CN109636087B - Dynamic clustering method and system for demand response resources - Google Patents
Dynamic clustering method and system for demand response resources Download PDFInfo
- Publication number
- CN109636087B CN109636087B CN201811245518.6A CN201811245518A CN109636087B CN 109636087 B CN109636087 B CN 109636087B CN 201811245518 A CN201811245518 A CN 201811245518A CN 109636087 B CN109636087 B CN 109636087B
- Authority
- CN
- China
- Prior art keywords
- demand response
- response resource
- clustering
- resource
- resources
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000004044 response Effects 0.000 title claims abstract description 352
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000000926 separation method Methods 0.000 claims description 19
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000010248 power generation Methods 0.000 abstract description 7
- 238000011161 development Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 abstract description 2
- 239000011159 matrix material Substances 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000003912 environmental pollution Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 239000003570 air Substances 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
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
- G06Q10/0631—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
- 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
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a demand response resource dynamic clustering method and a demand response resource dynamic clustering system, wherein the method comprises the steps of obtaining an initial clustering center of demand response resources according to Euclidean distances among corresponding characteristics of the demand response resources, and further clustering the demand response resources by using the initial clustering center of the demand response resources, so that the defect that the clustering result of the existing demand response resource dynamic clustering technology is not accurate is overcome, the accurate and reasonable demand response resource clustering result is obtained, the calculation reliability of the power generation reserve capacity is improved, and the ordered development of a power grid is promoted.
Description
Technical Field
The invention relates to the field of power grid system resource classification, in particular to a demand response resource dynamic grouping method and system.
Background
Social development is closely related to development of scientific technology and effective utilization of resources, wherein demand response resources have the characteristic of vividness, and are used as consumers of electric power energy, not only are the demand response resources dispersed unevenly and are large in quantity, so that the demand response resources need to be classified strictly and in detail in practical application, and only the demand response resources are reasonably classified, sufficient power generation reserve capacity can be calculated to meet peak load requirements;
at present, the classification of demand response resources is mainly to divide the demand response resources into residential user resources, commercial user resources and industrial user resources according to the types of response objects, the classification result is not detailed, the characteristics of single resources in the same type of resources may be greatly different, the single resources cannot be considered simultaneously when the demand response analysis is carried out, and sufficient power generation reserve capacity cannot be calculated accurately to meet peak load requirements, so that the problems of high power generation cost, large market price fluctuation, low system safety and reliability, environmental pollution and the like are caused.
Disclosure of Invention
The invention provides a method and a system for dynamically clustering demand response resources, which aims to obtain an initial clustering center of the demand response resources according to Euclidean distances among corresponding characteristics of the demand response resources, further accurately cluster the demand response resources by using the initial clustering center of the demand response resources, reasonably classify the demand response resources so as to calculate enough power generation reserve capacity, meet peak load requirements, overcome the problems that the classification result in the classification method in the prior art has large difference of resource objects in the same category and is not beneficial to corresponding analysis of resources, and save the operation cost of a power grid system.
The purpose of the invention is realized by adopting the following technical scheme:
in a method of dynamically clustering demand response resources, the improvement comprising:
acquiring an initial clustering center of the demand response resources according to Euclidean distances among the corresponding features of the demand response resources;
and clustering the demand response resources by using the demand response resource initial clustering center.
Preferably, the demand response resource corresponding feature includes: the type of the demand response resource, the response speed of the demand response resource, the response capacity of the demand response resource, the response duration of the demand response resource and the adjustable capacity conversion rate of the demand response resource.
Preferably, the obtaining an initial clustering center of the demand response resource according to the euclidean distance between the corresponding features of each demand response resource includes:
step a, if the Euclidean distance between the corresponding features of two demand response resources is the minimum in the Euclidean distance between the corresponding features of each demand response resource, the average feature of the corresponding features of the two demand response resources is an initial clustering center;
and b, removing the corresponding characteristic of the demand response resource, of which the Euclidean distance between the corresponding characteristic of any demand response resource in the corresponding characteristics of the two demand response resources is smaller than a threshold value alpha, returning to the step a until all the corresponding characteristics of the demand response resource are removed, and outputting all the initial clustering centers.
