CN110222361A - A kind of Power Output for Wind Power Field analogy method and device - Google Patents
A kind of Power Output for Wind Power Field analogy method and device Download PDFInfo
- Publication number
- CN110222361A CN110222361A CN201910328914.3A CN201910328914A CN110222361A CN 110222361 A CN110222361 A CN 110222361A CN 201910328914 A CN201910328914 A CN 201910328914A CN 110222361 A CN110222361 A CN 110222361A
- Authority
- CN
- China
- Prior art keywords
- day
- wind power
- class
- output
- power plant
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000007704 transition Effects 0.000 claims abstract description 137
- 239000011159 matrix material Substances 0.000 claims abstract description 110
- 238000004088 simulation Methods 0.000 claims description 50
- 239000000203 mixture Substances 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 11
- 238000012546 transfer Methods 0.000 claims description 8
- 230000005684 electric field Effects 0.000 claims description 7
- 230000006870 function Effects 0.000 description 20
- 230000005611 electricity Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Abstract
The present invention relates to a kind of Power Output for Wind Power Field analogy method and devices, determine wind power plant day output power class including the use of wind power plant history day output power data;Obtain all kinds of wind power plant day output powers state transition probability matrix and it is all kinds of between wind power plant day output power class between transition probability matrix;Using all kinds of wind power plant day output powers state transition probability matrix and it is all kinds of between wind power plant day output power class between transition probability matrix generate Power Output for Wind Power Field simulated series;The present invention obtains simulated series by transition probability matrix between the classification of day output power, state transition probability matrix of all categories and class, reduces error caused by problems of the prior art, improves the accuracy of simulated series.
Description
Technical field
The present invention relates to technical field of new energy power generation, and in particular to a kind of Power Output for Wind Power Field analogy method and dress
It sets.
Background technique
Time series modeling is when carrying out analytical calculation to electric system, according to different time scales, the demand of scene, when
Between Series Modeling produce any time length, the simulated series of any item number, can be provided for the simulation of more scenes calculating enough
Sample, compared to historical power data, the statistical property of a large amount of simulated series is more advantageous to staff and grasps electric system fortune
Professional etiquette rule.
Currently, common time series modeling method is broadly divided into indirect method and direct method two major classes.Indirect method is initially set up
Then wind speed time series models obtain wind power sequence using wind-driven generator power transformational relation.Building based on wind speed
Mould method is unable to satisfy the modeling essence of wind power plant access electric system due to the more difficult accurate acquisition of wind power transfer characteristic
Degree demand.Direct method is also known as wind power method, is to directly generate corresponding simulation wind on the basis of surveying wind power sequence
During electrical power sequence avoids and converts introduced error, but direct method is moved using Gaussian function fitting disturbance, due to wind
Electro-mechanical wave process be not it is symmetrical, can exist rise it is fast and under slow down, or rise slow and decline fast problem, cause to generate
Simulated series equally exist error.
Summary of the invention
In view of the deficiencies of the prior art, the object of the present invention is to provide a kind of Power Output for Wind Power Field analogy method and dresses
It sets, simulation sequence is obtained by transition probability matrix between the classification of day output power, state transition probability matrix of all categories and class
Column, reduce error caused by problems of the prior art, improve the accuracy of simulated series.
The purpose of the present invention is adopt the following technical solutions realization:
The present invention provides a kind of Power Output for Wind Power Field analogy method, it is improved in that the described method includes:
Wind power plant day output power class is determined using wind power plant history day output power data;
Obtain all kinds of wind power plant day output powers state transition probability matrix and it is all kinds of between wind power plant day it is defeated
Transition probability matrix between the class of power out;
Using all kinds of wind power plant day output powers state transition probability matrix and it is all kinds of between wind power plant day it is defeated
Transition probability matrix generates Power Output for Wind Power Field simulated series between the class of power out.
Preferably, described to determine that wind power plant day output power class includes: using wind power plant history day output power data
Using the characteristic value of each history day output power data of wind power plant as cluster sample, and will using K-means algorithm
Cluster sample is divided into K class;
Wherein, the characteristic value of the wind power plant history day output power data is that the day output power of history day wind power plant is flat
Mean value and the day very poor value of output power.
Preferably, the state transition probability matrix for obtaining all kinds of wind power plant day output powers and it is all kinds of between
Wind power plant day output power class between transition probability matrix include:
According to each moment output power value in the corresponding output power data of kth class by the corresponding output power number of kth class
According to being divided into N number of state interval;
As the following formula determine kth class wind power plant day output power state transition probability matrix Pk:
In formula, k ∈ [1, K], K are wind power plant day output power class sum,For the wind-powered electricity generation in the state interval m of kth class
Field historical juncture output power value is transferred to the probability of state interval n in subsequent time state, and m ∈ [1, N], n ∈ [1, N], N are
State interval sum;
Wherein, determine the wind power plant historical juncture output power value in the kth class in state interval m next as the following formula
Moment state is transferred to the probability of state interval n
In formula,It is shifted for the wind power plant historical juncture output power value in state interval m in subsequent time state
It is enabled to the number of state interval n as n-m > INT (N/3)INT () is bracket function;
Transition probability matrix P between determining class as the following formulacum:
In formula,F class probability, f ∈ are being transferred to next day for kth class wind power plant history day output power data
[1,K];
Wherein, it is general to determine that the kth class wind power plant history day output power data in next day are transferred to f class as the following formula
Rate
In formula, TkfF class transfer number, T are being transferred to next day for kth class wind power plant history day output power datak
For middle kth class wind power plant history day output power data count.
