CN114254800A - Method, terminal and storage medium for power load prediction - Google Patents

Method, terminal and storage medium for power load prediction Download PDF

Info

Publication number
CN114254800A
CN114254800A CN202111308391.XA CN202111308391A CN114254800A CN 114254800 A CN114254800 A CN 114254800A CN 202111308391 A CN202111308391 A CN 202111308391A CN 114254800 A CN114254800 A CN 114254800A
Authority
CN
China
Prior art keywords
load
sequence
curve
sub
power utilization
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.)
Pending
Application number
CN202111308391.XA
Other languages
Chinese (zh)
Inventor
申洪涛
陶鹏
张洋瑞
任鹏
赵俊鹏
张超
张冰玉
李春睿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
Marketing Service Center of State Grid Hebei Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
Marketing Service Center of State Grid Hebei Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, Marketing Service Center of State Grid Hebei Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202111308391.XA priority Critical patent/CN114254800A/en
Publication of CN114254800A publication Critical patent/CN114254800A/en
Pending legal-status Critical Current

Links

Images

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

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Power Engineering (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention provides a method, a terminal and a storage medium for power load prediction, wherein the method comprises the following steps: preprocessing an original load curve to obtain a load analysis sequence corresponding to the current day to be tested; adding a white noise sequence into the load analysis sequence, and performing empirical mode decomposition to determine intrinsic mode components of the power utilization units; when the intrinsic mode component of each power utilization unit does not meet the stop condition, recording the intrinsic mode component, and executing the operation of adding the white noise sequence into the analysis load sequence and then; otherwise, determining a sub-load prediction curve corresponding to each power utilization unit based on the recorded intrinsic modal components; and carrying out error processing on the sub-load prediction curves of the power utilization units, and adding the sub-load prediction curves subjected to the error processing to obtain a total load prediction curve. The invention can avoid the data with overlarge prediction difference from being substituted into the final prediction result and improve the prediction precision.