Further, the corresponding characteristic of the demand response resource i is determined according to the following formulaEuclidean distance d between corresponding features of demand response resource j ij ：
In the formula i r Is the r-th feature, j, of the demand response resource i r For the r-th feature of the demand response resource j, r ∈ [1, n ]]And n is the number of corresponding characteristics of the demand response resource.
Preferably, the clustering demand response resources by using the demand response resource initial clustering center includes:
and taking the initial clustering center of the demand response resource as an initial clustering center of an FCM clustering algorithm, clustering the corresponding characteristics of the demand response resource, and acquiring the clustering result of the demand response resource.
Preferably, after the demand response resource is clustered by using the demand response resource initial clustering center, the method includes:
evaluating the clustering result of the demand response resource according to the separation degree and the fuzzy degree of the clustering result of the demand response resource;
the separation degree of the clustering result of the demand response resource is in direct proportion to the clustering result of the demand response resource, and the fuzzy degree of the clustering result of the demand response resource is in inverse proportion to the clustering result of the demand response resource.
Further, the separation degree K of the clustering results of the demand response resources is determined according to the following formula PC ：
Determining the fuzzy degree K of the clustering result of the demand response resource according to the following formula CE ：
Where n is the number of demand response resources, c is the number of demand response resource clusters, μ ij Membership value for the jth demand response resource belonging to the ith group.
In a system for dynamic clustering of demand response resources, the improvement comprising:
the acquisition module is used for acquiring an initial clustering center of the demand response resources according to the Euclidean distance between the corresponding characteristics of each demand response resource;
and the clustering module is used for clustering the demand response resources by using the demand response resource initial clustering center.
Preferably, the demand response resource corresponding feature includes: the type of the demand response resource, the response speed of the demand response resource, the response capacity of the demand response resource, the response duration of the demand response resource and the adjustable capacity conversion rate of the demand response resource.
Preferably, the obtaining module is configured to:
step a, if the Euclidean distance between the corresponding features of two demand response resources is the minimum in the Euclidean distance between the corresponding features of each demand response resource, the average feature of the corresponding features of the two demand response resources is an initial clustering center;
and b, removing the corresponding characteristic of the demand response resource, of which the Euclidean distance between the corresponding characteristic of any demand response resource in the corresponding characteristics of the two demand response resources is smaller than a threshold value alpha, returning to the step a until all the corresponding characteristics of the demand response resource are removed, and outputting all the initial clustering centers.
Further, the Euclidean distance d between the corresponding feature of the demand response resource i and the corresponding feature of the demand response resource j is determined according to the following formula ij ：
In the formula i r Is the r-th feature, j, of the demand response resource i r Is the r-th characteristic of the demand response resource j，r∈[1,n]And n is the number of the corresponding characteristics of the demand response resource.
Preferably, the grouping module is configured to:
and taking the initial clustering center of the demand response resource as an initial clustering center of an FCM clustering algorithm, clustering the corresponding characteristics of the demand response resource, and acquiring the clustering result of the demand response resource.
Preferably, the system further comprises:
the evaluation module is used for evaluating the clustering result of the demand response resource according to the separation degree and the fuzzy degree of the clustering result of the demand response resource;
the separation degree of the clustering result of the demand response resource is in direct proportion to the clustering result of the demand response resource, and the fuzzy degree of the clustering result of the demand response resource is in inverse proportion to the clustering result of the demand response resource.
Further, the separation degree K of the clustering results of the demand response resources is determined according to the following formula PC ：
Determining the fuzzy degree K of the clustering result of the demand response resource according to the following formula CE ：
Where n is the number of demand response resources, c is the number of demand response resource clusters, μ ij Membership value for the jth demand response resource belonging to the ith group.
Compared with the closest prior art, the invention also has the following beneficial effects:
by adopting the technical scheme of the invention, the initial clustering center of the demand response resource is obtained according to the Euclidean distance between the corresponding features of each demand response resource, the demand response resource is classified based on the corresponding features of the demand response resource, the classification basis is reliable, and the accuracy of the classification result is ensured; the demand response resource initial clustering center is further utilized to cluster demand response resources, the demand response resource initial clustering center is selected, a clustering algorithm is carried out based on the set initial clustering center to realize dynamic clustering of the demand response resources, the step of initializing a membership matrix is avoided, the problem that the clustering algorithm is easy to fall into local convergence is solved, and the problems of large market price fluctuation, low system safety and reliability, environmental pollution and the like caused by the existing classification technology are solved.
