CN116885696A - Method, device and storage medium for estimating demand response baseline load - Google Patents
Method, device and storage medium for estimating demand response baseline load Download PDFInfo
- Publication number
- CN116885696A CN116885696A CN202310684961.8A CN202310684961A CN116885696A CN 116885696 A CN116885696 A CN 116885696A CN 202310684961 A CN202310684961 A CN 202310684961A CN 116885696 A CN116885696 A CN 116885696A
- Authority
- CN
- China
- Prior art keywords
- demand response
- load
- day
- user
- baseline
- 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
Links
- 230000004044 response Effects 0.000 title claims abstract description 207
- 238000000034 method Methods 0.000 title claims abstract description 126
- 238000012935 Averaging Methods 0.000 claims abstract description 11
- 238000013507 mapping Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 230000011218 segmentation Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 230000005611 electricity Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000008901 benefit Effects 0.000 abstract description 6
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000001739 rebound effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- 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
-
- 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
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
- H02J3/008—Circuit arrangements for ac mains or ac distribution networks involving trading of energy or energy transmission rights
-
- 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
- H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
- H02J3/14—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by switching loads on to, or off from, network, e.g. progressively balanced loading
- H02J3/144—Demand-response operation of the power transmission or distribution network
-
- 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
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Power Engineering (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Probability & Statistics with Applications (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method, equipment and storage medium for estimating demand response baseline load, which comprises the steps of dividing the load in demand response into demand response users and non-demand response users, clustering a large number of non-demand response users, mapping a load curve of the demand response users in a non-demand response period with a clustering curve of the non-demand response users, and further weighting and estimating the baseline load of the demand response users in the demand response period through errors of values before and after mapping. Meanwhile, a demand response baseline estimation method adopting a traditional averaging method is also included, and a final load baseline is obtained according to error weighting. The method has a wider application range, can be used for occasions with large and complex fluctuation of various loads such as resident loads, commercial loads and industrial loads, can obviously improve the estimation precision of the load base line, and the considered factors are closer to actual operation, so that the calculation result can obviously improve the technical and economic benefits of planning.
Description
Technical Field
The application relates to the technical field of demand response of power system loads, in particular to a method for estimating a demand response baseline load.
Background
The power generation side regulation capability in a novel power system taking new energy as a leading source is obviously reduced, the regulation capability of a demand side is required to be fully excavated, and the lack of flexibility caused by new energy grid connection is made up.
The demand response takes the resource at the demand side as the alternative resource of the electric energy at the supply side, thereby reducing the load of users and achieving the purpose of improving the utilization rate of social resources. Demand response enforcers motivate users to change the electricity usage behavior (load shedding or increasing) within a certain period of time (i.e., a demand response time window) by paying compensation to the participants. The participation compensation is equal to the product of the load response quantity and its compensation unit price. The load response amount is an absolute value of a difference between a load which the user does not participate in the demand response and a load which the user actually consumes after participating in the demand response, and the load response amount is an actual load of the user in the demand response period, and the load response amount is a user base line load. Once the user has performed an incentive type demand response, its baseline load cannot be obtained in reality by measurement, and it must be estimated.
Accurate baseline load estimation is important to the implementation of demand responses because it directly impacts the economic benefits of both the demand response implementer and the participants. However, existing user baseline load estimation methods such as the averaging method, the regression method, the control group method, and the like perform well when the demand response daily load characteristics are relatively similar to the daily typical load pattern, but have poor accuracy when the demand response daily load characteristics are not sufficiently similar to the daily typical pattern. This disadvantage is even more pronounced for residential users with more complex and variable load patterns. In addition, due to the high dependence on the historical data, the accuracy of the existing estimation method is drastically reduced and even completely fails under the condition that the historical data is missing, and the method cannot be applied to users lacking in the historical data record of newly added demand response items.
Disclosure of Invention
Aiming at various defects of demand response baseline load estimation, the application aims to provide a baseline load comprehensive estimation method under multi-source data, which is analyzed together from historical data and current day data so as to improve the accuracy of baseline load estimation.
In order to achieve the above purpose, the present application adopts the following technical scheme:
a method for estimating a demand response baseline load includes the steps of,
step 1: estimating the user baseline load in the demand response day by adopting an average method according to the electricity load data of the appointed days before the demand response day;
step 2: estimating the user baseline load in the demand response day by adopting a segmentation comparison group method according to the power load data of all users in the demand response day;
step 3: and in the non-demand response time period in the demand response day, calculating the errors of the average method and the segmentation comparison method in the step 1 and the step 2 respectively, and fitting to obtain the user baseline load of the demand response time period in the demand response day according to the errors of the non-demand response time period.
Further, the step 1 specifically comprises,
selecting user historical electricity load data of Y days before a demand response day to be estimated, and removing the non-representative days, namely the historical demand response day and holiday, until the Y days are complemented;
selecting X days with highest daily load level from the Y days, and calculating the load average value at each moment in the X days as a user base line load in a demand response day:
in the method, in the process of the application,indicating the user baseline load in the demand response day estimated according to the average method, high (X, Y) indicating the set of X days with highest load level among Y days satisfying the condition before the demand response day,/->Load values of the t-th period on the d-th day in the High (X, Y) set are shown.
Further, the step 2 specifically comprises,
step 2.1, dividing users into demand response users and non-demand response users according to whether to participate in demand response in a demand response day, and taking a set of the non-demand response users as a comparison group;
step 2.2, setting that multiple demand responses occur in the demand response day, wherein n non-demand response time periods exist in the demand response dayAnd have->Wherein: />And->Respectively i < th non-demand response period->Is a start-stop time of (a);
step 2.3 clustering all non-demand response users in the control group within the demand response day by adopting the algorithm of FIG. 3K-Means to form K load clustering curves
Step 2.4, acquiring a demand response day, wherein the demand response user is in n non-demand response time periodsLoad curve segment of (2) in>A representation; will->Non-demand response time periods respectively corresponding to K cluster load curves>Load curve segment->Mapping, i.e. in a certain non-demand response time segment +.>In, find the j-th load cluster curve meeting the minimum error between the two +.>Specifically as shown in formula (2):
at the same time, calculating load curve segments in n non-demand response periodsClustering curves with the corresponding j-th loadThe error between the two is shown in the following formula:
step 2.5 settingMapping the load curve segment in the ith non-demand response period to the jth load cluster curve, and obtaining the segmentation error alpha according to the step 2.4 i Clustering curves respectively mapped by load curve segments of demand response users in n non-demand response time periods in demand response days>i=1, 2,. -%, n; j=1, 2..k, weighting treatment is performed to obtain the user baseline load in the demand response day under the segment control group method:
further, the specific steps of the step 3 are as follows,
step 3.1 calculating the user baseline load obtained according to the averaging method described in step 1 during the demand response dayError from real data over n non-demand response periods:
wherein:and->Respectively representing average estimated user baseline loadAnd the user real load in the i-th non-demand response period +.>Errors in;
step 3.2 calculating the user baseline load obtained by the segmentation comparison group method in step 2 within the demand response dayError from real data over n non-demand response periods:
wherein:and->Respectively representing the user baseline load and the user real load estimated by the segmentation comparison group method in the ith non-demand response period +.>Errors in;
step 3.3, carrying out weighted combination prediction on the user baseline load according to the error magnitude obtained in the steps 3.1 and 3.2 to obtain the user baseline load P t The method is characterized by comprising the following steps:
in yet another aspect, the application also discloses a computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the method as described above.
In yet another aspect, the application also discloses a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the method as above.
According to the technical scheme, the application provides a user baseline load estimation method considering a segmentation comparison group method, loads in demand response are divided into demand response users and non-demand response users, a large number of non-demand response users are clustered, a load curve of the demand response users in a non-demand response period is mapped with a non-demand response user clustering curve, and further, the baseline load of the demand response users in the demand response period is weighted and estimated through errors of values before and after mapping. Meanwhile, in order to improve the precision of the baseline load estimation, a demand response baseline estimation method adopting a traditional averaging method is also included, and a final load baseline is obtained according to error weighting. Compared with the existing load baseline load estimation method, the method provided by the application has a wider application range, can be used for occasions with large, complex and changeable load fluctuation, such as resident load, commercial load, industrial load and the like, and can obviously improve the estimation precision of the load baseline.
The application aims at the inherent 'asynchronous matching' error mechanism of the existing baseline load estimation method, namely the reason that the input data (historical load data) and the output data (baseline load) of the existing baseline load estimation method are asynchronous in time to cause larger estimation errors. According to the estimation method of the demand response baseline load, provided by the application, the user baseline load in the demand response day is estimated by adopting a segmentation comparison group method based on a synchronous mode matching principle according to the power load data of all users in the demand response day, so that the problem of asynchronous matching of the existing estimation method is solved, the estimation precision can be effectively improved, and no history data is needed in the estimation process. Meanwhile, an average value method of asynchronous matching based on historical day data and a segment comparison group method of synchronous matching based on demand day data are optimally combined, a user base line estimation method based on optimal weight combination is provided, the advantages of the two estimation methods are fully fused, and estimation accuracy is greatly improved.
Compared with the prior art, the application has the following improvement and beneficial effects:
(1) The application improves and expands the traditional comparison group method for estimating the user baseline load in the demand response day, fully considers the multiple demand responses in the demand response day, and utilizes the load information before and after the DR period to synchronously match the DR user with the comparison group. And the estimation method is independent of any historical data, and is still applicable to users who newly join in a demand response and lack enough historical data.
(2) The application optimally combines an average value method based on historical day data and asynchronous matching and a segment comparison group method based on demand day data and synchronous matching, provides a user base line estimation method based on optimal weight combination, fully fuses the advantages of the two estimation methods, effectively prevents the influence of overlong multi-segment demand duration time, rebound effect of demand response and the like on the performance of the proposed method, and greatly improves the estimation precision.
Drawings
FIG. 1 is a flow chart of a method of an embodiment of the present application;
FIG. 2 is a schematic diagram of a demand response period within a demand response day;
FIG. 3K-Means algorithm calculation process.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application.
The demand response takes the demand side resource as the alternative resource of the supply side electric energy, and changes the electricity utilization behavior of the demand side resource through price signals and an excitation mechanism, thereby fully playing the due roles of the demand side resource in the aspects of improving the supply and demand balance capacity of the electric power system, peak clipping and valley filling, promoting new energy consumption and the like. The key to evaluating the effectiveness of demand response practices is the determination of the user's baseline load, as it directly affects the economic benefits of both the demand response practitioner and the participant. However, once the user has performed the demand response, the baseline load thereof cannot be obtained by measurement in reality, and it must be estimated. However, existing user baseline load estimation methods such as the averaging method, the regression method, the control group method, and the like perform well when the demand response daily load characteristics are relatively similar to the daily typical load pattern, but have poor accuracy when the demand response daily load characteristics are not sufficiently similar to the daily typical pattern. This disadvantage is even more pronounced for residential users with more complex and variable load patterns. In addition, due to the high dependence on the historical data, the accuracy of the existing estimation method is drastically reduced and even completely fails under the condition that the historical data is missing, and the method cannot be applied to users lacking in the historical data record of newly added demand response items.
Therefore, the embodiment of the application provides a user baseline load estimation method considering a segmentation comparison method, which is used for dividing the load in demand response into demand response users and non-demand response users, clustering a large number of non-demand response users, mapping a load curve of the demand response users in a non-demand response period with a clustering curve of the non-demand response users, and further weighting and estimating the baseline load of the demand response users in the demand response period through errors of values before and after mapping. Meanwhile, in order to improve the precision of the baseline load estimation, a demand response baseline estimation method adopting a traditional averaging method is also included, and a final load baseline is obtained according to error weighting. Compared with the existing load baseline load estimation method, the method provided by the application has a wider application range, can be used for occasions with large, complex and changeable load fluctuation, such as resident load, commercial load, industrial load and the like, and can obviously improve the estimation precision of the load baseline.
As shown in fig. 1, the method for estimating the demand response baseline load according to the present embodiment includes the steps of,
step 1: and estimating the user baseline load in the demand response day by adopting an average method according to the electricity load data of a certain day before the demand response day. The specific method comprises the following steps:
and selecting historical electricity load data of the user on Y days before the demand response day to be estimated, and eliminating the number of days (the historical demand response day and the holiday) which are not representative until the Y days are complemented. And selecting the X days with the highest daily load level from the Y days, and calculating the load average value at each moment in the X days as a user base line load in a demand response day.
In the method, in the process of the application,indicating the user baseline load in the demand response day estimated according to the average method, high (X, Y) indicating the set of X days with highest load level among Y days satisfying the condition before the demand response day,/->Load values of the t-th period on the d-th day in the High (X, Y) set are shown.
Step 2: estimating the user baseline load in the demand response day by adopting a segmentation comparison group method according to the power load data of all users in the demand response day;
step 2.1, dividing users into demand response users and non-demand response users according to whether to participate in demand response days, and obtaining the all-day load curves of k non-demand response usersAnd the set of all non-demand response users is used as a control group.
Step 2.2, setting that multiple demand responses occur in the demand response day, wherein n non-demand response time periods exist in the demand response dayAs particularly shown in fig. 2. As can be seen from the figure, there is +.>Wherein: />And->Respectively i < th non-demand response period->Is a start-stop time of (a).
Step 2.3, clustering all non-demand response users in the control group in the demand response day to form K load clustering curvesThe method specifically comprises the following 6 steps.
Step 2.3.1 load curves of k users not participating in demand response Performing per unit processing, i.e., ppndr.it=pndr.itmax (pndr.it) i=1,..k,;
step 2.3.2 willAs a sample data set, randomly selecting K (K is far smaller than K) samples as a cluster center;
step 2.3.3, respectively calculating the distances between other samples in the samples and the K clustering centers, and respectively taking the samples as the categories of the nearest clustering center;
step 2.3.4, averaging each class of the classified samples, and solving a new cluster centroid;
step 2.3.5 is compared with K cluster centroids obtained by previous calculation, if the cluster centroids change, step 2.3.3 is switched, otherwise step 2.3.6 is switched;
step 2.3.6 stops and outputs the clustering result when the centroid does not change (when one centroid is found, the samples assigned to this centroid in each iteration are consistent, i.e., each time the newly generated cluster is consistent, all sample points are no longer shifted from cluster to cluster, and the centroid does not change). The calculation process of the K-Means algorithm is shown in FIG. 3:
step 2.4, acquiring a demand response day, wherein the demand response user is in n non-demand response time periodsLoad curve segment of (2) in>And (3) representing. Will->Non-demand response time periods respectively corresponding to K cluster load curves>Load curve segment->Mapping, i.e. in a certain non-demand response time segment +.>In, find the j-th load cluster curve meeting the minimum error between the two +.>Specifically as shown in formula (2):
at the same time, calculating load curve segments in n non-demand response periodsClustering curves with the corresponding j-th loadThe error between the two is shown in the following formula:
step 2.5 settingMapping the load curve segment in the ith non-demand response period to the jth load cluster curve, and obtaining the segmentation error alpha according to the step 2.4 i Clustering curves respectively mapped by load curve segments of demand response users in n non-demand response time periods in demand response days>Weighting treatment is carried out to obtain a user baseline load in a demand response day under a segmented comparison group method, and the user baseline load is obtained;
step 3: and in the non-demand response time period in the demand response day, calculating the errors of the average method and the segmentation comparison method in the step 1 and the step 2 respectively, and fitting to obtain the user baseline load of the demand response time period in the demand response day according to the errors of the non-demand response time period.
Step 3.1 calculating the user baseline load obtained according to the averaging method described in step 1 during the demand response dayError from real data over n non-demand response periods:
wherein:and->Representing the average estimated user baseline load and the user real load, respectively, in the ith non-demand response period +.>Errors in the same.
Step 3.2 calculating the user baseline load obtained by the segmentation comparison group method in step 2 within the demand response dayError from real data over n non-demand response periods:
wherein:and->Respectively representing the user baseline load and the user real load estimated by the segmentation comparison group method in the ith non-demand response period +.>Errors in the same.
Step 3.3 according to the steps of3.1 and the error obtained in the step 3.2, carrying out weighted combination prediction on the user baseline load to obtain the user baseline load P t The method is characterized by comprising the following steps:
the following examples are given:
the simulation data set used in the application comes from certain actual measurement data. According to the application, load data of 763 resident users in 2020 are selected for simulation analysis, and the data sampling resolution is 1 hour.
After DR execution, the true baseline load is no longer present. Thus, to evaluate the performance of the baseline load estimation method, it is often necessary to conduct tests on those "DR-like days" (i.e., days that have similar conditions to the actual demand response day but do not actually perform DR events). On the "DR-like day", since DR is not actually performed, the load value actually measured is the actual baseline load. The application adopts three evaluation indexes to evaluate the baseline load estimation method, which are accuracy, deviation and robustness respectively.
(1) Accuracy. Accuracy can be measured by the mean absolute error (MeanAbsolute Error, MAE) of the estimated and actual values as shown in the following equation.
In the method, in the process of the application,and->Respectively representing the estimated value and the true value of the load baseline of the nth DR user in the nth period of the nth DR day; n represents the number of DR users to be estimated; d represents the number of DR days to be estimated; delta represents DR duration (hours); clearly, the smaller the MAE, the more accurate the CBL estimate.
(2) Deviation.
The Bias (Bias) can be expressed as an algebraic difference between the load baseline estimate and the true value, as shown in the following equation.
Unlike MAE, bias is calculated using the algebraic difference between the true and estimated values instead of the absolute value, which means Bias has a positive and negative score. If Bias is positive, indicating that the load baseline estimate is greater than its true value, that is, the project provider needs to pay more economic compensation to the project participant; conversely, the project participants get less compensation than they would have. Bias is more relevant to the interests of DR project providers and participants than MAE. Clearly, the closer Bias is to 0, indicating that the smaller the deviation of the load baseline estimation, the better the load baseline estimation method.
(3) Robustness. Robustness refers to the adaptability of the CBL estimation method under different scenarios (including for different users, different DR days and different DR periods), which can be measured by the relative error ratio (Relative Error Ratio, RER), the RER value of the nth DR user can be calculated by the following formula.
Wherein std (·) represents the standard deviation; avg (. Cndot.) represents taking the average;and B n,d (δ)∈R |δ| The load baseline estimate and actual values at DR event window delta are shown, respectively.
And calculating RER of all users, and averaging to obtain a final RER value, wherein the smaller RER value indicates that the robustness of the load baseline estimation method is better.
Table 1 lists the comparison results (average performance) of several different baseline load estimation methods under different scenarios.
TABLE 1 comparison of different baseline load estimation method indicators under different scenarios
Specifically, among the above 5 CBL estimation methods, the method provided by the present application shows the best performance in terms of deviation and robustness, and the estimation result is higher in accuracy.
In yet another aspect, the application also discloses a computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the method as described above.
In yet another aspect, the application also discloses a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the method as above.
In yet another embodiment of the present application, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to perform the method of estimating a demand response baseline load of any of the above embodiments.
It may be understood that the system provided by the embodiment of the present application corresponds to the method provided by the embodiment of the present application, and explanation, examples and beneficial effects of the related content may refer to corresponding parts in the above method.
The embodiment of the application also provides an electronic device, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus,
a memory for storing a computer program;
and the processor is used for realizing the method for estimating the demand response baseline load when executing the program stored in the memory.
The communication bus mentioned by the above electronic device may be a peripheral component interconnect standard (english: peripheral Component Interconnect, abbreviated: PCI) bus or an extended industry standard architecture (english: extended Industry Standard Architecture, abbreviated: EISA) bus, or the like. The communication bus may be classified as an address bus, a data bus, a control bus, or the like.
The communication interface is used for communication between the electronic device and other devices.
The Memory may include random access Memory (Random Access Memory, abbreviated as RAM) or nonvolatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; it may also be a digital signal processor (English: digital Signal Processing; DSP; for short), an application specific integrated circuit (English: application Specific Integrated Circuit; ASIC; for short), a Field programmable gate array (English: field-Programmable Gate Array; FPGA; for short), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
It is noted that in the present application, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application 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 scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (7)
1. A method for estimating a demand response baseline load is characterized by comprising the following steps,
step 1: estimating the user baseline load in the demand response day by adopting an average method according to the electricity load data of the appointed days before the demand response day;
step 2: estimating the user baseline load in the demand response day by adopting a segmentation comparison group method according to the power load data of all users in the demand response day;
step 3: and in the non-demand response time period in the demand response day, calculating the errors of the average method and the segmentation comparison method in the step 1 and the step 2 respectively, and fitting to obtain the user baseline load of the demand response time period in the demand response day according to the errors of the non-demand response time period.
2. The method of estimating a demand response baseline load according to claim 1, wherein: the step 1 specifically comprises the steps of,
selecting user historical electricity load data of Y days before a demand response day to be estimated, and removing the non-representative days, namely the historical demand response day and holiday, until the Y days are complemented;
selecting X days with highest daily load level from the Y days, and calculating the load average value at each moment in the X days as a user base line load in a demand response day:
in the method, in the process of the application,indicating the user baseline load in the demand response day estimated according to the average method, high (X, Y) indicating the set of X days with highest load level among Y days satisfying the condition before the demand response day,/->Load values of the t-th period on the d-th day in the High (X, Y) set are shown.
3. The method of estimating a demand response baseline load according to claim 2, wherein: the step 2 specifically comprises the steps of,
step 2.1, dividing users into demand response users and non-demand response users according to whether to participate in demand response in a demand response day, and taking a set of the non-demand response users as a comparison group;
step 2.2, setting that multiple demand responses occur in the demand response day, wherein n non-demand response time periods exist in the demand response dayAnd have->Wherein: />And->Respectively the ith non-demand response periodIs a start-stop time of (a);
step 2.3 Using the K-Means algorithm of FIG. 3 to make all non-demand response users in the control group respond to the demandClustering in the day to form K load clustering curves
Step 2.4, acquiring a demand response day, wherein the demand response user is in n non-demand response time periodsTo the load curve segment of (1)A representation; will->Non-demand response time periods respectively corresponding to K cluster load curves>Load curve segment of (2)Mapping, i.e. in a certain non-demand response time segment +.>In, find the j-th load cluster curve meeting the minimum error between the two +.>Specifically as shown in formula (2):
at the same time, calculating load curve segments in n non-demand response periodsClustering curve +.>The error between the two is shown in the following formula:
step 2.5 settingMapping the load curve segment in the ith non-demand response period to the jth load cluster curve, and obtaining the segmentation error alpha according to the step 2.4 i Clustering curves respectively mapped by load curve segments of demand response users in n non-demand response time periods in demand response days>Weighting treatment is carried out to obtain a user baseline load in a demand response day under a segmented comparison group method:
4. a method of estimating a demand response baseline load according to claim 3, wherein:
the step 2.3 specifically comprises the steps of,
step 2.3.1, load curves of k users not participating in demand responsePerforming per unit treatment, i.e. +.>
Step 2.3.2 willAs a sample data set, randomly selecting K samples as clustering centers, wherein K is far smaller than K;
step 2.3.3, respectively calculating the distances between other samples in the samples and the K clustering centers, and respectively taking the samples as the categories of the nearest clustering center;
step 2.3.4, averaging each class of the classified samples, and solving a new cluster centroid;
step 2.3.5 is compared with K cluster centroids obtained by previous calculation, if the cluster centroids change, step 2.3.3 is switched, otherwise step 2.3.6 is switched;
step 2.3.6 stops and outputs the clustering result when the centroid does not change.
5. The method of estimating a demand response baseline load according to claim 4, wherein:
the specific steps of the step 3 are as follows,
step 3.1 calculating the user baseline load obtained according to the averaging method described in step 1 during the demand response dayError from real data over n non-demand response periods:
wherein:and->User base representing average estimates, respectivelyLine load and user real load are +.>Errors in;
step 3.2 calculating the user baseline load obtained by the segmentation comparison group method in step 2 within the demand response dayError from real data over n non-demand response periods:
wherein:and->Respectively representing the user baseline load and the user real load estimated by the segmentation comparison group method in the ith non-demand response period +.>Errors in;
step 3.3, carrying out weighted combination prediction on the user baseline load according to the error magnitude obtained in the steps 3.1 and 3.2 to obtain the user baseline load P t The method is characterized by comprising the following steps:
6. a computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the method of any one of claims 1 to 5.
7. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method of any of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310684961.8A CN116885696A (en) | 2023-06-08 | 2023-06-08 | Method, device and storage medium for estimating demand response baseline load |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310684961.8A CN116885696A (en) | 2023-06-08 | 2023-06-08 | Method, device and storage medium for estimating demand response baseline load |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116885696A true CN116885696A (en) | 2023-10-13 |
Family
ID=88259390
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310684961.8A Pending CN116885696A (en) | 2023-06-08 | 2023-06-08 | Method, device and storage medium for estimating demand response baseline load |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116885696A (en) |
-
2023
- 2023-06-08 CN CN202310684961.8A patent/CN116885696A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021208079A1 (en) | Method and apparatus for obtaining power battery life data, computer device, and medium | |
West et al. | Model fit and model selection in structural equation modeling | |
CN111693931A (en) | Intelligent electric energy meter error remote calculation method and device and computer equipment | |
JP2013255390A (en) | Power demand forecasting device and power demand forecasting method | |
CN112183869A (en) | Building energy consumption prediction method and system based on big data | |
WO2020220437A1 (en) | Method for virtual machine software aging prediction based on adaboost-elman | |
CN112132485A (en) | Index data processing method and device, electronic equipment and storage medium | |
CN113484813B (en) | Intelligent ammeter fault rate prediction method and system under multi-environment stress | |
CN112101765A (en) | Abnormal data processing method and system for operation index data of power distribution network | |
Bin Othman et al. | Determination of transmission reliability margin using parametric bootstrap technique | |
CN115759393A (en) | Cumulative load baseline prediction method based on ensemble learning | |
CN108694472B (en) | Prediction error extreme value analysis method, device, computer equipment and storage medium | |
CN115018119A (en) | Power load prediction method and system | |
CN109684546A (en) | Recommended method, device, storage medium and terminal | |
CN113886454A (en) | Cloud resource prediction method based on LSTM-RBF | |
CN111414528B (en) | Method and device for determining equipment identification, storage medium and electronic equipment | |
CN112257958A (en) | Power saturation load prediction method and device | |
CN116885696A (en) | Method, device and storage medium for estimating demand response baseline load | |
CN111783883A (en) | Abnormal data detection method and device | |
CN113919610A (en) | ARIMA model construction method and evaluation method for low-voltage transformer area line loss prediction | |
CN106934009A (en) | One kind application arrangement method, device and computing device | |
CN116051185A (en) | Advertisement position data abnormality detection and screening method | |
CN108629506A (en) | Modeling method, device, computer equipment and the storage medium of air control model | |
Gao et al. | Ensuring high-quality data collection for mobile crowd sensing | |
CN114511409A (en) | User sample processing method and device and electronic 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 |