CN110111003A - A kind of new energy typical scene construction method based on improvement FCM clustering algorithm - Google Patents

A kind of new energy typical scene construction method based on improvement FCM clustering algorithm Download PDF

Info

Publication number
CN110111003A
CN110111003A CN201910382189.8A CN201910382189A CN110111003A CN 110111003 A CN110111003 A CN 110111003A CN 201910382189 A CN201910382189 A CN 201910382189A CN 110111003 A CN110111003 A CN 110111003A
Authority
CN
China
Prior art keywords
new energy
output
clustering
clustering algorithm
historical
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910382189.8A
Other languages
Chinese (zh)
Inventor
高丙团
凌静
陈晨
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southeast University
Liyang Research Institute of Southeast University
Original Assignee
Southeast University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Southeast University filed Critical Southeast University
Priority to CN201910382189.8A priority Critical patent/CN110111003A/en
Publication of CN110111003A publication Critical patent/CN110111003A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Artificial Intelligence (AREA)
  • Water Supply & Treatment (AREA)
  • Game Theory and Decision Science (AREA)
  • Primary Health Care (AREA)
  • Quality & Reliability (AREA)
  • Probability & Statistics with Applications (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Public Health (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Wind Motors (AREA)

Abstract

The invention discloses a kind of based on the new energy typical scene construction method for improving FCM clustering algorithm, includes the following steps S1: improving FCM clustering algorithm by establishing Cluster Validity Index function；S2: clustering is carried out to new energy power output historical data using FCM clustering algorithm is improved；S3: the new energy power output typical scene after clustering in each classification is chosen.The present invention is using the new energy power producing characteristics in the plentiful region of new energy as research object, go out force data using history timing of the improved FCM algorithm to its new energy and carries out clustering, representative several new energy power output scene set is obtained after original large scale scene reduction is merged, and there is certain practical application value.