Drawings
FIG. 1 is a flow chart of a method for dynamic clustering of demand response resources in accordance with an embodiment of the present invention;
FIG. 2 is a flowchart of a method for dynamic clustering of demand response resources according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for dynamically clustering demand response resources according to an embodiment of the present invention.
Detailed Description
The following detailed description of the embodiments of the invention refers to the accompanying drawings.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a method and a system for dynamically clustering demand response resources, which are explained below.
The demand response resources are classified based on an improved fuzzy C-means clustering algorithm, so that the demand response resources with similar characteristics are classified into the same category, and a foundation is laid for solving the problems of high power generation cost, large market price fluctuation, low system safety and reliability and environmental pollution such as air, water, soil and the like caused by unreasonable classification of the demand response resources.
Among a plurality of fuzzy clustering algorithms, the fuzzy C-mean fuzzy C-means algorithm (FCM) is most widely and successfully applied, and the membership degree of each sample point to all class centers is obtained by optimizing a target function, so that the class of the sample points is determined to achieve the purpose of automatically classifying sample data. Fuzzy clustering analysis is one of the main technologies of unsupervised machine learning, is a method for analyzing and modeling important data by using a fuzzy theory, establishes uncertainty description of sample categories, can objectively reflect the real world, is effectively applied to the fields of large-scale data analysis, data mining, vector quantization, image segmentation, pattern recognition and the like, has important theoretical and practical application values, and is continuously and abundantly researched along with the deep development of application.
Fig. 1 shows a flowchart of a method for dynamically clustering demand response resources in an embodiment of the present invention, and as shown in fig. 1, the method may include:
101. acquiring an initial clustering center of the demand response resource according to Euclidean distances among corresponding characteristics of the demand response resources;
102. and clustering the demand response resources by using the demand response resource initial clustering center.
Fig. 2 shows a detailed flowchart of the dynamic clustering method for demand response resources according to the embodiment of the present invention, and as shown in fig. 2, the clustering index of the demand response resources, that is, the influence factors of the demand response resource classification, needs to be found first, and these influence factor data are input, where the corresponding characteristics of the demand response resources may include: the type of the demand response resource, the response speed of the demand response resource, the response capacity of the demand response resource, the response duration of the demand response resource and the adjustable capacity conversion rate of the demand response resource; then, carrying out cluster evaluation on the demand response resources by using an improved FCM algorithm, and finally determining a dynamic clustering result of the demand response resources according to a membership matrix under the optimal clustering number;
the clustering index of the demand response resource is determined by the response characteristic of the demand response resource, and is divided into three grades of high, medium and low according to 4 aspects of response speed, response capacity, response duration and adjustable capacity conversion rate;
1) In the aspect of response speed, considering that the regulation and control speed of the power generation side is generally in the min level, the response speed of high-level demand response resources is specified to be within 5 min; the medium resource response speed is 5min-30min; the response speed of the low-level resources is more than 30min.
2) In terms of response capacity, users with large individual response capacity are high. The response capacity of the high-grade resources is more than 3000kW, the response capacity of the medium-grade resources is between 1000 and 3000kW, and the response capacity of the low-grade resources is less than 1000kW.
3) In the aspect of response time, the response time can last for more than 3 hours, and the response time is less than 0.5 hour, so that the normal type is adopted.
4) The adjustable capacity conversion rate reflects the difficulty of regulating and controlling demand response resources and the possibility of converting potential resources into adjustable resources by a user, and is determined by the common determination of whether resource distribution is concentrated, whether resources can be directly regulated and controlled, the willingness of the user to which the resources belong to participate in demand response and the like.
Considering that the FCM algorithm is sensitive to the clustering center, if the membership matrix is initialized unreasonably, the algorithm is easy to fall into a local optimal solution. The clustering of the demand response resources is divided into 2 stages for execution, the 1 st stage is used for selecting the clustering center according to the following steps, and the 2 nd stage is used for executing the FCM clustering algorithm according to the initial clustering center selected in the first stage, so that the step of initializing the membership matrix is avoided.
The Euclidean distance between any 2 demand response resource clustering indexes can be respectively calculated to generate a distance matrix D:
where M represents the number of demand response resource clustering indicators, d rs Representing the clustering index between the r-th resource and the s-th resourceThe Euclidean distance;
and (3) classifying the demand response resources corresponding to the 2 closest clustering indexes into a group, and taking the midpoint of the two demand response resources as a first initial clustering center.
And setting a minimum distance threshold value alpha between the clusters, finding out the clustering indexes of which the distances from the 2 clustering indexes in the first cluster are larger than alpha through a distance matrix D, classifying the demand response resources corresponding to the 2 clustering indexes with the minimum D value into an x cluster each time, and taking the midpoint of the x cluster as a 2 nd clustering center.
Specifically, the obtaining an initial clustering center of the demand response resource according to the euclidean distance between the corresponding features of each demand response resource may include:
step a, if the Euclidean distance between the corresponding features of two demand response resources is the minimum in the Euclidean distance between the corresponding features of each demand response resource, the average feature of the corresponding features of the two demand response resources is an initial clustering center;
removing the corresponding characteristic of the demand response resource, of which the Euclidean distance between the corresponding characteristic of any demand response resource in the corresponding characteristics of the two demand response resources is smaller than a threshold value alpha, returning to the step a until all the corresponding characteristics of the demand response resource are removed, and outputting all the initial clustering centers;
the principle of selecting the initial clustering centers is that the distance between each initial clustering center is larger than a distance threshold value alpha, so that the initial clustering centers are selected in a plurality of feasible intervals, and the defect that the algorithm is trapped in local convergence due to too close distance of the initial clustering centers is avoided, so that the distance threshold value alpha is as large as possible, but c initial clustering centers meeting the conditions cannot be selected due to too large distance threshold value alpha, and the value of alpha needs to be reduced at the moment.
Determining Euclidean distance d between corresponding characteristics of demand response resource i and corresponding characteristics of demand response resource j according to the following formula ij ：
In the formula i r Is the r-th feature, j, of the demand response resource i r For the r-th feature of the demand response resource j, r ∈ [1, n ]]And n is the number of corresponding characteristics of the demand response resource.
The clustering demand response resources by using the demand response resource initial clustering center may include:
taking the initial clustering center of the demand response resource as an initial clustering center of an FCM clustering algorithm, clustering the corresponding characteristics of the demand response resource, and acquiring the clustering result of the demand response resource;
when the FCM algorithm carries out cluster evaluation on demand response resources, the specific process is as follows:
the clustering algorithm is an iterative optimization process, and the idea is to make the similarity between vectors clustered to the same group larger and the similarity between vectors clustered to different groups smaller. In the process of clustering the demand response resources, defining the use value interval of the demand response resources as [0,1], wherein FCM ensures the degree of the use value of each demand response resource belonging to each cluster to be determined by the membership degree of the use value of each demand response resource in the interval, and the membership degree matrix corresponding to the clustering result is a fuzzy clustering matrix.
FCM clustering is used for clustering index x corresponding to n demand response resources j (j =1,2, \ 8230;, n) is divided into c subgroups,
and finding the center point v of the clustering index in each group i (i＝1,2,…,n)，
So that the value of the objective function is minimized, the objective function J m (c) The following were used:
in the formula: | v | (V) i -x j || 2 The Euclidean distance between the ith clustering center point and the jth demand response resource clustering index is obtained; m belongs to [1, ∞) as a fuzzy coefficient, and is generally 2; u. of ij Indicates the j-th demand response resource genusAnd the membership value of the group corresponding to the ith clustering central point meets the normalization regulation:
to find the necessary condition for minimizing the equation (2), the following intermediate function is constructed
In the formula: lambda [ alpha ] j Is a lagrange multiplier of the 3 constraints in equation (3). The necessary conditions for all the input parameters to be derived to minimize equation (2) are:
in the formula: k =1,2, \ 8230;, c;
it can be seen that the output of the FCM algorithm comprises 2 parts: the part 1 is c clustering central points, and each clustering central point represents the average characteristic of the demand response resource clustering index in the corresponding cluster; the 2 nd part is a c multiplied by n fuzzy partition matrix which represents the membership degree of each demand response resource belonging to each group, and the group to which each demand response resource belongs is usually determined according to the maximum membership principle of a fuzzy set;
when the clustering index value changes, the demand response resources need to be clustered again, and the membership value of the j-th demand response resource belonging to the group corresponding to the i-th clustering center point is obtained by the formula (3), so that the time required by clustering the demand response resources can be reduced, and the real-time requirement of dynamic clustering can be met.
Determining a dynamic clustering result of the demand response resources according to the membership matrix under the optimal clustering number, and therefore, after clustering the demand response resources by using the initial clustering center of the demand response resources, the method may include:
evaluating the clustering result of the demand response resource according to the separation degree and the fuzzy degree of the clustering result of the demand response resource;
the separation degree of the clustering result of the demand response resource is in direct proportion to the clustering result of the demand response resource, and the fuzzy degree of the clustering result of the demand response resource is in inverse proportion to the clustering result of the demand response resource.
Specifically, the degree of separation K of the clustering results of the demand response resources is determined as follows PC ：
Determining the fuzzy degree K of the clustering result of the demand response resource according to the following formula CE ：
Where n is the number of demand response resources, c is the number of demand response resource clusters, μ ij Membership values for the jth demand response resource belonging to the ith group; the KPC is used for evaluating the separation degree among different demand response resource clustering groups, and the larger the value is, the better the value is; the KCE is used for evaluating the fuzzy degree among different demand response resource clustering groups, and the smaller the value is, the better the value is.
The result of determining the dynamic clustering of the demand response resources according to the membership matrix under the optimal clustering number is shown in table 1, and specifically includes:
TABLE 1 dynamic clustering results
In the table, a 1 ,…a t+1 ；b 1 ,…b t+1 ；e 1 ,…e t+1 ；f 1 ,…f t+1 Respectively representing division points in numerical value intervals of response speed, response capacity, response duration and adjustable capacity conversion rate; t represents the number of classes of all demand response resources.
Fig. 3 is a schematic structural diagram of a demand response resource dynamic clustering system according to an embodiment of the present invention, and as shown in fig. 3, the system may include:
the acquisition module is used for acquiring an initial clustering center of the demand response resources according to the Euclidean distance between the corresponding characteristics of each demand response resource;
and the clustering module is used for clustering the demand response resources by utilizing the initial clustering center of the demand response resources.
The demand response resource corresponding feature may include: the type of the demand response resource, the response speed of the demand response resource, the response capacity of the demand response resource, the response duration of the demand response resource and the adjustable capacity conversion rate of the demand response resource.
Specifically, the obtaining module is configured to:
step a, if the Euclidean distance between the corresponding features of two demand response resources is the minimum in the Euclidean distance between the corresponding features of each demand response resource, the average feature of the corresponding features of the two demand response resources is an initial clustering center;
and b, removing the corresponding characteristic of the demand response resource, of which the Euclidean distance between the corresponding characteristic of any demand response resource in the corresponding characteristics of the two demand response resources is smaller than a threshold value alpha, returning to the step a until all the corresponding characteristics of the demand response resource are removed, and outputting all the initial clustering centers.
Determining Euclidean distance d between corresponding characteristics of demand response resource i and corresponding characteristics of demand response resource j according to the following formula ij ：
In the formula i r Is the r-th feature, j, of the demand response resource i r For the r-th feature of the demand response resource j, r ∈ [1, n ]]And n is the number of corresponding characteristics of the demand response resource.
Specifically, the grouping module is configured to: and taking the initial clustering center of the demand response resource as an initial clustering center of an FCM clustering algorithm, clustering the corresponding characteristics of the demand response resource, and acquiring the clustering result of the demand response resource.
The system may further include:
the evaluation module is used for evaluating the clustering result of the demand response resource according to the separation degree and the fuzzy degree of the clustering result of the demand response resource;
the separation degree of the clustering result of the demand response resource is in direct proportion to the clustering result of the demand response resource, and the fuzzy degree of the clustering result of the demand response resource is in inverse proportion to the clustering result of the demand response resource.
Specifically, the degree of separation K of the clustering results of the demand response resources is determined as follows PC ：
Determining the fuzzy degree K of the clustering result of the demand response resource according to the formula CE ：
Where n is the number of demand response resources, c is the number of demand response resource clusters, μ ij Membership values for the jth demand response resource belonging to the ith group.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (2)
1. A method for dynamic clustering of demand response resources, the method comprising:
acquiring an initial clustering center of the demand response resources according to Euclidean distances among the corresponding features of the demand response resources;
clustering demand response resources by using the demand response resource initial clustering center;
the demand response resource corresponding characteristics comprise: the type of the demand response resource, the response speed of the demand response resource, the response capacity of the demand response resource, the response duration of the demand response resource and the adjustable capacity conversion rate of the demand response resource;
the method for acquiring the initial clustering center of the demand response resource according to the Euclidean distance between the corresponding characteristics of each demand response resource comprises the following steps:
step a, if the Euclidean distance between the corresponding features of two demand response resources is the minimum in the Euclidean distance between the corresponding features of each demand response resource, the average feature of the corresponding features of the two demand response resources is an initial clustering center;
removing the corresponding characteristic of the demand response resource, of which the Euclidean distance between the corresponding characteristic of any demand response resource and the corresponding characteristic of the two demand response resources is smaller than a threshold value alpha, returning to the step a until all the corresponding characteristics of the demand response resource are removed, and outputting all the initial clustering centers;
determining Euclidean distance d between corresponding characteristics of demand response resource i and corresponding characteristics of demand response resource j according to the following formula ij ：
In the formula, j r1 Is the r1 th feature, j, of the demand response resource, j r2 For the r2 th feature of the demand response resource j, r ∈ [1, n ]]N is the number of the corresponding characteristics of the demand response resources;
the clustering of the demand response resources by using the demand response resource initial clustering center comprises:
taking the initial clustering center of the demand response resource as an initial clustering center of an FCM clustering algorithm, clustering the corresponding characteristics of the demand response resource, and acquiring the clustering result of the demand response resource;
after the demand response resource is clustered by using the demand response resource initial clustering center, the method includes:
evaluating the clustering result of the demand response resource according to the separation degree and the fuzzy degree of the clustering result of the demand response resource;
the separation degree of the clustering result of the demand response resource is in direct proportion to the clustering result of the demand response resource, and the fuzzy degree of the clustering result of the demand response resource is in inverse proportion to the clustering result of the demand response resource;
determining a degree of separation K of the clustering results of the demand response resources according to the following formula PC ：
Determining the fuzzy degree K of the clustering result of the demand response resource according to the formula CE ：
Where m is the number of demand response resources, c is the number of demand response resource clusters, μ ij Membership value for the jth demand response resource belonging to the ith group.
2. A demand response resource dynamic clustering system, the system comprising:
the acquisition module is used for acquiring an initial clustering center of the demand response resources according to the Euclidean distance between the corresponding characteristics of each demand response resource;
the clustering module is used for clustering the demand response resources by utilizing the demand response resource initial clustering center;
the demand response resource corresponding characteristics include: the type of the demand response resource, the response speed of the demand response resource, the response capacity of the demand response resource, the response duration of the demand response resource and the adjustable capacity conversion rate of the demand response resource;
the obtaining module is configured to:
the submodule a is used for determining that the Euclidean distance between the corresponding characteristics of the two demand response resources is the minimum in the Euclidean distance between the corresponding characteristics of the demand response resources, and then the average characteristic of the corresponding characteristics of the two demand response resources is an initial clustering center;
a submodule b for removing the corresponding characteristic of the demand response resource, of which the Euclidean distance between the corresponding characteristic of any demand response resource and the corresponding characteristic of the two demand response resources is smaller than a threshold value alpha, returning to the step a until all the corresponding characteristics of the demand response resource are removed, and outputting all the initial clustering centers;
determining Euclidean distance d between corresponding characteristics of demand response resource i and corresponding characteristics of demand response resource j according to the following formula ij ：
In the formula, j r1 Is the r1 th feature, j, of the demand response resource, j r2 For the r2 th feature of the demand response resource j, r ∈ [1, n ]]N is the number of the corresponding characteristics of the demand response resources;
the grouping module is configured to:
taking the initial clustering center of the demand response resource as an initial clustering center of an FCM clustering algorithm, clustering the corresponding characteristics of the demand response resource, and acquiring the clustering result of the demand response resource;
the system further comprises:
the evaluation module is used for evaluating the clustering result of the demand response resource according to the separation degree and the fuzzy degree of the clustering result of the demand response resource;
the separation degree of the clustering result of the demand response resource is in direct proportion to the clustering result of the demand response resource, and the fuzzy degree of the clustering result of the demand response resource is in inverse proportion to the clustering result of the demand response resource;
determining a degree of separation K of the clustering results of the demand response resources according to the following formula PC ：
Determining the fuzzy degree K of the clustering result of the demand response resource according to the following formula CE ：
Where m is the number of demand response resources, c is the number of demand response resource clusters, μ ij Membership values for the jth demand response resource belonging to the ith group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811245518.6A CN109636087B (en) | 2018-10-24 | 2018-10-24 | Dynamic clustering method and system for demand response resources |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811245518.6A CN109636087B (en) | 2018-10-24 | 2018-10-24 | Dynamic clustering method and system for demand response resources |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109636087A CN109636087A (en) | 2019-04-16 |
| CN109636087B true CN109636087B (en) | 2023-01-24 |
Family
ID=66066642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811245518.6A Active CN109636087B (en) | 2018-10-24 | 2018-10-24 | Dynamic clustering method and system for demand response resources |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109636087B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8195734B1 (en) * | 2006-11-27 | 2012-06-05 | The Research Foundation Of State University Of New York | Combining multiple clusterings by soft correspondence |
| CN105184683A (en) * | 2015-10-10 | 2015-12-23 | 华北电力科学研究院有限责任公司 | Probability clustering method based on wind electric field operation data |
| CN107656898A (en) * | 2017-10-16 | 2018-02-02 | 国电南瑞科技股份有限公司 | A kind of demand response resource cluster method |
-
2018
- 2018-10-24 CN CN201811245518.6A patent/CN109636087B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8195734B1 (en) * | 2006-11-27 | 2012-06-05 | The Research Foundation Of State University Of New York | Combining multiple clusterings by soft correspondence |
| CN105184683A (en) * | 2015-10-10 | 2015-12-23 | 华北电力科学研究院有限责任公司 | Probability clustering method based on wind electric field operation data |
| CN107656898A (en) * | 2017-10-16 | 2018-02-02 | 国电南瑞科技股份有限公司 | A kind of demand response resource cluster method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109636087A (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111008504B (en) | Wind power prediction error modeling method based on meteorological pattern recognition | |
| CN111028100A (en) | Refined short-term load prediction method, device and medium considering meteorological factors | |
| CN108805213B (en) | Power load curve double-layer spectral clustering method considering wavelet entropy dimensionality reduction | |
| CN108960586B (en) | Non-invasive load identification method adaptive to scene change | |
| CN112990558B (en) | Meteorological temperature and illumination prediction method based on deep migration learning | |
| CN113177366B (en) | Comprehensive energy system planning method and device and terminal equipment | |
| CN112186761B (en) | Wind power scene generation method and system based on probability distribution | |
| CN116109458A (en) | Reservoir flood discharge gate scheduling method, system, storage medium and computing equipment | |
| CN108399553A (en) | It is a kind of to consider geographical and circuit subordinate relation user characteristics label setting method | |
| CN113032367A (en) | Dynamic load scene-oriented cross-layer configuration parameter collaborative tuning method and system for big data system | |
| CN114240687A (en) | Energy hosting efficiency analysis method suitable for comprehensive energy system | |
| CN109146553A (en) | Spot Price forecasting system and its method based on multi-density cluster and multicore SVM | |
| CN110570091A (en) | Load identification method based on improved F-score feature selection and particle swarm BP neural network | |
| CN116526496B (en) | Novel auxiliary decision-making method for power system load control | |
| CN109636087B (en) | Dynamic clustering method and system for demand response resources | |
| CN117172486A (en) | Reinforced learning-based virtual power plant optical storage resource aggregation regulation and control method | |
| CN109784748A (en) | User power utilization behavior discrimination method and device under a kind of market and competitive mechanisms | |
| CN115149528A (en) | Intelligent electric energy meter distributed prediction method based on big data non-intrusive technology | |
| CN109149644B (en) | Light-storage integrated online strategy matching and collaborative optimization method based on big data analysis | |
| Bi et al. | Adaptive prediction of resources and workloads for cloud computing systems with attention-based and hybrid LSTM | |
| Chunni | SVM visual classification based on weighted feature of genetic algorithm | |
| CN111160475B (en) | Flexible load clustering method and device based on grid repartition wavelet clustering | |
| Zekić-Sušac | Machine learning in energy consumption management | |
| Huang et al. | A Hadoop configuration optimization method based on middle platform business operation requirements | |
| CN118070134B (en) | Method and system for predicting electricity consumption of users in park |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |