CN107368853A - Power network classification of the items based on machine learning determines method and device - Google Patents
Power network classification of the items based on machine learning determines method and device Download PDFInfo
- Publication number
- CN107368853A CN107368853A CN201710573258.4A CN201710573258A CN107368853A CN 107368853 A CN107368853 A CN 107368853A CN 201710573258 A CN201710573258 A CN 201710573258A CN 107368853 A CN107368853 A CN 107368853A
- Authority
- CN
- China
- Prior art keywords
- items
- classification
- load density
- curve
- item data
- 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 52
- 238000010801 machine learning Methods 0.000 title claims abstract description 33
- 238000009826 distribution Methods 0.000 claims abstract description 46
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 25
- 238000007621 cluster analysis Methods 0.000 claims abstract description 22
- 238000004590 computer program Methods 0.000 claims description 7
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 2
- 238000007726 management method Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000002902 bimodal effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- 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)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of power network classification of the items based on machine learning to determine method and device, is related to technical field of data processing, this method includes：Obtain multiple distribution projects history item data and each history item data corresponding to time series；The load density curve according to corresponding to history item data and the time series determine each history item data；Multiple load density curves are subjected to cluster analysis, obtain multiple classifications of the items；Acquisition each states characteristic information corresponding to classification of the items；Model is determined according to multiple classifications of the items, with each corresponding characteristic information of classification of the items and default machine learning algorithm structure classification of the items.The invention discloses a kind of power network classification of the items based on machine learning to determine method and device, to solve that the technical problem of forecasting accuracy can not be ensured using Earned Value, the predictablity rate for improving Project Cost branch exit pattern is realized, and then improves the technique effect of the precision of project management.
Description
Technical field
It is true more particularly, to a kind of power network classification of the items based on machine learning the present invention relates to technical field of data processing
Determine method and device.
Background technology
At present, going from strength to strength with electric power enterprise, distribution project management construction occupy critical role in current electric grid.
It is several that distribution project may be generally divided into Preliminary design, construction drawing design, preparation of construction, site operation, final account for completed project, project final accounting
In the individual stage, there is a certain proportion of expense to pay in each stage.According to substantial amounts of as shown by data, the expense branch of distribution project
Go out process and various modes, such as leveling style, single peak type isotype be present.
In order to improve the precision of project management, the expense branch exit pattern of distribution project is needed to make accurate prediction.
Traditional project management method is mainly using earning value method.Earn value method and mainly support project performance management
(Performance Management's), be exactly the actual difference with plan of item compared most crucial mesh, it is of interest that
Each project task in practice, in content, time, quality, cost etc. and the difference condition of plan, then according to these
Difference, remaining task in project can be predicted, adjusted and be controlled.But this value method of earning has the following disadvantages：Earn
The applicability of value method depends on the reasonability accuracy in other words of the project plan, and this point human factor is more, exist subjectivity,
The problem of one-sidedness, cause the accuracy of prediction result can not ensure.
The content of the invention
In view of this, it is an object of the invention to provide a kind of power network classification of the items based on machine learning determine method and
Device, to solve the technical problem that traditional Earned Value can not ensure forecasting accuracy.
In a first aspect, the embodiments of the invention provide a kind of power network classification of the items based on machine learning to determine method, bag
Include：
Obtain the history item data of multiple distribution projects and time series corresponding to each history item data；
The load according to corresponding to the history item data and the time series determine each history item data
Density curve；
Multiple load density curves are subjected to cluster analysis, obtain multiple classifications of the items；
Obtain characteristic information corresponding to each classification of the items；
According to multiple classifications of the items, with each corresponding characteristic information of classification of the items and default machine
Learning algorithm structure classification of the items determines model.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of the first of first aspect, wherein, institute
It is bent to state the load density according to corresponding to the history item data and the temporal information determine each history item data
Line, including：
Fitting of a polynomial is carried out to the history item data and the time series, obtains each history entries mesh number
According to corresponding matched curve；
Multiple matched curves are normalized respectively, obtain multiple load density curves.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of second of first aspect, wherein, institute
State and multiple load density curves are subjected to cluster analysis, obtain multiple classifications of the items, including：
The multiple load density curve is subjected to cluster analysis, obtains at least one curve combination, each curve
Combination includes at least one load density curve；
For curve combination each described, average load density curve corresponding with the curve combination is calculated；
In each curve combination, reject close more than the load of predetermined threshold value the difference between average load density curve
Write music line, until the average load density curve is restrained；
Determine that the curve combination during average load density curve convergence belongs to same project classification.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of the third of first aspect, wherein, institute
Stating default machine learning algorithm includes XGBoost algorithms, random forests algorithm, SVMs and/or k nearest neighbor algorithms.
Second aspect, the embodiment of the present invention also provide a kind of power network classification of the items based on machine learning and determine method, institute
The method of stating includes：
Obtain the characteristic information of target distribution project；
The classification of the items that the characteristic information is input to as described in relation to the first aspect is determined in model, obtains the target item
Purpose classification of the items.
With reference to second aspect, the embodiments of the invention provide the possible embodiment of the first of second aspect, the side
Method also includes：
Average load density curve corresponding to the classification of the items is defined as to the prediction curve of the destination item.
The third aspect, the embodiment of the present invention also provide a kind of power network classification of the items determining device based on machine learning, bag
Include：
First acquisition module, for the history item data for obtaining multiple distribution projects and each history item data
Corresponding time series；
Determining module, for determining each history entries mesh number according to the history item data and the time series
According to corresponding load density curve；
Cluster Analysis module, for multiple load density curves to be carried out into cluster analysis, obtain multiple classifications of the items；
Second acquisition module, for obtaining characteristic information corresponding to each classification of the items；
Module is built, for believing according to multiple classifications of the items, the feature corresponding with each classification of the items
Breath and default machine learning algorithm structure classification of the items determine model.
Fourth aspect, the embodiment of the present invention also provide a kind of power network classification of the items determining device based on machine learning, institute
Stating device includes：
3rd acquisition module, for obtaining the characteristic information of target distribution project；
Input module, determine in model, obtain for the characteristic information to be input to the classification of the items described in first aspect
To the classification of the items of the destination item.
5th aspect, the embodiment of the present invention also provide a kind of electronic equipment, including memory, processor, the memory
In be stored with the computer program that can be run on the processor, described in the computing device during computer program realize on
The step of stating the method described in first aspect.
6th aspect, the embodiment of the present invention also provide a kind of meter for the non-volatile program code that can perform with processor
Calculation machine computer-readable recording medium, described program code make the computing device realize the method described in above-mentioned first aspect.
The embodiment of the present invention passes through the history item data for obtaining multiple distribution projects first and each history item
Time series corresponding to data, each history item is then determined according to the history item data and the time series
Load density curve corresponding to data, multiple load density curves are subjected to cluster analysis, obtain multiple classifications of the items, then
Characteristic information corresponding to each classification of the items is obtained, finally can be according to multiple classifications of the items and each item
The characteristic information corresponding to mesh classification and default machine learning algorithm structure classification of the items determine model.
The embodiment of the present invention is input to structure also by obtaining the characteristic information of target distribution project, by the characteristic information
Classification of the items determine in model, the classification of the items of the destination item can be obtained.
The embodiment of the present invention carries out cluster analysis by the distribution project to substantial amounts of historical record, obtains multiple projects point
Class, the various features information of the distribution project of each historical record is regathered, project is built according to default machine learning algorithm
Classification determines model, finally determines model according to the characteristic information of target distribution project to be sorted to target using classification of the items
Distribution project is made accurate classification of the items and judged, improves the accuracy rate being predicted to the classification of the items of distribution project, improves
The efficiency of distribution project management, moreover, with the accumulation of data, the classification of the items of distribution project will be further accurate.
Other features and advantages of the present invention will illustrate in the following description, also, partly become from specification
Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages are in specification, claims
And specifically noted structure is realized and obtained in accompanying drawing.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description of the drawings
, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical scheme of the prior art
The required accompanying drawing used is briefly described in embodiment or description of the prior art, it should be apparent that, in describing below
Accompanying drawing is some embodiments of the present invention, for those of ordinary skill in the art, before creative work is not paid
Put, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is the flow chart that the power network classification of the items that the embodiment of the present invention one provides determines method；
Fig. 2 is the flow chart that the power network classification of the items that the embodiment of the present invention one provides determines the cluster analysis in method；
Fig. 3 is the flow chart for the power network destination item classification determination method that the embodiment of the present invention two provides；
Fig. 4 is the structure chart that the power network classification of the items that the embodiment of the present invention three provides determines square law device；
Fig. 5 is the structure chart that the power network classification of the items that the embodiment of the present invention four provides determines square law device.
Icon：
The acquisition modules of 11- first；12- determining modules；13- Cluster Analysis modules；The acquisition modules of 14-- second；15- is built
Module；The acquisition modules of 21- the 3rd；22- input modules.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with accompanying drawing to the present invention
Technical scheme be clearly and completely described, it is clear that described embodiment is part of the embodiment of the present invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, belongs to the scope of protection of the invention.
At present, project is predicted, adjust and controlled using Earned Value in the prior art, but due to no using conventional
The historical data and human factor of project are more, can not ensure forecasting accuracy, based on this, one kind provided in an embodiment of the present invention
Classification of the items determines method and device, can obtain multiple classifications of the items by being made a concrete analysis of to actual distribution project, then
The various features information of distribution project is collected, building classification of the items according to default machine learning algorithm determines model, finally utilizes
Classification of the items determines that model makes accurate item according to the characteristic information of target distribution project to be sorted to target distribution project
Mesh classification judges, improves the accuracy rate being predicted to the classification of the items of distribution project, improves the efficiency of distribution project management, and
And with the accumulation of data, the classification of the items of distribution project will be further accurate.
For ease of understanding the present embodiment, first to a kind of classification of the items determination side disclosed in the embodiment of the present invention
Method describes in detail, as shown in figure 1, a kind of power network classification of the items based on machine learning determines method, comprises the following steps.
Step S1, obtain the history item data of multiple distribution projects and time corresponding to each history item data
Sequence.
In embodiments of the present invention, distribution project is broken generally into Preliminary design, construction drawing design, preparation of construction, scene are applied
Work, final account for completed project, project final accounting several stages.There is a certain proportion of expense to pay in each stage distribution project, and
Substantial amounts of as shown by data, expense expenditure process can correspond to a variety of classifications of the items.The history item data of each distribution project are for example
Expense expenditure data, goods and materials amount data and capital quantity data of distribution project etc. can be included.Wherein, each distribution project is taken
With expenditure data in be included in multiple different time points expenditure expenditure data, goods and materials amount data and capital quantity data similarly,
Multiple time points in each history item data may be constructed a time series.
Step S2, determine that each history item data are corresponding according to the history item data and the time series
Load density curve.
It may comprise steps of in step s 2.
S201, fitting of a polynomial is carried out to the history item data and the time series, obtains each history
Matched curve corresponding to project data.
In embodiments of the present invention, fitting of a polynomial namely polynomial curve fitting, can be respectively according to history entries mesh number
According to being fitted to obtain a plurality of curve of approximation with time series, curve of approximation is matched curve corresponding to history item data.
S202, multiple matched curves are normalized respectively, obtain multiple load density curves.
Step S3, multiple load density curves are subjected to cluster analysis, obtain multiple classifications of the items.
In this step, cluster analysis is carried out to multiple load density curves, similar load density curve can be gathered
Class obtains multiple classifications of the items into same classification of the items.
On the basis of previous embodiment, as shown in Fig. 2 in another embodiment of the present invention, it can be wrapped in step S3
Include following steps.
S301, the multiple load density curve is subjected to cluster analysis, obtains at least one curve combination, it is each described
Curve combination includes at least one load density curve.
S302, for curve combination each described, it is bent to calculate average load density corresponding with the curve combination
Line.
S303, in each curve combination, the difference rejected between average load density curve is more than predetermined threshold value
Load density curve, until the average load density curve is restrained；
S304, determine that the curve combination during average load density curve convergence belongs to same project classification.
In embodiments of the present invention, multiple load density curves of history item are subjected to cluster analysis, obtain at least one
Individual curve combination.Each curve combination can include one, two or several density loads curves.For each curve group
Close, calculate average load density curve.In the curve combination, find out big with the difference between the average load density curve
In predetermined threshold value load density curve and reject, iteration carries out this process, until the average load density curve restrain.
When the average load density curve of a curve combination is restrained, this curve combination belongs to same project classification.With reference to
Practical work experience, each curve combination correspond to a kind of classification of the items.
In embodiments of the present invention, classification of the items can be divided into leveling style, single peak type, bimodal pattern, gradually rise type and by
Down type etc. is walked, in all examples being illustrated and described herein, any occurrence should be construed as merely exemplary,
Not as limitation, therefore, other examples of exemplary embodiment can have different types.
Step S4, obtain characteristic information corresponding to each classification of the items.
In embodiments of the present invention, characteristic information corresponding to each classification of the items has comprised at least item types, project work
The information such as phase, the amount of money and voltage class.
Step S5, according to multiple classifications of the items, the characteristic information corresponding with each classification of the items and
Default machine learning algorithm structure classification of the items determines model.
In actual applications, the default machine learning algorithm referred in step S5 can include XGBoost algorithms, with
Machine forest algorithm, SVMs and/or k nearest neighbor algorithms.Experience have shown that using XGBoost algorithms and random forests algorithm, tool
There is more preferable effect.
In the aforementioned embodiment, model is determined due to constructing classification of the items, therefore, in another embodiment of the present invention
In, the classification of the items of structure can be used to determine that model determines target distribution project according to the characteristic information of target distribution project
Classification of the items, as shown in figure 3, also providing a kind of power network classification of the items based on machine learning determines method, methods described can be with
Comprise the following steps.
Step S6, obtain the characteristic information of target distribution project.For example, item types, project duration, the amount of money and voltage etc.
The information such as level.
Step S7, the classification of the items that the characteristic information is input to as above-mentioned embodiment of the method is built is determined in model,
Obtain the classification of the items of the destination item.
In embodiments of the present invention, average load density curve corresponding to the classification of the items is defined as the target item
Purpose prediction curve.By checking that the tendency of average load density curve corresponding to the classification of the items can predict destination item
Expense expenditure trend.
As shown in figure 4, in another embodiment of the present invention, a kind of power network classification of the items based on machine learning determines dress
Put 10, including：First acquisition module 11, determining module 12, Cluster Analysis module 13, the second acquisition module 14 and structure module
15。
First acquisition module 11, for the history item data for obtaining multiple distribution projects and each history entries mesh number
According to corresponding time series.
Determining module 12, for determining each history item according to the history item data and the time series
Load density curve corresponding to data；
Cluster Analysis module 13, for multiple load density curves to be carried out into cluster analysis, obtain multiple projects point
Class；
Second acquisition module 14, for obtaining characteristic information corresponding to each classification of the items；
Module 15 is built, for according to multiple classifications of the items, the feature corresponding with each classification of the items
Information and default machine learning algorithm structure classification of the items determine model.
