CN113469506A - User baseline load estimation method, terminal and computer readable storage medium - Google Patents

User baseline load estimation method, terminal and computer readable storage medium Download PDF

Info

Publication number
CN113469506A
CN113469506A CN202110650982.9A CN202110650982A CN113469506A CN 113469506 A CN113469506 A CN 113469506A CN 202110650982 A CN202110650982 A CN 202110650982A CN 113469506 A CN113469506 A CN 113469506A
Authority
CN
China
Prior art keywords
load
user
sample
demand response
control group
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
CN202110650982.9A
Other languages
Chinese (zh)
Inventor
付文杰
申洪涛
陶鹏
任鹏
李飞
王飞
王喻玺
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
North China Electric Power University
Marketing Service Center of State Grid Hebei Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
North China Electric Power University
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, North China Electric Power University, Marketing Service Center of State Grid Hebei Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202110650982.9A priority Critical patent/CN113469506A/en
Publication of CN113469506A publication Critical patent/CN113469506A/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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Abstract

The invention belongs to the technical field of load estimation of power systems, and provides a user baseline load estimation method, a terminal and a computer readable storage medium. The user baseline load estimation method comprises the following steps: expanding a control group load sample set by adopting a data expansion method and a sample reduction technology; then, clustering load curves of comparison group users which do not participate in the demand response project on a demand response day by adopting a K-means algorithm to obtain a plurality of comparison group subsets; secondly, synchronously matching each user participating in the demand response project into a control group subset most similar to the load pattern of the user according to the load pattern of the user on the demand response day; and finally, estimating the baseline load of the demand response users in the same subset by using the load data of the control group users in the control group subset in the demand response period. When the number of the users in the comparison group is insufficient, the method can effectively improve the accuracy of baseline load estimation, and is beneficial to promoting the implementation and popularization of demand response.

Description

User baseline load estimation method, terminal and computer readable storage medium
Technical Field
The invention belongs to the technical field of load estimation of power systems, and particularly relates to a user baseline load estimation method, a terminal and a computer readable storage medium.
Background
With the advance of the marketization process of the power system, the demand response technology is gradually widely applied to the power system. Depending on the implementation of demand response, demand responses can be divided into price-type demand responses and incentive-type demand responses. Incentive-type demand responses aggregate large amounts of customer participation by paying participation compensation to achieve a larger overall capacity, which is then sold in the power market for profit. The participation compensation is the compensation paid to the participant by the incentive-type demand response enforcement, equal to the product of the load reduction and its unit price for compensation. The reduction amount is equal to the difference between the load that would have been consumed if the user did not participate in the demand response and the load that would have been actually consumed after participating in the demand response, where the latter is the actual measurement data, the former is the user baseline load, i.e., the load that would have been consumed if the user did not participate in the demand response. In order to accurately calculate the compensation obtained by the user's participation in the demand response, an estimate of the user's baseline is needed.
Among the numerous baseline load estimation methods, the control group method has strong practicability. The control group method has the advantages of being easy to implement, low in dependence degree on user historical load data, strong in adaptability to environmental changes and the like. However, the accuracy of the control group method is closely related to the diversity of the samples in the control group, and when the number of the control group users (users in the same area not participating in the demand response) is insufficient or seriously deficient, the baseline load estimation using the control group method has a large error. The invention provides a user baseline load estimation method, aiming at solving the problem that the estimation effect of a contrast group method is poor when the number of contrast group users is insufficient.
Disclosure of Invention
In view of this, the present invention provides a user baseline load estimation method, a terminal and a computer readable storage medium, which can improve the accuracy of baseline load estimation when the number of users in a control group is small.
A first aspect of an embodiment of the present invention provides a method for estimating a user baseline load, including:
generating a second load sample set of a control group user based on a first load sample set of the control group user, wherein the number of samples of the second load sample set is greater than that of the first load sample set, and samples in the same time period form the first load sample set;
matching and connecting samples of the second load sample set at different time intervals according to the corresponding relation to generate a load curve;
clustering the load curves, obtaining a comparison group clustering center curve and a comparison group subset after clustering, and determining the corresponding relation between a demand response group user curve and the comparison group subset according to the comparison group clustering center curve;
and estimating the base line load of the corresponding demand response group users according to the comparison group subset.
With reference to the first aspect, in some embodiments, before matching and connecting the samples of the second load sample set in different time periods according to the corresponding relationship, the method further includes:
and reducing the number of samples in the second load sample set to a preset number.
With reference to the first aspect, in some embodiments, the reducing the number of samples in the second load sample set to a preset number includes:
calculating a second sample with the smallest distance to the first sample, wherein the first sample and the second sample are both any samples in the second load sample set, and the first sample is different from the second sample;
calculating the product of the probability of the first sample and the probability of the first sample to obtain the probability product of the first sample, wherein the probability of the first sample is the reciprocal of the number of samples in the second load sample set;
and subtracting the first sample corresponding to the minimum value in the probability product.
With reference to the first aspect, in some embodiments, the generating a second load sample set of a control group user based on a first load sample set of the control group user comprises:
generating a distribution function curve based on the first load sample set of the control group of users;
sampling the distribution function curve to generate a second load sample set of the control group of users.
With reference to the first aspect, in some embodiments, the distribution function curve includes a cumulative distribution function curve, the generating a distribution function curve based on a first load sample set of control group users, sampling the distribution function curve to generate a second load sample set of the control group users includes:
and calculating a cumulative distribution function curve through the first load sample of the control group of users, and sampling an inverse function of a function corresponding to the cumulative distribution function curve to obtain the second load sample set.
With reference to the first aspect, in some embodiments, clustering the load curves to obtain a reference group cluster center curve and a reference group subset after clustering includes:
and obtaining the clustering center curve through a K-means algorithm, wherein the objective function of the K-means algorithm is to minimize the sum of the distances between the load curves of all the users in the control group and the clustering center curve.
With reference to the first aspect, in some embodiments, the demand response group user baseline load is determined as follows:
Figure BDA0003111146210000031
in the formula:
Figure BDA0003111146210000032
is the baseline load value for the demand response user n at time t on the demand response day d,
Figure BDA0003111146210000033
the actual load value of a comparison group user matched with the demand group user at the time t of the demand response day d; w is aiIs the weight coefficient of the ith comparison user, MkIs the number of users in the control group subset.
In combination with the first aspect, in some embodiments, the weight coefficients are determined as follows:
Figure BDA0003111146210000034
in the formula: s (i, n) represents the similarity between the ith control user and the demand response user n in the control group subset.
A second aspect of embodiments 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 user baseline load estimation method according to any one of the first aspect when executing the computer program.
A third aspect of embodiments of the present invention provides a computer-readable storage medium, which stores a computer program, which when executed by a processor implements the steps of the user baseline load estimation method according to any one of the first aspect.
Compared with the prior art, the invention has the following beneficial effects:
in the embodiment of the invention, when the number of the samples of the first load sample set of the contrast group user is insufficient, the number of the samples of the contrast group can be effectively expanded through the contrast group first load sample set to form a second load sample set. The second load sample set after the expansion of the invention not only keeps the sample characteristics of the reference group load before the expansion, but also increases the diversity of the load scene, thereby improving the accuracy of the baseline load estimation by using the reference group method.
According to the user baseline load estimation method provided by the invention, the distance calculation is carried out on the samples in the second load sample set, the sample probability product is obtained through the sample probability, the reduction target is found in a mode of searching the minimum distance probability product, the optimal sample is reserved, the sample is more representative, and the accuracy of the sampling sample is further improved.
According to the user baseline load estimation method provided by the invention, the curves with the same number as the samples in the control group are estimated by sequencing and connecting the samples in different time periods, so that the method is ready for matching with the users in the demand response group.
The user baseline load estimation method provided by the invention obtains the clustering center curve through a K-means algorithm, so that the sum of distances between the load curves of all comparison group users and the clustering center curve is minimum, the clustering center curve is obtained, the comparison components are divided into a plurality of comparison group subsets, after the clustering center curve is obtained, the comparison group subsets with high similarity are selected to be matched with the demand response group users by calculating the similarity between the demand response group user curve and the clustering center curve in a non-demand response period, and thus the corresponding relation between the response group users and the comparison group subsets is obtained.
According to the user baseline load estimation method provided by the invention, the weight coefficient is determined through the similarity between each sample in the comparison group subset and the comparison group user, and the baseline load of the corresponding demand response user is estimated according to the weight coefficient, so that the baseline load is high in similarity with the comparison group user, the accuracy is good, and the baseline load of the response group user when the response group user does not participate in the response can be more accurately reflected.
After the implementation of the incentive type demand response is finished, the baseline load of the residential user can be accurately estimated through the method, so that the load reduction amount of the user during the execution of the demand response is accurately calculated, and finally, the load aggregator provides reasonable compensation according to the load reduction amount. The method can effectively improve the fairness of the excitation type demand response participation parties and is beneficial to implementation and popularization of demand response.
The invention provides a resident user baseline load estimation method based on load scene estimation, which can improve the accuracy of baseline load estimation under special conditions and has a positive effect on implementation and popularization of demand response. The user baseline load estimation method provided by the invention is beneficial to guaranteeing the fairness of compensation settlement after the implementation of demand response, and meanwhile, the user participation demand response experience can be improved, and the good interaction between the user and the power company is promoted.
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 flow chart of an implementation of a user baseline load estimation method according to an embodiment of the present invention;
FIG. 2 is a functional block diagram of a user baseline load estimation device provided by an embodiment of the invention;
fig. 3 is a functional block diagram of a user baseline load estimation device 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.
Referring to fig. 1-3, the details are as follows: a user baseline load estimation method comprises steps 101 to 105.
Step 101, generating a second load sample set of a control group user based on a first load sample set of the control group user, wherein the number of samples of the second load sample set is greater than that of the first load sample set, and samples in the same time period form the first load sample set;
in some embodiments, the generating a second load sample set of the control group of users based on the first load sample set of the control group of users may include:
generating a distribution function curve based on the first load sample set of the control group of users;
sampling the distribution function curve to generate a second load sample set of the control group of users.
In some embodiments, the generating the distribution function curve based on a first load sample set of the control group of users and sampling the distribution function curve to generate a second load sample set of the control group of users may include:
and calculating a cumulative distribution function curve through the first load sample of the control group of users, and sampling an inverse function of a function corresponding to the cumulative distribution function curve to obtain the second load sample set.
More specifically, the second load sample set of the control group user is generated based on the first load sample set of the control group user, and there are various methods for implementing the second load sample set by expanding the first load sample set of the control group user, such as an interpolation method. The invention discloses an optional implementation mode, which adopts LHS-based daily load curve scene set generation and can comprise steps (1-1) to (1-4).
(1-1) recording the T, T-1, of the N users in the control group, and the first load sample set consisting of the load samples of the T periods is PtThe sampling size of the t-th period is NtStatistics of PtLoad average value of
Figure BDA0003111146210000061
And load variance σ2。
(1-2) calculating an accumulative probability distribution function F (P) according to the parameters of the mean value and the variance obtained in the previous step, and equally dividing F (P) into NtNon-overlapping subintervals, each interval having a spacing of 1/Nt；
(1-3) in each aliquot i, i ═ 1,2tRandomly generating a range of [0,1 ]]Random number of
Figure BDA0003111146210000062
Calculating the corresponding cumulative probability function value
Figure BDA0003111146210000063
The following were used:
Figure BDA0003111146210000064
(1-4) inverse function according to cumulative probability distribution function
Figure BDA0003111146210000065
Calculating sample values of load data
Figure BDA0003111146210000066
Namely:
Figure BDA0003111146210000067
through the four steps, the second load sample set in the t-th time period is obtained through sampling
Figure BDA0003111146210000068
According to the user baseline load estimation method, when the number of the samples of the first load sample set of the comparison group user is insufficient, the number of the samples of the comparison group can be effectively expanded through the first load sample set of the comparison group, and a second load sample set is formed. The second load sample set after the expansion of the invention not only keeps the sample characteristics of the reference group load before the expansion, but also increases the diversity of the load scene, thereby improving the accuracy of the baseline load estimation by using the reference group method.
Optionally, before matching and connecting the samples of the second load sample set according to the corresponding relationship in different time periods, the method may further include:
and 102, reducing the number of the samples in the second load sample set to a preset number.
As one possible implementation, step 102 may include:
calculating a second sample with the smallest distance to the first sample, wherein the first sample and the second sample are both any samples in the second load sample set, and the first sample is different from the second sample;
calculating the product of the probability of the first sample and the probability of the first sample to obtain the probability product of the first sample, wherein the probability of the first sample is the reciprocal of the number of samples in the second load sample set;
subtracting a first sample corresponding to the minimum value in the probability product;
and circularly executing the processes until the number of the samples in the second load sample set is reduced to a preset number.
More specifically, the purpose of reducing the number of samples is to reduce samples with too small sample spacing and low probability that affect the accuracy of expansion after expansion. The embodiment of the invention can adopt the time interval as a unit, eliminate the minimum distance samples one by one and keep the optimal representative samples until the preset reduction number is reached.
In one embodiment, the process of subtracting samples for a certain period of time may include steps (2-1) to (2-5).
(2-1) initializing, setting the final target sample number as
Figure BDA0003111146210000071
For initial N'tSamples, each sample being equal in probability, namely:
Figure BDA0003111146210000072
initializing a subtracted sample set to JtInitialize a reserved sample set to R { }t＝{1,2,...,N'tThe two sets record the number of samples subtracted and retained, respectively.
(2-2) calculation of RtTwo samples in
Figure BDA0003111146210000073
And
Figure BDA0003111146210000074
i,j＝1,2,...,N'tthe distance calculation formula is as follows:
Figure BDA0003111146210000081
(2-3) for arbitrary samples
Figure BDA0003111146210000082
Finding the sample at the smallest distance therefrom, i.e.
Figure BDA0003111146210000083
And calculating its probability product according to equation (5):
Figure BDA0003111146210000084
(2-4) in N'tIn one sample, find the minimum
Figure BDA0003111146210000085
Record its sample number, i.e.:
Figure BDA0003111146210000086
(2-5) updating the subtracted sample sets J, respectivelyt＝Jt∪l*And a set of retained samples Rt＝Rt\l*。
(2-6) judgment set RtWhether the number of samples in (1) has reached a preset number
Figure BDA0003111146210000087
If yes, stopping reduction and outputting the optimal representative sample
Figure BDA0003111146210000088
According to the user baseline load estimation method, the distance calculation is carried out on the samples in the second load sample set, the sample probability product is obtained through the sample probability, the reduction target is found in a mode of finding the minimum distance probability product, the optimal sample is reserved, the samples are more representative, and the accuracy of the sampling samples is further improved.
103, matching and connecting samples of the second load sample set at different time intervals according to the corresponding relation to generate a second load curve;
in this step, the purpose of generating the second load curve is to form a curve with the context of the user object for the corresponding group of users, and to prepare for matching the user curve of the response group, i.e. multi-period sample generation. The multi-session sample generation may include steps (3-1) to (3-5).
(3-1) mixing
Figure BDA0003111146210000089
The samples in the sequence are sorted in ascending order or descending order according to the load size to obtain the sorted load samples
Figure BDA00031111462100000810
(3-2) setting an initial value t equal to 1, a load sample fluctuation threshold epsilon, an initial load sample
Figure BDA00031111462100000811
(3-3) for
Figure BDA00031111462100000812
Of (4) an arbitrary sample
Figure BDA00031111462100000813
Matching
Figure BDA00031111462100000814
Corresponding next moment load sample
Figure BDA00031111462100000815
Where j is a random number in the set { i-epsilon.,. i + epsilon }, and let
Figure BDA0003111146210000091
(3-4) making T equal to T +1, returning to the step 3-3, and entering the step 3-5 until T equal to T.
(3-5) mixing
Figure BDA0003111146210000092
T1.. times.t, the load samples corresponding to T are connected to obtain the first
Figure BDA0003111146210000093
Line load curve
Figure BDA0003111146210000094
According to the user baseline load estimation method, the samples in different time periods are sequenced and connected to generate the curve with the same number as that of the samples in the comparison group, so that the method is ready for matching with the users in the demand response group.
104, clustering the load curves, obtaining a comparison group clustering center curve and a comparison group subset at the same time, and determining the corresponding relation between a demand response group user curve and the comparison group subset according to the comparison group clustering center curve;
in some embodiments, the clustering the load curves, and obtaining a reference cluster center curve and a reference subset at the same time, includes:
and obtaining the clustering center curve through a K-means algorithm, wherein the objective function of the K-means algorithm is to minimize the sum of the distances between the load curves of all the users in the control group and the clustering center curve.
Exemplarily, in order to find a matching relation between a load curve and a demand response group, the embodiment of the invention discloses a load pattern clustering and matching method based on a K-means algorithm, which comprises the following steps:
to be provided with
Figure BDA0003111146210000095
Representing the actual load curve of the control group users M, M1, 2, M on the demand response day d, the objective function of the K-means algorithm is to minimize the sum of the squares of the errors of the load curves of all the control group users and their cluster centers, i.e.:
Figure BDA0003111146210000096
wherein K represents the number of clusters,
Figure BDA0003111146210000097
denotes the K-th, K-1, 2.
Note that the demand response period is δ ═ δs,δs+1,...,δeIs }, δ ∈ T, where δsIs the start time of the demand response, δeIs the end time of the demand response. For each demand response day D e D, the LCS before and after the demand response time period is executed by the demand response user n are respectively recorded as:
Figure BDA0003111146210000101
Figure BDA0003111146210000102
similarly, the curve segments of the cluster centers of the control group subset before and after the demand response period are respectively recorded as:
Figure BDA0003111146210000103
Figure BDA0003111146210000104
in order to match each demand response user to the control subset that is most similar to its load pattern, the similarity of the demand response user to each control subset needs to be calculated. S (x, y) represents the similarity between the vector x and the vector y, and the calculation formula is shown as formula (12).
Figure BDA0003111146210000105
Where dist (x, y) represents the distance between vector x and vector y, and euclidean distance is used herein as a metric. The similarity between the demand response user n and the control group subset k can be calculated by equation (13).
Figure BDA0003111146210000106
And after calculating the similarity between each demand response user and each control group subset, matching the demand response users to the control group subsets with the highest similarity. The demand response users are matched to the subset of the control group with the highest similarity.
The user baseline load estimation method provided by the invention obtains the clustering center curve through a K-means algorithm, so that the sum of distances between the load curves of all comparison group users and the clustering center curve is minimum, the clustering center curve is obtained, the comparison group is divided into a plurality of comparison group subsets, after the clustering center curve is obtained, the comparison group subsets and the demand response group users with high similarity are selected to be matched through calculating the similarity between the demand response group user curve and the clustering center curve in a non-demand response period, and thus the corresponding relation between the response group users and the comparison group subsets is obtained. And 105, estimating the base line load of the corresponding demand response group users according to the control group subset.
For example, the demand response group user baseline load may be determined as follows:
Figure BDA0003111146210000111
in the formula:
Figure BDA0003111146210000112
is the baseline load value for the demand response user n at time t on the demand response day d,
Figure BDA0003111146210000113
the actual load value of a comparison group user matched with the demand group user at the time t of the demand response day d; w is aiIs the weight coefficient of the ith comparison user, MkIs the number of users in the control group subset.
Wherein the weight coefficient wiDetermined as follows:
Figure BDA0003111146210000114
in the formula: s (i, n) represents the similarity between the ith control user and the demand response user n in the control group subset.
Illustratively, the implementation of step 105 may include:
suppose that the demand response user n belongs to the kth class, and all comparison users in the class are marked as Ik＝{i|i＝1,2,...,MkIn which M iskIs against the number of users in the kth class. The load of each control consumer in the control subset k can be considered as an estimate of the baseline load of the demand response consumer n, and the baseline load of the demand response consumer n can be expressed as:
Figure BDA0003111146210000115
in the formula
Figure BDA0003111146210000116
Is the baseline load value for the demand response user n at time t on the demand response day d,
Figure BDA0003111146210000117
is that the user I belongs to IkThe actual load value at the time t of the demand response day d; w is aiIs the weighting factor before the ith comparison user.
Obviously, the distribution of the weights is related to the accuracy of the final baseline load estimation, and reasonable weight setting should follow the following principle: control users that are more similar to the demand response user to be estimated should be given more weight and the sum of all weight coefficients added equals 1. The present invention determines the weight coefficient according to equation (15).
Figure BDA0003111146210000118
Wherein S (i, n) represents the similarity between the ith comparison user and the demand response user n in the comparison group subset, which can be obtained by calculating the similarities of the two LCS before and after the demand response period, respectively, and then adding the similarities.
According to the user baseline load estimation method, the weight coefficient is determined through the similarity between each sample of the comparison group subset and the comparison group user, and the baseline load of the corresponding demand response user is estimated according to the weight coefficient, so that the baseline load is high in similarity with the comparison group user, good in precision, and capable of accurately reflecting the baseline load of the response group user when the response group user does not participate in response.
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. 2 shows a functional block diagram of the user baseline load estimation apparatus 30 provided in the embodiment of the present invention, and for convenience of explanation, only the parts related to the embodiment of the present invention are shown, and detailed descriptions are as follows:
as shown in fig. 2, the user baseline load estimation apparatus 30 includes: a control group sample expansion module 310, a control group sample subtraction module 320, a multi-period curve generation module 330, a control group sample and corresponding group matching module 340, and a baseline load estimation module 350.
The comparison group sample expansion module 310 is configured to obtain a cumulative distribution function curve by calculating the first load sample set, and sample the cumulative distribution function curve to obtain an expanded second load sample set.
The control group sample reduction module 320 is configured to obtain a probability product of the first sample by calculating a product of probabilities of the first sample in the second sample set and the first sample in the second sample set, reduce a sample corresponding to the minimum probability product, and retain an optimal sample to obtain a reduced second sample set.
The multi-period curve generating module 330 is configured to connect the subtracted second sample sets with the sample set to generate a final curve of the number of samples of the control group.
The comparison group sample and corresponding group matching module 340 is configured to cluster the multi-period curves through a K-means algorithm to obtain a clustering center curve, so that the sum of distances between load curves of all comparison group users and the clustering center curve is minimum, thereby obtaining the clustering center curve and dividing the comparison group into a plurality of comparison group subsets, and after obtaining the clustering center curve, matching the comparison group subsets with the response group users through a clustering center line, thereby obtaining a corresponding relationship between the response group users and the comparison group subsets.
The baseline load estimation module 350 is configured to determine a weight coefficient according to the similarity between each sample of the control group subset and the control group user, and generate a baseline load according to the weight coefficient and each sample of the control group subset.
From the above, it can be understood that the present invention implements the user baseline load estimation method through the above modules, and it should be understood that the above functional modules are a physical implementation of the method of the present invention.
The following are terminal embodiments of the invention, and for details not described in detail therein, reference may be made to the corresponding method embodiments described above.
Fig. 3 is a schematic diagram of a terminal according to an embodiment of the present invention. As shown in fig. 3, the terminal 4 of this embodiment includes: a processor 40, a memory 41 and a computer program 42 stored in said memory 41 and executable on said processor 40. The steps in the various method embodiments described above are implemented when the computer program 42 is executed by the processor 40. Alternatively, the processor 40, when executing the computer program 42, implements the functions of each module/unit in each device embodiment described above, for example, the functions of the units 310 to 350 shown in fig. 2.
Illustratively, the computer program 42 may be partitioned into one or more modules/units that are stored in the memory 41 and executed by the processor 40 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 42 in the terminal 4.
The terminal 4 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal may include, but is not limited to, a processor 40, a memory 41. Those skilled in the art will appreciate that fig. 3 is merely an example of a terminal 4 and is not intended to be limiting of terminal 4, and may include more or fewer components than those shown, or some components in combination, or different components, e.g., the terminal may also include input-output devices, network access devices, buses, etc.
The Processor 40 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 41 may be an internal storage unit of the terminal 4, such as a hard disk or a memory of the terminal 4. The memory 41 may also be an external storage device of the terminal 4, 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 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the terminal 4. The memory 41 is used for storing the computer program and other programs and data required by the terminal. The memory 41 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 according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. 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 estimating a baseline load of a user, comprising:
generating a second load sample set of a control group user based on a first load sample set of the control group user, wherein the number of samples of the second load sample set is greater than that of the first load sample set, and samples in the same time period form the first load sample set;
matching and connecting samples of the second load sample set at different time intervals according to the corresponding relation to generate a load curve;
clustering the load curves, obtaining a comparison group clustering center curve and a comparison group subset after clustering, and determining the corresponding relation between a demand response group user curve and the comparison group subset according to the comparison group clustering center curve;
and estimating the base line load of the corresponding demand response group users according to the comparison group subset.
2. The method of claim 1, wherein prior to matching and connecting samples of the second load sample set according to the correspondence at different time periods, the method further comprises:
and reducing the number of samples in the second load sample set to a preset number.
3. The method of claim 2, wherein the reducing the number of samples in the second load sample set to a predetermined number comprises:
calculating a second sample with the smallest distance to the first sample, wherein the first sample and the second sample are both any samples in the second load sample set, and the first sample is different from the second sample;
calculating the product of the probability of the first sample and the probability of the first sample to obtain the probability product of the first sample, wherein the probability of the first sample is the reciprocal of the number of samples in the second load sample set;
and subtracting the first sample corresponding to the minimum value in the probability product.
4. The method of claim 1, wherein generating a second set of load samples for a control group of users based on a first set of load samples for the control group of users comprises:
generating a distribution function curve based on the first load sample set of the control group of users;
sampling the distribution function curve to estimate a second set of load samples for the control group of users.
5. The method of claim 4, wherein the distribution function curve comprises a cumulative distribution function curve, the generating a distribution function curve based on a first set of load samples for a control group of users, and sampling the distribution function curve to generate a second set of load samples for the control group of users comprises:
and calculating a cumulative distribution function curve through the first load sample of the control group of users, and sampling an inverse function of a function corresponding to the cumulative distribution function curve to obtain the second load sample set.
6. The method of claim 1, wherein the clustering the load curves to obtain a reference cluster center curve and a reference subset after clustering comprises:
and obtaining the clustering center curve through a K-means algorithm, wherein the objective function of the K-means algorithm is to minimize the sum of the distances between the load curves of all the users in the control group and the clustering center curve.
7. The customer baseline load estimation method of claim 1, wherein the demand response group customer baseline load is determined according to the following equation:
Figure FDA0003111146200000021
in the formula:
Figure FDA0003111146200000022
is the baseline load value for the demand response user n at time t on the demand response day d,
Figure FDA0003111146200000023
the actual load value of a comparison group user matched with the demand group user at the time t of the demand response day d; w is aiIs the weight coefficient of the ith comparison user, MkIs the number of users in the control group subset.
8. The user baseline load estimation method of claim 7, wherein the weighting factor is determined according to the following equation:
Figure FDA0003111146200000024
in the formula: s (i, n) represents the similarity between the ith control user and the demand response user n in the control group subset.
9. A terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the user baseline load estimation method as claimed in any of claims 1 to 8 above.
10. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the user baseline load estimation method as claimed in any of claims 1 to 8 above.
CN202110650982.9A 2021-06-10 2021-06-10 User baseline load estimation method, terminal and computer readable storage medium Pending CN113469506A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110650982.9A CN113469506A (en) 2021-06-10 2021-06-10 User baseline load estimation method, terminal and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110650982.9A CN113469506A (en) 2021-06-10 2021-06-10 User baseline load estimation method, terminal and computer readable storage medium

Publications (1)

Publication Number Publication Date
CN113469506A true CN113469506A (en) 2021-10-01

Family

ID=77869594

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110650982.9A Pending CN113469506A (en) 2021-06-10 2021-06-10 User baseline load estimation method, terminal and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN113469506A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114662043A (en) * 2022-05-25 2022-06-24 广东电网有限责任公司佛山供电局 Real-time evaluation method for user load response condition and related device thereof
CN114662761A (en) * 2022-03-24 2022-06-24 国网江苏省电力有限公司南通供电分公司 Load prediction-based participatory demand response load identification method and system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120130544A1 (en) * 2008-09-10 2012-05-24 Enlighted, Inc. Logical Groupings of Intelligent Building Fixtures
CN112766543A (en) * 2020-12-31 2021-05-07 清华大学 User cluster baseline load estimation method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120130544A1 (en) * 2008-09-10 2012-05-24 Enlighted, Inc. Logical Groupings of Intelligent Building Fixtures
CN112766543A (en) * 2020-12-31 2021-05-07 清华大学 User cluster baseline load estimation method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
F. WANG .ETC: "Synchronous Pattern Matching Principle-Based Residential Demand Response Baseline Estimation: Mechanism Analysis and Approach Description", 《IEEE TRANSACTIONS ON SMART GRID》 *
陈笑: "含分布式电源的配电网风险评估研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114662761A (en) * 2022-03-24 2022-06-24 国网江苏省电力有限公司南通供电分公司 Load prediction-based participatory demand response load identification method and system
CN114662043A (en) * 2022-05-25 2022-06-24 广东电网有限责任公司佛山供电局 Real-time evaluation method for user load response condition and related device thereof
CN114662043B (en) * 2022-05-25 2022-08-19 广东电网有限责任公司佛山供电局 Real-time evaluation method for user load response condition and related device thereof

Similar Documents

Publication Publication Date Title
CN113469506A (en) User baseline load estimation method, terminal and computer readable storage medium
CN106646453B (en) A kind of Doppler radar method for tracking target based on predicted value measurement conversion
CN110119847A (en) A kind of prediction technique, device, storage medium and electronic equipment dispensing duration
Carbone Detrending moving average algorithm: a brief review
CN112446764A (en) Game commodity recommendation method and device and electronic equipment
CN113918598A (en) Product quantization searching method, device, terminal and storage medium
CN111160614B (en) Training method and device of resource transfer prediction model and computing equipment
CN109887012B (en) Point cloud registration method combined with self-adaptive search point set
CN115202890B (en) Data element production resource space distribution method, system and equipment
CN116452242A (en) Game profit prediction method, device and equipment based on fitting regression
CN115587310A (en) Baseline load estimation method and device, electronic equipment and storage medium
CN113190429B (en) Server performance prediction method and device and terminal equipment
CN113657525B (en) KMeans-based cross-feature federal clustering method and related equipment
CN113705957A (en) User cluster baseline load estimation method and device and terminal equipment
CN115796338A (en) Photovoltaic power generation power prediction model construction and photovoltaic power generation power prediction method
CN114065913A (en) Model quantization method and device and terminal equipment
CN111160969A (en) Power price prediction method and device
CN114356235A (en) Data standardization processing method and device, electronic equipment and storage medium
CN109472454B (en) Activity evaluation method, activity evaluation device, electronic equipment and storage medium
CN112598463A (en) C2M e-commerce order distribution method based on big data
CN110852767A (en) Passenger flow volume clustering method and terminal equipment
CN111563134A (en) Fingerprint database clustering method, system, equipment and storage medium of positioning system
CN111091420A (en) Method and device for predicting power price
CN115941699B (en) Edge computing resource allocation method for dynamic pricing
CN117056319A (en) Method and device for supplementing electricity consumption data and terminal equipment

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20211001