CN114626636B - Power grid load forecasting method, device, modeling method, computer equipment and medium - Google Patents
Power grid load forecasting method, device, modeling method, computer equipment and medium Download PDFInfo
- Publication number
- CN114626636B CN114626636B CN202210354777.2A CN202210354777A CN114626636B CN 114626636 B CN114626636 B CN 114626636B CN 202210354777 A CN202210354777 A CN 202210354777A CN 114626636 B CN114626636 B CN 114626636B
- Authority
- CN
- China
- Prior art keywords
- gray
- prediction model
- target
- power grid
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 90
- 238000013277 forecasting method Methods 0.000 title 1
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims description 28
- 230000006870 function Effects 0.000 claims description 25
- 230000009471 action Effects 0.000 claims description 22
- 238000011161 development Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 description 41
- 238000009825 accumulation Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000010248 power generation Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for AC mains or AC distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Power Engineering (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a power grid load prediction method, a device, a modeling method, computer equipment and a medium, wherein the prediction method comprises the steps of obtaining net load original data of a power grid; the method comprises the steps of preprocessing data of payload raw 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 payload predicted value according to the target gray prediction model. According to the invention, the improved gray prediction model is constructed by introducing the parameters representing the load fluctuation, and the power grid load is predicted by adopting the improved gray prediction model, so that the prediction precision is high, and the economic dispatch and the safe operation performance of the power grid are improved.
Description
Technical Field
The invention relates to the technical field of power system load prediction, in particular to a power grid load prediction method, a device, a modeling method, computer equipment and a medium.
Background
With renewable energy sources such as hydropower, photovoltaics and the like connected to a power grid, the fluctuation and randomness of the power grid are increased, and the economic dispatch and stable operation of the power grid face greater challenges. The net load is used as the difference between the load of the micro-grid and the output of renewable energy sources, and the accurate prediction is the key for ensuring the economic dispatch and the safe operation of the micro-grid.
In the prior art, the common load prediction methods comprise a traditional gray prediction Model (Gray Forecast Model, GM) prediction method and a discrete gray prediction Model (DISCRETE GRAY Forecast Model, GM) prediction method, wherein the gray prediction Model can predict a small amount of payload data sequences with low data integrity and reliability.
However, the existing prediction method has the problems that the traditional gray prediction model has certain error in the differential steering differential solving process, the discrete gray prediction model does not fully consider the fluctuation and randomness of load data after renewable energy is accessed, the two models are applied to a renewable energy micro-grid system, the prediction results have certain deviation, the prediction accuracy of the load data is low, and the safe operation and economic dispatching of a power grid are affected.
Disclosure of Invention
The invention provides a power grid load prediction method, a device, a modeling method, computer equipment and a medium, so as to improve a gray prediction model by introducing parameters representing load fluctuation, and the prediction precision is high.
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;
performing data preprocessing on the payload 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 predicted model.
Optionally, the functional expression of the target gray prediction model is:
x(1)(k+1)＝μ1×x(1)(k)α+μ2
Where α is a fluctuation coefficient, x (1) (k+1) is the (k+1) th data in the gray generation sequence, x (1) (k) is the kth data in the gray generation sequence, μ 1 is a development coefficient, and μ 2 is a gray action amount.
According to another aspect of the present invention, there is provided a modeling method of a power grid load prediction model for the above load prediction method, the modeling method including:
acquiring net load original data of a power grid;
performing data preprocessing on the payload original data to obtain a gray generation sequence;
creating a discrete gray prediction model containing fluctuation coefficients;
Determining a target fluctuation coefficient, a development coefficient and a gray action amount 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 action amount.
According to another aspect of the invention, a power grid load prediction device is provided, and the device is used for executing the power grid load prediction method, and comprises an original data acquisition unit, a data processing unit, a model correction unit and a prediction execution 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 gray prediction model 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 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 invention, a computer device is provided, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, said processor implementing the grid load prediction method as described above or the modeling method as described above when executing said program.
According to another aspect of the present invention, a computer readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements a grid load prediction method as described above, or implements a modeling method as described above.
According to the technical scheme, the data preprocessing is carried out on the net load original data to obtain the gray generation sequence, and the target gray prediction model is determined 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 net load prediction value is determined according to the target gray prediction model, the problem of low load prediction precision of the existing renewable energy micro-grid is solved, the gray prediction model is improved by introducing the fluctuation coefficient representing the change degree of the load data, the prediction precision is improved, and the economic dispatch and the safe operation performance of the renewable energy micro-grid are improved.