Preferably, the state transition probability matrix using all kinds of wind power plant day output powers and it is all kinds of between
Wind power plant day output power class between transition probability matrix generate Power Output for Wind Power Field simulated series include:
S1. simulated time day=1 is initialized;
If S2. the wind power plant day output power of simulated time day-1 belongs to the wind power plant day output power of r class, with
Machine generates transition probability value y between class1, and compare transition probability value y between class1The transition probability matrix P between classcumIn r row element
Size;
Wherein, if transition probability value y between class1The transition probability matrix P between classcumIn r row s column element it is equal or
Person transition probability matrix P between classcumIn r row s column element and r row s+1 column element between, then when simulating
Between the wind power plant day output power of day belong to s class, y1∈ [0,1], r ∈ [1, K], s ∈ [1, K-1], s+1 ∈ [1, K];
Simulated time day-1, is finally simulated the wind-powered electricity generation at moment by the simulation moment t=1 for S3. initializing simulated time day
Power Output for Wind Power Field value of the field output power value as simulated time day simulation moment t, and determine the Power Output for Wind Power Field
Be worth the wind power plant day in s class in output power belonging to state interval m;
S4. t=t+1 is enabled, it is random to generate state transition probability value y2, and compare state transition probability value y2With the wind of s class
Electric field day output power state transition probability matrix PsIn m row element size;
Wherein, if state transition probability value y2With s class wind power plant day output power state transition probability matrix PsIn
The element that m row n-th arranges is equal or between s class state transition probability matrix PsIn m row n-th arrange element and m row
Between the element of (n+1)th column, then the Power Output for Wind Power Field value of the simulation moment t of simulated time day belongs to state interval n, with
Machine generates the Power Output for Wind Power Field basic value between the state interval n, wherein y2∈ (0,1], n+1 ∈ [1, N];
S5. undulating value is randomly selected from the fluctuation value set obtained in advance, and is superimposed to the simulated time day simulation moment
The Power Output for Wind Power Field basic value of t obtains the Power Output for Wind Power Field value of simulated time day simulation moment t, if simulated time
The Power Output for Wind Power Field value of day simulation moment t belongs to state interval n, then goes to S6, otherwise repeatedly S5;
If S6. t=tday, then S7 is gone to, S4 is otherwise gone to, wherein tdayFor the last simulation moment of simulated time day;
If S7. day=Tday, then Power Output for Wind Power Field simulated series are exported, otherwise, enable day=day+1, and go to
S2, wherein TdayFor the last simulated time of simulated series.
Further, the acquisition process of the fluctuation value set obtained in advance includes:
Calculate the first-order difference amount between each wind power plant historical juncture output power of wind power plant history day output power, benefit
The parameter value that its corresponding Gaussian mixtures function is obtained with EM algorithm obtains the Gaussian mixtures function;
The output power fluctuation of wind farm value set of random numbers for meeting the Gaussian mixtures function is generated, as
The fluctuation value set obtained in advance.
The present invention provides a kind of Power Output for Wind Power Field simulator, it is improved in that described device includes:
Cluster cell, for determining wind power plant day output power class using wind power plant history day output power data;
Matrix determination unit, for obtaining the state transition probability matrix of all kinds of wind power plant day output powers and all kinds of
Between wind power plant day output power class between transition probability matrix;
Generation unit is simulated, for state transition probability matrix using all kinds of wind power plant day output powers and all kinds of
Between wind power plant day output power class between transition probability matrix generate Power Output for Wind Power Field simulated series.
Preferably, the cluster cell is specifically used for:
Using the characteristic value of each history day output power data of wind power plant as cluster sample, and will using K-means algorithm
Cluster sample is divided into K class;
Wherein, the characteristic value of the wind power plant history day output power data is that the day output power of history day wind power plant is flat
Mean value and the day very poor value of output power.
Preferably, the matrix determination unit includes:
First determining module, is used for:
According to each moment output power value in the corresponding output power data of kth class by the corresponding output power number of kth class
According to being divided into N number of state interval;
As the following formula determine kth class wind power plant day output power state transition probability matrix Pk:
In formula, k ∈ [1, K], K are wind power plant day output power class sum,For the wind-powered electricity generation in the state interval m of kth class
Field historical juncture output power value is transferred to the probability of state interval n in subsequent time state, and m ∈ [1, N], n ∈ [1, N], N are
State interval sum;
Wherein, determine the wind power plant historical juncture output power value in the kth class in state interval m next as the following formula
Moment state is transferred to the probability of state interval n
In formula,It is shifted for the wind power plant historical juncture output power value in state interval m in subsequent time state
It is enabled to the number of state interval n as n-m > INT (N/3)INT () is bracket function;
Second determining module, is used for:
Transition probability matrix P between determining class as the following formulacum:
In formula,F class probability, f ∈ are being transferred to next day for kth class wind power plant history day output power data
[1,K];
Wherein, it is general to determine that the kth class wind power plant history day output power data in next day are transferred to f class as the following formula
Rate
In formula, TkfF class transfer number, T are being transferred to next day for kth class wind power plant history day output power datak
For middle kth class wind power plant history day output power data count.
