CN104616210A - Method for fusion reconstruction and interaction of intelligent power distribution network big data - Google Patents
Method for fusion reconstruction and interaction of intelligent power distribution network big data Download PDFInfo
- Publication number
- CN104616210A CN104616210A CN201510061782.4A CN201510061782A CN104616210A CN 104616210 A CN104616210 A CN 104616210A CN 201510061782 A CN201510061782 A CN 201510061782A CN 104616210 A CN104616210 A CN 104616210A
- Authority
- CN
- China
- Prior art keywords
- grid
- data
- distribution network
- class
- density
- 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.)
- Granted
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 113
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000004927 fusion Effects 0.000 title claims abstract description 32
- 230000003993 interaction Effects 0.000 title abstract 4
- 238000011217 control strategy Methods 0.000 claims abstract description 10
- 230000008520 organization Effects 0.000 claims description 6
- 238000011084 recovery Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 230000002265 prevention Effects 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 230000010354 integration Effects 0.000 abstract description 3
- 238000013507 mapping Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000035876 healing Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a method for fusion reconstruction and interaction of intelligent power distribution network big data. The method is characterized by comprising the steps that (1) division of initial clusters is conducted on the intelligent power distribution network big data, an association rule is established according to the operating state of an intelligent power distribution network, and division of extended clusters is achieved; (2) current data are allocated to the initial clusters based on historical data, the operating state is predicted on the basis of the association rule, so that a self-healing control strategy is determined, and panoramic risk management and control and self-healing control are conducted. According to the method, division of the initial clusters is conducted according to the grid density, division of the extended clusters is conducted through establishment of the association rule, fusion reconstruction and interaction of the intelligent power distribution network big data are achieved, cluster efficiency and cluster accuracy of data streams are effectively improved, and the method has good extensibility and achieves system integration between panoramic risk management and control and self-healing control of the intelligent power distribution network. When the method for fusion reconstruction and interaction of the intelligent power distribution network big data is applied, the intelligent control level of the power distribution network can be improved, and the self-healing control function of the power distribution network is enhanced.
Description
Technical field
The invention belongs to the intelligent distribution network panorama risk management and control towards large data and self Healing Technology research field, relate to the large data fusion reconstruct of a kind of intelligent distribution network and exchange method.
Background technology
Power distribution network covers population collection ground, modern industry and commercial center; power load density is large, and supply path is short, and the cooperation difficulty of relay protection is large; distribution line close to operational limit, once occur that accident will affect the normal power supply of whole power distribution network electric load.Along with the access of a large amount of distributed power source/microgrid/energy storage device, the scale of power distribution network is more and more huger, and structure becomes increasingly complex, and its operation characteristic and control characteristic are also in generation marked change.Therefore, improve the intelligent level that power distribution network controls, the self-healing ability strengthening power distribution network is the inexorable trend of intelligent distribution network development.
Distribution, scheduling, marketing associate and further produce bulk information while close mode, and form the main source of large data, operation management and control is become more meticulous day by day becomes possibility.The problems such as, risk complicated mechanism, risk control capability numerous for current power distribution network influence factor and electrical network self-healing ability are relatively weak, research distribution, scheduling, the large Data fusion technique of marketing, intelligent distribution network self Healing Technology based on Complex Adaptive System Theory is furtherd investigate, realize distribution, scheduling, marketing data fusion and the effective management and control of power distribution network risk under orthofunction and self-healing, improve the safe and reliable level of intelligent distribution network.Therefore, the present invention proposes to merge reconfiguration technique based on the distribution of large data theory, scheduling, marketing panoramic view data, research knowledge based builds the power distribution network panorama risk management and control decision support technique with reasoning, realizes the intelligent distribution network self-healing control possessing fault analysis, service restoration, running optimizatin function.
Summary of the invention
For solving deficiency of the prior art, the invention provides the large data fusion reconstruct of a kind of intelligent distribution network and exchange method, battalion's auxiliary tone integration data analysis and the fusion reconstructing method greatly comprising distributed power source, power information collection and dispatch real time data is proposed, build the information interacting method based on correlation rule, solve the relatively not high problem lacked in ability with power distribution network self-healing control of power distribution network intelligent control level.
In order to realize above-mentioned target, the present invention adopts following technical scheme:.
The large data fusion reconstruct of a kind of intelligent distribution network and exchange method, is characterized in that, comprise step:
1) initial clustering division is carried out to the large data of intelligent distribution network, to be associated rule according to intelligent power distribution Running State, to realize the division of extended clustering;
2) current data is incorporated in the initial clustering based on historical data, based on correlation rule prediction running status, thus determine self-healing control strategy, carry out panorama risk management and control and self-healing control.
The reconstruct of aforesaid a kind of intelligent distribution network large data fusion and exchange method, is characterized in that, described step 1) concrete steps are:
1.1) by the every one dimension (S in n dimension data space S
j, j ∈ [1, n]) and be divided into m part interval, obtain the data space S that quantity is the multi-dimensional grid formation of n × m granularity;
1.2) scan-data space S also builds the data stream storage organization based on grid index; Quantity is that each grid cell in the multi-dimensional grid of n × m granularity is defined as four-tuple coarse gridding structure Grid
j, k, t=(grid, number, density, time), wherein, grid is grid position index, number is number of data points in grid, density is mesh-density, time is up-to-date reception data time;
1.3) the bottom grid density d ensity (Grid of statistical data analysis stream storage organization
j, k, t), with the grid Grid that unit grid density is maximum
h1centered by, scan the grid Grid that it is contiguous, whether determine by Grid and Grid according to density difference threshold epsilon
h1divide a class grid, and will with Grid
h1gather be a class grid combination be designated as Class
1;
1.4) in residue grid, with the grid Grid that unit grid density is maximum
h2centered by, scan the grid Grid that it is contiguous, whether determine by Grid and Grid according to density difference threshold epsilon
h2divide a class grid, and will with Grid
h2gather be a class grid combination be designated as Class
2;
1.5) step 1.4 is repeated), obtain the cluster (Class that initial clustering division numbers is r
1, Class
2..., Class
r);
1.6) fall into 5 types intelligent power distribution Running State situation: optimizing operation state State
1, normal operating condition State
2, fragile running status State
3, failure operation state State
4with collapse conditions State
5; Correlation rule is utilized to set up data space initial clustering Class
xand connecting each other between intelligent distribution network 5 kinds of running statuses, realizes extended clustering and divides, obtain data space extended clustering.
The reconstruct of aforesaid a kind of intelligent distribution network large data fusion and exchange method, is characterized in that: described step 2) concrete steps comprise:
2.1) based on correlation rule and the initial clustering of historical data, intelligent distribution network historical data is analyzed, determine essential characteristic and the boundary condition of intelligent distribution network 5 kinds of running statuses;
2.2) according to the initial clustering Class of historical data
xwith correlation rule and intelligent distribution network 5 kinds of running statuses, the current data meeting essential characteristic and boundary condition is incorporated into the initial clustering Class based on historical data
xin and predict running status;
2.3) according to step 2.2) in predict the running status that obtains, determine intelligent distribution network self-healing control strategy;
2.4) add up and judge whether extended clustering accuracy rate meets the demands, if do not meet, then repeat step 1)-2), based on historical data to the further meticulous division of initial clustering, increase point interval quantity such as the every one dimension in data space, reduce density differential threshold, and correlation rule is adjusted; When extended clustering accuracy rate meets the demands, continue to perform step 2).
The large data fusion reconstruct of aforesaid a kind of intelligent distribution network and exchange method, is characterized in that: step 1.1) in, described data are the large data of power distribution network in intelligent distribution network, and data form a series of data stream record: X
1, X
2..., the time that data arrive is designated as: t
1, t
2, Each data point X in data stream
in dimension, X
i=(x
i1, x
i2... x
in), i=1,2, N dimension data space S=S
1× S
2× ... × S
n, wherein, S
jfor jth dimension data space, wherein S
j=x
.j, j ∈ [1, n]; Every one dimension S
jdata space is divided equally for m part, S
j=S
j1∪ S
j2∪ ... ∪ S
jm; Data space S is by the multi-dimensional grid subspace S of n × m granularity
jkform, wherein j ∈ [1, n], k ∈ [1, m].
The reconstruct of aforesaid a kind of intelligent distribution network large data fusion and exchange method, is characterized in that: step 1.3) in, describedly whether to determine by Grid and Grid according to density difference threshold epsilon
h1divide a class grid, concrete steps are, if | density (Grid)-density (Grid
h) | < ε, then by Grid and Grid
h1clustering is a class.
The large data fusion reconstruct of aforesaid a kind of intelligent distribution network and exchange method, is characterized in that: step 1.6) in, described correlation rule is for setting up (Class
1, Class
2..., Class
r) and (State
1, State
2..., State
5) between shape as the implication expression formula of X → Y; Wherein, X is the guide of correlation rule, for several initial clusterings Class, Y are the follow-up of correlation rule, is one of power distribution network 5 kinds of running statuses.
The large data fusion reconstruct of aforesaid a kind of intelligent distribution network and exchange method, is characterized in that: described mesh-density is, for a grid (i, j), if its time adding data space is t
1, in grid, comprise data sequence (P
1, P
2..., P
l), (t
1, t
2..., t
l) time of arrival of respectively corresponding each data point, then the mesh-density density (i, j, t) of grid (i, j) is defined as:
In formula, λ is attenuation coefficient, wherein λ > 0, w (t-t
k) be moment t
kthe data point arrived is at the weights of moment t, and l is the quantity of data in data space.
The large data fusion reconstruct of aforesaid a kind of intelligent distribution network and exchange method, is characterized in that: described self-healing control strategy comprises: optimal control, prevention and control, emergency control and recovery control.
The large data fusion reconstruct of aforesaid a kind of intelligent distribution network and exchange method, is characterized in that: described 2.4), extended clustering accuracy rate is: use number of times and the ratio to the total degree that power distribution network controls that the power distribution network running status of correlation rule prediction is correct.
The beneficial effect that the present invention reaches: the present invention carries out initial clustering division by the mesh-density of the large data space of computational intelligence power distribution network, by being associated, rule carries out extended clustering division, realize the reconstruct of intelligent distribution network large data fusion with mutual, can effectively improve data stream clustering efficiency and clustering precision, and arbitrary shape and the cluster apart from discontinuous contiguous grid can be carried out; Initial clustering division is divided with extended clustering and combines, and such graded mesh structure greatly reduces space complexity and the time complexity of correlation rule mapping, is with good expansibility; By using the evaluation index of extended clustering accuracy rate as clustering scientific rationality, set up the large data clusters division of intelligent distribution network and control dynamic adjustment mechanism with correlation rule, realize intelligent distribution network panorama risk management and control and the self-healing control system integration, the large data fusion reconstruct of application intelligent distribution network and exchange method, power distribution network intelligent control level can be improved, strengthen power distribution network self-healing control function.
Accompanying drawing explanation
Fig. 1 is that the large data clusters of intelligent distribution network divides and correlation rule control flow chart;
Fig. 2 is intelligent distribution network self-healing control State Transferring graph of a relation.
Embodiment
Below in conjunction with accompanying drawing, the invention will be further described.Following examples only for technical scheme of the present invention is clearly described, and can not limit the scope of the invention with this.
As shown in Figure 1, the large data fusion reconstruct of a kind of intelligent distribution network and exchange method, comprise the large data initial clustering division of intelligent distribution network and divide with extended clustering, intelligent power distribution Running State and self-healing control two parts content, specific implementation step is as follows:
Step S01: carry out initial clustering division to the large data of intelligent distribution network, to be associated rule according to intelligent power distribution Running State, to realize the division of extended clustering;
Step S011: by the every one dimension (S in n dimension data space S
j, j ∈ [1, n]) and be divided into m part interval, obtain the data space S that quantity is the multi-dimensional grid formation of n × m granularity;
Described data are the large data of distribution in intelligent distribution network, and data form a series of data stream record: X
1, X
2..., the time that data arrive is designated as: t
1, t
2, Each data point X in data stream
in dimension, X
i=(x
i1, x
i2... x
in), i=1,2, N dimension data space S=S
1× S
2× ... × S
n, wherein, S
jfor jth dimension data space, S
j=x
.j, j ∈ [1, n]; Every one dimension S
jdata space is divided equally for m part, S
j=S
j1∪ S
j2∪ ... ∪ S
jm; Data space S is by the multi-dimensional grid subspace S of n × m granularity
jkform, wherein j ∈ [1, n], k ∈ [1, m];
Step S012: scan-data space S also builds the data stream storage organization based on grid index; Be defined as four-tuple coarse gridding structure Grid
j, k, t=(grid, number, density, time), wherein, each grid cell Grid
j, k, tbe a four-tuple, grid is grid position index, number is number of data points in grid, density is mesh-density, time is up-to-date reception data time, except grid position index grid and time have nothing to do, the equal and time correlation of its excess-three variable;
The definition of mesh-density, for a grid (i, j), if its time adding data space is t
1, in grid, comprise data sequence (P
1, P
2..., P
l), (t
1, t
2..., t
l) time of arrival of respectively corresponding each data point, then the mesh-density density (i, j, t) of grid (i, j) is defined as:
In formula, λ is attenuation coefficient, λ > 0, w (t-t
k) be moment t
kthe data point arrived is at the weights of moment t, and the implication of l is: the quantity of data in data space.