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 according to an embodiment of the present invention;
FIG. 2 is a flowchart of another power grid load prediction method according to an embodiment of the present invention;
FIG. 3 is a flowchart of yet 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 device 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 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 is noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present invention and in the foregoing figures, 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 or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a power grid load prediction method provided in an embodiment of the present invention, where the embodiment may be applicable to an application scenario of load prediction of a renewable energy micro-grid, where the renewable energy micro-grid may be a hydropower micro-grid, a photovoltaic micro-grid or a wind power generation micro-grid. The method may be performed by a grid load prediction device, which may be implemented in hardware and/or software, which may be configured in a grid dispatching system.
As shown in fig. 1, the power grid load prediction method specifically includes the following steps:
and step S1, acquiring net load original data of the power grid.
The net load raw data is calculated by subtracting renewable energy source output raw data from power grid load raw data, the power grid load raw data is the sum of power consumption of various electric equipment born by a power grid at any moment, the renewable energy source output raw data is power generation output power of a renewable energy source power generation system, and the renewable energy source power generation system can be a hydroelectric power generation system typically.
The method specifically comprises the steps of acquiring a sampling period and a sampling step length, recording power grid load original data and renewable energy source 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 source output original data.
Wherein the sampling period is a period of time prior to the target period of the payload prediction.
Illustratively, 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) }, where X (0) represents the payload raw data sequence, X (0) (1) represents the payload raw data of the 1 st sampling node, X (0) (2) represents the payload raw data of the 2 nd sampling node, and X (0) (N) represents the payload raw data of the N th sampling node.
And step S2, carrying out data preprocessing on the payload original data to obtain a gray generation sequence.
The gray generation sequence is a data sequence with load change regularity established according to the original data of the net load, the original data of the net load has larger volatility and stability in the micro-grid provided with the renewable energy source, and the gray generation sequence is used as model training data, so that the influence of the randomness of the original data of the net load on model training can be reduced.
Alternatively, the data preprocessing may include an accumulation generation operation, and the gray generation sequence includes a payload accumulation generation sequence.
Illustratively, if the number of data in the payload raw data is defined as N, the gray generation sequence may be denoted as X (1)＝{x(1)(1),x(1)(2),……,x(1) (N) }, where X (1) represents the payload accumulation generation sequence, X (1) (1) represents the payload accumulation data of the 1 st sampling node, X (1) (2) represents the payload accumulation data of the 2 nd sampling node, c (1) (N) represents the payload accumulation data of the N-th sampling node, and the payload accumulation data and the payload raw data satisfy: x (1) (k) represents the payload accumulated data of the kth sampling node, x (0) (i) represents the payload raw data of the ith sampling node, and k and i are positive integers greater than or equal to 1. Based on the foregoing formula, x (1) (1) is equal to the payload raw data of the 1 st sampling node, x (1) (2) is equal to the sum of the sums 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 sum of the sums of the payload raw data of the 1 st sampling node to the payload raw data of the N-th sampling node.
And step S3, 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.
The target gray prediction model can be a first-order single-variable discrete gray model comprising three parameters, wherein the three parameters of the model comprise a fluctuation coefficient, a development coefficient and a gray action amount, the fluctuation coefficient is a parameter representing the change degree of the net load original data, 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 representing the development trend of a gray generation sequence predicted value, and the gray action amount is a parameter reflecting the change relation of the data.
Alternatively, the functional expression of the target gray prediction model may be:
x (1)(k+1)＝μ1×x(1)(k)α+μ2 (equation one)
Where α is a fluctuation coefficient, x (1) (k+1) is (k+1) th data in the gray generation sequence, x (1) (k) is kth data in the gray generation sequence, μ 1 is a development coefficient, and μ 2 is a gray action amount.
As shown in connection with reference formula one, k=1, 2, 3..once again, substituting N-1 into the first formula to obtain a simultaneous equation as shown below:
Introducing a matrix vector notation:
In this step, the fluctuation coefficient α may be calculated by an assignment method and an error analysis method, and the development coefficient μ 1 and the gray action amount μ 2 may be calculated by a least square method, and the calculated target fluctuation coefficient α 1, development coefficient μ 1 and gray action amount μ 2 are substituted into the first formula to obtain the final target gray prediction model.
And S4, determining a net load predicted value according to the target gray predicted model.
In this step, the data in the gray generation sequence can be substituted into the target gray prediction model to calculate the net load accumulated data predicted value of the time period after the sampling periodAnd calculating a payload prediction value based on the inverse of the accumulation generation operation
Specifically, before the net load prediction is performed on the target period, firstly, determining a period of time before the target period as a sampling period, setting a sampling step length, recording the power grid load original data and the renewable energy source output original data of N sampling nodes, and subtracting the renewable energy source output original data from the power grid load original data of the same sampling node to obtain the net load original data corresponding to the N sampling nodes. And performing accumulation generation operation on the N pieces of payload raw data to obtain a gray generation sequence X (1) (i.e. a payload accumulation generation sequence). Substituting data in a gray generation sequence X (1) into a pre-established three-parameter discrete gray prediction model, wherein the three parameters comprise a fluctuation coefficient alpha, a development coefficient mu 1 and a gray action quantity mu 2, calculating a target fluctuation coefficient alpha 1 through an assignment method and an error analysis method, calculating a development coefficient mu 1 and a gray action quantity mu 2 through a least square method, and substituting the calculated target fluctuation coefficient alpha 1, the development coefficient mu 1 and the gray action quantity mu 2 into the formula one to obtain a final target gray prediction model. Further, data in the gray generation sequence is substituted into the target gray prediction model, and a net load accumulated data prediction value of a period after the sampling period is calculatedAnd calculating a payload prediction value based on the inverse of the accumulation generation operation
The method comprises the steps of preprocessing data of the net load raw 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, determining a net load prediction value according to the target gray prediction model, solving the problem that the prediction result deviation is large after the renewable energy source is accessed into a power grid in the existing prediction method, and improving the gray prediction model by introducing the fluctuation coefficient representing the change degree of the load data, thereby being beneficial to improving the prediction precision.
Optionally, fig. 2 is a flowchart of another power grid load prediction method according to the first 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, a discrete gray prediction model containing fluctuation coefficients is obtained.
The function structure of the discrete gray prediction model is the same as that of the target gray prediction model, and a specific function expression is shown in a formula I.
And step S302, 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 representing the change degree of the payload original data, and can fluctuate with the value of 1 according to the data difference in the sequence.
Optionally, the preset assignment interval may be [0.5,1.5], and the preset step size may be 0.01.
Illustratively, if the fluctuation coefficient is defined to be 1.01 in combination with the reference formula I, the corresponding assignment model is x (1)(k+1)＝μ1×x(1)(k)1.01+μ2.
And step S303, carrying out error analysis on the predicted value and the true value of the assignment model, and determining a target fluctuation coefficient according to an error analysis objective function.
The predicted value of the assignment model is a predicted value of the net load calculated according to the assignment model, and the actual value is original net load data calculated according to the sampling data.
Alternatively, the error analysis objective function may be an objective function that takes as an objective function the minimum value of the average absolute percentage error of the predicted value and the actual value, wherein the average absolute percentage error is the average percentage of the deviations between the absolute value and the actual value of the deviations between all the individual payload predicted values and the payload raw data, or an objective function that takes as an objective function the minimum value of the average absolute error of the predicted value and the actual value, wherein the average absolute error is the average of the absolute value of the deviations between all the individual payload predicted values and the payload raw data.
For example, taking the average absolute percentage error minimum of the predicted value and the true value as an objective function, if the number of data in the payload original data sequence X (0) is defined as N, the expression of the error analysis objective function is shown as formula two:
Where k=1, 2, the term, N; Representing the predicted value of the assignment model.
Taking the minimum value of the average absolute error between the predicted value and the true value as an objective function, if the number of data in the defined payload original data sequence X (0) is N, the expression of the error analysis objective function is shown as a formula III:
Where k=1, 2, the term, N; Representing the predicted value of the assignment model.
Optionally, determining the target fluctuation coefficient according to the error analysis objective function comprises determining the target fluctuation coefficient according to a minimum value of an average absolute percentage error of a predicted value and a true value of the assignment model, or determining the target fluctuation coefficient according to a minimum value of an average absolute error of a predicted value and a true value of the assignment model.