Preferably, the simulation generation unit is specifically used for:
S1. simulated time day=1 is initialized;
If S2. the wind power plant day output power of simulated time day-1 belongs to the wind power plant day output power of r class, with
Machine generates transition probability value y between class1, and compare transition probability value y between class1The transition probability matrix P between classcumIn r row element
Size;
Wherein, if transition probability value y between class1The transition probability matrix P between classcumIn r row s column element it is equal or
Person transition probability matrix P between classcumIn r row s column element and r row s+1 column element between, then when simulating
Between the wind power plant day output power of day belong to s class, y1∈ [0,1], r ∈ [1, K], s ∈ [1, K-1], s+1 ∈ [1, K];
Simulated time day-1, is finally simulated the wind-powered electricity generation at moment by the simulation moment t=1 for S3. initializing simulated time day
Power Output for Wind Power Field value of the field output power value as simulated time day simulation moment t, and determine the Power Output for Wind Power Field
Be worth the wind power plant day in s class in output power belonging to state interval m;
S4. t=t+1 is enabled, it is random to generate state transition probability value y2, and compare state transition probability value y2With the wind of s class
Electric field day output power state transition probability matrix PsIn m row element size;
Wherein, if state transition probability value y2With s class wind power plant day output power state transition probability matrix PsIn
The element that m row n-th arranges is equal or between s class state transition probability matrix PsIn m row n-th arrange element and m row
Between the element of (n+1)th column, then the Power Output for Wind Power Field value of the simulation moment t of simulated time day belongs to state interval n, with
Machine generates the Power Output for Wind Power Field basic value between the state interval n, wherein y2∈ (0,1], n+1 ∈ [1, N];
S5. undulating value is randomly selected from the fluctuation value set obtained in advance, and is superimposed to the simulated time day simulation moment
The Power Output for Wind Power Field basic value of t obtains the Power Output for Wind Power Field value of simulated time day simulation moment t, if simulated time
The Power Output for Wind Power Field value of day simulation moment t belongs to state interval n, then goes to S6, otherwise repeatedly S5;
If S6. t=tday, then S7 is gone to, S4 is otherwise gone to, wherein tdayFor the last simulation moment of simulated time day;
If S7. day=Tday, then Power Output for Wind Power Field simulated series are exported, otherwise, enable day=day+1, and go to
S2, wherein TdayFor the last simulated time of simulated series.
Further, the acquisition process of the fluctuation value set obtained in advance includes:
Calculate the first-order difference amount between each wind power plant historical juncture output power of wind power plant history day output power, benefit
The parameter value that its corresponding Gaussian mixtures function is obtained with EM algorithm obtains the Gaussian mixtures function;
The output power fluctuation of wind farm value set of random numbers for meeting the Gaussian mixtures function is generated, as
The fluctuation value set obtained in advance.
Compared with the immediate prior art, the invention has the benefit that
The present invention provides a kind of Power Output for Wind Power Field analogy method and device, passes through and utilizes wind power plant history day output work
Rate data determine wind power plant day output power class;Obtain all kinds of wind power plant day output powers state transition probability matrix and
Between all kinds of wind power plant day output power class between transition probability matrix;Utilize the state of all kinds of wind power plant day output powers
Transition probability matrix and it is all kinds of between wind power plant day output power class between transition probability matrix generate wind power plant output work
Rate simulated series;The present invention passes through transition probability between the classification of day output power, state transition probability matrix of all categories and class
Matrix obtains simulated series, and reducing the simulated series generated in the prior art has that jump is serious, improves simulation
The accuracy of sequence.
Detailed description of the invention
Fig. 1 is Power Output for Wind Power Field analogy method flow chart of the present invention;
Fig. 2 is Power Output for Wind Power Field simulator schematic diagram of the present invention.
Specific embodiment
Specific embodiments of the present invention will be described in further detail with reference to the accompanying drawing.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
All other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
The present invention provides a kind of Power Output for Wind Power Field analogy method, as shown in Figure 1, which comprises
Wind power plant day output power class is determined using wind power plant history day output power data;
Obtain all kinds of wind power plant day output powers state transition probability matrix and it is all kinds of between wind power plant day it is defeated
Transition probability matrix between the class of power out;
Using all kinds of wind power plant day output powers state transition probability matrix and it is all kinds of between wind power plant day it is defeated
Transition probability matrix generates Power Output for Wind Power Field simulated series between the class of power out.
In an embodiment of the present invention, described to determine wind power plant day output work using wind power plant history day output power data
Rate class includes:
Using the characteristic value of each history day output power data of wind power plant as cluster sample, and will using K-means algorithm
Cluster sample is divided into K class;
Wherein, the characteristic value of the wind power plant history day output power data is that the day output power of history day wind power plant is flat
Mean value and the day very poor value of output power.In embodiments of the present invention, wind power plant history day output power data are normalized
Data afterwards.
In an embodiment of the present invention, the selection process of K value includes:
Based on given K value range, cluster sample is clustered using K-means algorithm, generates the class set of different K values
It closes, and calculates the Dai Weisenbaoding index of the class set of different K values, by the class set cooperation of the smallest K value of Dai Weisenbaoding index
For the wind power plant day output power class;
The Dai Weisenbaoding index D BI of the class set of k-th of K value is calculated as followsk:
In formula, NkFor k-th of K value class sum, Si,kFor data in the i-th class class of k-th of K value to the Europe of the i-th class cluster mass center
Family name's distance average, Sj,kFor Euclidean distance average value of the data to jth class cluster mass center in the jth class class of k-th of K value, wi,kFor
The characteristic value of i-th class cluster mass center of k-th of K value, wj,kFor the characteristic value of the jth class cluster mass center of k-th of K value, | | wi,k+wj,k||2
For the i-th class cluster centroid feature value of k-th K value and the norm of jth class cluster centroid feature value.
In addition, the state transition probability matrix for obtaining all kinds of wind power plant day output powers and it is all kinds of between wind
Electric field day output power class between transition probability matrix include:
According to each moment output power value in the corresponding output power data of kth class by the corresponding output power number of kth class
According to being divided into N number of state interval;This process includes obtaining the extreme value section of each moment output power value in kth class, its difference is removed
The interval of state interval is obtained with preset status number N, obtains N number of state interval according to the interval.
In an embodiment of the present invention, the acquisition of preset status number N includes:
Based on given state number interval, using iterative algorithm obtain the simulated series obtained in the prior art and at that time
Between corresponding history output power residual sum of squares (RSS), by the corresponding simulation obtained in the prior art of least residual quadratic sum
The corresponding status number of sequence is as the status number N in the embodiment of the present invention.
As the following formula determine kth class wind power plant day output power state transition probability matrix Pk:
In formula, k ∈ [1, K], K are wind power plant day output power class sum,For the wind-powered electricity generation in the state interval m of kth class
Field historical juncture output power value is transferred to the probability of state interval n in subsequent time state, and m ∈ [1, N], n ∈ [1, N], N are
State interval sum;
Wherein, determine the wind power plant historical juncture output power value in the kth class in state interval m next as the following formula
Moment state is transferred to the probability of state interval n
In formula,It is shifted for the wind power plant historical juncture output power value in state interval m in subsequent time state
It is enabled to the number of state interval n as n-m > INT (N/3)INT () is bracket function;
Transition probability matrix P between determining class as the following formulacum:
In formula,F class probability, f ∈ are being transferred to next day for kth class wind power plant history day output power data
[1,K];
Wherein, it is general to determine that the kth class wind power plant history day output power data in next day are transferred to f class as the following formula
Rate
In formula, TkfF class transfer number, T are being transferred to next day for kth class wind power plant history day output power datak
For middle kth class wind power plant history day output power data count.
Preferably, the state transition probability matrix using all kinds of wind power plant day output powers and it is all kinds of between
Wind power plant day output power class between transition probability matrix generate Power Output for Wind Power Field simulated series include:
S1. simulated time day=1 is initialized;
If S2. the wind power plant day output power of simulated time day-1 belongs to the wind power plant day output power of r class, with
Machine generates transition probability value y between class1, and compare transition probability value y between class1The transition probability matrix P between classcumIn r row element
Size;
Wherein, if transition probability value y between class1The transition probability matrix P between classcumIn r row s column element it is equal or
Person transition probability matrix P between classcumIn r row s column element and r row s+1 column element between, then when simulating
Between the wind power plant day output power of day belong to s class, y1∈ [0,1], r ∈ [1, K], s ∈ [1, K-1], s+1 ∈ [1, K];
Simulated time day-1, is finally simulated the wind-powered electricity generation at moment by the simulation moment t=1 for S3. initializing simulated time day
Power Output for Wind Power Field value of the field output power value as simulated time day simulation moment t, and determine the Power Output for Wind Power Field
Be worth the wind power plant day in s class in output power belonging to state interval m;
S4. t=t+1 is enabled, it is random to generate state transition probability value y2, and compare state transition probability value y2With the wind of s class
Electric field day output power state transition probability matrix PsIn m row element size;
Wherein, if state transition probability value y2With s class wind power plant day output power state transition probability matrix PsIn
The element that m row n-th arranges is equal or between s class state transition probability matrix PsIn m row n-th arrange element and m row
Between the element of (n+1)th column, then the Power Output for Wind Power Field value of the simulation moment t of simulated time day belongs to state interval n, with
Machine generates the Power Output for Wind Power Field basic value between the state interval n, wherein y2∈ (0,1], n+1 ∈ [1, N];
S5. undulating value is randomly selected from the fluctuation value set obtained in advance, and is superimposed to the simulated time day simulation moment
The Power Output for Wind Power Field basic value of t obtains the Power Output for Wind Power Field value of simulated time day simulation moment t, if simulated time
The Power Output for Wind Power Field value of day simulation moment t belongs to state interval n, then goes to S6, otherwise repeatedly S5;
If S6. t=tday, then S7 is gone to, S4 is otherwise gone to, wherein tdayFor the last simulation moment of simulated time day;
If S7. day=Tday, then Power Output for Wind Power Field simulated series are exported, otherwise, enable day=day+1, and go to
S2, wherein TdayFor the last simulated time of simulated series.
Further, the acquisition process of the fluctuation value set obtained in advance includes:
Calculate the first-order difference amount between each wind power plant historical juncture output power of wind power plant history day output power, benefit
The parameter value that its corresponding Gaussian mixtures function is obtained with EM algorithm obtains the Gaussian mixtures function;
The output power fluctuation of wind farm value set of random numbers for meeting the Gaussian mixtures function is generated, as
The fluctuation value set obtained in advance.
Based on same design, the present invention provides a kind of Power Output for Wind Power Field simulator, as shown in Fig. 2, described device
Include:
Cluster cell, for determining wind power plant day output power class using wind power plant history day output power data;
Matrix determination unit, for obtaining the state transition probability matrix of all kinds of wind power plant day output powers and all kinds of
Between wind power plant day output power class between transition probability matrix;
Generation unit is simulated, for state transition probability matrix using all kinds of wind power plant day output powers and all kinds of
Between wind power plant day output power class between transition probability matrix generate Power Output for Wind Power Field simulated series.
Preferably, the cluster cell is specifically used for:
Using the characteristic value of each history day output power data of wind power plant as cluster sample, and will using K-means algorithm
Cluster sample is divided into K class;
Wherein, the characteristic value of the wind power plant history day output power data is that the day output power of history day wind power plant is flat
Mean value and the day very poor value of output power.
Preferably, the matrix determination unit includes:
First determining module, is used for:
According to each moment output power value in the corresponding output power data of kth class by the corresponding output power number of kth class
According to being divided into N number of state interval;
As the following formula determine kth class wind power plant day output power state transition probability matrix Pk:
In formula, k ∈ [1, K], K are wind power plant day output power class sum,For the wind-powered electricity generation in the state interval m of kth class
Field historical juncture output power value is transferred to the probability of state interval n in subsequent time state, and m ∈ [1, N], n ∈ [1, N], N are
State interval sum;
Wherein, determine the wind power plant historical juncture output power value in the kth class in state interval m next as the following formula
Moment state is transferred to the probability of state interval n
In formula,It is shifted for the wind power plant historical juncture output power value in state interval m in subsequent time state
It is enabled to the number of state interval n as n-m > INT (N/3)INT () is bracket function;
Second determining module, is used for:
Transition probability matrix P between determining class as the following formulacum:
In formula,F class probability, f ∈ are being transferred to next day for kth class wind power plant history day output power data
[1,K];
Wherein, it is general to determine that the kth class wind power plant history day output power data in next day are transferred to f class as the following formula
Rate
In formula, TkfF class transfer number, T are being transferred to next day for kth class wind power plant history day output power datak
For middle kth class wind power plant history day output power data count.
Preferably, the simulation generation unit is specifically used for:
S1. simulated time day=1 is initialized;
If S2. the wind power plant day output power of simulated time day-1 belongs to the wind power plant day output power of r class, with
Machine generates transition probability value y between class1, and compare transition probability value y between class1The transition probability matrix P between classcumIn r row element
Size;
Wherein, if transition probability value y between class1The transition probability matrix P between classcumIn r row s column element it is equal or
Person transition probability matrix P between classcumIn r row s column element and r row s+1 column element between, then when simulating
Between the wind power plant day output power of day belong to s class, y1∈ [0,1], r ∈ [1, K], s ∈ [1, K-1], s+1 ∈ [1, K];
Simulated time day-1, is finally simulated the wind-powered electricity generation at moment by the simulation moment t=1 for S3. initializing simulated time day
Power Output for Wind Power Field value of the field output power value as simulated time day simulation moment t, and determine the Power Output for Wind Power Field
Be worth the wind power plant day in s class in output power belonging to state interval m;
S4. t=t+1 is enabled, it is random to generate state transition probability value y2, and compare state transition probability value y2With the wind of s class
Electric field day output power state transition probability matrix PsIn m row element size;
Wherein, if state transition probability value y2With s class wind power plant day output power state transition probability matrix PsIn
The element that m row n-th arranges is equal or between s class state transition probability matrix PsIn m row n-th arrange element and m row
Between the element of (n+1)th column, then the Power Output for Wind Power Field value of the simulation moment t of simulated time day belongs to state interval n, with
Machine generates the Power Output for Wind Power Field basic value between the state interval n, wherein y2∈ (0,1], n+1 ∈ [1, N];
S5. undulating value is randomly selected from the fluctuation value set obtained in advance, and is superimposed to the simulated time day simulation moment
The Power Output for Wind Power Field basic value of t obtains the Power Output for Wind Power Field value of simulated time day simulation moment t, if simulated time
The Power Output for Wind Power Field value of day simulation moment t belongs to state interval n, then goes to S6, otherwise repeatedly S5;
If S6. t=tday, then S7 is gone to, S4 is otherwise gone to, wherein tdayFor the last simulation moment of simulated time day;
If S7. day=Tday, then Power Output for Wind Power Field simulated series are exported, otherwise, enable day=day+1, and go to
S2, wherein TdayFor the last simulated time of simulated series.
Further, the acquisition process of the fluctuation value set obtained in advance includes:
Calculate the first-order difference amount between each wind power plant historical juncture output power of wind power plant history day output power, benefit
The parameter value that its corresponding Gaussian mixtures function is obtained with EM algorithm obtains the Gaussian mixtures function;
The output power fluctuation of wind farm value set of random numbers for meeting the Gaussian mixtures function is generated, as
The fluctuation value set obtained in advance.
In conclusion the present invention provides a kind of Power Output for Wind Power Field analogy method and device, by being gone through using wind power plant
History day, output power data determined wind power plant day output power class;The state transfer for obtaining all kinds of wind power plant day output powers is general
Rate matrix and it is all kinds of between wind power plant day output power class between transition probability matrix;It is exported using all kinds of wind power plant days
The state transition probability matrix of power and it is all kinds of between wind power plant day output power class between transition probability matrix generate wind
Electric field output power simulated series;The present invention passes through classification, state transition probability matrix of all categories and the class of day output power
Between transition probability matrix obtain simulated series, reduce the simulated series generated in the prior art there is a problem of jump it is serious,
Improve the accuracy of simulated series.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Finally it should be noted that: the above embodiments are merely illustrative of the technical scheme of the present invention and are not intended to be limiting thereof, to the greatest extent
Invention is explained in detail referring to above-described embodiment for pipe, it should be understood by those ordinary skilled in the art that: still
It can be with modifications or equivalent substitutions are made to specific embodiments of the invention, and without departing from any of spirit and scope of the invention
Modification or equivalent replacement, should all cover within the scope of the claims of the present invention.
Claims (10)
1. a kind of Power Output for Wind Power Field analogy method, which is characterized in that the described method includes:
Wind power plant day output power class is determined using wind power plant history day output power data;
Obtain all kinds of wind power plant day output powers state transition probability matrix and it is all kinds of between wind power plant day output work
Transition probability matrix between the class of rate;
Using all kinds of wind power plant day output powers state transition probability matrix and it is all kinds of between wind power plant day output work
Transition probability matrix generates Power Output for Wind Power Field simulated series between the class of rate.
2. the method as described in claim 1, which is characterized in that described to determine wind using wind power plant history day output power data
Electric field day, output power class included:
Using the characteristic value of each history day output power data of wind power plant as cluster sample, and will be clustered using K-means algorithm
Sample is divided into K class;
Wherein, the characteristic value of the wind power plant history day output power data is the day output power average value of history day wind power plant
With the very poor value of day output power.
3. the method as described in claim 1, which is characterized in that the state for obtaining all kinds of wind power plant day output powers turns
Move probability matrix and it is all kinds of between wind power plant day output power class between transition probability matrix include:
The corresponding output power data of kth class are divided according to each moment output power value in the corresponding output power data of kth class
For N number of state interval;
As the following formula determine kth class wind power plant day output power state transition probability matrix Pk:
In formula, k ∈ [1, K], K are wind power plant day output power class sum,It is gone through for the wind power plant in the state interval m of kth class
History moment output power value is transferred to the probability of state interval n in subsequent time state, and m ∈ [1, N], n ∈ [1, N], N are state
Section sum;
Wherein, determine the wind power plant historical juncture output power value in the kth class in state interval m in subsequent time as the following formula
State is transferred to the probability of state interval n
In formula,Shape is transferred in subsequent time state for the wind power plant historical juncture output power value in state interval m
The number of state section n is enabled as n-m > INT (N/3)INT () is bracket function;
Transition probability matrix P between determining class as the following formulacum:
In formula,F class probability, f ∈ [1, K] are being transferred to next day for kth class wind power plant history day output power data;
Wherein, determine that the kth class wind power plant history day output power data are transferred to f class probability in next day as the following formula
In formula, TkfF class transfer number, T are being transferred to next day for kth class wind power plant history day output power datakFor in
Kth class wind power plant history day output power data count.
4. the method as described in claim 1, which is characterized in that the state using all kinds of wind power plant day output powers turns
Move probability matrix and it is all kinds of between wind power plant day output power class between transition probability matrix generate Power Output for Wind Power Field
Simulated series include:
S1. simulated time day=1 is initialized;
It is random raw if S2. the wind power plant day output power of simulated time day-1 belongs to the wind power plant day output power of r class
At transition probability value y between class1, and compare transition probability value y between class1The transition probability matrix P between classcumIn r row element it is big
It is small;
Wherein, if transition probability value y between class1The transition probability matrix P between classcumIn r row s column element it is equal or be situated between
The transition probability matrix P between classcumIn between the element of r row s column and the element of r row s+1 column, then simulated time day
Wind power plant day output power belong to s class, y1∈ [0,1], r ∈ [1, K], s ∈ [1, K-1], s+1 ∈ [1, K];
S3. the simulation moment t=1 of simulated time day is initialized, the wind power plant that simulated time day-1 is finally simulated the moment is defeated
Power Output for Wind Power Field value of the performance number as simulated time day simulation moment t out, and determine that the Power Output for Wind Power Field value exists
The wind power plant day of s class in output power belonging to state interval m;
S4. t=t+1 is enabled, it is random to generate state transition probability value y2, and compare state transition probability value y2With the wind power plant of s class
The state transition probability matrix P of day output powersIn m row element size;
Wherein, if state transition probability value y2With s class wind power plant day output power state transition probability matrix PsIn m
The element that row n-th arranges is equal or between s class state transition probability matrix PsIn m row n-th arrange element and m row n-th
Between the element of+1 column, then the Power Output for Wind Power Field value of the simulation moment t of simulated time day belongs to state interval n, random raw
At the Power Output for Wind Power Field basic value between the state interval n, wherein y2∈ (0,1], n+1 ∈ [1, N];
S5. undulating value is randomly selected from the fluctuation value set obtained in advance, and is superimposed to simulated time day simulation moment t's
Power Output for Wind Power Field basic value obtains the Power Output for Wind Power Field value of simulated time day simulation moment t, if simulated time day
The Power Output for Wind Power Field value of simulation moment t belongs to state interval n, then goes to S6, otherwise repeatedly S5;
If S6. t=tday, then S7 is gone to, S4 is otherwise gone to, wherein tdayFor the last simulation moment of simulated time day;
If S7. day=Tday, then Power Output for Wind Power Field simulated series are exported, otherwise, enable day=day+1, and go to S2,
In, TdayFor the last simulated time of simulated series.
5. method as claimed in claim 4, which is characterized in that the acquisition process packet of the fluctuation value set obtained in advance
It includes:
The first-order difference amount between each wind power plant historical juncture output power of wind power plant history day output power is calculated, EM is utilized
Algorithm obtains the parameter value of its corresponding Gaussian mixtures function, obtains the Gaussian mixtures function;
The output power fluctuation of wind farm value set of random numbers for meeting the Gaussian mixtures function is generated, as described
The fluctuation value set obtained in advance.
6. a kind of Power Output for Wind Power Field simulator, which is characterized in that described device includes:
Cluster cell, for determining wind power plant day output power class using wind power plant history day output power data;
Matrix determination unit, for obtain all kinds of wind power plant day output powers state transition probability matrix and it is all kinds of between
Wind power plant day output power class between transition probability matrix;
Simulate generation unit, for using all kinds of wind power plant day output powers state transition probability matrix and it is all kinds of between
Wind power plant day output power class between transition probability matrix generate Power Output for Wind Power Field simulated series.
7. device as claimed in claim 6, which is characterized in that the cluster cell is specifically used for:
Using the characteristic value of each history day output power data of wind power plant as cluster sample, and will be clustered using K-means algorithm
Sample is divided into K class;
Wherein, the characteristic value of the wind power plant history day output power data is the day output power average value of history day wind power plant
With the very poor value of day output power.
8. device as claimed in claim 6, which is characterized in that the matrix determination unit includes:
First determining module, is used for:
The corresponding output power data of kth class are divided according to each moment output power value in the corresponding output power data of kth class
For N number of state interval;
As the following formula determine kth class wind power plant day output power state transition probability matrix Pk:
In formula, k ∈ [1, K], K are wind power plant day output power class sum,It is gone through for the wind power plant in the state interval m of kth class
History moment output power value is transferred to the probability of state interval n in subsequent time state, and m ∈ [1, N], n ∈ [1, N], N are state
Section sum;
Wherein, determine the wind power plant historical juncture output power value in the kth class in state interval m in subsequent time as the following formula
State is transferred to the probability of state interval n
In formula,Shape is transferred in subsequent time state for the wind power plant historical juncture output power value in state interval m
The number of state section n is enabled as n-m > INT (N/3)INT () is bracket function;
Second determining module, for determining transition probability matrix P between class as the following formulacum:
In formula,F class probability, f ∈ [1, K] are being transferred to next day for kth class wind power plant history day output power data;
Wherein, determine that the kth class wind power plant history day output power data are transferred to f class probability in next day as the following formula
In formula, TkfF class transfer number, T are being transferred to next day for kth class wind power plant history day output power datakFor in
Kth class wind power plant history day output power data count.
9. device as claimed in claim 6, which is characterized in that the simulation generation unit is specifically used for:
S1. simulated time day=1 is initialized;
It is random raw if S2. the wind power plant day output power of simulated time day-1 belongs to the wind power plant day output power of r class
At transition probability value y between class1, and compare transition probability value y between class1The transition probability matrix P between classcumIn r row element it is big
It is small;
Wherein, if transition probability value y between class1The transition probability matrix P between classcumIn r row s column element it is equal or be situated between
The transition probability matrix P between classcumIn between the element of r row s column and the element of r row s+1 column, then simulated time day
Wind power plant day output power belong to s class, y1∈ [0,1], r ∈ [1, K], s ∈ [1, K-1], s+1 ∈ [1, K];
S3. the simulation moment t=1 of simulated time day is initialized, the wind power plant that simulated time day-1 is finally simulated the moment is defeated
Power Output for Wind Power Field value of the performance number as simulated time day simulation moment t out, and determine that the Power Output for Wind Power Field value exists
The wind power plant day of s class in output power belonging to state interval m;
S4. t=t+1 is enabled, it is random to generate state transition probability value y2, and compare state transition probability value y2With the wind power plant of s class
The state transition probability matrix P of day output powersIn m row element size;
Wherein, if state transition probability value y2With s class wind power plant day output power state transition probability matrix PsIn m
The element that row n-th arranges is equal or between s class state transition probability matrix PsIn m row n-th arrange element and m row n-th
Between the element of+1 column, then the Power Output for Wind Power Field value of the simulation moment t of simulated time day belongs to state interval n, random raw
At the Power Output for Wind Power Field basic value between the state interval n, wherein y2∈ (0,1], n+1 ∈ [1, N];
S5. undulating value is randomly selected from the fluctuation value set obtained in advance, and is superimposed to simulated time day simulation moment t's
Power Output for Wind Power Field basic value obtains the Power Output for Wind Power Field value of simulated time day simulation moment t, if simulated time day
The Power Output for Wind Power Field value of simulation moment t belongs to state interval n, then goes to S6, otherwise repeatedly S5;
If S6. t=tday, then S7 is gone to, S4 is otherwise gone to, wherein tdayFor the last simulation moment of simulated time day;
If S7. day=Tday, then Power Output for Wind Power Field simulated series are exported, otherwise, enable day=day+1, and go to S2,
In, TdayFor the last simulated time of simulated series.
10. device as claimed in claim 9, which is characterized in that the acquisition process packet of the fluctuation value set obtained in advance
It includes:
The first-order difference amount between each wind power plant historical juncture output power of wind power plant history day output power is calculated, EM is utilized
Algorithm obtains the parameter value of its corresponding Gaussian mixtures function, obtains the Gaussian mixtures function;
The output power fluctuation of wind farm value set of random numbers for meeting the Gaussian mixtures function is generated, as described
The fluctuation value set obtained in advance.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910328914.3A CN110222361A (en) | 2019-04-23 | 2019-04-23 | A kind of Power Output for Wind Power Field analogy method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910328914.3A CN110222361A (en) | 2019-04-23 | 2019-04-23 | A kind of Power Output for Wind Power Field analogy method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110222361A true CN110222361A (en) | 2019-09-10 |
Family
ID=67820132
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910328914.3A Pending CN110222361A (en) | 2019-04-23 | 2019-04-23 | A kind of Power Output for Wind Power Field analogy method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110222361A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113449471A (en) * | 2021-06-25 | 2021-09-28 | 东北电力大学 | Wind power output simulation generation method for continuously improving MC (multi-channel) by utilizing AP (access point) clustering-skipping |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107103411A (en) * | 2017-04-08 | 2017-08-29 | 东北电力大学 | Based on the markovian simulation wind power time series generation method of improvement |
CN109636066A (en) * | 2019-01-04 | 2019-04-16 | 广东工业大学 | A kind of wind power output power prediction technique based on fuzzy time series data mining |
-
2019
- 2019-04-23 CN CN201910328914.3A patent/CN110222361A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107103411A (en) * | 2017-04-08 | 2017-08-29 | 东北电力大学 | Based on the markovian simulation wind power time series generation method of improvement |
CN109636066A (en) * | 2019-01-04 | 2019-04-16 | 广东工业大学 | A kind of wind power output power prediction technique based on fuzzy time series data mining |
Non-Patent Citations (1)
Title |
---|
黄越辉等: "基于K-means MCMC算法的中长期风电时间序列建模方法研究", 《电网技术》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113449471A (en) * | 2021-06-25 | 2021-09-28 | 东北电力大学 | Wind power output simulation generation method for continuously improving MC (multi-channel) by utilizing AP (access point) clustering-skipping |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104077632B (en) | A kind of wind electric field power prediction method based on deep neural network | |
CN103390116B (en) | Use the photovoltaic power station power generation power forecasting method of stepping mode | |
CN107909211B (en) | Wind field equivalent modeling and optimization control method based on fuzzy c-means clustering algorithm | |
CN109145957A (en) | The identification and processing method and processing device of power distribution network abnormal index based on big data | |
CN106786560A (en) | A kind of power system stability characteristic automatic extraction method and device | |
CN110287942A (en) | Training method, age estimation method and the corresponding device of age estimation model | |
CN112186761A (en) | Wind power scene generation method and system based on probability distribution | |
CN108132441A (en) | The range of operation of energy-storage battery module state-of-charge determines method and device | |
CN108133279A (en) | Wind power probability forecasting method, storage medium and equipment | |
CN106503279A (en) | A kind of modeling method for transient stability evaluation in power system | |
CN110222361A (en) | A kind of Power Output for Wind Power Field analogy method and device | |
CN109711612A (en) | A kind of Wind power forecasting method and device optimizing echo state network | |
CN111680823A (en) | Wind direction information prediction method and system | |
CN117318018A (en) | Short-term prediction method and system for wind power output | |
CN111242266A (en) | Operation data management system | |
CN109816149A (en) | A kind of wind power plant is contributed scene generating method and device at random | |
CN116010831A (en) | Combined clustering scene reduction method and system based on potential decision result | |
CN106897771B (en) | New energy sample board machine selection method and system based on chaotic genetic algorithm | |
CN115600494A (en) | Low-voltage distribution area topology automatic identification method and device | |
CN115860190A (en) | Training of load detection model, method for detecting power load and related device | |
Özkan et al. | A data mining-based wind power forecasting method: results for wind power plants in turkey | |
CN111553040B (en) | Power grid topology analysis high-performance computing method and device based on GPU acceleration | |
CN110648248B (en) | Control method, device and equipment for power station | |
CN113806077A (en) | Data center server regulation and control method and device based on artificial intelligence | |
CN110943473A (en) | Generator coherence identification method based on wide area measurement system and clustering theory |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190910 |