Step S013: from the mesh-density density (Grid of bottom upwards statistical data analysis stream storage organization
j, k, t), with the grid Grid that bottom floor units mesh-density is maximum
h1centered by, scan the grid Grid that it is contiguous, whether determine by Grid and Grid according to density difference threshold epsilon
h1divide a class grid, and will with Grid
h1gather be a class grid combination be designated as Class
1; Be specially, if | density (Grid)-density (Grid
h) | < ε, then by Grid and Grid
h1clustering is a class;
Step S014: in residue grid, with the grid Grid that bottom floor units mesh-density is maximum
h2centered by, scan the grid Grid that it is contiguous, whether determine by Grid and Grid according to density difference threshold epsilon
h2divide a class grid, and will with Grid
h2gather be a class grid combination be designated as Grid
h2; Therefore, the grid of initial clustering can have any shape, and grid distance can be discontinuous;
Step S015: repeat step S014, obtain the cluster that initial clustering division numbers is r, be expressed as (Class
1, Class
2..., Class
r);
Cluster analysis is by becoming different classifications by the Data Placement in data space, make the similarity of data object in same class large as far as possible, in inhomogeneity, the otherness of data object is large as far as possible, object is the structure distribution finding and determine data, further describes power distribution network running state information implicit in the existing data of Data Concurrent.
Step S016: according to the classification of power distribution network running status, is divided into 5 kinds of situations by the intelligent power distribution Running State possessing self-healing function: optimizing operation state State
1, normal operating condition State
2, fragile running status State
3, failure operation state State
4with collapse conditions State
5; Correlation rule is utilized to set up data space initial clustering Class
xand connecting each other between intelligent distribution network 5 kinds of running statuses, realizes extended clustering and divides, obtain data space extended clustering;
Normal operating condition State
2a kind of running status of economic stability, optimizing operation state State
1it is a kind of desirable running status; Fragile running status State
3, failure operation state State
4with collapse conditions State
5it is all abnormal operational conditions.
Correlation rule is exactly to set up the implication expression formula of shape as X → Y; Wherein, X and Y is called as the guide of correlation rule and follow-up respectively; Correlation rule guide in the present invention refers to several initial clusterings Class, correlation rule is follow-up refer to power distribution network 5 kinds of running statuses one of them; The problem of extended clustering accuracy rate μ is there is between this corresponding relation; Extended clustering accuracy rate μ is the ratio of correct Prediction number of states and all predicted state quantity;
Containing the core of expression formula X → Y is the mapping relations be associated between the data space at guide X place of rule and the data space at follow-up Y place, and object is to help people to catch now and prediction future.Concrete process of establishing is as follows: the historical data 1. analyzing guide's X data space and follow-up Y data space, respectively disposal data variable; 2. build the mutual relationship in data variable and follow-up Y data space between data variable in guide X data space, and carry out sorting that (core of mutual relationship is the scientific formulate between quantification two data values according to mutual relationship power; Mutual relationship refers to that by force another data value probably can increase thereupon when a data value increases; Mutual relationship is weak just means that another data value changes hardly when a data value increases; ); 3. consider the strong and weak factor with data variable span two aspect of mutual relationship, build the mapping relations in some subspaces and follow-up Y data space between particular subspace in guide X data space; 4. based on the mapping relations between the guide X built and follow-up Y, to present and following data in a certain subspace of guide X, directly can predict that it should be in the particular subspace of follow-up Y.
Step S02: current data incorporated in the initial clustering based on historical data, based on correlation rule prediction running status, thus determines self-healing control strategy, carries out panorama risk management and control and self-healing control.