Specifically, combining the formula II and the formula III, determining the fluctuation coefficient of the assignment model corresponding to the minimum value of the average absolute percentage error as a target fluctuation coefficient, or determining the fluctuation coefficient of the assignment model corresponding to the minimum value of the average absolute error as a target fluctuation coefficient.
And step S304, determining a target gray prediction model according to the target fluctuation coefficient.
Specifically, defining a target fluctuation coefficient as alpha 1, a corresponding target gray prediction model as DGM (1, alpha 1), calculating gray parameters (development coefficient mu 1 and gray action quantity mu 2) of the target gray prediction model as DGM (1, alpha 1) by adopting a least square method, and ensuring a true value x (1) (k+1) and a net load predicted valueThe minimum simulation error S satisfies:
And performing iterative operation by adopting Matlab software programming, and calculating the development coefficient mu 1 and the gray action quantity mu 2 of the DGM (1, alpha 1) to obtain a final target gray prediction model.
Therefore, according to the technical scheme provided by the embodiment of the invention, the improved gray prediction model is constructed by introducing the parameter representing the fluctuation of the load, and the power grid load is predicted by adopting the improved gray prediction model, so that the model is simple and the prediction precision is high.
Optionally, fig. 3 is a flowchart of still another power grid load prediction method according to the first embodiment of the present invention, and on the basis of fig. 1, a specific implementation manner of model verification is added before the prediction is performed, so that model prediction accuracy is advantageously ensured.
As shown in fig. 3, the load prediction method specifically includes the following steps:
and step S1, acquiring net load original data of the power grid.
And step S2, carrying out data preprocessing on the payload original data to obtain a gray generation sequence.
And step S3, determining a target gray prediction model according to the gray generation sequence.
And S501, carrying out error analysis on the predicted value and the true value of the target gray prediction model.
And step S502, correcting the fluctuation coefficient of the target gray prediction model according to the error analysis result.
And step S503, a new target gray prediction model is established according to the modified fluctuation coefficient.
Optionally, the error analysis method includes at least one of a mean absolute error analysis method, a mean absolute percentage error analysis method, and a precision grade evaluation method.
Wherein the mean absolute error analysis is the average of the absolute values of the deviations between all individual payload predictions and the payload raw data, and the expression of the mean absolute error refers to the above-mentioned formula three.
The mean absolute percentage error analysis is the mean percentage of the deviation between the absolute value and the actual value of the deviation between all individual payload predictions and the payload raw data, and the expression for the mean absolute percentage error can be referred to above in equation two.
The criteria for the evaluation of the precision grade can be referred to in the following table 1.
| Precision grade | Relative error |
| Primary (you) | 0.01 |
| Second grade (good) | 0.05 |
| Three-stage (difference) | 0.10 |
| Four-stage (disqualification) | 0.20 |
As shown in table 1, the relative error may be an average absolute percentage error, that is, if the average percentage of the 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 class of the target gray prediction model is first order (excellent).
Specifically, after error analysis is performed on the predicted value and the true value of the target gray prediction model, if the error of the target gray prediction model is smaller than a preset error threshold value or the precision level of the target gray prediction model reaches a preset level (for example, one level), the target gray prediction model is determined to meet the requirement, and if the error of the target gray prediction model is larger than the preset error threshold value or the precision level of the target gray prediction model does not reach the preset level (for example, one level), the fluctuation coefficient of the target gray prediction model is corrected until the error or the precision level of the target gray prediction model reaches a set standard. And in the subsequent load prediction process, calculating a net load predicted value by adopting the corrected target gray prediction model.
The prediction method of the present invention will be described in detail with reference to specific examples.
For example, a sampling period may be defined as 7:00-9:00, a sampling step length is 15 minutes, the power grid load original data and the renewable energy source output original data of each sampling node are recorded, a group of sampling data as 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 in total.
As shown in reference table 2, the payload raw data corresponding to the 8 sampling nodes is calculated by adopting the method described in the step S1, 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 1579.83 is the payload raw data of the 8 th sampling node.
After obtaining the payload raw data, performing accumulation generation operation by adopting the method recorded in the step S2 to obtain a gray generation sequence:
X(1)={448.11,1067.03,1850.62,2797.62,3898.57,5171.87,6599.76,8179.59}
After the payload original data sequence X (0) and the gray generation sequence X (1) are obtained, determining gray parameters of a target gray prediction model by adopting the method recorded in the steps S301 to S305, calculating to obtain a target fluctuation coefficient alpha 1 equal to 0.94 by taking the average absolute percentage error minimum value of the predicted value and the true value as a target function, at this time, the target gray prediction model is DGM (1,1,0.94), performing iterative operation by adopting Matlab software programming, and calculating to obtain a development coefficient mu 1 = 1.9846 and a gray action quantity mu 2 = 455.0049 of the DGM (1,1,0.94), thereby obtaining a function expression of the target gray prediction model as X (1)(k+1)＝1.9846×x(1)(k)0.94 +455.0049.
By adopting the method described in the step S4, the data in the gray generation sequence X (1) is substituted into the target gray prediction model, and the calculated payload predicted values of the sampling nodes are sequentially as follows:
{448.11,623.45,782.67,943.64,1106.12,1268.29,1427.90,1582.62}。
by adopting the method described in the step S501, the error analysis is performed on the payload raw data and the payload predicted value of each sampling node, so that the relative error of the target gray prediction model is 0.0028, the relative error is less than 0.01, the accuracy grade of the target gray prediction model is determined to be one grade, and the payload prediction of the target period can be performed according to the target gray prediction model meeting the requirement.
Illustratively, in combination with the data in Table 2, taking the example of a target period of 9:00-10:00 for performing load prediction, 4 predictions may be obtained, with a 9:15 payload prediction value of 1730.24, a 9:30 payload prediction value of 1868.77, a 9:45 payload prediction value of 1996.51, and a 10:00 payload prediction value of 2112.07.
Therefore, the technical scheme of the embodiment of the invention improves the discrete gray prediction model by introducing the parameter representing the fluctuation of the load, determines the net load prediction value according to the improved discrete gray prediction model, solves the problem of low load prediction precision of the existing renewable energy micro-grid, and is beneficial to improving the prediction precision and improving the economic dispatch and the safe operation performance of the renewable energy micro-grid by introducing the fluctuation coefficient representing the fluctuation degree of the load data.
Example two
Based on the above embodiment, the second embodiment of the present invention provides a modeling method for a power grid load prediction model, which is used in the above load prediction method, where the prediction model in the present embodiment introduces parameters representing load fluctuation to improve the 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:
and step S10, acquiring the net load original data of the power grid.
And step S20, carrying out data preprocessing on the payload original data to obtain a gray generation sequence.
And S30, creating a discrete gray prediction model containing fluctuation coefficients, wherein the discrete gray prediction model is a first-order single-variable discrete gray prediction model.
Wherein the fluctuation coefficient is a parameter characterizing the degree of change of the payload raw data.
And S40, determining a target fluctuation coefficient, a development coefficient and a gray action amount of the discrete gray prediction model according to the gray generation sequence.
And S50, determining a target gray prediction model according to the target fluctuation coefficient, the development coefficient and the gray action amount.
Optionally, the function 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) is the kth data in the gray generation sequence, mu 1 is a development coefficient, and mu 2 is a gray action amount.
Optionally, determining the target fluctuation coefficient of the discrete gray prediction model according to the gray generation sequence comprises the steps of 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, performing error analysis on a predicted value and a true value of the assignment model, and determining the target fluctuation coefficient according to an error analysis target function.
Optionally, determining the target fluctuation coefficient according to the error analysis objective function comprises determining the target fluctuation coefficient according to a minimum value of an average absolute percentage error of a predicted value and a true value of the assignment model, or determining the target fluctuation coefficient according to a minimum value of an average absolute error of a predicted value and a true value of the assignment model.
Optionally, the preset assignment interval is [0.5,1.5], and the preset step length is 0.01.
Therefore, according to the technical scheme provided by the embodiment of the invention, the improved gray prediction model is constructed by introducing the parameters representing the load fluctuation, so that the model prediction precision is improved, and the economic dispatch and the safe operation performance of the renewable energy micro-grid are improved.
Example III
Based on any one of the above embodiments, the third embodiment of the present invention provides a power grid load prediction device, which can execute the power grid load prediction method provided by any one of the above embodiments, or the modeling method provided by any one of the above embodiments, and has the functional module and the beneficial effects corresponding to the execution method.
Fig. 5 is a schematic structural diagram of a power grid load prediction device according to a third embodiment of the present invention.
As shown in fig. 5, the apparatus 00 includes an original data acquisition unit 101, a data processing unit 102, a model correction unit 103, and a prediction execution unit 104. The system comprises an original data acquisition unit 101 for acquiring the net load original data of a power grid, a data processing unit 102 for carrying out data preprocessing on the net load original data to obtain a gray generation sequence, a model correction unit 103 for 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 a prediction execution unit 104 for determining a net load predicted value according to the target gray prediction model.
Optionally, the function 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) is the kth data in the gray generation sequence, mu 1 is a development coefficient, and mu 2 is a gray action amount.
Optionally, the model correction unit 103 is configured to obtain a discrete gray prediction model including a fluctuation coefficient, assign a value to 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, perform error analysis on a predicted value and a true value of the assignment model, determine a target fluctuation coefficient according to an error analysis objective function, and determine a target gray prediction model according to the target fluctuation coefficient.
Optionally, determining the target fluctuation coefficient according to the error analysis objective function comprises determining the target fluctuation coefficient according to a minimum value of an average absolute percentage error of a predicted value and a true value of the assignment model, or determining the target fluctuation coefficient according to a minimum value of an average absolute error of a predicted value and a true value of the assignment model.
Optionally, the preset assignment interval is [0.5,1.5], and the preset step length is 0.01.
Example IV
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 in the memory and capable of running on the processor, where the processor implements the power grid load prediction method described above, or implements the power grid load prediction method described above when executing the program.
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, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Computer devices may also represent various forms of mobile equipment, such as personal digital processing, cellular telephones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing equipment. 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, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may 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 required 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.
Various components in the computer device 10 are connected to the I/O interface 15, including an input unit 16, such as a keyboard, mouse, etc., an output unit 17, such as various types of displays, speakers, etc., a storage unit 18, such as a magnetic disk, optical disk, etc., 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, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. 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 above-described grid load prediction method or modeling method may be implemented as a computer program tangibly embodied on 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 arrangement 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the grid load prediction method or 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 in any other suitable way (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may 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), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being 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 a special or general purpose programmable processor, operable to receive data and instructions from, and to 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 a computer device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can 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 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 a Local Area Network (LAN), a Wide Area Network (WAN), a blockchain network, 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 (8)
1. A method for predicting grid load, comprising:
acquiring net load original data of a power grid;
performing data preprocessing on the payload 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;
determining a payload prediction value according to the target gray prediction model;
Determining a target gray prediction model according to the gray generation sequence, comprising:
obtaining a discrete gray prediction model containing fluctuation coefficients;
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;
Performing error analysis on the predicted value and the true value of the assignment model, and determining the target fluctuation coefficient according to an error analysis objective function;
determining the target gray prediction model according to the target fluctuation coefficient;
The determining the target fluctuation coefficient according to the error analysis objective function comprises the following steps:
Determining the target fluctuation coefficient according to the average absolute percentage error minimum value of the predicted value and the true value of the assignment model, or
And determining the target fluctuation coefficient according to the average absolute error minimum value of the predicted value and the true value of the assignment model.
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
Where α is a fluctuation coefficient, x (1) (k+1) is the (k+1) th data in the gray generation sequence, x (1) (k) is the kth data in the gray generation sequence, μ 1 is a development coefficient, and μ 2 is a gray action amount.
3. The method of claim 1, wherein the predetermined assignment interval is [0.5,1.5], and the predetermined step size is 0.01.
4. The method as recited in claim 1, further comprising:
performing error analysis on the predicted value and the true value of the target gray prediction model;
And correcting the fluctuation coefficient of the target gray prediction model according to the error analysis result.
5. A method for modeling a load prediction model of a power grid, for use in the load prediction method of any one of claims 1-4, the modeling method comprising:
acquiring net load original data of a power grid;
performing data preprocessing on the payload original data to obtain a gray generation sequence;
creating a discrete gray prediction model containing fluctuation coefficients;
Determining a target fluctuation coefficient, a development coefficient and a gray action amount 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 action amount.
6. A power grid load prediction apparatus for performing the power grid load prediction method of any one of claims 1-4, the apparatus comprising:
the original data acquisition unit is used for acquiring the net load original data of the power grid;
The data processing unit is used for carrying out data preprocessing on the payload original data to obtain a gray generation sequence;
the model correction unit is used for 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 the prediction execution unit is used for determining a payload predicted value according to the target gray prediction model.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the grid load prediction method of any one of claims 1-4 when the program is executed;
or implement the power grid load prediction model modeling method as claimed in claim 5.
8. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements a method of grid load prediction according to any of claims 1-4;
or implement the power grid load prediction model modeling method as claimed in claim 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210354777.2A CN114626636B (en) | 2022-04-06 | 2022-04-06 | Power grid load forecasting method, device, modeling method, computer equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210354777.2A CN114626636B (en) | 2022-04-06 | 2022-04-06 | Power grid load forecasting method, device, modeling method, computer equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114626636A CN114626636A (en) | 2022-06-14 |
| CN114626636B true CN114626636B (en) | 2025-01-10 |
Family
ID=81906598
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210354777.2A Active CN114626636B (en) | 2022-04-06 | 2022-04-06 | Power grid load forecasting method, device, modeling method, computer equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114626636B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239849A (en) * | 2017-04-17 | 2017-10-10 | 西安电子科技大学 | One kind is based on improved exponential smoothing gray model Methods of electric load forecasting |
| CN109934394A (en) * | 2019-03-01 | 2019-06-25 | 国网上海市电力公司 | A Demand Side Response Forecasting Method Based on Grey and Markov Theory |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110163447A (en) * | 2019-05-29 | 2019-08-23 | 电子科技大学 | Long term power load forecasting method based on residual GM grey forecasting model |
| CN110991715A (en) * | 2019-11-22 | 2020-04-10 | 国网河北省电力有限公司电力科学研究院 | Power distribution network energy efficiency evaluation system and method based on improved grey correlation degree |
-
2022
- 2022-04-06 CN CN202210354777.2A patent/CN114626636B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239849A (en) * | 2017-04-17 | 2017-10-10 | 西安电子科技大学 | One kind is based on improved exponential smoothing gray model Methods of electric load forecasting |
| CN109934394A (en) * | 2019-03-01 | 2019-06-25 | 国网上海市电力公司 | A Demand Side Response Forecasting Method Based on Grey and Markov Theory |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114626636A (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| CN114817985A (en) | Privacy protection method, device, equipment and storage medium for electricity consumption data | |
| CN114626636B (en) | Power grid load forecasting method, device, modeling method, computer equipment and medium | |
| CN118316023A (en) | Regional wind power probability prediction method and device, electronic equipment and storage medium | |
| CN117667938A (en) | Database index updating method, device, equipment and storage medium | |
| CN117455067A (en) | Electric quantity consumption prediction method and device, electronic equipment and storage medium | |
| CN115422761B (en) | Calculation method and device for parallel simulation calculation time in electromagnetic transient simulation | |
| CN116957133A (en) | Wind power generation power and photovoltaic power generation power prediction method and device | |
| CN116307159A (en) | Load prediction method and device, electronic equipment and storage medium | |
| CN115860249A (en) | Distributed photovoltaic power generation power prediction method, device, equipment and medium | |
| CN115564329A (en) | Typical capacity scene determining method, device, equipment and storage medium | |
| CN115438007A (en) | File merging method and device, electronic equipment and medium | |
| CN117293923B (en) | Method, device, equipment and storage medium for generating day-ahead scheduling plan of power grid | |
| CN114841457B (en) | Power load estimation method and system, electronic device, and storage medium | |
| CN113989004B (en) | Resource allocation method and device, electronic equipment and readable storage medium | |
| CN118468059B (en) | Power station characteristic determining method and device for electric power system, electronic equipment and medium | |
| CN115373449B (en) | Data processing method, device, equipment and storage medium | |
| CN116914737A (en) | Photovoltaic bearing capacity evaluation method, device, equipment and storage medium for power distribution network | |
| CN117878905A (en) | Power grid load prediction method, device, equipment and medium based on white noise signals | |
| CN118399447A (en) | Access method, device, equipment and medium of energy storage system | |
| CN117592618A (en) | Active user prediction method, device, server and storage medium | |
| CN116911466A (en) | Method, device, equipment and medium for determining park construction degree | |
| CN119089969A (en) | Model training method, device, electronic device and storage medium based on cloud architecture | |
| CN119647426A (en) | Engineering general algorithm preparation method, device and medium suitable for user side energy storage | |
| CN116167519A (en) | Monitoring amount prediction method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |