CN108764335A - Method and device for generating typical scene of multi-energy demand of comprehensive energy system - Google Patents
Method and device for generating typical scene of multi-energy demand of comprehensive energy system Download PDFInfo
- Publication number
- CN108764335A CN108764335A CN201810524561.XA CN201810524561A CN108764335A CN 108764335 A CN108764335 A CN 108764335A CN 201810524561 A CN201810524561 A CN 201810524561A CN 108764335 A CN108764335 A CN 108764335A
- Authority
- CN
- China
- Prior art keywords
- cluster
- vector
- energy requirement
- cluster centre
- typical scene
- 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 47
- 239000013598 vector Substances 0.000 claims abstract description 114
- 238000011156 evaluation Methods 0.000 claims abstract description 21
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000010438 heat treatment Methods 0.000 claims description 5
- 238000010168 coupling process Methods 0.000 claims description 4
- 238000005859 coupling reaction Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 240000002853 Nelumbo nucifera Species 0.000 description 3
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 3
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012804 iterative process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 1
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012546 transfer 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for generating a typical scene of multi-energy demand of an integrated energy system, wherein the method comprises the following steps: s1: acquiring a multi-energy demand load vector of each day to obtain a vector set; s2: if the iteration instruction is acquired, executing S3, and if the evaluation instruction is acquired, executing S4; s3: in each iteration, determining a corresponding number of clustering centers in a vector set until the difference between the clustering error square of the current iteration and the clustering error square of the last iteration is judged to be less than a preset value, and determining all clustering centers of the current iteration to be typical scenes; s4: and acquiring a value range of the number of the cluster centers, determining the cluster centers with corresponding number in the vector set according to each value in the value range, calculating a cluster evaluation index corresponding to each value, and determining all the cluster centers corresponding to the minimum cluster evaluation index as a typical scene. The typical scene generated by the method can comprehensively and accurately analyze the comprehensive energy system.
Description
Technical field
The present invention relates to integrated energy system fields more particularly to a kind of integrated energy system multi-energy requirement typical scene to give birth to
At method and device.
Background technology
Integrated energy system is related to production, transfer and the consumption of the various energy resources such as electric, hot, cold, gas.In integrated energy system
Planning stage and operation mode design phase etc. are required to carry out it a large amount of Simulation Analysis, can portray comprehensive energy
The typical scene of system multi-energy requirement is these Simulation Analysis necessity input datas.
However, if all analyzed annual load data, computation burden can be significantly greatly increased and without generally representing
Property.More scene analysis technologies reduce the similar scene in corresponding time scale by data analysis, have efficiently extracted several
Typical day scene, convergence effect is preferable, avoids cumbersome calculating, alleviates the burden of system-computed analysis.
It is more mature to the method for the scenario building of power load at present, mainly by " rich big, rich small, withered big, withered
It is small " or the input of the extreme scenes as simulation model such as " summer is big, the summer is small, the winter is big, winter small ", it is negative in difference to analyze electric system
Problems faced under lotus scene, but this mode consider a problem it is overly conservative, for pursue economic benefit based on synthesis energy
Source system is more suitable in terms of system run all right and reliability only in the case where analyzing extreme event, but is simulated to long-term operation
With economic analysis and be not suitable for, it is difficult to obtain the solution of closing to reality on probability.
Invention content
An embodiment of the present invention provides a kind of integrated energy system multi-energy requirement typical scene generation method and devices, can
Generate the typical scene for carrying out comprehensive reliable analysis to integrated energy system.
According to an aspect of the present invention, a kind of integrated energy system multi-energy requirement typical scene generation method is provided, is wrapped
It includes:
S1:The multi-energy requirement load vector for getting each day, obtains vectorial set;
S2:If obtaining iterative instruction, S3 is executed, if obtaining assessment instruction, executes S4;
S3:In each iteration, the cluster centre of corresponding number is determined in the vector set, until judging current
The difference of the cluster square-error of the cluster square-error of secondary iteration and last iteration is less than preset value, it is determined that works as previous iteration
All cluster centres be typical scene;
S4:The value range for obtaining cluster centre number, in the value range, according to each value in the vector
The cluster centre of corresponding number is determined in set, and calculates the corresponding cluster evaluation index of each value, determines that minimum cluster is commented
It is typical scene to estimate the corresponding all cluster centres of index.
Preferably, the multi-energy requirement load vector is born by the gas turbine heating load of each period, user's electricity in one day
Lotus and garden are formed with cold demand.