Step S021: based on correlation rule and the initial clustering of historical data, analyze intelligent distribution network historical data, determines intelligent distribution network 5 kinds of running status State
yessential characteristic and boundary condition, wherein, y ∈ [1,5]; Essential characteristic comprises voltage fluctuation, current fluctuation, phase angle fluctuation etc., and boundary condition refers to above-mentioned each physical quantity fluctuation range, duration etc.Running status has similar essential characteristic and boundary condition based on the historical data in the some initial clusterings corresponding to correlation rule;
Step S022: according to data space initial clustering Class
xwith intelligent distribution network 5 kinds of running status State
ybetween based on historical data set up correlation rule, the current data meeting essential characteristic and boundary condition are incorporated into the initial clustering Class that step S015 obtains
xin and the corresponding 5 kinds of running status State of prediction
yin one of them; Wherein, several initial clusterings Class
xwith a running status State
ycorresponding, the initial clustering Class of its correspondence
xconcrete quantity basis actual conditions and determining, generally select about 10;
Step S023: according to predicting the running status State obtained in step S022
y, determine intelligent distribution network self-healing control strategy: as shown in Figure 2, described self-healing control strategy comprises: optimal control, prevention and control, emergency control and recovery control.
By normal operating condition State
2to optimizing operation state State
1control be optimal control, when optimal control refers to that electrical network is in normal operating condition, by changing supply path, optimizing transformer operation manners, regulating reactive-load compensation equipment etc., reduce grid loss, reduce operating cost, make it forward optimizing operation state to.Fragile running status State
3, failure operation state State
4with collapse conditions State
5be all abnormal operational conditions, intervention must be carried out to abnormal operational conditions and control, make it to get back to normal operating condition; Above three kinds of abnormal operational conditions are to normal operating condition State
2intervention control to be defined as respectively: prevention and control, emergency control and recovery control; When prevention and control refer to that power distribution network is in fragile running status, by checking maintenance electrical secondary system, adjustment protection limits, regulating the intervening measure such as reactive-load compensation and circuit switched, eliminate the potential safety hazard of power distribution network, make it forward normal operating condition to; When emergency control refers to that power distribution network is in failure operation state, by taking excision fault, cutting the intervening measures such as machine, cutting load, Active Splitting, eliminate the fault of power distribution network, make it forward normal operating condition to; When recovery control refers to that power distribution network is in collapse conditions, attempt selecting rational supply path, recovery system is powered, and realizes islet operation or is incorporated into the power networks, and makes it forward normal operating condition to;
Step S024: add up and judge whether extended clustering accuracy rate μ can meet the demands, if can not meet, then repeat step S011-S023, based on historical data to the further meticulous division of initial clustering, increase point interval quantity m such as the every one dimension in data space S, reduce density difference threshold epsilon, and correlation rule is adjusted; When extended clustering accuracy rate μ meets the demands, continue to perform step S023.
Extended clustering accuracy rate μ statistical method: will the power distribution network running status of correlation rule prediction be used to carry out Statistical Comparison analysis with without the power distribution network running status (being realized by power system simulation software) of intervening, the cluster that can be expanded accuracy rate μ=(using the number of times that the power distribution network running status of correlation rule prediction is correct)/(total degree to power distribution network controls).
The present invention has following beneficial effect:
1) Grid Clustering is combined with correlation rule, propose the large data fusion reconstruct of a kind of intelligent distribution network and exchange method, can effectively improve data stream clustering efficiency and clustering precision, and arbitrary shape and the cluster apart from discontinuous contiguous grid can be carried out;
2) initial clustering is divided to divide with extended clustering combine, and such graded mesh structure greatly reduces space complexity and the time complexity of correlation rule mapping, and be with good expansibility;
3) by using the evaluation index of extended clustering accuracy rate μ as clustering scientific rationality, set up the large data clusters division of intelligent distribution network and control dynamic adjustment mechanism with correlation rule;
The above is only the preferred embodiment of the present invention; it should be pointed out that for those skilled in the art, under the prerequisite not departing from the technology of the present invention principle; can also make some improvement and distortion, these improve and distortion also should be considered as protection scope of the present invention.
Claims (9)
1. the large data fusion reconstruct of intelligent distribution network and an exchange method, is characterized in that, comprise step:
1) initial clustering division is carried out to the large data of intelligent distribution network, to be associated rule according to intelligent power distribution Running State, to realize the division of extended clustering;
2) current data is incorporated in the initial clustering based on historical data, based on correlation rule prediction running status, thus determine self-healing control strategy, carry out panorama risk management and control and self-healing control.