Description

New energy typical scene construction method based on improved FCM clustering algorithm
The technical field is as follows:
the invention relates to a construction method of a new energy typical output scene, in particular to a construction method of a new energy typical scene based on an improved FCM clustering algorithm.
Background
With the large-scale development and utilization of new energy in China, the power generation of the new energy is continuously and rapidly developed, and the increase scale of installed capacity is continuously enlarged. With the continuous increase of the installed capacity of new energy, the proportion of the new energy in the power supply of the power grid is continuously improved, and the consumption demand of the new energy puts higher requirements on the economic operation of the power system, the consumption capacity evaluation of the new energy of the power grid, the formulation of a power grid dispatching plan and the like. Therefore, considering the seasonality and periodicity of new energy output such as wind power, photoelectricity and the like, representative typical output scenes are extracted from historical output data, the typical output scenes are used for reflecting the new energy output characteristics in medium and long periods, and the method has important significance for power supply planning of a power system containing high-proportion new energy.
In recent years, researchers at home and abroad research and study the construction of a new energy typical output scene. At present, the selection methods of medium-and-long-term new energy output scenes or load characteristics which are widely applied generally include three types: a typical daily method, a time sequence simulation method and a clustering algorithm. The typical daily method generally refers to taking the output characteristic of the day closest to the average value in a certain period as a typical daily output scene, or selecting the representative day in a certain period as a typical daily output scene. The output characteristics of the new energy are obtained simply and quickly through a typical daily method, but the variation characteristics of the output of the new energy all year around cannot be reflected due to insufficient abundant scenes, and the error is large in medium-term and long-term power supply planning calculation. The time sequence simulation method is to obtain a simulated output time sequence by adjusting the actual output time sequence data of the historical new energy according to the change of the installed capacity and other factors. The annual output time sequence obtained by the time sequence simulation method is close to the actual output characteristics of new energy such as wind power, photovoltaic and the like every day, the result is accurate and reliable, and the defect is low calculation efficiency. The clustering algorithm is used for extracting, classifying and simplifying information of a new energy actual output scene of a long time sequence by a clustering analysis method so as to obtain a typical scene set. The clustering algorithm not only ensures the original characteristics of the output data, but also considers the calculation efficiency. At present, most researches analyze a large amount of actual loads or wind power data through a classical clustering algorithm to obtain a user load and wind power output scene set capable of accurately reflecting actual characteristics, but the selection of the number of clusters and the correlation among multiple types of new energy resources in the same region are not deeply discussed.
In view of this, it is necessary to improve and optimize the conventional FCM clustering algorithm, so as to perform clustering analysis on historical time-series output data of new energy in a certain new energy-rich area, generate a new energy typical output scene set of the area, and verify the validity of the method in an actual problem.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a new energy typical scene construction method based on an improved FCM clustering algorithm, which can solve the defects in the prior art.
The technical scheme is as follows: in order to achieve the purpose, the invention adopts the following technical scheme:
a new energy typical scene construction method based on an improved FCM clustering algorithm comprises the following steps:
s1: improving an FCM clustering algorithm by establishing a clustering effectiveness index function;
s2: clustering and dividing the new energy output historical data by using an improved FCM clustering algorithm;
s3: and selecting a typical scene of the new energy output in each category after clustering.
The new energy typical scene construction method based on the improved FCM clustering algorithm comprises a clustering effectiveness index function CH in step S1(+)Comprises the following steps:
wherein c is the number of clusters, n is the number of samples, Tc、PcThe sum of squares of inter-class and intra-class dispersion.
In the method for constructing the new energy typical scene based on the improved FCM clustering algorithm, the improved FCM clustering algorithm process by establishing the clustering effectiveness index function in the step S1 is as follows:
1) setting the variation range of the cluster number c
2) Calling an FCM clustering algorithm, and updating a clustering center until a target function converges;
3) calculating CH(+)Indexes;
4) c +1, go to step 2) until
5) Comparing CH at different c values(+)Determining the size of the index, and determining the optimal clustering number;
6) and outputting the clustering result under the optimal clustering number.
The new energy typical scene construction method based on the improved FCM clustering algorithm comprises the steps that the new energy comprises wind energy and light energy, and the process of clustering and dividing the historical data of the new energy output by using the improved FCM clustering algorithm in the step S2 comprises the following steps:
1) collecting historical output data of wind power and photoelectric new energy;
2) preprocessing historical output data of the new energy, including correction of lost data and mutation data and the like, to obtain a set of output data of the wind power plant at n continuous days and m equal time intervals each dayThe photovoltaic power station output data set of the photovoltaic power station corresponding to the time interval isWherein,representing the wind power output data of the nth day,representing photoelectric output data of the nth day;
3) historical data X of wind power and photoelectric output by using the improved FCM clustering algorithm provided in the step S1w、XsAnd performing cluster division.
In the new energy typical scene construction method based on the improved FCM clustering algorithm, the selection process of the new energy output typical scene in each category after clustering in step S3 is as follows:
1) reading the output data of each historical day in the class;
2) calculating the average of all historical solar output powers that would belong to that classj is the total number of the historical days belonging to the class, PiThe solar output power of the historical day i;
3) calculating the distance d between the output power and the average power of each historical dayi＝|Pi-Pavg|；
4) To diAnd performing ascending sorting, and taking the historical sunrise curve closest to the selection as a typical scene of the type.
Has the advantages that: the invention provides a new energy typical scene set construction method based on an improved FCM clustering algorithm and an operation cost optimization model of a power system containing high-proportion new energy by taking the new energy output characteristic of a new energy rich area as a research object. And performing cluster analysis on historical time sequence output data of the new energy source by using a typical scene set construction method based on an improved FCM clustering algorithm to generate a typical output scene set of the site. Simulation results of the specific implementation mode show that annual features of wind power and photoelectric typical scenes generated by the new energy typical scene set construction method based on the improved FCM clustering algorithm are obvious, actual output conditions are met, and the method has the advantages of high calculation efficiency and small error in actual engineering application.
Drawings
FIG. 1 is a clustering validity index of a wind power output scene in an embodiment of the present invention;
FIG. 2 is a typical output curve of a wind-powered spring in autumn according to an embodiment of the present invention;
FIG. 3 is a typical output curve of wind power in summer according to an embodiment of the present invention;
FIG. 4 is a typical wind-powered winter output curve according to an embodiment of the present invention;
FIG. 5 is a typical photoelectric spring and autumn output curve in accordance with an embodiment of the present invention;
FIG. 6 is a graph of typical photovoltaic summer output curves in accordance with an embodiment of the present invention;
fig. 7 is a typical output curve of a photovoltaic winter season in an embodiment of the present invention.
Detailed Description
The technical solution of the present invention will be further described with reference to the following embodiments.
The invention discloses a new energy typical scene construction method based on an improved FCM clustering algorithm, which comprises the following steps:
s1: improving an FCM clustering algorithm by establishing a clustering effectiveness index function;
s2: clustering and dividing the new energy output historical data by using an improved FCM clustering algorithm;
s3: and selecting a typical scene of the new energy output in each category after clustering.
Further, the FCM clustering algorithm in step S1 is a clustering algorithm based on partitioning, and by introducing the concept of membership function, the relationship between the object and the class cluster is expanded to be described by an arbitrary value on the [0,1] closed interval, and by determining the value of the membership function, the object is partitioned to which class cluster it is more inclined to belong.
First, the concept of fuzzy subsets is defined as:
for any x ∈ U, a number μ can be determinedA(x)∈[0,1]To describe the degree to which x belongs to A, defined as the membership function of A, the membership of the element in U to the fuzzy subset A is given by a constant μA(x) A description is given. Mu.sA(x) The closer the membership is to 0, the smaller the degree to which x belongs to a; mu.sA(x) Closer to 1, the greater the degree to which x belongs to a.
For a data set X ═ X1,x2,x3,…,xnUsing FCM clustering to divide the data set X into c classes (2 ≦ c ≦ n), where the set of cluster centers may be denoted as V ≦ V ≦ n1,v2,…,vcIn fuzzy partition, each data object is described to belong to a certain class by a certain membership value, but is not strictly divided into a certain class.
Ith data sample X in dataset XiMembership mu belonging to class jijExpressed by the following numerical relationship:
with a value of [0,1]Random number initialization membership matrix U in interval ═ mui,jSolving the minimum value of the objective function on the basis that the minimum value satisfies the constraint condition in the above formula:
membership value muijThe calculation is as follows:
wherein F (X, V) represents the weighted sum of squares of distances from the data sample to the cluster center, and the weight is the data sample XiMembership mu belonging to class jijThe power f of (1), the smoothing factor (fuzzy weighting parameter) f ∈ [1, + ∞ ]), and the exponent for adjusting the membership can be used to control the smoothing degree for adjusting the membership, and in general embodiments, the smoothing factor f is generally 2 if there is no special requirement. U ═ μi,jIs the fuzzy membership matrix. dij＝||xi-vjAnd | | l represents the Euclidean distance from the ith data sample to the jth cluster center.
The FCM clustering algorithm flow can be summarized as follows:
1) setting clustering number c, iteration number k equal to 0, maximum iteration number T and termination error epsilon, and initializing clusteringCenter V0；
2) Updating membership matrix U with equation (4)k；
3) Updating the next clustering center V by using the formula (3) and the formula (4)k+1；
4) If | | | Uk+1-UkIf | < epsilon, the algorithm is ended. Otherwise, let k be k +1, return to step 2).
Further, the cluster validity index function CH in step S1(+)Comprises the following steps:
wherein, Tc、PcIs the sum of squared deviations between classes and within classes. The sum of squared differences between classes can reflect the differences between classes, and the larger the value is, the better the difference is; the intra-class dispersion square sum reflects the difference between samples of the same class, and the smaller the value, the better. Finding the best cluster number c can be converted to maximizing the index.
Further, the FCM clustering algorithm flow improved by establishing the clustering validity index function in step S1 is summarized as follows:
1) setting the variation range of the cluster number c
2) Calling an FCM clustering algorithm, and updating a clustering center until a target function converges;
3) calculating CH(+)Indexes;
4) c +1, go to step 2) until
5) Comparing CH at different c values(+)Index size, determining optimal clusteringCounting;
6) and outputting the clustering result under the optimal clustering number.
Further, the new energy in step S2 includes wind energy and light energy, and the process of clustering and dividing the historical data of new energy output by using the improved FCM clustering algorithm includes:
1) collecting historical output data of wind power and photoelectric new energy;
2) preprocessing historical output data of the new energy, including correction of lost data and mutation data and the like, to obtain a set of output data of the wind power plant at n continuous days and m equal time intervals each dayThe photovoltaic power station output data set of the photovoltaic power station corresponding to the time interval isWherein,representing the wind power output data of the nth day,representing photoelectric output data of the nth day;
3) historical data X of wind power and photoelectric output by using the improved FCM clustering algorithm provided in the step S1w、XsAnd performing cluster division.
Further, the selecting process of the new energy output typical scene in each category after clustering in step S3 is as follows:
1) reading the output data of each historical day in the class;
2) calculating the average of all historical solar output powers that would belong to that classj is the same asTotal number of class history days, PiThe solar output power of the historical day i;
3) calculating the distance d between the output power and the average power of each historical dayi＝|Pi-Pavg|；
4) To diAnd performing ascending sorting, and taking the historical sunrise curve closest to the selection as a typical scene of the type.
Taking a new energy enrichment area in Zhejiang province as an example, the new energy output typical scene set is constructed by using the construction method of the new energy output typical scene set based on the improved FCM algorithm. The method is characterized in that the wind power installation machine is 50MW and the photovoltaic power generation installation machine is 320MW in the region, the output data of the wind power and the photovoltaic power generation from 6 months and 1 days in 2017 to 5 months and 5 months in 2018 in the region are selected as samples, the wind power and the photovoltaic power output have periodicity related to seasons, typical scene construction is carried out after the wind power and the photovoltaic historical output data samples are divided into three types of spring, autumn, summer and winter, the constructed typical scene set of the new energy is applied to the actual problem of medium-long term operation cost optimization of a high-proportion new energy power system, and the actual application value of the method is evaluated.
Example 1:
in the embodiment 1, the wind power and photoelectric historical output data are subjected to scene division by using an improved FCM clustering algorithm, clustering effectiveness index operation is firstly carried out in a clustering process, and then scene division is carried out after an optimal clustering number is obtained. Taking the wind power of the region as an example, the clustering effectiveness CH of the wind power output scene of each season is calculated(+)Index, using extremum normalization to CH(+)The index is processed as shown in the following formula:
clustering validity CH of processed wind power output scene(+)The index is shown in FIG. 1.
As can be seen from FIG. 1, the clustering effectiveness index CH of each wind power season(+)And taking the maximum value when the number of the clusters is 2, namely the optimal cluster number of the wind power output scene in each season is 2. Similarly, the optimal clustering number of the photoelectric seasonal output scene is 2. Fig. 2 to 4 show typical output curves after wind power is grouped into two types, namely spring and autumn, summer and winter, and fig. 5 to 7 show typical output curves after photoelectric wind power is grouped into two types, namely spring and autumn, summer and winter. It can be seen from the above-mentioned output curve graph that the clustering results are roughly divided according to the output level. The probability distribution conditions of the typical wind power and photoelectric output scene in each season are respectively shown in the table 1 and the table 2.
TABLE 1 wind power output typical scene probability distribution situation in each season
TABLE 2 typical scene probability distribution of photoelectric output in each season
The output curves of fig. 2 to 7 visually represent typical output sizes and variation trends of wind power and photoelectric seasons. The wind power has stronger volatility, and the peak and valley change process and the anti-peak regulation characteristic are obvious. The photoelectric output also has certain fluctuation, the output intensity is closely related to the illumination intensity, and the maximum value is taken at about 13 hours per day. It can be seen from the above output curve graph that the clustering results are roughly divided according to the output level, and table 1 and table 2 respectively show the probability distribution of typical output scenes of wind power and photoelectric power in each season.
Example 2:
the embodiment 2 applies a typical wind power/photoelectric output scene to the operation cost optimization field of a high-proportion new energy power system, in order to reduce the phenomenon of wind abandonment and light abandonment in a region, the sum of the punishment cost of the electric quantity of the wind abandonment and the light abandonment and the operation cost of all units is the lowest as an optimization target, the maximum consumption of new energy is considered while the economic operation is carried out, and the objective function is as follows:
wherein T represents the total number of simulation periods, cwAs a wind power penalty coefficient, csAs a result of the photoelectric penalty factor,representing the predicted output of the wind power in the time period t,representing the actual output of the wind power in the time period t,representing the predicted output of the photo-electricity over time t,represents the actual contribution of the photo-electricity during the time period t,representing the actual output of thermal power in the time period t, ath，bth，cthFor the thermal power generation cost coefficient, as，bs，csFor the cost coefficient of wind power generation, aw，bw，cwIs a photoelectric power generation cost coefficient.
The constraints considered by the optimization model include:
1) and electric quantity balance constraint: the total power generation amount of regional thermal power, wind power and photoelectricity is balanced with the load of a user.
Where u represents the user load in that area.
2) And (3) generating power constraint: the generated energy of each type of unit meets the maximum and minimum generated energy constraints.
Wherein q isthminRepresenting the minimum power generation of the thermal power plant, qthmaxRepresents the maximum power generation amount of the thermal power station, and q is the samewmin、qwmax、qwmin、qwmaxAnd the maximum and minimum power generation quantities of wind power and photoelectricity are represented.
3) And (3) climbing restraint of the thermal power generating unit:
wherein, γdownAnd gammaupRespectively representing the downward climbing speed and the upward climbing speed of the thermal power generating unit,andrepresenting the power generation of the thermal power plant during the t-1 and t periods, respectively.
And verifying and comparing scenes constructed by a year-round time sequence method, an improved FCM algorithm and a typical daily method by using the power system operation cost optimization model, wherein the typical daily method selects the daily output of wind power and photoelectric power which is closest to the average value in spring and autumn, summer and winter as a typical scene. The performance comparison conditions of the three scene construction methods are obtained by taking the annual output scene constructed by the annual time sequence method as a comparison standard, and are shown in table 3.
TABLE 3 Scenario construction method Performance comparison
It can be seen that the operation efficiency is remarkably improved due to the large reduction of the number of scenes in the scene construction method based on the improved FCM clustering algorithm and the typical daily method. However, compared with the wind power and photoelectric annual output scenes constructed by the annual time sequence method, the scenes constructed by improving the FCM clustering algorithm and the typical daily method have certain errors. Compared with a scene construction method based on a whole-year time sequence method, the improved FCM clustering algorithm has the advantages that the error rates of wind power and photoelectric prediction results are respectively 33.4% and 27.1%, and compared with a scene construction method based on a whole-year time sequence method, the error rates of wind power and photoelectric prediction results are respectively 49.8% and 51.9%.

Claims (5)

1. A new energy typical scene construction method based on an improved FCM clustering algorithm is characterized by comprising the following steps: the method comprises the following steps:
s1: improving an FCM clustering algorithm by establishing a clustering effectiveness index function;
s2: clustering and dividing the new energy output historical data by using an improved FCM clustering algorithm;
s3: and selecting a typical scene of the new energy output in each category after clustering.
2. According to the rightThe method for constructing the new energy typical scene based on the improved FCM clustering algorithm in claim 1 is characterized in that: clustering validity index function CH in step S1(+)Comprises the following steps:
wherein c is the number of clusters, n is the number of samples, Tc、PcThe sum of squares of inter-class and intra-class dispersion.
3. The method for constructing the new energy typical scene based on the improved FCM clustering algorithm according to claim 1, wherein: the FCM clustering algorithm process after the improvement by establishing the clustering validity indicator function in step S1 is:
1) setting the variation range of the cluster number c
2) Calling an FCM clustering algorithm, and updating a clustering center until a target function converges;
3) calculating CH(+)Indexes;
4) c +1, go to step 2) until
5) Comparing CH at different c values(+)Determining the size of the index, and determining the optimal clustering number;
6) and outputting the clustering result under the optimal clustering number.
4. The method for constructing the new energy typical scene based on the improved FCM clustering algorithm according to claim 1, wherein: the new energy comprises wind energy and light energy, and the process of clustering and dividing the historical data of the new energy output by using the improved FCM clustering algorithm in the step S2 is as follows:
1) collecting historical output data of wind power and photoelectric new energy;
2) for new energy historyPreprocessing the output data, including correcting lost data and mutation data, and obtaining a wind power plant output data set with n continuous days and m equal time intervals every dayThe photovoltaic power station output data set of the photovoltaic power station corresponding to the time interval isWherein,representing the wind power output data of the nth day,representing photoelectric output data of the nth day;
3) historical data X of wind power and photoelectric output by using the improved FCM clustering algorithm provided in the step S1w、XsAnd performing cluster division.
5. The method for constructing the new energy typical scene based on the improved FCM clustering algorithm according to claim 1, wherein: the selection process of the new energy output typical scene in each category after clustering in the step S3 is as follows:
1) reading the output data of each historical day in the class;
2) calculating the average of all historical solar output powers that would belong to that classj is the total number of the historical days belonging to the class, PiThe solar output power of the historical day i;
3) calculating the distance d between the output power and the average power of each historical dayi＝|Pi-Pavg|；
4) To diAnd performing ascending sorting, and taking the historical sunrise curve closest to the selection as a typical scene of the type.
CN201910382189.8A 2019-05-08 2019-05-08 A kind of new energy typical scene construction method based on improvement FCM clustering algorithm Pending CN110111003A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910382189.8A CN110111003A (en) 2019-05-08 2019-05-08 A kind of new energy typical scene construction method based on improvement FCM clustering algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910382189.8A CN110111003A (en) 2019-05-08 2019-05-08 A kind of new energy typical scene construction method based on improvement FCM clustering algorithm

Publications (1)

Publication Number Publication Date
CN110111003A true CN110111003A (en) 2019-08-09

Family

ID=67489012

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910382189.8A Pending CN110111003A (en) 2019-05-08 2019-05-08 A kind of new energy typical scene construction method based on improvement FCM clustering algorithm

Country Status (1)

Country Link
CN (1) CN110111003A (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110943477A (en) * 2019-11-19 2020-03-31 国网江苏省电力有限公司经济技术研究院 Method and device for improving consumption of distributed power supply by optimized charging of electric automobile
CN111523230A (en) * 2020-04-22 2020-08-11 国网能源研究院有限公司 Adaptive clustering method for wind and light load composite typical scene
CN111612033A (en) * 2020-04-15 2020-09-01 广东电网有限责任公司 Distribution transformer fault diagnosis method based on gravity search and density peak clustering
CN111626645A (en) * 2020-07-01 2020-09-04 国网新疆电力有限公司 Method and system for measuring and calculating future-year energy storage configuration capacity
CN112036754A (en) * 2020-06-30 2020-12-04 南昌木本医疗科技有限公司 Financial big data wind control platform based on block chain
CN112072695A (en) * 2020-08-13 2020-12-11 明阳智慧能源集团股份公司 Wind power base collecting circuit control method, system, storage medium and computing equipment
CN112241403A (en) * 2020-10-29 2021-01-19 深圳供电局有限公司 Electric energy quality data cleaning method and system for typical scene
CN112785457A (en) * 2021-02-02 2021-05-11 东南大学 Typical scene construction method of distributed energy supply system based on panel data
CN113239503A (en) * 2021-05-10 2021-08-10 上海电气工程设计有限公司 New energy output scene analysis method and system based on improved k-means clustering algorithm
CN113256068A (en) * 2021-04-25 2021-08-13 国网宁夏电力有限公司 Wisdom energy internet system
CN114511224A (en) * 2022-02-09 2022-05-17 中国电力科学研究院有限公司 Method, system, equipment and medium for constructing operation risk scene of composite power grid

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070106333A1 (en) * 2003-08-22 2007-05-10 Fernandez Dennis S Integrated biosensor and simulation system for diagnosis and therapy
CN108376262A (en) * 2018-02-23 2018-08-07 新疆大学 A kind of analysis model construction method of wind power output typical characteristics
CN109524993A (en) * 2018-12-19 2019-03-26 中国农业大学 The typical week power output scene generating method of wind-powered electricity generation photovoltaic for Mid-long Term Optimized Scheduling

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070106333A1 (en) * 2003-08-22 2007-05-10 Fernandez Dennis S Integrated biosensor and simulation system for diagnosis and therapy
CN108376262A (en) * 2018-02-23 2018-08-07 新疆大学 A kind of analysis model construction method of wind power output typical characteristics
CN109524993A (en) * 2018-12-19 2019-03-26 中国农业大学 The typical week power output scene generating method of wind-powered electricity generation photovoltaic for Mid-long Term Optimized Scheduling

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
姚建峰 等: ""基于改进FCM聚类算法的清洁能源典型场景构建"", 《电网与清洁能源》 *

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110943477A (en) * 2019-11-19 2020-03-31 国网江苏省电力有限公司经济技术研究院 Method and device for improving consumption of distributed power supply by optimized charging of electric automobile
CN111612033A (en) * 2020-04-15 2020-09-01 广东电网有限责任公司 Distribution transformer fault diagnosis method based on gravity search and density peak clustering
CN111523230A (en) * 2020-04-22 2020-08-11 国网能源研究院有限公司 Adaptive clustering method for wind and light load composite typical scene
CN111523230B (en) * 2020-04-22 2023-05-26 国网能源研究院有限公司 Self-adaptive clustering method for wind-light load composite typical scene
CN112036754B (en) * 2020-06-30 2022-09-16 上海即科智能技术集团有限公司 Financial big data wind control system based on block chain
CN112036754A (en) * 2020-06-30 2020-12-04 南昌木本医疗科技有限公司 Financial big data wind control platform based on block chain
CN111626645A (en) * 2020-07-01 2020-09-04 国网新疆电力有限公司 Method and system for measuring and calculating future-year energy storage configuration capacity
CN111626645B (en) * 2020-07-01 2023-04-18 国网新疆电力有限公司 Method and system for measuring and calculating future-year energy storage configuration capacity
CN112072695B (en) * 2020-08-13 2022-05-17 明阳智慧能源集团股份公司 Wind power base collecting circuit control method, system, storage medium and computing equipment
CN112072695A (en) * 2020-08-13 2020-12-11 明阳智慧能源集团股份公司 Wind power base collecting circuit control method, system, storage medium and computing equipment
CN112241403A (en) * 2020-10-29 2021-01-19 深圳供电局有限公司 Electric energy quality data cleaning method and system for typical scene
CN112241403B (en) * 2020-10-29 2024-05-28 深圳供电局有限公司 Electric energy quality data cleaning method and system for typical scene
CN112785457A (en) * 2021-02-02 2021-05-11 东南大学 Typical scene construction method of distributed energy supply system based on panel data
CN112785457B (en) * 2021-02-02 2023-10-10 东南大学 Panel data-based typical scene construction method for distributed energy supply system
CN113256068A (en) * 2021-04-25 2021-08-13 国网宁夏电力有限公司 Wisdom energy internet system
CN113239503A (en) * 2021-05-10 2021-08-10 上海电气工程设计有限公司 New energy output scene analysis method and system based on improved k-means clustering algorithm
CN113239503B (en) * 2021-05-10 2022-09-23 上海电气工程设计有限公司 New energy output scene analysis method and system based on improved k-means clustering algorithm
CN114511224A (en) * 2022-02-09 2022-05-17 中国电力科学研究院有限公司 Method, system, equipment and medium for constructing operation risk scene of composite power grid

Similar Documents

Publication Publication Date Title
CN110111003A (en) A kind of new energy typical scene construction method based on improvement FCM clustering algorithm
US11581740B2 (en) Method, system and storage medium for load dispatch optimization for residential microgrid
CN114792156B (en) Photovoltaic output power prediction method and system based on curve characteristic index clustering
CN107528350B (en) A kind of wind power output typical scene generation method adapting to long -- term generation expansion planning
CN107679687A (en) A kind of photovoltaic output modeling method and Generation System Reliability appraisal procedure
CN111754037B (en) Long-term load hybrid prediction method for regional terminal integrated energy supply system
CN111275238B (en) Large-scale power station photovoltaic output sequence generation method based on hourly clear sky index
CN112165084B (en) Multi-time scale optimization method considering photovoltaic-load bilateral prediction uncertainty
CN111404193B (en) Data-driven-based microgrid random robust optimization scheduling method
CN111626473A (en) Two-stage photovoltaic power prediction method considering error correction
CN112149890A (en) Comprehensive energy load prediction method and system based on user energy label
CN112561252B (en) Reactive power combination evaluation method for power grid in new energy-containing region
CN112418346B (en) Numerical weather forecast total radiation system error classification calculation method
CN110133755A (en) Separated modeling forecast Control Algorithm is directly dissipated under more weather patterns based on GRA-LMBP weight
CN117272850B (en) Elastic space analysis method for safe operation scheduling of power distribution network
CN115829105A (en) Photovoltaic power prediction method based on historical data feature search
CN112186761A (en) Wind power scene generation method and system based on probability distribution
CN113452033A (en) Method for controlling voltage of high-proportion photovoltaic power distribution network with partition autonomy and storage medium
CN112633565A (en) Photovoltaic power aggregation interval prediction method
CN116826710A (en) Peak clipping strategy recommendation method and device based on load prediction and storage medium
Meng et al. A new PV generation power prediction model based on GA-BP neural network with artificial classification of history day
CN108694475B (en) Short-time-scale photovoltaic cell power generation capacity prediction method based on hybrid model
CN113947499A (en) Water, wind and light planning scheme set optimization method based on hierarchical optimization model
CN117955098A (en) High-proportion new energy power system typical scene generation method and system
CN116484998A (en) Distributed photovoltaic power station power prediction method and system based on meteorological similar day

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
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20201208

Address after: 213300 room 428, building a, 218 Hongkou Road, Kunlun Street, Liyang City, Changzhou City, Jiangsu Province (in Zhongguancun Science and Technology Industrial Park, Jiangsu Province)

Applicant after: Liyang Research Institute of Southeast University

Applicant after: SOUTHEAST University

Address before: Four pailou Nanjing Xuanwu District of Jiangsu Province, No. 2 210096

Applicant before: SOUTHEAST University

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

Application publication date: 20190809