As shown in figure 5, in another embodiment of the present invention, a kind of power network classification of the items based on machine learning determines dress
20 are put, described device includes：
3rd acquisition module 21, for obtaining the characteristic information of target distribution project；
Input module 22, model is determined for the characteristic information to be inputted in above-mentioned steps S5 into the classification of the items determined
In, obtain the classification of the items of the destination item.
In another embodiment of the present invention, a kind of electronic equipment, including memory, processor, the storage are also provided
The computer program that can be run on the processor is stored with device, is realized described in the computing device during computer program
The step of above-mentioned classification of the items determines method.
In another embodiment of the present invention, a kind of non-volatile program code that can perform with processor is also provided
Computer-readable medium, described program code make the computing device classification of the items determine method.
A kind of power network classification of the items based on machine learning provided in an embodiment of the present invention determines method and device, by right
The distribution project of substantial amounts of historical record carries out cluster analysis, obtains multiple classifications of the items, regathers matching somebody with somebody for each historical record
The various features information of net project, classification of the items is built according to default machine learning algorithm and determines model, finally utilizes project
Classification determines that model makes accurate project point to target distribution project according to the characteristic information of target distribution project to be sorted
Class judges, improves the accuracy rate being predicted to the classification of the items of distribution project, improves the efficiency of distribution project management, moreover,
With the accumulation of data, the classification of the items of distribution project will be further accurate.
In several embodiments provided by the present invention, it should be understood that disclosed apparatus and method, can also pass through
Other modes are realized.Device embodiment described above is only schematical, for example, flow chart and block diagram in accompanying drawing
Show the device of multiple embodiments according to the present invention, method and computer program product architectural framework in the cards,
Function and operation.At this point, each square frame in flow chart or block diagram can represent the one of a module, program segment or code
Part, a part for the module, program segment or code include one or more and are used to realize holding for defined logic function
Row instruction.It should also be noted that at some as in the implementation replaced, the function that is marked in square frame can also with different from
The order marked in accompanying drawing occurs.For example, two continuous square frames can essentially perform substantially in parallel, they are sometimes
It can perform in the opposite order, this is depending on involved function.It is it is also noted that every in block diagram and/or flow chart
The combination of individual square frame and block diagram and/or the square frame in flow chart, function or the special base of action as defined in performing can be used
Realize, or can be realized with the combination of specialized hardware and computer instruction in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate to form an independent portion
Point or modules individualism, can also two or more modules be integrated to form an independent part.
If the function is realized in the form of software function module and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are causing a computer equipment (can be
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the present invention.
And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access
Memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.Need
It is noted that herein, such as first and second or the like relational terms are used merely to an entity or operation
Made a distinction with another entity or operation, and not necessarily require or imply these entities or exist between operating any this
Actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to nonexcludability
Comprising so that process, method, article or equipment including a series of elements not only include those key elements, but also wrapping
Include the other element being not expressly set out, or also include for this process, method, article or equipment intrinsic want
Element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that wanted including described
Other identical element also be present in the process of element, method, article or equipment.
Finally it should be noted that：Embodiment described above, it is only the embodiment of the present invention, to illustrate the present invention
Technical scheme, rather than its limitations, protection scope of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, it will be understood by those within the art that：Any one skilled in the art
The invention discloses technical scope in, it can still modify to the technical scheme described in previous embodiment or can be light
Change is readily conceivable that, or equivalent substitution is carried out to which part technical characteristic；And these modifications, change or replacement, do not make
The essence of appropriate technical solution departs from the spirit and scope of technical scheme of the embodiment of the present invention, should all cover the protection in the present invention
Within the scope of.Therefore, protection scope of the present invention described should be defined by scope of the claims.
Claims (10)
1. a kind of power network classification of the items based on machine learning determines method, it is characterised in that including：
Obtain the history item data of multiple distribution projects and time series corresponding to each history item data；
The load density according to corresponding to the history item data and the time series determine each history item data
Curve；
Multiple load density curves are subjected to cluster analysis, obtain multiple classifications of the items；
Obtain characteristic information corresponding to each classification of the items；
According to multiple classifications of the items, with each corresponding characteristic information of classification of the items and default machine learning
Algorithm structure classification of the items determines model.
2. according to the method for claim 1, it is characterised in that described to be believed according to the history item data and the time
Breath determines load density curve corresponding to each history item data, including：
Fitting of a polynomial is carried out to the history item data and the time series, obtains each history item data pair
The matched curve answered；
Multiple matched curves are normalized respectively, obtain multiple load density curves.
3. according to the method for claim 2, it is characterised in that described that multiple load density curves are subjected to cluster point
Analysis, obtains multiple classifications of the items, including：
The multiple load density curve is subjected to cluster analysis, obtains at least one curve combination, each curve combination
Include at least one load density curve；
For curve combination each described, average load density curve corresponding with the curve combination is calculated；
In each curve combination, the load density song for being more than predetermined threshold value the difference between average load density curve is rejected
Line, until the average load density curve is restrained；
Determine that existing curve combination belongs to same project classification during the average load density curve convergence.
4. according to the method for claim 3, it is characterised in that the default machine learning algorithm include XGBoost algorithms,
Random forests algorithm, SVMs and/or k nearest neighbor algorithms.
5. a kind of power network classification of the items based on machine learning determines method, it is characterised in that methods described includes：
Obtain the characteristic information of target distribution project；
The classification of the items that the characteristic information is input to as described in claims 1 to 3 is any is determined in model, obtains the mesh
The classification of the items of mark project.
6. according to the method for claim 5, it is characterised in that methods described also includes：
Average load density curve corresponding to the classification of the items is defined as to the prediction curve of the destination item.
A kind of 7. power network classification of the items determining device based on machine learning, it is characterised in that including：
First acquisition module (11), for the history item data for obtaining multiple distribution projects and each history item data
Corresponding time series；
Determining module (12), for determining each history entries mesh number according to the history item data and the time series
According to corresponding load density curve；
Cluster Analysis module (13), for multiple load density curves to be carried out into cluster analysis, obtain multiple classifications of the items；
Second acquisition module (14), for obtaining characteristic information corresponding to each classification of the items；
Module (15) is built, for believing according to multiple classifications of the items, the feature corresponding with each classification of the items
Breath and default machine learning algorithm structure classification of the items determine model.
8. a kind of power network classification of the items determining device based on machine learning, it is characterised in that described device includes：
3rd acquisition module (21), for obtaining the characteristic information of target distribution project；
Input module (22), determined for the characteristic information to be input to the classification of the items as described in claims 1 to 3 is any
In model, the classification of the items of the destination item is obtained.
9. a kind of electronic equipment, including memory, processor, it is stored with what can be run on the processor in the memory
Computer program, it is characterised in that realize that the claims 1 to 3 are any during computer program described in the computing device
Described in method the step of.
10. a kind of computer-readable medium for the non-volatile program code that can perform with processor, it is characterised in that described
Program code makes any methods describeds of claim 1-3 described in the computing device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710573258.4A CN107368853A (en) | 2017-07-14 | 2017-07-14 | Power network classification of the items based on machine learning determines method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710573258.4A CN107368853A (en) | 2017-07-14 | 2017-07-14 | Power network classification of the items based on machine learning determines method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107368853A true CN107368853A (en) | 2017-11-21 |
Family
ID=60308399
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710573258.4A Pending CN107368853A (en) | 2017-07-14 | 2017-07-14 | Power network classification of the items based on machine learning determines method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107368853A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108551167A (en) * | 2018-04-25 | 2018-09-18 | 浙江大学 | A kind of electric power system transient stability method of discrimination based on XGBoost algorithms |
| CN115099554A (en) * | 2022-05-08 | 2022-09-23 | 广东电网有限责任公司电力调度控制中心 | Power grid operation information analysis method and device based on machine learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164779A (en) * | 2013-04-08 | 2013-06-19 | 国家电网公司 | Processing method and device of electric power system data |
| CN104881706A (en) * | 2014-12-31 | 2015-09-02 | 天津弘源慧能科技有限公司 | Electrical power system short-term load forecasting method based on big data technology |
| CN105184486A (en) * | 2015-09-08 | 2015-12-23 | 国网智能电网研究院 | Power grid business classification method based on directed acyclic graphs support vector machine |
| WO2016113481A1 (en) * | 2015-01-16 | 2016-07-21 | Peugeot Citroen Automobiles Sa | Method for identifying the open-circuit voltage curve of an ageing electric cell |
-
2017
- 2017-07-14 CN CN201710573258.4A patent/CN107368853A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164779A (en) * | 2013-04-08 | 2013-06-19 | 国家电网公司 | Processing method and device of electric power system data |
| CN104881706A (en) * | 2014-12-31 | 2015-09-02 | 天津弘源慧能科技有限公司 | Electrical power system short-term load forecasting method based on big data technology |
| WO2016113481A1 (en) * | 2015-01-16 | 2016-07-21 | Peugeot Citroen Automobiles Sa | Method for identifying the open-circuit voltage curve of an ageing electric cell |
| CN105184486A (en) * | 2015-09-08 | 2015-12-23 | 国网智能电网研究院 | Power grid business classification method based on directed acyclic graphs support vector machine |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108551167A (en) * | 2018-04-25 | 2018-09-18 | 浙江大学 | A kind of electric power system transient stability method of discrimination based on XGBoost algorithms |
| CN115099554A (en) * | 2022-05-08 | 2022-09-23 | 广东电网有限责任公司电力调度控制中心 | Power grid operation information analysis method and device based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Henn et al. | Metaheuristics for order batching and sequencing in manual order picking systems | |
| Sethi et al. | Hierarchical decision making in stochastic manufacturing systems | |
| Gan et al. | Joint optimization of maintenance, buffer, and spare parts for a production system | |
| CN111401801B (en) | Processing system and method for determining decentralized storage of target object warehouse | |
| CN107016571A (en) | Data predication method and its system | |
| CN109242135A (en) | A kind of model method for running, device and service server | |
| CN106452884A (en) | A data distribution method and apparatus in a block chain system | |
| CN103685347B (en) | Method and device for allocating network resources | |
| CN109741177A (en) | Appraisal procedure, device and the intelligent terminal of user credit | |
| CN107292420A (en) | Data processing method and device | |
| CN106407305A (en) | Data mining system and method | |
| CN111932044A (en) | Steel product price prediction system and method based on machine learning | |
| CN114170002A (en) | Method and device for predicting access frequency | |
| CN107368853A (en) | Power network classification of the items based on machine learning determines method and device | |
| CN115330201A (en) | Power grid digital project pareto optimization method and system | |
| CN108304975A (en) | A kind of data prediction system and method | |
| CN107688901A (en) | Data adjustment method and device | |
| CN106528774A (en) | Method and apparatus for predicting distribution network project management trend | |
| Raoofpanah et al. | Extended hybrid tabu search and simulated annealing algorithm for location-inventory model with multiple products, multiple distribution centers and multiple capacity levels | |
| CN110298390A (en) | A kind of feature selection approach and device of air control model | |
| CN107844496A (en) | Statistical information output intent and device | |
| CN116976712A (en) | Root cause determination method, device, equipment and storage medium for abnormality index | |
| CN111984637B (en) | Missing value processing method and device in data modeling, equipment and storage medium | |
| NAPITUPULU | Artificial neural network application in gross domestic product forecasting an Indonesia case | |
| CN114140023A (en) | Project risk determination method and device, electronic equipment and storage medium |
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: 20171121 |