2., based on the reconstruct of the large data fusion of a kind of intelligent distribution network described in claim 1 and exchange method, it is characterized in that, described step 1) concrete steps are:
1.1) by the every one dimension (S in n dimension data space S
j, j ∈ [1, n]) and be divided into m part interval, obtain the data space S that quantity is the multi-dimensional grid formation of n × m granularity;
1.2) scan-data space S also builds the data stream storage organization based on grid index; Quantity is that each grid cell in the multi-dimensional grid of n × m granularity is defined as four-tuple coarse gridding structure Grid
j, k, t=(grid, number, density, time), wherein, grid is grid position index, number is number of data points in grid, density is mesh-density, time is up-to-date reception data time;
1.3) the bottom grid density d ensity (Grid of statistical data analysis stream storage organization
j, k, t), with the grid Grid that unit grid density is maximum
h1centered by, scan the grid Grid that it is contiguous, whether determine by Grid and Grid according to density difference threshold epsilon
h1divide a class grid, and will with Grid
h1gather be a class grid combination be designated as Class
1;
1.4) in residue grid, with the grid Grid that unit grid density is maximum
h2centered by, scan the grid Grid that it is contiguous, whether determine by Grid and Grid according to density difference threshold epsilon
h2divide a class grid, and will with Grid
h2gather be a class grid combination be designated as Class
2;
1.5) step 1.4 is repeated), obtain the cluster (Class that initial clustering division numbers is r
1, Class
2..., Class
r);
1.6) fall into 5 types intelligent power distribution Running State situation: optimizing operation state State
1, normal operating condition State
2, fragile running status State
3, failure operation state State
4with collapse conditions State
5; Correlation rule is utilized to set up data space initial clustering Class
xand connecting each other between intelligent distribution network 5 kinds of running statuses, realizes extended clustering and divides, obtain data space extended clustering.
3. the reconstruct of a kind of intelligent distribution network according to claim 1 large data fusion and exchange method, is characterized in that: described step 2) concrete steps comprise:
2.1) based on correlation rule and the initial clustering of historical data, intelligent distribution network historical data is analyzed, determine essential characteristic and the boundary condition of intelligent distribution network 5 kinds of running statuses;
2.2) according to the initial clustering Class of historical data
xwith correlation rule and intelligent distribution network 5 kinds of running statuses, the current data meeting essential characteristic and boundary condition is incorporated into the initial clustering Class based on historical data
xin and predict running status;
2.3) according to step 2.2) in predict the running status that obtains, determine intelligent distribution network self-healing control strategy;
2.4) add up and judge whether extended clustering accuracy rate meets the demands, if do not meet, then repeat step 1)-2), based on historical data to the further meticulous division of initial clustering, increase point interval quantity such as the every one dimension in data space, reduce density differential threshold, and correlation rule is adjusted; When extended clustering accuracy rate meets the demands, continue to perform step 2).
4. the large data fusion reconstruct of a kind of intelligent distribution network according to claim 2 and exchange method, is characterized in that: step 1.1) in, described data are the large data of power distribution network in intelligent distribution network, and data form a series of data stream record: X
1, X
2..., the time that data arrive is designated as: t
1, t
2, Each data point X in data stream
in dimension, X
i=(x
i1, x
i2... x
in), i=1,2, N dimension data space S=S
1× S
2× ... × S
n, wherein, S
jfor jth dimension data space, wherein S
j=x
j, j ∈ [1, n]; Every one dimension S
jdata space is divided equally for m part, S
j=S
j1∪ S
j2∪ ... ∪ S
jm; Data space S is by the multi-dimensional grid subspace S of n × m granularity
jkform, wherein j ∈ [1, n], k ∈ [1, m].
5. the reconstruct of a kind of intelligent distribution network according to claim 2 large data fusion and exchange method, is characterized in that: step 1.3) in, describedly whether to determine by Grid and Grid according to density difference threshold epsilon
h1divide a class grid, concrete steps are, if | density (Grid)-density (Grid
h) | < ε, then by Grid and Grid
h1clustering is a class.
6. the large data fusion reconstruct of a kind of intelligent distribution network according to claim 2 and exchange method, is characterized in that: step 1.6) in, described correlation rule is for setting up (Class
1, Class
2..., Class
r) and (State
1, State
2..., State
5) between shape as the implication expression formula of X → Y; Wherein, X is the guide of correlation rule, for several initial clusterings Class, Y are the follow-up of correlation rule, is one of power distribution network 5 kinds of running statuses.
7. the large data fusion reconstruct of a kind of intelligent distribution network according to claim 2 and exchange method, is characterized in that: described mesh-density is, for a grid (i, j), if its time adding data space is t
1, in grid, comprise data sequence (P
1, P
2..., P
l), (t
1, t
2..., t
l) time of arrival of respectively corresponding each data point, then the mesh-density density (i, j, t) of grid (i, j) is defined as:
In formula, λ is attenuation coefficient, λ >0, w (t-t
k) be moment t
kthe data point arrived is at the weights of moment t, and l is the quantity of data in data space.
8. the large data fusion reconstruct of a kind of intelligent distribution network according to claim 3 and exchange method, is characterized in that: described self-healing control strategy comprises: optimal control, prevention and control, emergency control and recovery control.
9. the large data fusion reconstruct of a kind of intelligent distribution network according to claim 3 and exchange method, is characterized in that: described 2.4), extended clustering accuracy rate is: use number of times and the ratio to the total degree that power distribution network controls that the power distribution network running status of correlation rule prediction is correct.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510061782.4A CN104616210B (en) | 2015-02-05 | 2015-02-05 | A kind of intelligent distribution network big data fusion reconstruct and exchange method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510061782.4A CN104616210B (en) | 2015-02-05 | 2015-02-05 | A kind of intelligent distribution network big data fusion reconstruct and exchange method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104616210A true CN104616210A (en) | 2015-05-13 |
CN104616210B CN104616210B (en) | 2017-12-08 |
Family
ID=53150643
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510061782.4A Expired - Fee Related CN104616210B (en) | 2015-02-05 | 2015-02-05 | A kind of intelligent distribution network big data fusion reconstruct and exchange method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104616210B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104899795A (en) * | 2015-05-27 | 2015-09-09 | 云南电网有限责任公司 | Method for partitioning power supply areas based on distribution network GIS system |
CN104980440A (en) * | 2015-06-23 | 2015-10-14 | 南京邮电大学 | Active power distribution network big data transmission method based on content filtering and multi-Agent cooperation |
CN105470951A (en) * | 2015-12-10 | 2016-04-06 | 浙江大学 | Big data mining technology based reliable power supply capacity evaluation method for power distribution network |
CN105548779A (en) * | 2016-02-02 | 2016-05-04 | 中国农业大学 | Low voltage power distribution network wattless operation state early warning method and system |
CN106681300A (en) * | 2016-12-14 | 2017-05-17 | 云南电网有限责任公司电力科学研究院 | Data clustering analysis method and system of power devices |
CN109389172A (en) * | 2018-10-11 | 2019-02-26 | 中南大学 | A kind of radio-signal data clustering method based on printenv grid |
CN109406943A (en) * | 2018-11-16 | 2019-03-01 | 国网江苏省电力有限公司盐城供电分公司 | A kind of active distribution network monitoring method based on big data |
CN111241145A (en) * | 2018-11-28 | 2020-06-05 | 中国移动通信集团浙江有限公司 | Self-healing rule mining method and device based on big data |
CN112347113A (en) * | 2020-09-16 | 2021-02-09 | 北京中兵数字科技集团有限公司 | Aviation data fusion method, aviation data fusion device and storage medium |
CN117150438A (en) * | 2023-10-31 | 2023-12-01 | 成都汉度科技有限公司 | Communication data fusion method and system based on edge calculation |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102831393A (en) * | 2012-07-19 | 2012-12-19 | 安徽工业大学 | Rapid image recognizing method of power tower pole outline |
US20130157729A1 (en) * | 2011-12-16 | 2013-06-20 | Joseph Akwo Tabe | Energy harvesting computer device in association with a communication device configured with apparatus for boosting signal reception |
CN104182830A (en) * | 2014-08-14 | 2014-12-03 | 天津大学 | A method for mining a weak reliability link of a power distribution system based on multi-dimensional analysis |
-
2015
- 2015-02-05 CN CN201510061782.4A patent/CN104616210B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130157729A1 (en) * | 2011-12-16 | 2013-06-20 | Joseph Akwo Tabe | Energy harvesting computer device in association with a communication device configured with apparatus for boosting signal reception |
CN102831393A (en) * | 2012-07-19 | 2012-12-19 | 安徽工业大学 | Rapid image recognizing method of power tower pole outline |
CN104182830A (en) * | 2014-08-14 | 2014-12-03 | 天津大学 | A method for mining a weak reliability link of a power distribution system based on multi-dimensional analysis |
Non-Patent Citations (2)
Title |
---|
何明: "应用网格化方法构建城市配电网大数据", 《电网技术》 * |
李贵兵 等: "大数据下的智能数据分析技术研究", 《科技资讯》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104899795A (en) * | 2015-05-27 | 2015-09-09 | 云南电网有限责任公司 | Method for partitioning power supply areas based on distribution network GIS system |
CN104980440A (en) * | 2015-06-23 | 2015-10-14 | 南京邮电大学 | Active power distribution network big data transmission method based on content filtering and multi-Agent cooperation |
CN105470951A (en) * | 2015-12-10 | 2016-04-06 | 浙江大学 | Big data mining technology based reliable power supply capacity evaluation method for power distribution network |
CN105548779A (en) * | 2016-02-02 | 2016-05-04 | 中国农业大学 | Low voltage power distribution network wattless operation state early warning method and system |
CN106681300A (en) * | 2016-12-14 | 2017-05-17 | 云南电网有限责任公司电力科学研究院 | Data clustering analysis method and system of power devices |
CN109389172A (en) * | 2018-10-11 | 2019-02-26 | 中南大学 | A kind of radio-signal data clustering method based on printenv grid |
CN109389172B (en) * | 2018-10-11 | 2022-05-20 | 中南大学 | Radio signal data clustering method based on non-parameter grid |
CN109406943A (en) * | 2018-11-16 | 2019-03-01 | 国网江苏省电力有限公司盐城供电分公司 | A kind of active distribution network monitoring method based on big data |
CN111241145A (en) * | 2018-11-28 | 2020-06-05 | 中国移动通信集团浙江有限公司 | Self-healing rule mining method and device based on big data |
CN112347113A (en) * | 2020-09-16 | 2021-02-09 | 北京中兵数字科技集团有限公司 | Aviation data fusion method, aviation data fusion device and storage medium |
CN117150438A (en) * | 2023-10-31 | 2023-12-01 | 成都汉度科技有限公司 | Communication data fusion method and system based on edge calculation |
CN117150438B (en) * | 2023-10-31 | 2024-02-06 | 成都汉度科技有限公司 | Communication data fusion method and system based on edge calculation |
Also Published As
Publication number | Publication date |
---|---|
CN104616210B (en) | 2017-12-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104616210A (en) | Method for fusion reconstruction and interaction of intelligent power distribution network big data | |
CN104283308B (en) | Smart central strategy control system for micro-grid | |
CN105139095A (en) | Power distribution network running state evaluation method based on attribute area module | |
Chanda et al. | Quantifying resiliency of smart power distribution systems with distributed energy resources | |
CN105469317B (en) | A kind of reliability of power communication network analysis method | |
CN110429714A (en) | A kind of cloud platform intelligent distribution system based on big data | |
CN113705085B (en) | Intelligent power grid multi-level structure modeling and risk assessment method | |
Dehghani et al. | Multi-stage resilience management of smart power distribution systems: A stochastic robust optimization model | |
CN108695846A (en) | A kind of unit style power distribution network operation risk assessment method | |
CN107453354B (en) | A kind of weak link recognition methods of power distribution network | |
CN102290811A (en) | Method for evaluating accident prearranged plan and running way | |
CN105574600A (en) | Power grid communication service oriented communication risk early warning and risk avoidance method | |
CN102118061A (en) | Method and system for centralized control of regional power grid | |
CN112712271A (en) | Power grid meshing evaluation method, system, medium and electronic equipment | |
CN108427764A (en) | The anti-lost system of collection for big data | |
CN103532133A (en) | Load transfer system and method used in case of failure of 35kV power distribution network on basis of MAS (Multi-Agents) | |
CN108832630B (en) | Power grid CPS prevention control method based on expected accident scene | |
de Assis et al. | Optimal allocation of remote controlled switches in radial distribution systems | |
CN112561129B (en) | First-aid repair material allocation method based on distribution line fault information | |
CN114204675A (en) | Power distribution station electric energy data acquisition terminal based on cloud edge cooperation | |
CN103400213A (en) | Backbone net rack survivability assessment method based on LDA (Linear Discriminant Analysis) and PCA (Principal Component Analysis) | |
CN116827807B (en) | Power communication network node importance evaluation method based on multi-factor evaluation index | |
Yang et al. | Optimal resource allocation to enhance power grid resilience against hurricanes | |
CN116881838A (en) | Power node importance degree dividing method for physical information fusion | |
Tong et al. | Artificial intelligence-based lightning protection of smart grid distribution system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171208 |
|
CF01 | Termination of patent right due to non-payment of annual fee |