequence may be substituted into the target gray prediction model, and the net load accumulated data prediction value of the time period after the sampling period may be calculated

And calculating a net load prediction value according to the inverse of the accumulation generation operation

Specifically, before the net load prediction is carried out on the target time interval, firstly, a period of time before the target time interval is determined as a sampling period, a sampling step length is set, the power grid load original data and the renewable energy output original data of the N sampling nodes are recorded, and the power grid load original data of the same sampling node is adopted to subtract the renewable energy output original data to obtain the net load original data corresponding to the N sampling nodes. Accumulating the N net load original data to obtain a gray generation sequence X⁽¹⁾(i.e., payload accumulation generation sequence). Generating gray into sequence X⁽¹⁾Substituting the data in the step (a) into a pre-established three-parameter discrete gray prediction model, wherein the three parameters comprise: coefficient of fluctuation alpha, coefficient of development mu₁And amount of Grey effect μ₂Calculating a target fluctuation coefficient alpha by an assigning method and an error analysis method₁And calculating the coefficient of development mu by least squares₁And amount of Grey effect μ₂The calculated target fluctuation coefficient alpha₁Coefficient of development mu₁And amount of Grey effect μ₂And substituting the formula I to obtain a final target gray prediction model. And substituting the data in the gray generation sequence into the target gray prediction model, and calculating the predicted value of the net load accumulated data of the time period after the sampling period

And calculating net negatives from the inverse of the accumulate generating operationPredicted value of load

Therefore, a gray generation sequence is obtained by carrying out data preprocessing on the net load original data, a target gray prediction model is determined according to the gray generation sequence, the target gray prediction model is a discrete gray prediction model established based on a target fluctuation coefficient, and a net load prediction value is determined according to the target gray prediction model, so that the problem that the prediction result of the existing prediction method is large in deviation after the renewable energy source is connected to the power grid is solved, the gray prediction model is improved by introducing the fluctuation coefficient representing the load data change degree, and the prediction precision is improved.

Optionally, fig. 2 is a flowchart of another grid load prediction method provided in an embodiment of the present invention, and on the basis of fig. 1, a specific implementation of determining the target fluctuation coefficient is exemplarily shown.

As shown in fig. 2, the step S3 specifically includes the following steps:

step S301: and obtaining a discrete gray prediction model containing fluctuation coefficients.

The function structure of the discrete gray prediction model is the same as that of the target gray prediction model, and the specific function expression is shown in formula one.

Step S302: and assigning the fluctuation coefficient of the discrete gray prediction model based on a preset assignment interval and a preset step length to obtain an assignment model.

The fluctuation coefficient is a parameter for representing the change degree of the net load original data, and can fluctuate up and down by a value of 1 according to the data difference in the sequence.

Optionally, the preset assignment interval may be: [0.5, 1.5 ]; the preset step size may be 0.01.

Illustratively, with reference to formula one, if the fluctuation coefficient is defined as 1.01, the corresponding assignment model is: x is the number of⁽¹⁾(k+1)＝μ₁×x⁽¹⁾(k)^1.01+μ₂。

Step S303: and carrying out error analysis on the predicted value and the actual value of the assignment model, and determining a target fluctuation coefficient according to an error analysis target function.

The predicted value of the assignment model is a net load predicted value calculated according to the assignment model, and the real value is net load original data calculated according to the sampling data.

Optionally, the error analysis objective function may be an objective function that takes as the minimum value of the average absolute percentage error of the predicted values and the actual values, wherein the average absolute percentage error is the average percentage of the deviation between the absolute values and the actual values of the deviations between all the individual predicted payload values and the raw payload data; or taking the minimum value of the average absolute error of the predicted value and the true value as an objective function, wherein the average absolute error is the average of the absolute values of the deviations between all the single net load predicted values and the net load original data.

Illustratively, if the minimum value of the average absolute percentage error between the predicted value and the true value is taken as an objective function, the payload raw data sequence X is defined⁽⁰⁾If the number of data in the error analysis target function is N, the expression of the error analysis target function is shown in formula two:

wherein k is 1,2, … …, N;

representing the predicted value of the assignment model.

Taking the minimum value of the average absolute error of the predicted value and the true value as an objective function, and defining the original data sequence X of the net load if the net load is defined⁽⁰⁾If the number of data in the error analysis target function is N, the expression of the error analysis target function is shown in formula three:

wherein k is 1,2, … …, N;

representing the predicted value of the assignment model.

Optionally, determining the target fluctuation coefficient according to the error analysis objective function includes: determining a target fluctuation coefficient according to the minimum value of the average absolute percentage error of the predicted value and the actual value of the assignment model; or determining the target fluctuation coefficient according to the minimum value of the average absolute error between the predicted value and the real value of the assignment model.

Specifically, determining the fluctuation coefficient of the assignment model corresponding to the minimum value of the average absolute percentage error as a target fluctuation coefficient by combining a formula II and a formula III; or determining the fluctuation coefficient of the assignment model corresponding to the minimum average absolute error value as the target fluctuation coefficient.

Step S304: and determining a target gray prediction model according to the target fluctuation coefficient.

Specifically, the target fluctuation coefficient is defined as α₁The corresponding target gray prediction model is DGM (1,1, α)₁) Calculating a target gray prediction model as DGM (1,1, alpha) by adopting a least square method₁) Ash parameter (coefficient of development μ)₁And amount of Grey effect μ₂) Ensuring the true value x⁽¹⁾(k +1) and payload prediction

The minimum simulation error S satisfies:

adopting Matlab software to program and execute iterative operation, calculating DGM (1,1, alpha)₁) Coefficient of development mu₁And amount of Grey effect μ₂And obtaining a final target gray prediction model.

Therefore, according to the technical scheme of the embodiment of the invention, the improved grey prediction model is constructed by introducing the parameters representing the load fluctuation, and the power grid load is predicted by adopting the improved grey prediction model, so that the model is simple and the prediction precision is high.

Optionally, fig. 3 is a flowchart of another power grid load prediction method provided by an embodiment of the present invention, and on the basis of fig. 1, before prediction is performed, a specific implementation manner of model verification is added, which is beneficial to ensuring model prediction accuracy.

As shown in fig. 3, the load prediction method specifically includes the following steps:

step S1: and acquiring the net load raw data of the power grid.

Step S3: and determining a target gray prediction model according to the gray generation sequence.

Step S501: and carrying out error analysis on the predicted value and the true value of the target gray prediction model.

Step S502: and correcting the fluctuation coefficient of the target gray prediction model according to the error analysis result.

Step S503: and establishing a new target gray prediction model according to the corrected fluctuation coefficient.

Optionally, the error analysis method comprises at least one of: the method comprises a mean absolute error analysis method, a mean absolute percentage error analysis method and a precision grade evaluation method.

The average absolute error analysis method is the average of the absolute values of the deviations between all the single net load predicted values and the net load original data, and the expression of the average absolute error refers to the third formula.

The average absolute percentage error analysis method is an average percentage of deviation between the absolute value and the actual value of deviation between all the single net load predicted values and the net load original data, and the expression of the average absolute percentage error can refer to the formula two.

The criteria for the evaluation of the accuracy grade can be referred to the following table 1.

Grade of accuracy	Relative error
		First order (you)	0.01
Second grade (Liang)	0.05
		Third grade (poor)	0.10
Four-stage (unqualified)	0.20

As shown in table 1, the relative error may be an average absolute percentage error, that is, if the average percentage of deviation between the absolute value and the actual value of the deviation between the single payload predicted value and the payload raw data of the target gray prediction model is less than 0.01, the accuracy level of the target gray prediction model is one level (excellent).

Specifically, after error analysis is performed on a predicted value and a true value of the target gray prediction model, if an error of the target gray prediction model is smaller than a preset error threshold, or a precision level of the target gray prediction model reaches a preset level (for example, one level), it is determined that the target gray prediction model meets requirements; and if the error of the target gray prediction model is larger than a preset error threshold value, or the precision grade of the target gray prediction model does not reach a preset grade (for example, one grade), correcting the fluctuation coefficient of the target gray prediction model until the error or the precision grade of the target gray prediction model reaches a set standard. And in the subsequent load prediction process, calculating the net load prediction value by adopting the corrected target gray prediction model.

The prediction method of the present invention will be described in detail below with reference to specific examples.

Illustratively, the sample period may be defined as 7: 00-9: 00, the sampling step length is 15 minutes, the power grid load original data and the renewable energy output original data of each sampling node are recorded, a group of sampling data shown in table 2 is established, the sampling period is 2 hours, the sampling step length is 15 minutes, and the data of 8 sampling nodes are recorded.

With reference to table 2, the method described in step S1 is adopted to calculate the payload raw data corresponding to 8 sampling nodes as follows:

X⁽⁰⁾＝{448.11，618.92，783.93，947，1100.95，1273.3，1427.89，1579.83}

wherein 448.11 is the payload raw data of the 1 st sampling node, 618.92 is the payload raw data of the 2 nd sampling node, and … … and 1579.83 are the payload raw data of the 8 th sampling node.

