CN110363383A - A kind of distributed power generation monitoring technology based under digital development - Google Patents
A kind of distributed power generation monitoring technology based under digital development Download PDFInfo
- Publication number
- CN110363383A CN110363383A CN201910476223.8A CN201910476223A CN110363383A CN 110363383 A CN110363383 A CN 110363383A CN 201910476223 A CN201910476223 A CN 201910476223A CN 110363383 A CN110363383 A CN 110363383A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- power generation
- business
- distributed power
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 225
- 238000010248 power generation Methods 0.000 title claims abstract description 142
- 238000005516 engineering process Methods 0.000 title claims abstract description 12
- 238000011161 development Methods 0.000 title claims abstract description 9
- 238000013461 design Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000002360 preparation method Methods 0.000 claims abstract description 9
- 238000007711 solidification Methods 0.000 claims abstract description 5
- 230000008023 solidification Effects 0.000 claims abstract description 5
- 238000010276 construction Methods 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 17
- 230000013011 mating Effects 0.000 claims description 17
- 238000012795 verification Methods 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 16
- 238000013499 data model Methods 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 230000005611 electricity Effects 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 6
- 238000000611 regression analysis Methods 0.000 claims description 6
- 230000008901 benefit Effects 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000011160 research Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 238000012098 association analyses Methods 0.000 claims description 3
- 238000009412 basement excavation Methods 0.000 claims description 3
- 238000007418 data mining Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000005065 mining Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 210000001520 comb Anatomy 0.000 claims description 2
- 239000000470 constituent Substances 0.000 claims description 2
- 238000007689 inspection Methods 0.000 claims description 2
- 230000001737 promoting effect Effects 0.000 claims description 2
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 238000013139 quantization Methods 0.000 abstract description 3
- 238000007726 management method Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000003416 augmentation Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Water Supply & Treatment (AREA)
- Algebra (AREA)
- Public Health (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a kind of distributed power generation monitoring technology based under digital development, belong to generation monitoring field.The invention fully considers grid company specialized management needs and grid company operation hot spot, in conjunction with monitoring business new system, carry out the detailed design of monitoring business, specifically include distributed power generation monitoring service design, data preparation, data processing, business model, it calculates and analyzes, the monitoring service link greatly of achievement solidification six, the hot spot of true reflection grid company inside and outside concern, difficult point, risk point, advanced optimize the content and range of distributed power generation monitoring business, constantly expand the breadth and depth of monitoring business, quantization reflects novel monitoring system, the execution of comprehensive support grid company strategy and whole operation.
Description
Technical field
The invention belongs to generation monitoring technical fields, and in particular to a kind of distributed power generation prison based under digital development
Survey technology.
Technical background
Currently in grid company operation data asset management, distributed power generation monitoring there are monitoring system missing,
Monitoring business sheet one, monitoring instrument tradition, monitoring content is on the low side, monitoring result shows that form needs to be enriched, Monitoring Result is to industry
The problems such as closed loop service ability of business is weak.Upper level distributed power generation operation data asset management monitoring, it is main by removing
Data mode carries out monitoring analysis, base's power grid unit in terms of distributed power generation data acquisition there is also difficulty, data and
Shi Xing, authenticity questions, also affect the development of monitoring analysis work to a certain extent, and the technological means for monitoring analysis is fallen
Afterwards, lack the tool and environment of data analysis mining, the basis of big data application is also very weak, does not establish lasting, substantial, complete
Kind specialized team constrains the depth and range of distributed power generation monitoring analysis, the exhibition of conventional electric power generation business monitoring result
Existing form with report and report etc. in writing form based on, visualization is not high.
Specifically there are problems that at following 4 points:
First is that distributed power generation monitoring visual angle is single.Grid company carries out distributed power generation monitoring business still with electricity at present
Based on net company visual angle, lacks the application at client visual angle, do not embody theory customer-centric really, lead to distributed power generation
There is certain discrepancy in monitoring result and client's subjective perception, therefore grid company needs to use for reference external view evaluation, extends distribution
Formula generation monitoring visual angle bases oneself upon client's core demand and carries out monitoring.
Second is that distributed power generation monitoring mode tradition.Current distributed power generation monitoring is still according to conventional power generation profession item
Line is carried out monitoring, is carried out in such a way that service logic carries out monitoring, and the complicated monitoring of different type distributed power generation can not be adapted to
Service conditions, it is therefore desirable to which innovation, which is carried out, monitors new model by the business that influent factor carries out distributed power generation monitoring, and innovation is opened
Exhibition industry business monitoring.
Third is that distributed power generation data source is single.Current distributed power generation business monitoring is mainly in existing grid company
Based on portion's data, it is short of the acquisition and analysis to third party evaluation data and distributed power generation client's subjective perception data, it is right
The accuracy of monitoring result has a certain impact.Therefore it needs to establish distributed power generation external data collection mechanism, acquires multi-source
Change objective data and carry out monitoring, associated data value is deeply excavated in augmentation data fusion.
Fourth is that distributed power generation monitoring instrument tradition.Due to lacking the application of big data analysis tool, traditional monitoring means
It is difficult to meet the needs of to mass data processing and analysis.Therefore it needs to study and use of the new technology, new tool carries out distribution
The monitoring of power generation business constructs specialized monitoring model and improves monitoring efficiency and accuracy.
Business effect is monitored to play distributed power generation conscientiously, the strengthened research of monitoring business is realized, is based on grid company
Monitoring business new system fully considers specialized management needs and grid company operation hot spot, monitors business achievement in conjunction with early period, open
It opens up distributed power generation and monitors business detailed design, it is true to reflect the hot spot paid close attention to grid company inside and outside, difficult point, risk point, into
One-step optimization distributed power generation monitors the content and range of business, constantly expands the breadth and depth of monitoring business, quantization reflection
Novel monitoring system, comprehensive support grid company strategy executes and whole operation.
Summary of the invention
Business effect is monitored to play grid company conscientiously, realizes the strengthened research of monitoring business, the present invention is based on monitorings
Business new system fully considers that grid company specialized management needs and operation hot spot is carried out and divided in conjunction with monitoring early period business achievement
Cloth generation monitoring business detailed design, the true distributed power generation hot spot for reflecting the concern of grid company inside and outside, difficult point, risk
Point advanced optimizes the content and range of distributed power generation monitoring business, constantly expands the breadth and depth of monitoring business, quantization
Reflect novel monitoring system, the execution of comprehensive support grid company strategy and whole operation.
The present invention, which is that the following technical solution is employed, to be implemented: a kind of distributed power generation monitoring based under digital development
Technology, comprising:
Step S1: selected distributed power generation monitoring range formulates key link and work step that monitoring business is carried out;
Step S2: the service design stage mainly includes that distributed power generation monitoring requirements collect and theme determination, business combing
With Monitoring Design etc.;
Step S3: data preparation stage mainly includes distributed power generation monitoring data demand and trace to the source, data acquisition and mention
It takes;
Step S4: data processing stage mainly includes distributed power generation monitoring data quality verification, data cleansing processing etc.;
Step S5: the business model stage mainly includes distributed power generation monitoring data model construction, model training and verifying
Deng;
Step S6: calculating the analysis phase mainly includes that distributed power generation monitoring data calculate excavation, Monitoring Result output etc.;
Step S7: achievement cure stage mainly includes the optimization of distributed power generation monitoring model and tool configuration etc..
Optionally, the step S1:
Region zones are carried out according to the rank in province, city, county, area, specify boundary and the range of research area;It formulates distributed
Generation monitoring service design, data preparation, data processing, business model, calculating and analysis, achievement solidification six monitoring business ring greatly
Section provides preparation for precisely monitoring distributed power generation situation.
Optionally, the step S2:
(a) distributed power generation monitoring requirements are collected determines with theme
From grid company strategy operation needs, company leader's requirement, business department's demand etc., combing integration is distributed
Generation monitoring business demand;According to monitoring business demand, the related service being related to is combed out, summarizes refine according to demand, is formed
Monitor theme.
(b) distributed power generation monitoring business combing and Monitoring Design
For distributed power generation condition monitoring business-subject, from construction, installation, power generation, consumption, clearing;Efficiency, benefit,
Risk closes the dimensions such as rule, quality, organizes test unit, determines distributed power generation monitoring object, monitoring range, monitoring objective, prison
Survey mode decomposes business tine, forms specific monitoring content;In conjunction with inside and outside visual angle, according to regulatory requirements be associated with
System, business rule, the mapping relations etc. that tissue test unit combing monitoring business tine is related to.
Optionally, the step S3:
(a) distributed power generation monitoring data demand with trace to the source
According to monitoring business tine, monitoring business rule, from distributed power generation basic condition, operating condition, service quality
Angularly, tissue test unit carries out the combing work of distributed power generation condition monitoring business inside and outside data, for data requirements
Each of table business datum item, traces back and comes sources operation system, sources, tables of data, corresponding field clearly, differentiate data item it
Between association matching relationship, and be based on test unit's related ends, Develop Data demand differenceization compare, form unified monitoring
Business datum demand schedule.
(b) acquisition of distributed power generation monitoring data and extraction
Fortune inspection is stored in from source system acquisition part or full dose distributed power generation monitoring data in conjunction with verification process of tracing to the source
Data area;The detail business datum of range needed for extracting, the input source calculated as business data model.
Optionally, the step S4:
(a) distributed power generation monitoring data quality verification
From data integrity, normalization, reasonability, accuracy, consistency etc., using R, Python, Java,
Distributed power generation condition monitoring correlation detailed data Develop Data kernel of mass of the tools such as MatLab, SAS, EXCEL to extraction
It looks into, the availability and validity of verify data, forms quality of data inventory, promote business department and provincial company development source data
It administers.
(b) distributed power generation monitoring data cleaning treatment
Based on distributed power generation condition monitoring business reality and data requirements, data cleansing, transformation rule are formed, cleans nothing
Data are imitated, the valid data collection of detail business datum is formed.Relationship maps relationship between combined data table, data item is formed
The corresponding wide table of detail business datum of Monitoring Rules.According to business demand, Data Integration tool is write, output meets monitoring requirements
Detail business datum table, formed monitoring grade data.
Optionally, the step S5:
(a) distributed power generation monitoring business data model building
Based on distributed power generation condition monitoring business tine, rule and data requirements, organizes test unit's association, gathers
The digging technologies such as class construct applicable business data model, carry out abstract to business and digitization is expressed, construct business datum
Model.For the mating power grid construction monitoring to generate electricity in a distributed manner:
A1. regression analysis: by being fitted the mating electricity power engineering construction period probability density curve of distributed power generation, acquisition is applied
Work duration probability density function, and then solve and create mating electricity power engineering construction Optimal Project Duration.
A1.1 solves probability density function
Duration feature: approximation obeys unimodal normal distribution, axisymmetricly concave function form.
Thinking: according to typical case data, kernel density function Fitted probability density curve obtains expression formula
A1.2 solves optimum interval endpoint value
Principle: in probability density curve, there are symmetrical two o'clock, the speedup (probability of stochastic variable probability change rate
The second dervative of density function) it is maximum.
A1.3 result verification method
Principle: calculated result is verified using histogram, optimum interval should include the mountain portions in histogram.
A2. it association analysis: calculates mating power grid construction project and goes into operation completion rate and operation completion rate, and be associated ratio
It is right, focusing go into operation, the lower unit of operation completion rate, estimate project schedule plan execute risk.
Go into operation completion rate=practical on-stream item number/plan on-stream item number
Operation completion rate=practical operation item number/plan operation item number
A3. it clustering: calculates the mating power grid construction project of distributed power generation and goes into operation (operation) extension item number and extension
Duration, and clustering is carried out to extension duration, grasp extension duration integrated distribution situation.
Project delay: actually go into operation (operation) time > plan goes into operation (operation) time
M- plan goes into operation (operation) time when extension duration=actually go into operation (operation)
Other monitoring models can be constructed according to specific business model.
(b) model training and verifying
It organizes test unit to carry out model training and verifying work, extracts a certain proportion of data, substitute into distributed power generation
Condition monitoring data model is trained, the parameters such as accuracy, degree of fitting based on training result, verify model feasibility,
Reasonability and accuracy.To model training verification result, is assessed in conjunction with business is practical, business model ginseng is adaptively adjusted
Number, meets monitoring requirements.
Optionally, the step S6:
Data are calculated to excavate and be exported with Monitoring Result, and using distributed power generation condition monitoring model, Develop Data is calculated, closed
Connection excavates, and forms monitoring result;Constituent parts monitoring result is collected, and carries out diversity ratio pair, optimizes the monitoring to be formed and be summarized
As a result;Distributed power generation condition monitoring is interpreted as a result, forming the achievements such as result chart, monitoring report.
Optionally, the step S7:
Model iteration optimization and tool algorithm configure, and assess the deviation feelings of distributed power generation monitoring result and practical business
Condition optimizes model;Solidify monitoring report mould using tools such as data processing, data minings according to the report template of setting
Formula.
Detailed description of the invention
It, below will be to the prior art in order to more clearly illustrate the embodiment of the present invention and technical solution in the prior art
The required attached drawing used does some simple introductions in description, it is obvious that and attached drawing below is a part of the embodiments of the present invention,
It for those of ordinary skill in the art, can also be according to these attached drawings under the premise of not paying any creative work
Obtain other attached drawings.
Fig. 1 is distributed power generation monitoring technology route map;
Fig. 2 is the mating power grid construction project overall process monitoring step of distributed roof photovoltaic;
Fig. 3 is distributed power generation monitoring business rule combing;
Fig. 4 is the combing of distributed power generation monitoring data demand;
Fig. 5 is that distributed power generation monitoring data are traced to the source;
Fig. 6 distributed power generation monitoring data quality verification frame;
Fig. 7 distributed power generation monitoring data quality verification content;
Fig. 8 is distributed power generation monitoring business data model building;
Fig. 9 is that distributed power generation monitoring regression analysis solves probability density function figure;
Figure 10 is that distributed power generation monitoring regression analysis solves optimum interval endpoint value;
Figure 11 is distributed power generation monitoring Regression Analysis Result verification method functional arrangement.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
A kind of distributed power generation monitoring technology based under digital development of the present invention, as shown in Figure 1, comprising:
The clear monitoring range of step S1.Region zones are carried out according to the rank in province, city, county, area, specify the side of research area
Boundary and range, such as Senior Residents in Fengxian District of Shanghai;Formulation distributed power generation monitoring service design, data preparation, data processing, business are built
Mould, calculating and analysis, achievement solidification six monitoring service link greatly provide preparation for precisely monitoring distributed power generation situation.Specifically
Case can be by taking the distributed roof photovoltaic of Senior Residents in Fengxian District of Shanghai as an example.
Step S2 service design:
(a) distributed power generation monitoring monitoring business demand collects
Monitoring function positioning is executed based on grid company strategy operation, external view is adhered to and sees that fortune is seen at visual angle by company, company
Seek two visual angles, source service party and state overall situation, corporate strategy operation needs, company leader's aid decision, business department's essence
Benefit manages, all kinds of demands of grass-roots unit's work improvement comb for specific distributed power generation monitoring field and are integrally formed prison
The power grids related services such as business demand, such as reflection construction, operation, consumption, clearing are surveyed, reflection emission reduction, clean energy resource consumption account for
Than etc. public's hot spot demand.
(b) distributed power generation monitoring business division combing
Business demand is monitored according to distributed power generation, the business being related to is combed, clears the incidence relation between business, is focused
Value point, the sensitive spot of grid company operation determine distributed power generation business monitoring key point and relating dot, form monitoring business
Theme, such as the theme that grid company, local government, upstream and downstream firms, the public pay close attention to.
(c) distributed power generation monitoring business tine determines
Theme is monitored for distributed power generation, from construction, installation, power generation, consumption, clearing;Efficiency, benefit, risk, conjunction
The dimensions such as rule, quality determine monitoring object, monitoring range, monitoring objective, monitoring mode, decompose business tine, form specific prison
Survey content.Business is described in detail for the mating power grid construction project overall process of roof photovoltaic in a distributed manner and monitors specific steps, such as
Fig. 2.
(d) distributed power generation monitoring business rule combing
In conjunction with inside and outside visual angle, is required according to regulatory and incidence relation, combing distributed power generation monitor business tine
Business rule, mapping relations for being related to etc., such as Fig. 3.
Step S3 data preparation:
(a) distributed power generation monitoring data demand combs
According to distributed power generation monitoring business tine, monitoring business rule, combing monitoring business datum item forms number in detail
According to demand schedule, such as Fig. 4.
Corresponding distributed power generation monitoring dimension, monitoring point and monitoring business rule, logic, comb each monitoring point, dimension
The original field of corresponding business datum, process calculated field indicate Chinese connotation, the english note of each field, clear every
A explanation of field, field type, unit, measuring accuracy etc..It such as goes into operation, in terms of the monitoring of operation timeliness, is related to provincial company, districts and cities
Company, year, 16 data fields such as build Guan Danwei, project name, project code, voltage class, project type.
(b) distributed power generation monitoring data are traced to the source
For each of data requirements table business datum item, traces back and comes sources operation system, tables of data, corresponding field clearly,
Clear the association matching relationship between data item, such as Fig. 5.
(c) distributed power generation monitoring data acquire
In conjunction with the combing of distributed power generation monitoring data demand and verifying of tracing to the source, pass through the modes such as collection under system interface, line
Full dose data needed for obtaining monitoring business-subject, and carry out the integrality of acquisition data, checking consistency.
(d) distributed power generation monitoring data are extracted
It is combed in conjunction with distributed power generation monitoring data demand, required detail business datum is extracted, as business datum mould
The input source that type calculates.
Step S4 data processing:
(a) distributed power generation monitoring data quality verification
Data integrity, normalization, reasonability, accuracy, consistency etc. carry out the detailed business data of extraction
The quality of data is verified, the availability and validity of verify data, forms quality of data inventory, and department's source data of promoting business are controlled
Reason, such as Fig. 6, Fig. 7.
(b) distributed power generation monitoring data cleaning conversion
Business reality and data requirements are monitored based on distributed power generation, forms data cleansing, transformation rule, cleans invalid number
According to the valid data collection of formation detail business datum;Cleaning rule: invalid data, supplement missing data are deleted;Transformation rule:
Data type conversion, data item merging, dimension transformation etc..
(c) distributed power generation monitoring data association matching
Relationship maps relationship between combined data table, data item forms the wide table of detail business datum.
The mating power grid capital construction basic information table that generates electricity in a distributed manner is main table, will be in data collection list by " project code "
" building Guan Danwei ", " practical settlement time ", " practical final accounts time ", " general item investment ", " construction place requisition and cleaning
Expense " is matched in basic information table.
(d) distributed power generation monitoring data are integrated
Data Integration foot is write according to monitoring business demand to the wide table of distributed power generation detail business datum after matching
This, output meets the detail business datum table of monitoring requirements, forms monitoring grade data.
Step S5 business model:
(a) distributed power generation monitoring business data model building
Based on distributed power generation monitoring business tine, rule and data requirements, the digging technologies such as association, cluster, structure
Mutually applicable business data model is built, abstract is carried out to business and digitization is expressed, such as Fig. 8.
(a1) distributed power generation monitors regression analysis: by being fitted the mating electricity power engineering construction period probability of distributed power generation
Density curve obtains construction period probability density function, and then solves and create mating electricity power engineering construction Optimal Project Duration.
1. solving probability density function
Duration feature: approximation obeys unimodal normal distribution, axisymmetricly concave function form.
Thinking: kernel density function Fitted probability density curve obtains expression formula, as shown in Figure 9.
2. solving optimum interval endpoint value
Principle: in probability density curve, there are symmetrical two o'clock, the speedup (probability of stochastic variable probability change rate
The second dervative of density function) it is maximum, as shown in Figure 10.
3. result verification method
Principle: calculated result is verified using histogram, optimum interval should be comprising the mountain portions in histogram, such as Figure 11 institute
Show.
(a2) it association analysis: calculates mating power grid construction project and goes into operation completion rate and operation completion rate, and be associated ratio
It is right, focusing go into operation, the lower unit of operation completion rate, estimate project schedule plan execute risk.
Go into operation completion rate=practical on-stream item number/plan on-stream item number
Operation completion rate=practical operation item number/plan operation item number
(a3) it clustering: calculates the mating power grid construction project of distributed power generation and goes into operation (operation) extension item number and extension
Duration, and clustering is carried out to extension duration, grasp extension duration integrated distribution situation.
Project delay: actually go into operation (operation) time > plan goes into operation (operation) time
M- plan goes into operation (operation) time when extension duration=actually go into operation (operation)
(b) model training and verifying
In conjunction with business datum feature and data requirements, sample data is extracted, distributed power generation is substituted into and monitors business datum mould
Type is trained, and verifies the feasibility, reasonability and accuracy of model.
(c) model is adjusted and improved
In conjunction with business model training verification result, model parameter is adaptively adjusted, meets monitoring business demand.
Step S6 data calculate and analysis:
(a) data, which calculate, excavates
Using monitoring model, calculating, association mining are carried out to distributed power generation full dose data, form monitoring result.
(b) Monitoring Result exports
Monitoring result is interpreted in conjunction with distributed power generation business, the various forms achievements such as result chart, monitoring report is formed, opens
Exhibition shows content design and configuration, and various dimensions embody monitoring result.
The solidification of step S7 achievement:
(a) model iteration optimization
Distributed power generation monitoring result and the actual deviation situation of business are assessed, business monitoring model is optimized.
(b) tool algorithm configures
According to algorithm, the data processing of model flexible configuration distributed power generation, data mining and business monitoring instrument, according to setting
Fixed report template.Solidify monitoring report mode.
Claims (8)
1. a kind of distributed power generation monitoring technology based under digital development characterized by comprising
Step S1: selected distributed power generation monitoring range formulates key link and work step that monitoring business is carried out;
Step S2: the service design stage mainly includes that distributed power generation monitoring requirements collect and theme determination, business combing and prison
Survey design etc.;
Step S3: data preparation stage mainly include distributed power generation monitoring data demand and trace to the source, data acquisition with extract etc.;
Step S4: data processing stage mainly includes distributed power generation monitoring data quality verification, data cleansing processing etc.;
Step S5: the business model stage mainly includes distributed power generation monitoring data model construction, model training and verifying etc.;
Step S6: calculating the analysis phase mainly includes that distributed power generation monitoring data calculate excavation, Monitoring Result output etc.;
Step S7: achievement cure stage mainly includes the optimization of distributed power generation monitoring model and tool configuration etc..
2. the method according to claim 1, wherein in the step S1 according to province, city, county, area rank into
Row region zones specify boundary and the range of research area;It formulates distributed power generation and monitors service design, data preparation, data
Processing, business model, calculating and analysis, achievement solidification six monitoring service link greatly, mention for precisely monitoring distributed power generation situation
For preparing.
3. the method according to claim 1, wherein including: in the step S2
(1) distributed power generation monitoring requirements are collected determines with theme
From grid company strategy operation needs, company leader's requirement, business department's demand etc., distributed power generation is integrated in combing
Monitor business demand;According to monitoring business demand, the related service being related to is combed out, summarizes refine according to demand, forms monitoring
Theme.
(2) distributed power generation monitoring business combing and Monitoring Design
For distributed power generation condition monitoring business-subject, from construction, installation, power generation, consumption, clearing;Efficiency, benefit, risk,
The dimensions such as rule, quality are closed, test unit is organized, determines distributed power generation monitoring object, monitoring range, monitoring objective, monitoring side
Formula decomposes business tine, forms specific monitoring content;In conjunction with inside and outside visual angle, according to regulatory requirements and incidence relation, group
Knit business rule, mapping relations etc. that test unit's combing monitoring business tine is related to.
4. the method according to claim 1, wherein in the step S3:
(1) distributed power generation monitoring data demand with trace to the source
According to monitoring business tine, monitoring business rule, from distributed power generation basic condition, operating condition, service quality isogonism
Degree, tissue test unit carries out distributed power generation condition monitoring business inside and outside data and combs work, in data requirements table
Each business datum item, trace back and come sources operation system, sources, tables of data, corresponding field clearly, differentiate between data item
It is associated with matching relationship, and is based on test unit's related ends, Develop Data demand differenceization compares, and forms unified monitoring business
Data requirements table.
(2) acquisition of distributed power generation monitoring data and extraction
Fortune inspection data are stored in from source system acquisition part or full dose distributed power generation monitoring data in conjunction with verification process of tracing to the source
Region;The detail business datum of range needed for extracting, the input source calculated as business data model.
5. the method according to claim 1, wherein in the step S4:
(1) distributed power generation monitoring data quality verification
From data integrity, normalization, reasonability, accuracy, consistency etc., using R, Python, Java, MatLab,
The tools such as SAS, EXCEL verify number to the distributed power generation condition monitoring correlation detailed data Develop Data quality verification of extraction
According to availability and validity, form quality of data inventory, department and the provincial company of promoting business are carried out source data and administered.
(2) distributed power generation monitoring data cleaning treatment
Business reality and data requirements are monitored based on distributed power generation, forms data cleansing, transformation rule, cleans invalid data,
Form the valid data collection of detail business datum.Relationship maps relationship between combined data table, data item forms Monitoring Rules
The corresponding wide table of detail business datum.According to business demand, Data Integration tool is write, output meets the detail industry of monitoring requirements
Business tables of data forms monitoring grade data.
6. the method according to claim 1, wherein in the step S5:
(1) distributed power generation monitoring business data model building
Based on distributed power generation monitoring business tine, rule and data requirements, tissue test unit's association, cluster etc. are excavated
Technology constructs applicable business data model, carries out abstract to business and digitization is expressed, construct business data model.With
For the mating power grid construction monitoring of distributed power generation:
A. regression analysis: by being fitted the mating electricity power engineering construction period probability density curve of distributed power generation, construction work is obtained
Phase probability density function, and then solve and create mating electricity power engineering construction Optimal Project Duration.
A1 solves probability density function
Duration feature: approximation obeys unimodal normal distribution, axisymmetricly concave function form.
Thinking: according to typical case data, kernel density function Fitted probability density curve obtains expression formula
A2 solves optimum interval endpoint value
Principle: in probability density curve, there are symmetrical two o'clock, the speedup (probability density of stochastic variable probability change rate
The second dervative of function) it is maximum.
A3 result verification method
Principle: calculated result is verified using histogram, optimum interval should include the mountain portions in histogram.
B. association analysis: calculating mating power grid construction project and go into operation completion rate and operation completion rate, and be associated comparison, focuses
It goes into operation, the lower unit of operation completion rate, estimates project schedule plan and execute risk.
Go into operation completion rate=practical on-stream item number/plan on-stream item number
Operation completion rate=practical operation item number/plan operation item number
C. clustering: calculating the mating power grid construction project of distributed power generation and go into operation (operation) extension item number and extension duration,
And clustering is carried out to extension duration, grasp extension duration integrated distribution situation.
Project delay: actually go into operation (operation) time > plan goes into operation (operation) time
M- plan goes into operation (operation) time when extension duration=actually go into operation (operation)
Other monitoring models can be constructed according to specific business model.
(2) model training and verifying
It organizes test unit to carry out model training and verifying work, extracts a certain proportion of data, substitute into distributed power generation monitoring
Data model is trained, the parameters such as accuracy, degree of fitting based on training result, verify the feasibility of model, reasonability and
Accuracy.To model training verification result, is assessed in conjunction with business is practical, business model parameter is adaptively adjusted, meets prison
Survey demand.
7. the method according to claim 1, wherein data calculate excavation in the step S6 and Monitoring Result is defeated
Out, using distributed power generation monitoring model, Develop Data calculating, association mining form monitoring result;Collect constituent parts monitoring knot
Fruit, and diversity ratio pair is carried out, optimize the monitoring result to be formed and be summarized;Distributed power generation condition monitoring is interpreted as a result, being formed
As a result the achievements such as chart, monitoring report.
8. the method according to claim 1, wherein model iteration optimization is matched with tool algorithm in the step S7
It sets, assesses the deviation situation of distributed power generation monitoring result and practical business, optimize model;According to the report mould of setting
Plate solidifies monitoring report mode using tools such as data processing, data minings.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910476223.8A CN110363383A (en) | 2019-06-03 | 2019-06-03 | A kind of distributed power generation monitoring technology based under digital development |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910476223.8A CN110363383A (en) | 2019-06-03 | 2019-06-03 | A kind of distributed power generation monitoring technology based under digital development |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110363383A true CN110363383A (en) | 2019-10-22 |
Family
ID=68215561
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910476223.8A Pending CN110363383A (en) | 2019-06-03 | 2019-06-03 | A kind of distributed power generation monitoring technology based under digital development |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110363383A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112115127A (en) * | 2020-09-09 | 2020-12-22 | 陕西云基华海信息技术有限公司 | Distributed big data cleaning method based on python script |
Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090326726A1 (en) * | 2008-06-25 | 2009-12-31 | Versify Solutions, Llc | Aggregator, monitor, and manager of distributed demand response |
CN101872181A (en) * | 2009-04-22 | 2010-10-27 | 韩国电力公社 | Prediction method for monitoring performance of power plant instruments |
US20110167020A1 (en) * | 2010-01-06 | 2011-07-07 | Zhiping Yang | Hybrid Simulation Methodologies To Simulate Risk Factors |
CN103489078A (en) * | 2013-10-09 | 2014-01-01 | 国网上海市电力公司 | Intelligent charging and battery-swapping service network asset life-cycle management method based on RFID |
CN103792927A (en) * | 2007-03-12 | 2014-05-14 | 艾默生过程管理电力和水力解决方案有限公司 | Use of statistical analysis in power plant performance monitoring |
CN104517199A (en) * | 2015-01-16 | 2015-04-15 | 国家电网公司 | New energy power generation online monitoring method based on real time data |
CN105184471A (en) * | 2015-08-27 | 2015-12-23 | 北京国电通网络技术有限公司 | Method and device for online monitoring of project construction period |
CN105589958A (en) * | 2015-12-22 | 2016-05-18 | 浪潮软件股份有限公司 | Distributed big data planning method |
CN105608758A (en) * | 2015-12-17 | 2016-05-25 | 山东鲁能软件技术有限公司 | Big data analysis platform apparatus and method based on algorithm configuration and distributed stream computing |
CN105760980A (en) * | 2015-11-27 | 2016-07-13 | 国网山东省电力公司潍坊供电公司 | Intelligent operation system based on intelligent power grid framework |
CN105844426A (en) * | 2016-04-12 | 2016-08-10 | 国网上海市电力公司 | Grid-connected power plant technology supervision used quality assessing data processing method |
CN106228300A (en) * | 2016-07-20 | 2016-12-14 | 中国电力科学研究院 | A kind of distributed power source operation management system |
CN107038512A (en) * | 2016-02-03 | 2017-08-11 | 中国电力科学研究院 | A kind of index system method for building up |
CN107832869A (en) * | 2017-10-18 | 2018-03-23 | 国网上海市电力公司 | A kind of generated power forecasting method of wind-power electricity generation and photovoltaic generation |
KR20180078807A (en) * | 2016-12-30 | 2018-07-10 | 한국에너지기술연구원 | Wind resource prediction system using sea surface temperature |
GB201810314D0 (en) * | 2018-06-22 | 2018-08-08 | Moixa Energy Holdings Ltd | Systems for machine learning, optimising and managing local multi-asset flexibility of distributed energy storage resources |
WO2018199659A1 (en) * | 2017-04-28 | 2018-11-01 | 주식회사 효성 | Method for asset management of substation |
CN108804601A (en) * | 2018-05-29 | 2018-11-13 | 国网浙江省电力有限公司 | Power grid operation monitors the active analysis method of big data and device |
CN108879947A (en) * | 2018-06-06 | 2018-11-23 | 华南理工大学 | A kind of distributed photovoltaic power generation Control management system based on deep learning algorithm |
CN109409676A (en) * | 2018-09-27 | 2019-03-01 | 国网经济技术研究院有限公司 | Power grid project management method and system based on bidirectional risk identification model |
-
2019
- 2019-06-03 CN CN201910476223.8A patent/CN110363383A/en active Pending
Patent Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103792927A (en) * | 2007-03-12 | 2014-05-14 | 艾默生过程管理电力和水力解决方案有限公司 | Use of statistical analysis in power plant performance monitoring |
US20090326726A1 (en) * | 2008-06-25 | 2009-12-31 | Versify Solutions, Llc | Aggregator, monitor, and manager of distributed demand response |
CN101872181A (en) * | 2009-04-22 | 2010-10-27 | 韩国电力公社 | Prediction method for monitoring performance of power plant instruments |
US20110167020A1 (en) * | 2010-01-06 | 2011-07-07 | Zhiping Yang | Hybrid Simulation Methodologies To Simulate Risk Factors |
CN103489078A (en) * | 2013-10-09 | 2014-01-01 | 国网上海市电力公司 | Intelligent charging and battery-swapping service network asset life-cycle management method based on RFID |
CN104517199A (en) * | 2015-01-16 | 2015-04-15 | 国家电网公司 | New energy power generation online monitoring method based on real time data |
CN105184471A (en) * | 2015-08-27 | 2015-12-23 | 北京国电通网络技术有限公司 | Method and device for online monitoring of project construction period |
CN105760980A (en) * | 2015-11-27 | 2016-07-13 | 国网山东省电力公司潍坊供电公司 | Intelligent operation system based on intelligent power grid framework |
CN105608758A (en) * | 2015-12-17 | 2016-05-25 | 山东鲁能软件技术有限公司 | Big data analysis platform apparatus and method based on algorithm configuration and distributed stream computing |
CN105589958A (en) * | 2015-12-22 | 2016-05-18 | 浪潮软件股份有限公司 | Distributed big data planning method |
CN107038512A (en) * | 2016-02-03 | 2017-08-11 | 中国电力科学研究院 | A kind of index system method for building up |
CN105844426A (en) * | 2016-04-12 | 2016-08-10 | 国网上海市电力公司 | Grid-connected power plant technology supervision used quality assessing data processing method |
CN106228300A (en) * | 2016-07-20 | 2016-12-14 | 中国电力科学研究院 | A kind of distributed power source operation management system |
KR20180078807A (en) * | 2016-12-30 | 2018-07-10 | 한국에너지기술연구원 | Wind resource prediction system using sea surface temperature |
WO2018199659A1 (en) * | 2017-04-28 | 2018-11-01 | 주식회사 효성 | Method for asset management of substation |
CN107832869A (en) * | 2017-10-18 | 2018-03-23 | 国网上海市电力公司 | A kind of generated power forecasting method of wind-power electricity generation and photovoltaic generation |
CN108804601A (en) * | 2018-05-29 | 2018-11-13 | 国网浙江省电力有限公司 | Power grid operation monitors the active analysis method of big data and device |
CN108879947A (en) * | 2018-06-06 | 2018-11-23 | 华南理工大学 | A kind of distributed photovoltaic power generation Control management system based on deep learning algorithm |
GB201810314D0 (en) * | 2018-06-22 | 2018-08-08 | Moixa Energy Holdings Ltd | Systems for machine learning, optimising and managing local multi-asset flexibility of distributed energy storage resources |
CN109409676A (en) * | 2018-09-27 | 2019-03-01 | 国网经济技术研究院有限公司 | Power grid project management method and system based on bidirectional risk identification model |
Non-Patent Citations (1)
Title |
---|
龚秋霖等: "火电厂化学技术监督模式的探索与发展", 《华东电力》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112115127A (en) * | 2020-09-09 | 2020-12-22 | 陕西云基华海信息技术有限公司 | Distributed big data cleaning method based on python script |
CN112115127B (en) * | 2020-09-09 | 2023-03-03 | 陕西云基华海信息技术有限公司 | Distributed big data cleaning method based on python script |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Tang et al. | Spatio-temporal variation and coupling coordination relationship between urbanisation and habitat quality in the Grand Canal, China | |
Giordono et al. | Opposition “overblown”? Community response to wind energy siting in the Western United States | |
CN109636870A (en) | A kind of long and narrow figure spot piecemeal melts method and device | |
CN105930424A (en) | Method for realizing online asynchronous acquisition and intelligent mining of power distribution network data | |
KR102513348B1 (en) | A system and method for improving estimation to maximize profit of adjusted payments | |
CN110009416A (en) | A kind of system based on big data cleaning and AI precision marketing | |
CN103559588A (en) | Log mining method based on Petri network behavior profile | |
Yuanyuan et al. | A new framework on regional smart water | |
CN110363383A (en) | A kind of distributed power generation monitoring technology based under digital development | |
CN109861231A (en) | A kind of electric system Interval Power Flow method based on convex polygon | |
Xiong et al. | Resilience Enhancement for Distribution System With Multiple Non-Anticipative Uncertainties Based On Multi-Stage Dynamic Programming | |
CN110334912A (en) | A kind of distributed generation resource networking contact efficiency assessment method | |
CN117035700A (en) | BIM-based hydraulic and hydroelectric engineering forward collaborative design method | |
CN110119879A (en) | A kind of power engineering life cycle cost research method based on system dynamics | |
CN109389158A (en) | It early can system architecture method based on the dispatching of power netwoks of data mining and human-computer interaction | |
Esmat | Flexibility market for congestion management in smart grids | |
Olufemi et al. | Determinants of commercialisation level among smallholder maize farmers in eastern cape, South Africa: a case study of qamata and tyefu municipality | |
CN106096910A (en) | A kind of architecture design method based on information activities | |
Napolitano et al. | Integrated cost-benefit analysis and prescriptive decision tree model for a flood risk management problem | |
CN108470076A (en) | Data resource planning system and method and data management system | |
CN104299066B (en) | Organizational Structure Information Mining Method Based on Enterprise Process Management System | |
Morrow et al. | Improving LMP based day ahead forecasts using Auto Regressive Integrated Moving Average (ARIMA) with shadow pricing, EFORd rates, and transmission loss ratios | |
Zhang et al. | A methodology for building generation trajectories to balance continuous-time load profiles | |
Coles et al. | Impact assessment, process projects and output-to-purpose reviews: work in progress in the Department for International Development (DFID) | |
Shiasi | Preserving Intangible Heritage in Iranian Traditional Architecture: Italian Experts' Approaches in the Mid-20th Century |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191022 |
|
WD01 | Invention patent application deemed withdrawn after publication |