It is preferably, described that the cluster centre of corresponding number is determined in all vector set in each iteration,
Until judging that the difference of the cluster square-error when the cluster square-error and last iteration of previous iteration is less than preset value, then really
All cluster centres of settled previous iteration specifically include for typical scene:
S31:Iterations N=1 is initialized, the cluster centre of corresponding number is determined in the vector set, and to poly-
Class center is updated, then to updated cluster centre calculate the cluster square-error of iv-th iteration;
S32:Iterations N=N+1 is enabled, the cluster centre of corresponding number is determined in the vector set, and to cluster
Center is updated, then to updated cluster centre calculate the cluster square-error of iv-th iteration;
S33:Judge whether the difference of the cluster square-error when the cluster square-error and last iteration of previous iteration is small
In preset value, if being not less than, S32 is re-executed, if being less than, executes S34;
S34:Determine that all cluster centres when previous iteration are typical scene.
Preferably, the calculation formula of the cluster square-error is:
In formula, K is the corresponding cluster centre number of iteration each time, njFor the multi-energy requirement load vector number of jth class,
mjFor the cluster centre that the cluster centre to jth class is updated, xiFor i-th of multi-energy requirement load vector of jth class.
Preferably, described to determine that the cluster centre of corresponding number specifically includes in the vector set:
T0:I=1 is enabled, and obtains constant M and cluster centre number K;
T1:In the vector set, the distance between vector two-by-two is calculated;
T2:It determines all distances with i-th of multi-energy requirement load vector correlation, and by being ranked up from small to large, takes
Density parameter of the m-th distance as i-th of multi-energy requirement load vector;
T3:I=i+1 is enabled, step T2 is re-executed, until determining the density parameter of all multi-energy requirement load vectors;
T4:All multi-energy requirement load vectors are ranked up from small to large by density parameter, by row in institute's directed quantity
Sequence takes the vector of preset proportion, obtains high density vector set;
T5:The multi-energy requirement load vector of density parameter minimum is determined as first cluster centre;
T6:In the high density vector set, calculate between each vector and each fixed cluster centre away from
From, minimum range corresponding with fixed each cluster centre is taken, is maximized in all minimum ranges, it will be maximum
It is worth corresponding multi-energy requirement load vector to increase as new cluster centre;
T7:Judge whether the number of cluster centre equal to K re-executes T6 if being not equal to, if being equal to, terminates.
Preferably, the distance is Euclidean distance.
Preferably, the calculation formula of the cluster evaluation index is:
dij=| | zi-zj||
In formula, SiIndicate degree of scatter vectorial in ith cluster, SjIndicate the degree of scatter of vector in j-th of cluster,
dijIndicate that the distance between ith cluster and j-th of cluster, K values are cluster number, CiFor ith cluster, niIt is poly- for i-th
The vectorial number of class.
According to another aspect of the present invention, a kind of integrated energy system multi-energy requirement typical scene generating means are provided, are wrapped
It includes:
First acquisition module, the multi-energy requirement load vector for getting each day, obtains vectorial set;
If second acquisition module triggers the first determining module for obtaining iterative instruction, if obtaining assessment instruction,
Trigger the second determining module;
First determining module, in each iteration, being determined in the vector set in the cluster of corresponding number
The heart, until judge that the difference of the cluster square-error when the cluster square-error and last iteration of previous iteration is less than preset value,
Then determine that all cluster centres when previous iteration are typical scene;
Second determining module, the value range for obtaining cluster centre number, in the value range, according to each
Value determines the cluster centre of corresponding number in the vector set, and calculates the corresponding cluster evaluation index of each value,
Determine that the corresponding all cluster centres of minimum cluster evaluation index are typical scene.
According to another aspect of the present invention, a kind of integrated energy system multi-energy requirement typical scene generating means are provided, are wrapped
It includes:Memory, and it is coupled to the processor of the memory;
The processor is configured as, based on the instruction being stored in the memory devices, executing as described above comprehensive
Close energy resource system multi-energy requirement typical scene generation method.
According to another aspect of the present invention, a kind of computer-readable medium is provided, computer program is stored thereon with, the journey
Above-described integrated energy system multi-energy requirement typical scene generation method is realized when sequence is executed by processor.