After the payload raw data is obtained, the method described in step S2 is used to perform the accumulation generation operation to obtain a gray generation sequence:

X⁽¹⁾＝{448.11，1067.03，1850.62，2797.62，3898.57，5171.87，6599.76，8179.59}

obtaining a payload raw data sequence X⁽⁰⁾And gray generation sequence X⁽¹⁾Then, the gray parameters of the target gray prediction model are determined by the method described in the above steps S301 to S305, and the target fluctuation coefficient α is calculated by taking the minimum value of the average absolute percentage error between the predicted value and the true value as the target function₁Equal to 0.94, at this time, the target gray prediction model is DGM (1,1, 0.94), and the iterative operation is executed by adopting Matlab software programming, so that the development coefficient mu of the DGM (1,1, 0.94) is calculated₁1.9846 sum Grey Effect μ₂455.0049, from this, the functional expression for the target gray prediction model is: x is a radical of a fluorine atom⁽¹⁾(k+1)＝1.9846×x⁽¹⁾(k)^0.94+455.0049。

The gray color is generated into the sequence X by the method described in the above step S4⁽¹⁾Substituting the data into a target grey prediction model, and calculating to obtain the net load prediction value of each sampling node:

{448.11，623.45，782.67，943.64，1106.12，1268.29，1427.90，1582.62}。

by adopting the method recorded in the step S501, the error analysis is performed on the payload raw data and the payload predicted value of each sampling node, the relative error of the target gray prediction model is obtained to be 0.0028, the relative error is less than 0.01, the accuracy grade of the target gray prediction model is judged to be one grade, and the payload prediction in the target time period can be carried out according to the target gray prediction model meeting the requirements.

Illustratively, the target period for combining the data in table 2 to perform load prediction is 9: 00-10: 00 for example, 4 predictions can be obtained, in order: the net load predicted value of 9:15 is 1730.24; the net load predicted value of 9:30 is 1868.77; the net load predicted value of 9:45 is 1996.51; the net load predicted value of 10:00 is 2112.07.

Therefore, according to the technical scheme of the embodiment of the invention, the discrete grey prediction model is improved by introducing the parameter representing the load volatility, and the net load prediction value is determined according to the improved discrete grey prediction model, so that the problem of low load prediction precision of the existing renewable energy micro-grid is solved, and the grey prediction model is improved by introducing the fluctuation coefficient representing the load data change degree, so that the prediction precision is improved, and the economic dispatching and safe operation performance of the renewable energy micro-grid are improved.

Example two

Based on the above embodiment, the second embodiment of the present invention provides a power grid load prediction model modeling method, which is used for the load prediction method, and the prediction model in this embodiment introduces a parameter representing load volatility to improve a discrete gray prediction model.

Fig. 4 is a flowchart of a modeling method of a power grid load prediction model according to a second embodiment of the present invention.

As shown in fig. 4, the modeling method specifically includes the following steps:

step S10: and acquiring net load original data of the power grid.

Step S20: and carrying out data preprocessing on the net load original data to obtain a gray generation sequence.

Step S30: and creating a discrete gray prediction model containing the fluctuation coefficients, wherein the discrete gray prediction model is a first-order univariate discrete gray prediction model.

Wherein, the fluctuation coefficient is a parameter for representing the change degree of the net load original data.

Step S40: and determining a target fluctuation coefficient, a development coefficient and a gray acting quantity of the discrete gray prediction model according to the gray generation sequence.

Step S50: and determining a target gray prediction model according to the target fluctuation coefficient, the development coefficient and the gray action quantity.

Optionally, the functional expression of the target gray prediction model is: x is the number of⁽¹⁾(k+1)＝μ₁×x⁽¹⁾(k)^α+μ₂(ii) a Wherein alpha is a fluctuation coefficient, x⁽¹⁾(k +1) is the (k +1) th data in the gray generation sequence, x⁽¹⁾(k) Generating the kth data in sequence, μ, for gray₁To develop the coefficient, mu₂The grey effect is indicated.

Optionally, determining the target fluctuation coefficient of the discrete gray prediction model according to the gray generation sequence includes: assigning a fluctuation coefficient of the discrete gray prediction model based on a preset assignment interval and a preset step length to obtain an assignment model; and carrying out error analysis on the predicted value and the actual value of the assignment model, and determining a target fluctuation coefficient according to an error analysis target function.

Optionally, the preset assignment interval is: [0.5, 1.5 ]; the preset step size is 0.01.

Therefore, according to the technical scheme of the embodiment of the invention, the improved grey prediction model is constructed by introducing the parameters representing the load volatility, so that the model prediction precision is favorably improved, and the economic dispatching and safe operation performance of the renewable energy microgrid are improved.

EXAMPLE III

Based on any of the above embodiments, a third embodiment of the present invention provides a power grid load prediction apparatus, which can execute the power grid load prediction method provided in any of the above embodiments, or the modeling method provided in any of the above embodiments, and has corresponding functional modules and beneficial effects of the execution method.

Fig. 5 is a schematic structural diagram of a power grid load prediction apparatus according to a third embodiment of the present invention.

As shown in fig. 5, the apparatus 00 includes: a raw data acquisition unit 101, a data processing unit 102, a model modification unit 103, and a prediction execution unit 104. The system comprises an original data acquisition unit 101, a data processing unit and a data processing unit, wherein the original data acquisition unit 101 is used for acquiring net load original data of a power grid; the data processing unit 102 is configured to perform data preprocessing on the payload raw data to obtain a gray generation sequence; the model correction unit 103 is used for determining a target grey prediction model according to the grey generation sequence, wherein the target grey prediction model is a discrete grey prediction model established based on a target fluctuation coefficient; and the prediction execution unit 104 is used for determining a net load prediction value according to the target gray prediction model.

Optionally, the model modification unit 103 is configured to perform: obtaining a discrete gray prediction model containing a fluctuation coefficient; assigning a fluctuation coefficient of the discrete gray prediction model based on a preset assignment interval and a preset step length to obtain an assignment model; carrying out error analysis on the predicted value and the actual value of the assignment model, and determining a target fluctuation coefficient according to an error analysis target function; and determining a target gray prediction model according to the target fluctuation coefficient.

Example four

Based on any one of the above embodiments, a fourth embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the method for predicting a power grid load as described above is implemented; or, the power grid load prediction method is realized.

Fig. 6 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. Computer 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. The computer device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, 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. 6, the computer device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM)12, a Random Access Memory (RAM)13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM)12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the computer device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

A number of components in the computer device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the computer device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 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, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as a grid load prediction method or a modeling method.

In some embodiments, the grid load prediction method or modeling method described above may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18.

In some embodiments, part or all of the computer program may be loaded and/or installed onto the computer device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the grid load prediction method or the modeling method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the grid load prediction method or the modeling method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Computer programs for implementing the methods of the present invention can 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 performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a 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. A 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 a computer 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) by which a user may provide input to the computer device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can 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, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end 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 back-end, 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. A client and server are generally 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 host and VPS service are overcome.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.

The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A power grid load prediction method is characterized by comprising the following steps:

acquiring net load original data of a power grid;

2. The method of claim 1, wherein the functional expression of the target gray prediction model is:

x⁽¹⁾(k+1)＝μ₁×x⁽¹⁾(k)^α+μ₂

wherein, alpha is a fluctuation coefficient, x⁽¹⁾(k +1) is the (k +1) th data in the gray generation sequence, x⁽¹⁾(k) Generating the kth data, μ, in the sequence for the gray color₁To develop the coefficient, mu₂The grey effect is indicated.

3. The method of claim 1, wherein determining a target gray prediction model from the gray generation sequence comprises:

obtaining a discrete gray prediction model containing a fluctuation coefficient;

assigning the fluctuation coefficient of the discrete gray prediction model based on a preset assignment interval and a preset step length to obtain an assignment model;

carrying out error analysis on the predicted value and the real value of the assignment model, and determining the target fluctuation coefficient according to an error analysis target function;

and determining the target gray prediction model according to the target fluctuation coefficient.

4. The method of claim 3, wherein determining the target ripple coefficient according to an error analysis objective function comprises:

determining the target fluctuation coefficient according to the minimum value of the average absolute percentage error between the predicted value and the real value of the assignment model; alternatively, the first and second electrodes may be,

and determining the target fluctuation coefficient according to the minimum value of the average absolute error between the predicted value and the real value of the assignment model.

5. The method of claim 3, wherein the preset assignment interval is: [0.5, 1.5 ]; the preset step length is 0.01.

6. The method of claim 1, further comprising:

carrying out error analysis on the predicted value and the real value of the target gray prediction model;

and correcting the fluctuation coefficient of the target gray prediction model according to the error analysis result.

7. A modeling method of a power grid load prediction model, which is used for the load prediction method of any one of claims 1 to 6, and comprises the following steps:

acquiring net load original data of a power grid;

creating a discrete grey prediction model containing fluctuation coefficients;

8. A grid load prediction device for performing the grid load prediction method of any one of claims 1-6, the device comprising:

the system comprises an original data acquisition unit, a data processing unit and a data processing unit, wherein the original data acquisition unit is used for acquiring net load original data of a power grid;

the data processing unit is used for carrying out data preprocessing on the net load original data to obtain a gray generation sequence;

the model correction unit is used for determining a target grey prediction model according to the grey generation sequence, and the target grey prediction model is a discrete grey prediction model established based on a target fluctuation coefficient;

and the prediction execution unit is used for determining a net load prediction value according to the target gray prediction model.

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements a grid load prediction method as claimed in any one of claims 1 to 6;

alternatively, a method of modelling a grid load prediction model as claimed in claim 7 is implemented.

10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out a grid load prediction method according to any one of claims 1-6;