Description

Method, terminal and storage medium for power load prediction
Technical Field
The invention relates to the technical field of power grid load prediction, in particular to a method, a terminal and a storage medium for power load prediction.
Background
The demand side response means that a series of incentive mechanisms are implemented, and the power price is adjusted to guide a user to actively carry out matching management on the operation of the power distribution network, so that the problem that the traditional power distribution network cannot actively generate power according to the demand of the user is solved, and the stability of the power supply demand is improved.
The power load prediction has an important role in the demand side response, and a power supply party can adjust the demand side response in time according to the result of the power load prediction to balance the power supply load of the power distribution network. The current ultra-short term load prediction mainly takes artificial intelligence and signal analysis as main factors, although a short prediction period can be realized, the prediction precision is low, and especially for power load prediction in a household application scene, the prediction accuracy requirement cannot be met due to complex interference factors.
Disclosure of Invention
The embodiment of the invention provides a method, a terminal and a storage medium for power load prediction, which aim to solve the problem that the requirement on the accuracy of power load prediction cannot be met due to complex interference factors.
In a first aspect, an embodiment of the present invention provides a method for power load prediction, including:
preprocessing an original load curve to obtain a load analysis sequence corresponding to the current day to be tested;
adding a white noise sequence into the load analysis sequence, and performing empirical mode decomposition to determine intrinsic mode components of the power utilization units;
when the intrinsic mode component of each power utilization unit does not meet the stop condition, recording the intrinsic mode component, and executing the operation of adding the white noise sequence into the analysis load sequence and then; otherwise, determining a sub-load prediction curve corresponding to each power utilization unit based on the recorded intrinsic modal components;
and carrying out error processing on the sub-load prediction curves of the power utilization units, and adding the sub-load prediction curves subjected to the error processing to obtain a total load prediction curve.
In one possible implementation, the white noise sequence follows a normal distribution.
In one possible implementation manner, the error processing of the sub-load prediction curve of each power consumption unit includes:
and carrying out error processing on the sub-load prediction curve of each power utilization unit based on the following error processing functions:
Figure BDA0003340971820000021
wherein, aiThe weight of the power utilization unit i in the day to be measured; x is the number ofiPredicting a curve for the sub-load of the power utilization unit i on the day to be tested; x'iThe actual sub-load of the electricity utilization unit i on the day to be tested; a isi、xiAnd x'iThe value range of (a) is a positive number, and the value range of i is a positive integer.
In a possible implementation manner, preprocessing an original load curve to obtain a load analysis sequence corresponding to the day to be tested includes:
acquiring an original load curve, and determining a load characteristic vector according to a key characteristic variable and power utilization time;
calculating the position difference between the load characteristic vector of the day to be detected and the historical load characteristic vector, and determining a historical approximate vector of the day to be detected from the historical load characteristic vector based on the position difference;
and determining a load analysis sequence according to the historical approximate vector and the original load curve.
In one possible implementation, the weight aiThe calculation method of (2) comprises:
Figure BDA0003340971820000031
wherein the absolute error
Figure BDA0003340971820000032
Number of approximate vectors for history; the above-mentioned
Figure BDA0003340971820000033
Predicting load of a pre-acquired electricity utilization unit i in a history approximate vector j; x'i,jApproximating the actual load of the vector j for the power utilization unit i in history; said EiAnd, and
Figure BDA0003340971820000034
the value ranges of (a) and (b) are positive integers.
In a possible implementation manner, before determining the load analysis sequence according to the historical approximate vector and the original load curve, the method further includes: and analyzing the data missing condition of the power load curve corresponding to the historical approximate vector, and when the missing data does not exceed a preset threshold value, performing data filling according to a filling formula.
In one possible implementation, the filling formula is:
Figure BDA0003340971820000035
wherein, D isn+jThe data is missing data and is the (n + j) th data in the power load curve; said DnThe nth data in the power data set; said Dn+iThe data is the n + i th data in the power load curve; the value ranges of i, j and n are positive integers, and i is>j，Dn、Dn+jAnd Dn+iThe value range of (1) is positive; the value of n is chosen empirically and manually.
In one possible implementation manner, adding a white noise sequence to the load analysis sequence, and performing empirical mode decomposition to determine an intrinsic mode component of each power consumption unit includes:
adding a white noise sequence into the load analysis sequence to determine a correction analysis sequence;
obtaining a maximum value and a minimum value in the correction analysis sequence through differentiation, and determining an upper envelope line and a lower envelope line of the correction analysis sequence through cubic spline fitting;
and calculating a mean value according to the upper envelope line and the lower envelope line, and determining the intrinsic mode component of each power utilization unit according to the difference value between the load analysis sequence and the mean value.
In one possible implementation, the eigenmode component of each consumer unit satisfies the following condition:
number of extreme points N within the entire data sequenceeAnd the number of zero-crossing points NzThe difference value of (A) meets the set condition; and the combination of (a) and (b),
at any point in time, the sum of the upper envelope determined by the local maxima of the data sequence and the lower envelope determined by the local minima is zero.
In a possible implementation manner, the setting condition is: the absolute value of the difference between the number of extreme points and the number of zero-crossing points is less than or equal to 1.
In a possible implementation manner, before determining the sub-load prediction curve corresponding to each electricity consumption unit based on the recorded eigenmode component, the method further includes:
carrying out normalization processing on the recorded intrinsic mode component and the load analysis sequence, and determining a normalization correlation coefficient;
and when the normalized correlation coefficient is smaller than or equal to the coefficient threshold value, rejecting the eigenmode component corresponding to the normalized correlation coefficient.
In a possible implementation manner, the normalized correlation coefficient is:
Figure BDA0003340971820000041
wherein, r isjNormalized correlation coefficients for the jth eigenmode component with the load analysis sequence; the t is a sampling point of the signal; c is mentionedj(t) is the jth eigenmode component; the above-mentioned
Figure BDA0003340971820000042
Is the mean of the eigenmode components; the y (t0 is a load analysis sequence; the
Figure BDA0003340971820000043
Mean of the load analysis sequences.
In one possible implementation, the threshold value TH is set from the standard deviation TH ═ std (r) of the correlation coefficientj) Obtaining, namely:
Figure BDA0003340971820000051
if rjTH, reserving the jth intrinsic mode component; otherwise, eliminating the j-th intrinsic mode component.
In one possible implementation, the stop condition includes:
the eigenmode components satisfy the following termination function:
Figure BDA0003340971820000052
wherein, theSdIs the standard deviation between two successive iteration results; h isj(t) the eigenmode component obtained in the jth iteration; said SdNumerical range (0.2, 0.3).
In a second aspect, an embodiment of the present invention provides an apparatus for power load prediction, including:
the preprocessing module is used for preprocessing the original load curve to obtain a load analysis sequence corresponding to the current day to be detected;
the determining module is used for adding a white noise sequence into the load analysis sequence and carrying out empirical mode decomposition to determine intrinsic mode components of the power utilization units;
the first analysis module is used for recording the intrinsic modal component when the intrinsic modal component of each power utilization unit does not meet the stop condition, and executing the operation of adding the white noise sequence into the analysis load sequence and then; otherwise, determining a sub-load prediction curve corresponding to each power utilization unit based on the recorded intrinsic modal components;
and the second analysis module is used for carrying out error processing on the sub-load prediction curves of the power utilization units and adding the sub-load prediction curves subjected to the error processing to obtain a total load prediction curve.
In a third aspect, an embodiment of the present invention provides a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect or any possible implementation manner of the first aspect when executing the computer program.
In a fourth aspect, the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the method according to the first aspect or any one of the possible implementation manners of the first aspect.
The embodiment of the invention provides a method, a terminal and a storage medium for power load prediction. And carrying out empirical mode decomposition on the load analysis sequence added with the white noise sequence to determine the intrinsic mode component of each power utilization unit, controlling the operation of the white noise based on the stop condition, and determining the sub-load prediction curve corresponding to each power utilization unit based on the recorded intrinsic mode component. And carrying out error processing on the sub-load prediction curves of the power utilization units, avoiding data with overlarge prediction difference from being substituted into a final prediction result, and adding the sub-load prediction curves subjected to error processing to obtain a total load prediction curve.
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 embodiments or the prior art descriptions will be briefly described 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 inventive exercise.
FIG. 1 is a schematic flow chart diagram of a method for power load prediction according to an embodiment of the present invention;
FIG. 2 is a partial flow diagram of a method for power load prediction according to another embodiment of the present invention;
FIG. 3 is a partial flow diagram of a method for power load prediction according to another embodiment of the present invention;
FIG. 4 is a schematic structural diagram of an apparatus for power load prediction according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a terminal according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following description is made by way of specific embodiments with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a method for power load prediction according to an embodiment of the present invention. As shown in fig. 1, the method comprises the steps of:
s101, preprocessing an original load curve to obtain a load analysis sequence corresponding to the day to be tested.
The method for predicting the power load provided by the embodiment of the invention is mainly used for a household power load prediction scene. Specifically, the corresponding load monitoring devices are deployed in each power utilization loop of the home building in advance, such as: a power load control terminal, and the like.
In one possible implementation, as shown in fig. 2, step S101 includes the following steps:
and S1011, acquiring an original load curve, and determining a load characteristic vector according to the key characteristic variable and the power utilization time.
S1012, calculating the position difference between the load characteristic vector of the current day to be measured and the historical load characteristic vector, and determining a historical approximate vector of the current day to be measured from the historical load characteristic vector based on the position difference;
and S1013, determining a load analysis sequence according to the historical approximate vector and the original load curve.
In step S1011, the load monitoring device records the real-time power load of the historical approximate vector, and then generates a power load curve from the recorded real-time data, where the abscissa is the time axis and the ordinate is the load value of the historical approximate vector at a certain time point.
According to factors affecting the household power load, corresponding key characteristic variables are determined, such as: whether it is a working day, temperature, rainfall, etc.
In this embodiment, the setting of the key characteristic variables includes: and dividing the day to be measured and the historical data into a class of sundays according to the date class, and a class of Mondays to Saturdays. The method has the advantages that the check-in rate of the family at weekdays and other times is judged to be obviously different according to experience, and the check-in rate indirectly influences the change of the power load of the family.
And dividing the highest temperature and the lowest temperature of the current day to be measured and the historical data into four categories according to the temperature of less than 0 ℃, 0-10 ℃, 10-20 ℃ and 20-30 ℃. The air temperature affects the working conditions of household heating and cooling systems, such as air conditioners, heating systems and other devices, and further causes the change of power load.
And classifying the rainfall conditions of the day to be measured and the historical data into four categories of no precipitation, light rain, medium rain and heavy rain based on the rainfall amount. The rainfall condition affects the traveling condition of people, so that the living rate of the family is affected, and the change of the power load of the family is indirectly affected.
And generating a load characteristic vector X (Date, Tmax, Tmin, Rain) based on the division condition of the key characteristic variables, wherein the Date, Tmax, Tmin and Rain sequentially represent the Date type, the highest temperature of the day, the lowest temperature of the day and the membership degree of different types of the precipitation conditions of the current day and historical data. The membership degree is a matrix, is calculated based on a fuzzy C-means algorithm, and represents the degree of the current day to be measured and the degree of the historical data belonging to each category on a certain key characteristic variable. Compared with a hard clustering method, the fuzzy clustering idea provides a more scientific classification method, and a more objective classification result can be obtained by calculating the membership degree, so that the generated load characteristic vector is more accurate.
In step S1012, the euclidean distance, which is the position difference between the load feature vector of the day to be measured and the historical load feature vector, is calculated. If the Euclidean distance is smaller than or equal to the set approximate threshold, the characteristic variable type corresponding to the historical load characteristic vector is similar to the current day to be measured, the power load predicted by taking the historical load characteristic vector as a sample is supposed to be closest to the actual power load of the current day to be measured, and therefore the historical load characteristic vector is judged to be the historical approximate vector of the current day to be measured. In a plurality of historical data, the accuracy of the prediction curve may be reduced due to the fact that the difference between some historical data and the characteristic variable to be measured is large, so that a more approximate historical vector is screened out, and the power load prediction accuracy on the day to be measured is improved.
And S102, adding the white noise sequence into the load analysis sequence, and performing empirical mode decomposition to determine intrinsic mode components of the power utilization units.
In one possible implementation, the white noise sequence follows a normal distribution in step S102.
S103, when the intrinsic mode components of the power utilization units do not meet the stop condition, recording the intrinsic mode components, and adding a white noise sequence into the analysis load sequence and performing subsequent operation; otherwise, determining the sub-load prediction curve corresponding to each electricity utilization unit based on the recorded intrinsic modal components.
Since more than one history approximate vector on the current day to be measured is determined from the history load feature vectors based on the position difference in step S1012, there should be several power load curves corresponding to the history approximate vectors. In this case, it is difficult to decide which curve should be used for prediction at the same time point, and therefore, by adopting integrated empirical mode decomposition, the power load curves corresponding to each historical approximate vector are subjected to empirical mode decomposition by adding a white noise sequence, so as to obtain a smaller time interval, and frequency conversion processing is performed, so that a low-frequency curve and a high-frequency curve are decomposed. The low-frequency curve mainly represents the basic load and has strong regularity and periodicity, for example, when the current day to be measured is aligned with the weeks of months and months of historical data, the low-frequency curves of the current day to be measured and the low-frequency curves of the historical data are close to each other; the high-frequency curve mainly represents sudden load, when the day to be measured and the historical data are in the aspects of weather, time interval temperature and the like, the uncertainty is large, and the part of the high-frequency curve with sudden change is relatively close.
And S104, carrying out error processing on the sub-load prediction curves of the power utilization units, and adding the sub-load prediction curves subjected to the error processing to obtain a total load prediction curve.
However, due to the wide variety of household power loads, for the electricity usage particularity of such buildings, electricity usage metering is performed in advance in each regional loop of the household with different functions according to different branch tables, for example: energy consumption metering devices are respectively arranged on household heating and ventilation systems, power supply systems and other power consumption units, and a plurality of sub-power load prediction curves corresponding to the power consumption units are obtained through integrated empirical mode decomposition. Theoretically, the final total load prediction curve can be obtained by adding the plurality of power load prediction curves, but actually, the sum of the total load and the sub-load has a deviation, and therefore, further correction is required to perform error processing on the sub-load prediction curve.
In the embodiment, the white noise sequence is added into the load analysis sequence corresponding to the current day to be tested, so that the characteristics in the load analysis series are highlighted, the subsequent decomposition is facilitated, and the prediction precision is improved. And carrying out empirical mode decomposition on the load analysis sequence added with the white noise sequence to determine the intrinsic mode component of each power utilization unit, controlling the operation of the white noise based on the stop condition, and determining the sub-load prediction curve corresponding to each power utilization unit based on the recorded intrinsic mode component. And carrying out error processing on the sub-load prediction curves of the power utilization units, avoiding data with overlarge prediction difference from being substituted into a final prediction result, and adding the sub-load prediction curves subjected to error processing to obtain a total load prediction curve.
In one possible implementation manner, in step S104, performing error processing on the sub-load prediction curve of each power consumption unit includes:
and carrying out error processing on the sub-load prediction curve of each power utilization unit based on the following error processing functions:
Figure BDA0003340971820000101
wherein, aiThe weight of the power utilization unit i in the day to be measured; x is the number ofiPredicting a curve for the sub-load of the power utilization unit i on the day to be tested; x is the number ofi ′The actual sub-load of the electricity utilization unit i on the day to be tested; a isi、xiAnd xi ′The value range of (a) is a positive number, and the value range of i is a positive integer.
Specifically, the minimum value of f is obtained, and a total load prediction curve of each power utilization unit in the current day to be measured after error processing is obtained. On the basis of the traditional short-term power load prediction, aiming at the complex particularity of the type of the household power unit, the prediction curve obtained by the integrated empirical mode decomposition is subjected to further error processing. Compared with the method that the predicted loads of all household power utilization units are simply added, more accurate adjustment is achieved through error processing, and prediction accuracy is improved.
In one possible implementation, the weight aiThe calculation method of (2) comprises:
Figure BDA0003340971820000111
wherein the absolute error
Figure BDA0003340971820000112
Number of approximate vectors for history;
Figure BDA0003340971820000113
predicting load of a pre-acquired electricity utilization unit i in a history approximate vector j; x'i,jApproximating the actual load of the vector j for the power utilization unit i in history; eiAnd, and
Figure BDA0003340971820000114
the value ranges of (a) and (b) are positive integers.
In one possible implementation manner, before determining the load analysis sequence according to the historical approximate vector and the original load curve in step S1013, the method further includes: and analyzing the data missing condition of the power load curve corresponding to the historical approximate vector, and when the missing data does not exceed a preset threshold value, performing data filling according to a filling formula.
In one possible implementation, the fill formula is:
Figure BDA0003340971820000115
wherein D isn+jThe data is missing data and is the (n + j) th data in the power load curve; dnThe nth data in the power data set; dn+iThe data is the n + i th data in the power load curve; i. the value ranges of j and n are positive integers and i>j，Dn、Dn+jAnd Dn+iThe value range of (1) is positive; the value of n is chosen empirically.
Optionally, the preset threshold is one fourth to one half of the data quantity contained in the power load curve.
For example: when n is 1, i is 6, there is a set of data (1, 3, 5, x, 9, 11, 9) included in the power load curve, and the fourth data is missing, and because only one of the 7 data is missing, if the predetermined threshold is not exceeded, that is, the missing data is not large, that is, j is 3, the padding 5 at x is calculated according to the padding formula, and is closer to the predicted 7. However, if the missing data exceeds the preset threshold, or the proportion of the missing data to all the data in the power load curve exceeds the preset proportion, that is, the missing data is excessive, at this time, if the data filling is still performed by using the filling formula, the power load curve of the historical approximate vector may be inaccurate, and a large error may be generated in the subsequent prediction, so that the power load curve with excessive missing data is regarded as being unsatisfactory and is not used as an input sample of the power load prediction.
In one possible implementation, as shown in fig. 3, step S102 includes the following steps:
and S1021, adding the white noise sequence into the load analysis sequence to determine a correction analysis sequence.
And S1022, solving a maximum value and a minimum value in the correction analysis sequence through differentiation, and determining an upper envelope line and a lower envelope line of the correction analysis sequence through cubic spline fitting.
And S1023, calculating a mean value according to the upper envelope line and the lower envelope line, and determining the intrinsic mode component of each power utilization unit according to the difference value between the load analysis sequence and the mean value.
In one possible implementation, the computational formula for the integrated empirical mode decomposition is as follows:
Figure BDA0003340971820000121
where x (t) is the household electrical load signal, imfi(t) is the eigenmode component from the ith iteration, rnAnd (t) is a direct current or linear eigenmode component obtained after the last iteration.
In one possible implementation manner, in step S1023, the eigenmode component of each power consumption unit satisfies the following condition:
number of extreme points N within the entire data sequenceeAnd the number of zero-crossing points NzThe difference value of (A) meets the set condition; and, at any point in time, the sum of the upper envelope determined by the local maxima of the data sequence and the lower envelope determined by the local minima is zero.
I.e. the whole data sequence, (N)z-1)≤Ne≤(Nz+1), and [ f)max(t)+fmin(t)]2 ═ 0; wherein N iszNumber of zero-crossing points, NeIs the number of extreme points, fmax(t) is the upper envelope, fmin(t) is the lower envelope.
And under the condition of meeting two conditions of the intrinsic modal components, continuously and iteratively screening to obtain the modal components. And connecting all maximum value points and all minimum value points by a cubic spline curve respectively to obtain an upper envelope line and a lower envelope line, taking the average value of the upper envelope line and the lower envelope line, continuously deleting and iterating, and finally terminating the process according to a stopping condition to obtain a series of intrinsic mode components. And repeating the above process to repeatedly circulate the remaining modal components until the residual components are monotonous functions and the modal components can not be resolved again, or the separated final intrinsic modal components are smaller than expected, and finishing the whole resolving process.
In one possible implementation, the conditions are set as follows: the absolute value of the difference between the number of extreme points and the number of zero-crossing points is less than or equal to 1.
In a possible implementation manner, before determining the sub-load prediction curve corresponding to each electricity consumption unit based on the recorded eigenmode component in step S103, the method further includes:
carrying out normalization processing on the recorded intrinsic mode component and the load analysis sequence, and determining a normalization correlation coefficient;
and when the normalized correlation coefficient is smaller than or equal to the coefficient threshold value, rejecting the eigenmode component corresponding to the normalized correlation coefficient.