As can be seen from the above technical solutions, the embodiment of the present invention has the following advantages:
The present invention provides a kind of integrated energy system multi-energy requirement typical scene generation method and devices, wherein the party
Method includes:S1:The multi-energy requirement load vector for getting each day, obtains vectorial set;S2:If obtaining iterative instruction, execute
S3 executes S4 if obtaining assessment instruction;S3:In each iteration, in determining the cluster of corresponding number during vector is gathered
The heart, until judge that the difference of the cluster square-error when the cluster square-error and last iteration of previous iteration is less than preset value,
Then determine that all cluster centres when previous iteration are typical scene;S4:The value range for obtaining cluster centre number, in value
In range, the cluster centre of corresponding number is determined in vector is gathered according to each value, and calculate the corresponding collection of each value
Group's evaluation index determines that the corresponding all cluster centres of minimum cluster evaluation index are typical scene.The present invention passes through two kinds of sides
Formula generates the typical scene for being analyzed integrated energy system, when obtaining the instruction without limitation scene number, then leads to
The number for crossing cluster centre is iterated and then generates typical scene, when obtaining the instruction of limitation scene number value range,
Then by accordingly carrying out cluster assessment to each value, and then generate typical scene.The typical case that method through the invention generates
Scene, can comprehensively, accurately integrated energy system is analyzed.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention without having to pay creative labor, may be used also for those of ordinary skill in the art
To obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of one embodiment of integrated energy system multi-energy requirement typical scene generation method provided by the invention
Flow diagram;
Fig. 2 is a kind of another implementation of integrated energy system multi-energy requirement typical scene generation method provided by the invention
The flow diagram of example;
Fig. 3 is a kind of one embodiment of integrated energy system multi-energy requirement typical scene generating means provided by the invention
Structural schematic diagram.
Specific implementation mode
An embodiment of the present invention provides a kind of integrated energy system multi-energy requirement typical scene generation method and devices, can
Generate the typical scene for carrying out comprehensive reliable analysis to integrated energy system.
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that disclosed below
Embodiment be only a part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
All other embodiment that those of ordinary skill is obtained without making creative work, belongs to protection of the present invention
Range.
Referring to Fig. 1, one of a kind of integrated energy system multi-energy requirement typical scene generation method provided by the invention
Embodiment, including:
101, the multi-energy requirement load vector for getting each day, obtains vectorial set;
If 102, obtaining iterative instruction, 103 are executed, if obtaining assessment instruction, executes 104;
103, in each iteration, the cluster centre of corresponding number is determined in vector is gathered, until judging when previous
The difference of the cluster square-error of the cluster square-error of iteration and last iteration is less than preset value, it is determined that when previous iteration
All cluster centres are typical scene;
104, the value range for obtaining cluster centre number, in value range, according to each value in vector is gathered
It determines the cluster centre of corresponding number, and calculates the corresponding cluster evaluation index of each value, determine minimum cluster evaluation index
Corresponding all cluster centres are typical scene.
The present invention generates the typical scene for being analyzed integrated energy system by two ways, unlimited when obtaining
When the instruction of scene number processed, then typical scene is generated by the number of cluster centre is iterated, when acquisition limiting field
When the instruction of scape number value range, then by accordingly carrying out cluster assessment to each value, and then typical scene is generated.Pass through
The present invention method generate typical scene, can comprehensively, accurately integrated energy system is analyzed.
It is above a kind of one embodiment of integrated energy system multi-energy requirement typical scene generation method, to be had more
The explanation of body is provided below a kind of another embodiment of integrated energy system multi-energy requirement typical scene generation method, please join
Read Fig. 2, a kind of another embodiment of integrated energy system multi-energy requirement typical scene generation method provided by the invention, packet
It includes:
201, the multi-energy requirement load vector for getting each day, obtains vectorial set;
In the present embodiment, in order to facilitate more scene analysis, the definition for having unified to data object is needed, by multi-energy requirement
Load vector be defined as that the cold demand in gas turbine heating load, user's electric load and the garden of each period in one day forms to
Amount:
In formula, T is total period in one day, and n is the total number of days of statistics of initial scene, and i is to belong to a certain in n days set
It, H is the heating load of gas turbine, and L is user's electric load, and C is the cold demand of use of garden.
If 202, obtaining iterative instruction, 203 are executed, if obtaining assessment instruction, executes 207;
In the present embodiment, typical scene is sought can generating by two ways.The first is not provided with scene quantity
The upper limit, second be by give scene quantity be arranged a value range, carry out exploration assessment.It is understood that working as
When getting iterative instruction, then the first scene acquiring method is carried out, when getting assessment instruction, then carries out second of scene
Acquiring method.
203, iterations N=1 is initialized, the cluster centre of corresponding number is determined in vector is gathered, and in cluster
The heart is updated, then to updated cluster centre calculate the cluster square-error of iv-th iteration;
204, iterations N=N+1 is enabled, the cluster centre of corresponding number is determined in vector is gathered, and to cluster centre
It is updated, then to updated cluster centre calculate the cluster square-error of iv-th iteration;
205, judge whether the difference of the cluster square-error when the cluster square-error and last iteration of previous iteration is small
In preset value, if being not less than, 204 are re-executed, if being less than, executes 206;
206, determine that all cluster centres when previous iteration are typical scene;
Step 203 to step 206 is the first scene acquiring method (i.e. iterative process), in the present embodiment, cluster
The calculation formula (criterion function) of square-error is:
In formula, K is the corresponding cluster centre number of iteration each time, njFor the multi-energy requirement load vector number of jth class,
mjFor the cluster centre that the cluster centre to jth class is updated, xiFor i-th of multi-energy requirement load vector of jth class.
In the above iterative process, the cluster centre quantity of iteration is arranged in advance each time, and each iteration
Cluster centre quantity is and other are secondary inconsistent, common, can increase cluster centre quantity with the increase of iterations
Add, or other set-up modes are not specifically limited herein.
In an iterative process, first time iteration only generates corresponding cluster centre and calculates corresponding cluster square-error,
Since second of iteration, then start to calculate the difference for clustering square-error between iteration twice, such as when previous iteration is second
When secondary iteration, then the difference of the cluster square-error of second of iteration cluster square-error and first time iteration is calculated, judges difference
Whether convergence criterion is met, if meeting criterion, it is determined that the cluster centre of second of grey iterative generation is typical scene, if discontented
Foot, then continue third time iteration.
In the present invention, the general formula for calculating the difference of the cluster square-error of iteration twice is:
Δ J=| Jc(iter+1)-Jc(iter) | (iter=0,1,2 ...)
In formula, iter is cluster iterations, is sequence of natural numbers.In the present invention, J is definedc(0)=0.It needs to illustrate
, when Δ J is less than preset value, that is, determine that the criterion function when previous iteration is restrained, therefore, when gathering for previous grey iterative generation
The typical scene that class center as finally determines.
207, the value range for obtaining cluster centre number, in value range, according to each value in vector is gathered
It determines the cluster centre of corresponding number, and calculates the corresponding cluster evaluation index of each value, determine minimum cluster evaluation index
Corresponding all cluster centres are typical scene.
The calculation formula of cluster evaluation index is:
Dij=| | zi-zj||
In formula, SiIndicate degree of scatter vectorial in ith cluster, SjIndicate the degree of scatter of vector in j-th of cluster,
dijIndicate that the distance between ith cluster and j-th of cluster, K values are cluster number, CiFor ith cluster, niIt is poly- for i-th
The vectorial number of class.
It is understood that the value range of cluster centre number can be a value set, i.e., the collection of different K values
It closes, after each K values correspond to and generate respective cluster centre, the corresponding cluster of each K values can be calculated by above formula and commented
Estimate index, the fine or not key for evaluating Clustering Effect is that the data similarity in class is higher, and discrimination is relatively low, on the contrary, between class
Data field indexing is higher, and similarity is relatively low.It is, DBI is smaller, then show that Clustering Effect is better.Therefore the minimum index value of selection
Corresponding K values, the typical scene that the cluster centre generated as finally determines.
Either the first scene acquiring method or second of scene acquiring method determine corresponding in vector is gathered
The process of several cluster centres is specially:
T0:I=1 is enabled, and obtains constant M and cluster centre number K;
It should be noted that constant M is used to determine the density parameter of each vector, and cluster centre number K then can root
Determined according to situation, if the first scene acquiring method, into each iteration can corresponding true defining K value, and in second of scene
In acquiring method, multiple assignment can be carried out to K in value range.
T1:In vector is gathered, the distance between vector two-by-two is calculated;
In the present embodiment, which is Euclidean distance:
D=| | xi-xj||2i,j∈(1,2,…,n)j≠i
In formula, | | | |2For two norm oeprators, i.e. Euclidean distance operation.
T2:It determines all distances with i-th of multi-energy requirement load vector correlation, and by being ranked up from small to large, takes
Density parameter of the m-th distance as i-th of multi-energy requirement load vector;
It is understood that by multi-energy requirement load vector xiWith xj(j=1's, 2 ..., n, j ≠ i) arranges apart from ascending order,
M-th distance is used as x in sortingiDensity parameter εi。
T3:I=i+1 is enabled, step T2 is re-executed, until determining the density parameter of all multi-energy requirement load vectors;
T4:All multi-energy requirement load vectors are ranked up from small to large by density parameter, by row in institute's directed quantity
Sequence takes the vector of preset proportion, obtains high density vector set;
It should be noted that by institute's directed quantity by density parameter by being ranked up from small to large after, these vector in the past
Face takes the vector of preset proportion as high density vector set.
T5:The multi-energy requirement load vector of density parameter minimum is determined as first cluster centre;
T6:In high density vector set, the distance between each vector and each fixed cluster centre are calculated, is taken
Minimum range corresponding with fixed each cluster centre, is maximized in all minimum ranges, and maximum value is corresponding
Multi-energy requirement load vector increases as new cluster centre;
It should be noted that when only determining first cluster centre z1When, second cluster centre z2It then can be by each
Vector and z1The distance between determine, be minimized in multiple distances, the minimum value it is corresponding vector be second cluster
Center z2.Then third cluster centre then first needs to calculate each vector and z1、z2The distance between, respectively in z1With other to
It is minimized in all distance values between amount, in z2All distance values between other vectors are minimized, finally two
It is maximized between a minimum value, the corresponding vector of the maximum value is third cluster centre z3, subsequent cluster centre with
This analogizes, and details are not described herein again.Its general formula is:
max(min(d(xi,z1)),min(d(xi,z2)),...,min(d(xi,zj-1)))。
T7:Judge whether the number of cluster centre equal to K re-executes T6 if being not equal to, if being equal to, terminates.
Be above a kind of integrated energy system multi-energy requirement typical scene generation method provided by the invention is carried out it is detailed
It describes in detail bright, a kind of integrated energy system multi-energy requirement typical scene generating means provided by the invention will be illustrated below,
Referring to Fig. 3, a kind of one embodiment of integrated energy system multi-energy requirement typical scene generating means provided by the invention, packet
It includes:
First acquisition module 301, the multi-energy requirement load vector for getting each day, obtains vectorial set;
If second acquisition module 302 triggers the first determining module 303 for obtaining iterative instruction, refers to if obtaining assessment
It enables, then triggers the second determining module 304;
First determining module 303, in each iteration, being determined in vector set in the cluster of corresponding number
The heart, until judge that the difference of the cluster square-error when the cluster square-error and last iteration of previous iteration is less than preset value,
Then determine that all cluster centres when previous iteration are typical scene;
Second determining module 304, the value range for obtaining cluster centre number, in value range, according to each
Value determines the cluster centre of corresponding number in vector is gathered, and calculates the corresponding cluster evaluation index of each value, determines
The corresponding all cluster centres of minimum cluster evaluation index are typical scene.
Optionally, multi-energy requirement load vector by the gas turbine heating load of each period in one day, user's electric load and
Garden is formed with cold demand.
Optionally, the first determining module 303 includes:
Initialization submodule, for initializing iterations N=1, in determining the cluster of corresponding number during vector is gathered
The heart, and cluster centre is updated, then to updated cluster centre calculate the cluster square-error of iv-th iteration;
Iteration submodule determines the cluster centre of corresponding number for enabling iterations N=N+1 in vector is gathered, and
Cluster centre is updated, then to updated cluster centre calculate the cluster square-error of iv-th iteration;
Judging submodule, for judging the cluster square-error when the cluster square-error and last iteration of previous iteration
Difference whether be less than preset value, if being not less than, retriggered iteration submodule triggers determination sub-module if being less than;
Determination sub-module, for determining that all cluster centres when previous iteration are typical scene.
Optionally, the calculation formula for clustering square-error is:
In formula, K is that the corresponding cluster centre number of iteration, nj are the multi-energy requirement load vector number of jth class each time,
Mj is the cluster centre being updated to the cluster centre of jth class, xiFor i-th of multi-energy requirement load vector of jth class.
Optionally, initialization submodule, iteration submodule and the second determining module include:Determination unit, for
The cluster centre of corresponding number is determined in duration set;
Determination unit includes:
Subelement is obtained, for enabling i=1, and obtains constant M and cluster centre number K;
Computation subunit calculates the distance between vector two-by-two used in gathering in vector;
First sorting subunit for determining all distances with i-th of multi-energy requirement load vector correlation, and is pressed from small
To being ranked up greatly, density parameter of the m-th distance as i-th of multi-energy requirement load vector is taken;
Subelement is recycled, for enabling i=i+1, the first sorting subunit of retriggered, until determining that all multi-energy requirements are negative
The density parameter of lotus vector;
Second sorting subunit, for all multi-energy requirement load vectors to be ranked up from small to large by density parameter,
The vector for taking preset proportion by sequence in institute's directed quantity, obtains high density vector set;
Determination subelement, for the multi-energy requirement load vector of density parameter minimum to be determined as first cluster centre;
Increase subelement, in high density vector set, calculating each vector and each fixed cluster centre
The distance between, minimum range corresponding with fixed each cluster centre is taken, is maximized in all minimum ranges, it will
The corresponding multi-energy requirement load vector of maximum value increases as new cluster centre;
Judgment sub-unit, for judging whether the number of cluster centre is equal to K, if being not equal to, retriggered increases son
Unit terminates if being equal to.
Optionally, distance is Euclidean distance.
Optionally, the calculation formula of cluster evaluation index is:
dij=| | zi-zj||
In formula, SiIndicate degree of scatter vectorial in ith cluster, SjIndicate the degree of scatter of vector in j-th of cluster,
dijIndicate that the distance between ith cluster and j-th of cluster, K values are cluster number, CiFor ith cluster, niIt is poly- for i-th
The vectorial number of class.
A kind of another embodiment of integrated energy system multi-energy requirement typical scene generating means provided by the invention, packet
It includes:Memory, and it is coupled to the processor of the memory;
The processor is configured as, based on the instruction being stored in the memory devices, executing as described above comprehensive
Close energy resource system multi-energy requirement typical scene generation method.
The invention further relates to a kind of computer-readable mediums, are stored thereon with computer program, which is held by processor
Above-described integrated energy system multi-energy requirement typical scene generation method is realized when row.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be the indirect coupling by some interfaces, device or unit
It closes or communicates to connect, can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can be stored in a computer read/write memory medium.Based on this understanding, technical scheme of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) executes the complete of each embodiment the method for the present invention
Portion or part steps.And storage medium above-mentioned includes:USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although with reference to before
Stating embodiment, invention is explained in detail, it will be understood by those of ordinary skill in the art that:It still can be to preceding
The technical solution recorded in each embodiment is stated to modify or equivalent replacement of some of the technical features;And these
Modification or replacement, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of integrated energy system multi-energy requirement typical scene generation method, which is characterized in that including:
S1:The multi-energy requirement load vector for getting each day, obtains vectorial set;
S2:If obtaining iterative instruction, S3 is executed, if obtaining assessment instruction, executes S4;
S3:In each iteration, the cluster centre of corresponding number is determined in the vector is gathered, until judging to change when previous
The difference of the cluster square-error of the cluster square-error in generation and last iteration is less than preset value, it is determined that when the institute of previous iteration
It is typical scene to have cluster centre;
S4:The value range for obtaining cluster centre number is gathered according to each value in the vector in the value range
The cluster centre of middle determining corresponding number, and the corresponding cluster evaluation index of each value is calculated, determine that minimum cluster assessment refers to
It is typical scene to mark corresponding all cluster centres.
2. integrated energy system multi-energy requirement typical scene generation method according to claim 1, which is characterized in that described
Multi-energy requirement load vector is by the cold requirement groups in the gas turbine heating load of each period, user's electric load and garden in one day
At.
3. integrated energy system multi-energy requirement typical scene generation method according to claim 1, which is characterized in that described
In each iteration, the cluster centre of corresponding number is determined in all vector set, until judging to work as previous iteration
Cluster square-error and the difference of cluster square-error of last iteration be less than preset value, it is determined that it is all when previous iteration
Cluster centre specifically includes for typical scene:
S31:Iterations N=1 is initialized, the cluster centre of corresponding number is determined in the vector set, and in cluster
The heart is updated, then to updated cluster centre calculate the cluster square-error of iv-th iteration;
S32:Iterations N=N+1 is enabled, the cluster centre of corresponding number is determined in the vector set, and to cluster centre
It is updated, then to updated cluster centre calculate the cluster square-error of iv-th iteration;
S33:It is pre- to judge whether the difference when the cluster square-error of the cluster square-error and last iteration of previous iteration is less than
If value, if being not less than, re-executes S32, if being less than, executes S34;
S34:Determine that all cluster centres when previous iteration are typical scene.
4. integrated energy system multi-energy requirement typical scene generation method according to claim 3, which is characterized in that described
Cluster square-error calculation formula be:
In formula, K is the corresponding cluster centre number of iteration each time, njFor the multi-energy requirement load vector number of jth class, mjFor
To the cluster centre that the cluster centre of jth class is updated, xiFor i-th of multi-energy requirement load vector of jth class.
5. integrated energy system multi-energy requirement typical scene generation method according to any one of claims 1 to 4, special
Sign is, described to determine that the cluster centre of corresponding number specifically includes in the vector set:
T0:I=1 is enabled, and obtains constant M and cluster centre number K;
T1:In the vector set, the distance between vector two-by-two is calculated;
T2:It determines all distances with i-th of multi-energy requirement load vector correlation, and by being ranked up from small to large, takes m-th
Density parameter of the distance as i-th of multi-energy requirement load vector;
T3:I=i+1 is enabled, step T2 is re-executed, until determining the density parameter of all multi-energy requirement load vectors;
T4:All multi-energy requirement load vectors are ranked up from small to large by density parameter, are taken by sequence in institute's directed quantity
The vector of preset proportion obtains high density vector set;
T5:The multi-energy requirement load vector of density parameter minimum is determined as first cluster centre;
T6:In the high density vector set, the distance between each vector and each fixed cluster centre are calculated, is taken
Minimum range corresponding with fixed each cluster centre, is maximized in all minimum ranges, by maximum value pair
The multi-energy requirement load vector answered increases as new cluster centre;
T7:Judge whether the number of cluster centre equal to K re-executes T6 if being not equal to, if being equal to, terminates.
6. the integrated energy system multi-energy requirement typical scene generation method according to claim 5 any one, feature
It is, the distance is Euclidean distance.
7. integrated energy system multi-energy requirement typical scene generation method according to claim 1, which is characterized in that described
The calculation formula of cluster evaluation index is:
dij=| | zi-zj||
In formula, SiIndicate degree of scatter vectorial in ith cluster, SjIndicate the degree of scatter of vector in j-th of cluster, dijTable
Show that the distance between ith cluster and j-th of cluster, K values are cluster number, CiFor ith cluster, niFor ith cluster to
Measure number.
8. a kind of integrated energy system multi-energy requirement typical scene generating means, which is characterized in that including:
First acquisition module, the multi-energy requirement load vector for getting each day, obtains vectorial set;
If second acquisition module triggers the first determining module for obtaining iterative instruction, if obtaining assessment instruction, triggers
Second determining module;
First determining module, in each iteration, the cluster centre of corresponding number being determined in the vector set, directly
It is less than preset value to the difference for judging the cluster square-error when the cluster square-error and last iteration of previous iteration, it is determined that
When all cluster centres of previous iteration are typical scene;
Second determining module, the value range for obtaining cluster centre number, in the value range, according to each value
The cluster centre of corresponding number is determined in the vector set, and calculates the corresponding cluster evaluation index of each value, is determined
The corresponding all cluster centres of minimum cluster evaluation index are typical scene.
9. a kind of integrated energy system multi-energy requirement typical scene generating means, which is characterized in that including:Memory and coupling
It is connected to the processor of the memory;
The processor is configured as, based on the instruction being stored in the memory devices, executing as claim 1 to 7 is arbitrary
Integrated energy system multi-energy requirement typical scene generation method described in one.
10. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that the program is executed by processor
Integrated energy system multi-energy requirement typical scene generation method described in Shi Shixian claim 1 to 7 any one.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810524561.XA CN108764335A (en) | 2018-05-28 | 2018-05-28 | Method and device for generating typical scene of multi-energy demand of comprehensive energy system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810524561.XA CN108764335A (en) | 2018-05-28 | 2018-05-28 | Method and device for generating typical scene of multi-energy demand of comprehensive energy system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108764335A true CN108764335A (en) | 2018-11-06 |
Family
ID=64002803
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810524561.XA Pending CN108764335A (en) | 2018-05-28 | 2018-05-28 | Method and device for generating typical scene of multi-energy demand of comprehensive energy system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108764335A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109685348A (en) * | 2018-12-14 | 2019-04-26 | 广东电网有限责任公司 | A kind of power equipment typical mode of operation determines method |
CN110009527A (en) * | 2019-04-04 | 2019-07-12 | 国家电网有限公司 | A kind of integrated energy system user portrait method and system |
CN110046801A (en) * | 2019-03-25 | 2019-07-23 | 国网江苏省电力有限公司经济技术研究院 | A kind of typical scene generation method of power distribution network electric system |
CN112132111A (en) * | 2020-10-10 | 2020-12-25 | 安徽江淮汽车集团股份有限公司 | Parking typical scene extraction method, device, storage medium and device |
CN112258233A (en) * | 2020-10-22 | 2021-01-22 | 国网新疆电力有限公司经济技术研究院 | Method and device for site selection and capacity determination of regional comprehensive energy station |
CN112560174A (en) * | 2020-12-08 | 2021-03-26 | 中国航天空气动力技术研究院 | Static aeroelasticity low dynamic test data extraction method, device, medium and equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110055212A1 (en) * | 2009-09-01 | 2011-03-03 | Cheng-Fa Tsai | Density-based data clustering method |
CN102819677A (en) * | 2012-07-30 | 2012-12-12 | 河海大学 | Rainfall site similarity evaluation method on basis of single rainfall type |
US20160004762A1 (en) * | 2014-07-07 | 2016-01-07 | Edward-Robert Tyercha | Hilbert Curve Partitioning for Parallelization of DBSCAN |
CN105574642A (en) * | 2015-11-06 | 2016-05-11 | 广东工业大学 | Smart grid big data-based electricity price execution checking method |
CN106021361A (en) * | 2016-05-10 | 2016-10-12 | 中国空间技术研究院 | Sequence alignment-based self-adaptive application layer network protocol message clustering method |
CN106649877A (en) * | 2017-01-06 | 2017-05-10 | 广东工业大学 | Density peak-based big data mining method and apparatus |
-
2018
- 2018-05-28 CN CN201810524561.XA patent/CN108764335A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110055212A1 (en) * | 2009-09-01 | 2011-03-03 | Cheng-Fa Tsai | Density-based data clustering method |
CN102819677A (en) * | 2012-07-30 | 2012-12-12 | 河海大学 | Rainfall site similarity evaluation method on basis of single rainfall type |
US20160004762A1 (en) * | 2014-07-07 | 2016-01-07 | Edward-Robert Tyercha | Hilbert Curve Partitioning for Parallelization of DBSCAN |
CN105574642A (en) * | 2015-11-06 | 2016-05-11 | 广东工业大学 | Smart grid big data-based electricity price execution checking method |
CN106021361A (en) * | 2016-05-10 | 2016-10-12 | 中国空间技术研究院 | Sequence alignment-based self-adaptive application layer network protocol message clustering method |
CN106649877A (en) * | 2017-01-06 | 2017-05-10 | 广东工业大学 | Density peak-based big data mining method and apparatus |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109685348A (en) * | 2018-12-14 | 2019-04-26 | 广东电网有限责任公司 | A kind of power equipment typical mode of operation determines method |
CN110046801A (en) * | 2019-03-25 | 2019-07-23 | 国网江苏省电力有限公司经济技术研究院 | A kind of typical scene generation method of power distribution network electric system |
CN110046801B (en) * | 2019-03-25 | 2023-07-21 | 国网江苏省电力有限公司经济技术研究院 | Typical scene generation method of power distribution network power system |
CN110009527A (en) * | 2019-04-04 | 2019-07-12 | 国家电网有限公司 | A kind of integrated energy system user portrait method and system |
CN112132111A (en) * | 2020-10-10 | 2020-12-25 | 安徽江淮汽车集团股份有限公司 | Parking typical scene extraction method, device, storage medium and device |
CN112258233A (en) * | 2020-10-22 | 2021-01-22 | 国网新疆电力有限公司经济技术研究院 | Method and device for site selection and capacity determination of regional comprehensive energy station |
CN112258233B (en) * | 2020-10-22 | 2024-05-31 | 国网新疆电力有限公司经济技术研究院 | Method and device for determining site selection and capacity of regional comprehensive energy station |
CN112560174A (en) * | 2020-12-08 | 2021-03-26 | 中国航天空气动力技术研究院 | Static aeroelasticity low dynamic test data extraction method, device, medium and equipment |
CN112560174B (en) * | 2020-12-08 | 2022-12-02 | 中国航天空气动力技术研究院 | Static aeroelasticity low dynamic test data extraction method, device, medium and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108764335A (en) | Method and device for generating typical scene of multi-energy demand of comprehensive energy system | |
CN110163258A (en) | A kind of zero sample learning method and system reassigning mechanism based on semantic attribute attention | |
CN113393474B (en) | Feature fusion based three-dimensional point cloud classification and segmentation method | |
CN103258210B (en) | A kind of high-definition image classification method based on dictionary learning | |
CN104820905A (en) | Space trajectory big data analysis-based person management and control method and system | |
CN105044662A (en) | Fingerprint clustering multi-point joint indoor positioning method based on WIFI signal intensity | |
CN110298035A (en) | Word vector based on artificial intelligence defines method, apparatus, equipment and storage medium | |
CN103886048A (en) | Cluster-based increment digital book recommendation method | |
CN110119144A (en) | Based on the matched multirobot SLAM algorithm of sub- map feature | |
CN103440471B (en) | The Human bodys' response method represented based on low-rank | |
CN109815541B (en) | Method and device for dividing rail transit vehicle product parts and modules and electronic equipment | |
CN112199532A (en) | Zero sample image retrieval method and device based on Hash coding and graph attention machine mechanism | |
CN103177265B (en) | High-definition image classification method based on kernel function Yu sparse coding | |
CN107066558A (en) | Boot entry based on artificial intelligence recommends method and device, equipment and computer-readable recording medium | |
CN107678446A (en) | A kind of unmanned plane for extensive target complex cooperates with target assignment method | |
CN113222181B (en) | Federated learning method facing k-means clustering algorithm | |
CN105469063A (en) | Robust human face image principal component feature extraction method and identification apparatus | |
CN106250933A (en) | Method, system and the FPGA processor of data clusters based on FPGA | |
CN109919172A (en) | A kind of clustering method and device of multi-source heterogeneous data | |
CN110188825A (en) | Image clustering method, system, equipment and medium based on discrete multiple view cluster | |
CN116993555A (en) | Partition method, system and storage medium for identifying territory space planning key region | |
CN111582912A (en) | Portrait modeling method based on deep embedding clustering algorithm | |
CN103207804B (en) | Based on the MapReduce load simulation method of group operation daily record | |
Li et al. | Msvit: training multiscale vision transformers for image retrieval | |
CN103150476A (en) | System efficiency evaluation method based on data station field |
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: 20181106 |