The method comprises the steps of obtaining a load analysis sequence, determining intrinsic mode components of the load analysis sequence, and determining which intrinsic mode components are true components of the load analysis sequence and which are false and meaningless intrinsic mode components by using a correlation coefficient between the intrinsic mode components and the load analysis sequence as an index according to a common correlation coefficient method. And determining the eigenmode components of which the normalized correlation coefficients are less than or equal to a coefficient threshold value as false eigenmodes, and removing the false eigenmode components to be used as a part of residual errors. In addition, all intrinsic mode components and the original signal are subjected to normalization processing, so that the situation that real components with small amplitude are removed is avoided.
In one possible implementation, the normalized correlation coefficient is:
Figure BDA0003340971820000141
wherein r isjNormalized correlation coefficient of j-th eigenmode component and load analysis sequence; t is a sampling point of the signal; c. Cj(t) is the jth eigenmode component;
Figure BDA0003340971820000142
is the mean of the eigenmode components; y (t) is a payload analysis sequence;
Figure BDA0003340971820000143
mean of the load analysis sequences.
In one possible implementation, the threshold value TH is set from the standard deviation TH ═ std (r) of the correlation coefficientj) Obtaining, namely:
Figure BDA0003340971820000144
if rjTH, reserving the jth intrinsic mode component; otherwise, eliminating the j-th intrinsic mode component.
In one possible implementation, the stop condition in step S103 includes:
the eigenmode components satisfy the following termination function:
Figure BDA0003340971820000145
wherein S isdIs the standard deviation between two successive iteration results; h isj(t) the eigenmode component obtained in the jth iteration; sdNumerical range (0.2, 0.3).
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
The following are embodiments of the apparatus of the invention, reference being made to the corresponding method embodiments described above for details which are not described in detail therein.
Fig. 4 is a schematic structural diagram of an apparatus for power load prediction according to an embodiment of the present invention, and for convenience of description, only the parts related to the embodiment of the present invention are shown, and detailed descriptions are as follows:
as shown in fig. 4, includes: a preprocessing module 401, a determination module 402, a first analysis module 403 and a second analysis module 404.
The preprocessing module 401 is configured to preprocess the original load curve to obtain a load analysis sequence corresponding to the current day to be measured.
And a determining module 402, configured to add a white noise sequence to the load analysis sequence, and perform empirical mode decomposition to determine an intrinsic mode component of each power consuming unit.
A first analysis module 403, configured to record an intrinsic mode component of each power consumption unit when the intrinsic mode component does not satisfy a stop condition, and perform the operations after adding a white noise sequence to the analysis load sequence; otherwise, determining the sub-load prediction curve corresponding to each electricity utilization unit based on the recorded intrinsic mode component.
And a second analysis module 404, configured to perform error processing on the sub-load prediction curves of each power consumption unit, and add the sub-load prediction curves after the error processing to obtain a total load prediction curve.
In this embodiment, the white noise sequence is added to the load analysis sequence corresponding to the current day to be measured, so as to highlight the features in the load analysis series and facilitate the subsequent decomposition, thereby improving the prediction accuracy. And carrying out empirical mode decomposition on the load analysis sequence added with the white noise sequence to determine the intrinsic mode component of each power utilization unit, controlling the operation of the white noise based on the stop condition, and determining the sub-load prediction curve corresponding to each power utilization unit based on the recorded intrinsic mode component. And carrying out error processing on the sub-load prediction curves of the power utilization units, avoiding data with overlarge prediction difference from being substituted into a final prediction result, and adding the sub-load prediction curves subjected to error processing to obtain a total load prediction curve.
Fig. 5 is a schematic diagram of a terminal according to an embodiment of the present invention. As shown in fig. 5, the terminal 5 of this embodiment includes: a processor 50, a memory 51 and a computer program 52 stored in said memory 51 and executable on said processor 50. The processor 50, when executing the computer program 52, implements the steps in each of the above-described method embodiments for power load prediction, such as the steps S101 to S104 shown in fig. 1. Alternatively, the processor 50, when executing the computer program 52, implements the functions of each module/unit in the above-mentioned device embodiments, for example, the functions of the modules 401 to 404 shown in fig. 4.
Illustratively, the computer program 52 may be partitioned into one or more modules/units that are stored in the memory 51 and executed by the processor 50 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 52 in the terminal 5. For example, the computer program 52 may be divided into modules/units 41 to 43 shown in fig. 4.
The terminal 5 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal 5 may include, but is not limited to, a processor 50, a memory 51. It will be appreciated by those skilled in the art that fig. 5 is only an example of a terminal 5 and does not constitute a limitation of the terminal 5 and may include more or less components than those shown, or some components in combination, or different components, for example the terminal may also include input output devices, network access devices, buses, etc.
The Processor 50 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 51 may be an internal storage unit of the terminal 5, such as a hard disk or a memory of the terminal 5. The memory 51 may also be an external storage device of the terminal 5, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) and the like provided on the terminal 5. Further, the memory 51 may also include both an internal storage unit and an external storage device of the terminal 5. The memory 51 is used for storing the computer program and other programs and data required by the terminal. The memory 51 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal and method may be implemented in other ways. For example, the above-described apparatus/terminal embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method for predicting the power load may be implemented by a computer program, which may be stored in a computer readable storage medium and used by a processor to implement the steps of the above embodiments of the method for predicting the power load. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media which may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.

Claims (10)

1. A method for power load prediction, comprising:
preprocessing an original load curve to obtain a load analysis sequence corresponding to the current day to be tested;
adding a white noise sequence into the load analysis sequence, and performing empirical mode decomposition to determine intrinsic mode components of the power utilization units;
when the intrinsic mode component of each power utilization unit does not meet the stop condition, recording the intrinsic mode component, and executing the operation of adding the white noise sequence into the analysis load sequence and then; otherwise, determining a sub-load prediction curve corresponding to each power utilization unit based on the recorded intrinsic modal components;
and carrying out error processing on the sub-load prediction curves of the power utilization units, and adding the sub-load prediction curves subjected to the error processing to obtain a total load prediction curve.
2. The method of claim 1, wherein the white noise sequence follows a normal distribution.
3. The method of claim 1, wherein error processing the sub-load prediction curves for each power-consuming unit comprises:
and carrying out error processing on the sub-load prediction curve of each power utilization unit based on the following error processing functions:
Figure RE-FDA0003520467720000011
wherein, aiThe weight of the power utilization unit i in the day to be measured; x is the number ofiPredicting a curve for the sub-load of the power utilization unit i on the day to be tested; x'iThe actual sub-load of the electricity utilization unit i on the day to be tested; a isi、xiAnd x'iThe value range of (a) is a positive number, and the value range of i is a positive integer.
4. The method of claim 1, wherein preprocessing the original load curve to obtain a load analysis sequence corresponding to the current day to be tested comprises:
acquiring an original load curve, and determining a load characteristic vector according to a key characteristic variable and power utilization time;
calculating the position difference between the load characteristic vector of the day to be detected and the historical load characteristic vector, and determining a historical approximate vector of the day to be detected from the historical load characteristic vector based on the position difference;
and determining a load analysis sequence according to the historical approximate vector and the original load curve.
5. The method of claim 1, wherein adding a white noise sequence to the load analysis sequence and performing empirical mode decomposition to determine the eigenmode components of each power-consuming element comprises:
adding a white noise sequence into the load analysis sequence to determine a correction analysis sequence;
obtaining a maximum value and a minimum value in the correction analysis sequence through differentiation, and determining an upper envelope line and a lower envelope line of the correction analysis sequence through cubic spline fitting;
and calculating a mean value according to the upper envelope line and the lower envelope line, and determining the intrinsic mode component of each power utilization unit according to the difference value between the load analysis sequence and the mean value.
6. The method according to any one of claims 1 to 5, wherein before determining the sub-load prediction curve corresponding to each electricity consumption unit based on the recorded eigenmode component, the method further comprises:
carrying out normalization processing on the recorded intrinsic mode component and the load analysis sequence, and determining a normalization correlation coefficient;
and when the normalized correlation coefficient is smaller than or equal to the coefficient threshold value, rejecting the eigenmode component corresponding to the normalized correlation coefficient.
7. The method of claim 6, wherein the normalized correlation coefficient is:
Figure RE-FDA0003520467720000021
wherein, r isjNormalized correlation coefficients for the jth eigenmode component with the load analysis sequence; the t is a sampling point of the signal; c is mentionedj(t) is the jth eigenmode component; the above-mentioned
Figure RE-FDA0003520467720000022
Is the mean of the eigenmode components; the y (t) is a load analysis sequence; the above-mentioned
Figure RE-FDA0003520467720000023
Mean of the load analysis sequences.
8. The method of claim 1, wherein the stop condition comprises:
the eigenmode components satisfy the following termination function:
Figure RE-FDA0003520467720000031
wherein, the SdIs the standard deviation between two successive iteration results; h isj(t) the eigenmode component obtained in the jth iteration; said SdNumerical range (0.2, 0.3).
9. A terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of the preceding claims 1 to 8 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
CN202111308391.XA 2021-11-05 2021-11-05 Method, terminal and storage medium for power load prediction Pending CN114254800A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111308391.XA CN114254800A (en) 2021-11-05 2021-11-05 Method, terminal and storage medium for power load prediction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111308391.XA CN114254800A (en) 2021-11-05 2021-11-05 Method, terminal and storage medium for power load prediction

Publications (1)

Publication Number Publication Date
CN114254800A true CN114254800A (en) 2022-03-29

Family

ID=80790582

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111308391.XA Pending CN114254800A (en) 2021-11-05 2021-11-05 Method, terminal and storage medium for power load prediction

Country Status (1)

Country Link
CN (1) CN114254800A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115496285A (en) * 2022-09-26 2022-12-20 上海玫克生储能科技有限公司 Power load prediction method and device and electronic equipment
CN117559448A (en) * 2024-01-12 2024-02-13 山东德源电力科技股份有限公司 Power consumption load prediction analysis method and system for special transformer acquisition terminal

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115496285A (en) * 2022-09-26 2022-12-20 上海玫克生储能科技有限公司 Power load prediction method and device and electronic equipment
CN115496285B (en) * 2022-09-26 2023-09-12 上海玫克生储能科技有限公司 Power load prediction method and device and electronic equipment
CN117559448A (en) * 2024-01-12 2024-02-13 山东德源电力科技股份有限公司 Power consumption load prediction analysis method and system for special transformer acquisition terminal
CN117559448B (en) * 2024-01-12 2024-03-22 山东德源电力科技股份有限公司 Power consumption load prediction analysis method and system for special transformer acquisition terminal

Similar Documents

Publication Publication Date Title
CN114254800A (en) Method, terminal and storage medium for power load prediction
CN110889545A (en) Power load prediction method and device and readable storage medium
WO2018105341A1 (en) Prediction system and prediction method
CN111815065B (en) Short-term power load prediction method based on long-short-term memory neural network
CN111028100A (en) Refined short-term load prediction method, device and medium considering meteorological factors
CN112508299A (en) Power load prediction method and device, terminal equipment and storage medium
CN110991815A (en) Distribution room power energy scheduling method and system
CN112651563A (en) Load prediction method and device, computer readable storage medium and electronic equipment
Zhu et al. Hybrid of EMD and SVMs for short-term load forecasting
CN117494931A (en) Marginal carbon emission factor determining method, system and equipment based on power grid node
CN116091118A (en) Electricity price prediction method, device, equipment, medium and product
Pantazis et al. A posteriori probabilistic feasibility guarantees for Nash equilibria in uncertain multi-agent games
CN113902181A (en) Short-term prediction method and equipment for common variable heavy overload
CN112686470A (en) Power grid saturation load prediction method and device and terminal equipment
CN113962874A (en) Bus load model training method, device, equipment and storage medium
CN111127114A (en) Method and device for determining power load declaration data
CN113268929B (en) Short-term load interval prediction method and device
CN116307111A (en) Reactive load prediction method based on K-means clustering and random forest algorithm
CN115935212A (en) Adjustable load clustering method and system based on longitudinal trend prediction
CN114462298A (en) Electric power measurement asset management method, device, equipment and storage medium
CN114880406A (en) Data management method and device
CN113705929A (en) Spring festival holiday load prediction method based on load characteristic curve and typical characteristic value fusion
CN113743519A (en) Power grid bus typical load curve identification method
CN113570105A (en) Power load prediction method and device and terminal
CN113487080B (en) Wind speed dynamic scene generation method, system and terminal based on wind speed classification

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