CN108960522A - A kind of photovoltaic power generation quantity prediction analysis method - Google Patents
A kind of photovoltaic power generation quantity prediction analysis method Download PDFInfo
- Publication number
- CN108960522A CN108960522A CN201810780001.0A CN201810780001A CN108960522A CN 108960522 A CN108960522 A CN 108960522A CN 201810780001 A CN201810780001 A CN 201810780001A CN 108960522 A CN108960522 A CN 108960522A
- Authority
- CN
- China
- Prior art keywords
- power generation
- photovoltaic power
- days
- data
- generation quantity
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Mathematical Optimization (AREA)
- Tourism & Hospitality (AREA)
- Mathematical Physics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Pure & Applied Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Educational Administration (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of photovoltaic power generation quantity prediction analysis methods of technical field of photovoltaic power generation, and this method comprises the following steps: S1: the environmental data in acquisition photovoltaic plant location；S2: prediction model is established according to acquisition data, and collected environmental data is quantified weather variable by fuzzy technology；S3: dividing sample data set is training dataset and validation data set；S4: the correlativity between variable is described using Spearman rank correlation coefficient, and is tested to it；S5: method of gradual regression selection variables are used；S6: by the accuracy rate of rear verifying probabilistic verification model if more than 90%, then obtain final result, otherwise S3 is repeated, until prediction accuracy reaches 90% or more, the present invention carries out correlation analysis according to photovoltaic plant history generated energy data and weather parameters, based on big data analysis and multiple regression analysis, seek direct or coupling of each environmental factor to photovoltaic power generation quantity, realizes prediction and assessment to generated energy in photovoltaic plant.
Description
Technical field
The present invention relates to technical field of photovoltaic power generation, specially a kind of photovoltaic power generation quantity prediction analysis method.
Background technique
Photovoltaic power generation is easy to be influenced by factors such as irradiation level, temperature, humidity, wind-force, wind direction, weather situations, therefore
Photovoltaic power generation has fluctuation and intermittence, and large-scale photovoltaic power station, which is incorporated into the power networks, will affect the safety and stability warp of electric system
Ji operation.Carrying out prediction to the output power of photovoltaic plant facilitates dispatching of power netwoks department overall arrangement normal power supplies and photovoltaic hair
The cooperation of electricity, adjusts operation plan, reasonable arrangement grid operation mode, readily available bigger economic benefit and society in time
Meeting benefit, for this purpose, it is proposed that a kind of photovoltaic power generation quantity prediction analysis method.
Summary of the invention
The purpose of the present invention is to provide a kind of photovoltaic power generation quantity prediction analysis methods, to solve to mention in above-mentioned background technique
Out the problem of.
To achieve the above object, the invention provides the following technical scheme: a kind of photovoltaic power generation quantity prediction analysis method, the party
Method includes the following steps:
S1: the environmental data in acquisition photovoltaic plant location；
S2: prediction model is established according to acquisition data, and collected environmental data is quantified day by fuzzy technology
Gas variable；
S3: dividing sample data set is training dataset and validation data set；
S4: the correlativity between variable is described using Spearman rank correlation coefficient, and is tested to it；
S5: method of gradual regression selection variables are used；
S6: by the accuracy rate of rear verifying probabilistic verification model if more than 90%, then final result is obtained, is otherwise repeated
S3, until prediction accuracy reaches 90% or more.
Preferably, the environmental data acquired in the S1 include height above sea level, month, irradiation level, temperature, humidity, wind-force,
Wind direction, weather, heavy rain number of days, light rain number of days, strong wind number of days, calm number of days in 10 days in 10 days in 10 days in 10 days.
Preferably, fuzzy technology includes three parts in the S2, and be fuzzy value respectively with membership function, fuzzy quantity it is anti-
It is blurred, the fuzzy revising of weather variable.
Preferably, the irradiation level is that ultraviolet index is selected to carry out approximate representation, and ultraviolet index variation range is with 0~10
Number replace.
Preferably, the prediction model is the parameter value being calculated in model using least-squares estimation.
Preferably, the data acquired in the S1 are stored to real-time database and history library, real-time database Redis, history library use
HBase。
Compared with prior art, the beneficial effects of the present invention are: the present invention according to photovoltaic plant history generated energy data and
Weather parameters carries out correlation analysis, is based on big data analysis and multiple regression analysis, seeks each environmental factor to photovoltaic power generation
Prediction and assessment to generated energy in photovoltaic plant are realized in the direct or coupling of amount, are the production and scheduling of photovoltaic enterprise
Data basis is provided, enterprise is greatly improved and puts into operation profit, meanwhile, the present invention does not need additionally to increase in photovoltaic plant professional
Generated energy prediction meanss, reduce cost, have wide application prospect.
Detailed description of the invention
Fig. 1 is flow chart of the present invention；
Fig. 2 is parameter Estimation figure of the present invention；
Fig. 3 is the former data of the present invention and prediction data comparison diagram.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Fig. 1-3 is please referred to, the present invention provides a kind of technical solution: a kind of photovoltaic power generation quantity prediction analysis method, this method
Include the following steps:
S1: the environmental data in acquisition photovoltaic plant location；
S2: prediction model is established according to acquisition data, and collected environmental data is quantified day by fuzzy technology
Gas variable, prediction model is regression model, and regression model can be written as y=α0+α1χ1+...+αkχk+ε
Wherein, α0It is constant term, αj<j=1 ..., k>it is y to χjRegression coefficient, ε is stochastic error；
Estimation is made to k+1 parameter in model, n times test in the observation data that obtain bring (1) formula into, use rectangle
Array indicates to obtain Y=X β+ε.
S3: dividing sample data set is training dataset and validation data set；
S4: the correlativity between variable is described using Spearman rank correlation coefficient, and is tested to it；
S5: using method of gradual regression selection variables, and the screening removal biggish data of Acquisition Error improve the accuracy of analysis；
S6: by the accuracy rate of rear verifying probabilistic verification model if more than 90%, then final result is obtained, is otherwise repeated
S3, until prediction accuracy reaches 90% or more.
Wherein, the environmental data acquired in S1 include height above sea level, month, irradiation level, temperature, humidity, wind-force, wind direction,
Weather, heavy rain number of days, light rain number of days, strong wind number of days, calm number of days in 10 days in 10 days in 10 days in 10 days, acquisition data are a variety of
Class is wide, effectively increases the accuracy of prediction；
Fuzzy technology includes three parts in S2, and is fuzzy value and membership function, the anti fuzzy method of fuzzy quantity, weather respectively
The fuzzy revising of variable, fuzzy value and membership function are that fuzzy value is found out by membership function, and the present invention selects triangle to be subordinate to
Function, formula areTriangular membership curve shape is by parameter a, b, c
It determines, parameter a and c respectively correspond the vertex of left and right two of triangle lower part, and parameter b corresponds to the vertex of triangular-shaped upper portion, obscure
The anti fuzzy method of amount is that the exact value that can most replace fuzzy value is determined using weighted mean method, and formula isWherein
kiFor weight coefficient, the fuzzy revising of weather variable is the method for correcting weather fuzzy value, if weather is respectively fine day, cloudy day and rain
It when:
Wherein " ∧ " " ∨ " is respectively and takes to take small fortune greatly
It calculates, T1And T2Mean temperature respectively with reference to day and on the day before referring to day；
Irradiation level is that ultraviolet index is selected to carry out approximate representation, and ultraviolet index variation range is with 0~10 number come generation
It replaces, convenient for the accurate and visual irradiation level for understanding different times of staff；
Prediction model is the parameter value being calculated in model using least-squares estimation, convenient for improving the reliable of prediction
Property；
The data acquired in S1 are stored to real-time database and history library, real-time database Redis, history library HBase, convenient for adopting
Collect the storage and maintenance of data.
When work: a. quantifies weather variable by fuzzy technology first with environmental monitoring data, and new change can be obtained
Measure NEW；
B. sample data set is secondly divided, training dataset and validation data set are divided into；
C. the analysis of Spearman rank correlation is done to training dataset again, rejects the lesser variable of related coefficient；
D. with new training dataset fit regression model, as shown in Figure 2, the P value of wind speed variable is 0.067, according to parameter
Rudimentary model can be obtained in estimated value: generated energy=3767.60+23.34*NEW-228.95+87.876*FS；
E. successive Regression selection variables are used, have Fig. 2 it is found that the P value of variable passes through parametric test, generated energy less than 0.01
=3795.72+16.24xNEW-228.16xWD；
F. new verify data is substituted into model, using the accuracy rate of posterior probability verifying model, calculating accuracy rate is
93.2%, it is greater than 90% to get final mask out.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (6)
1. a kind of photovoltaic power generation quantity prediction analysis method, it is characterised in that: this method comprises the following steps:
S1: the environmental data in acquisition photovoltaic plant location；
S2: prediction model is established according to acquisition data, and collected environmental data is quantified weather by fuzzy technology and is become
Amount；
S3: dividing sample data set is training dataset and validation data set；
S4: the correlativity between variable is described using Spearman rank correlation coefficient, and is tested to it；
S5: method of gradual regression selection variables are used；
S6: by the accuracy rate of rear verifying probabilistic verification model if more than 90%, then final result is obtained, otherwise repeatedly S3, directly
Until prediction accuracy reaches 90% or more.
2. a kind of photovoltaic power generation quantity prediction analysis method according to claim 1, it is characterised in that: acquired in the S1
Environmental data includes height above sea level, month, irradiation level, temperature, humidity, wind-force, wind direction, weather, heavy rain number of days, 10 days in 10 days
Interior light rain number of days, strong wind number of days, calm number of days in 10 days in 10 days.
3. a kind of photovoltaic power generation quantity prediction analysis method according to claim 1, it is characterised in that: obscure skill in the S2
Art includes three parts, and is the fuzzy revising of fuzzy value and membership function, the anti fuzzy method of fuzzy quantity, weather variable respectively.
4. a kind of photovoltaic power generation quantity prediction analysis method according to claim 2, it is characterised in that: the irradiation level is choosing
With ultraviolet index come approximate representation, ultraviolet index variation range is replaced with 0~10 number.
5. a kind of photovoltaic power generation quantity prediction analysis method according to claim 2, it is characterised in that: the prediction model is
The parameter value in model is calculated using least-squares estimation.
6. a kind of photovoltaic power generation quantity prediction analysis method according to claim 1, it is characterised in that: acquired in the S1
Data are stored to real-time database and history library, real-time database Redis, history library HBase.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810780001.0A CN108960522A (en) | 2018-07-16 | 2018-07-16 | A kind of photovoltaic power generation quantity prediction analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810780001.0A CN108960522A (en) | 2018-07-16 | 2018-07-16 | A kind of photovoltaic power generation quantity prediction analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108960522A true CN108960522A (en) | 2018-12-07 |
Family
ID=64481325
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810780001.0A Pending CN108960522A (en) | 2018-07-16 | 2018-07-16 | A kind of photovoltaic power generation quantity prediction analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108960522A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909916A (en) * | 2019-10-24 | 2020-03-24 | 国网辽宁省电力有限公司 | Entropy weight method based wind power generation monthly electric quantity interval prediction method |
| CN111680826A (en) * | 2020-05-14 | 2020-09-18 | 沂南力诺太阳能电力工程有限公司 | Photovoltaic power generation capacity prediction analysis method |
| WO2020228568A1 (en) * | 2019-05-14 | 2020-11-19 | 京东方科技集团股份有限公司 | Method for training power generation amount prediction model of photovoltaic power station, power generation amount prediction method and device of photovoltaic power station, training system, prediction system and storage medium |
| CN114137357A (en) * | 2021-11-11 | 2022-03-04 | 国网江西省电力有限公司电力科学研究院 | Information interaction comprehensive power management method for power transmission line on-line monitoring device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559561A (en) * | 2013-11-13 | 2014-02-05 | 上海电气集团股份有限公司 | Super-short-term prediction method of photovoltaic power station irradiance |
| CN104050517A (en) * | 2014-06-27 | 2014-09-17 | 哈尔滨工业大学 | Photovoltaic power generation forecasting method based on GRNN |
| CN104268659A (en) * | 2014-10-09 | 2015-01-07 | 国电南瑞科技股份有限公司 | Photovoltaic power station generated power super-short-term prediction method |
| CN105488592A (en) * | 2015-12-02 | 2016-04-13 | 国家电网公司 | Method for predicting generated energy of photovoltaic power station |
| CN105512763A (en) * | 2015-12-07 | 2016-04-20 | 河海大学常州校区 | Method and system for predicting photovoltaic power station middle-short term power generation |
| CN106803128A (en) * | 2015-11-26 | 2017-06-06 | 华为技术有限公司 | The Forecasting Methodology and device of photovoltaic generation |
| CN107909218A (en) * | 2017-12-06 | 2018-04-13 | 南通大学 | A kind of short-term method for forecasting photovoltaic power generation quantity |
-
2018
- 2018-07-16 CN CN201810780001.0A patent/CN108960522A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559561A (en) * | 2013-11-13 | 2014-02-05 | 上海电气集团股份有限公司 | Super-short-term prediction method of photovoltaic power station irradiance |
| CN104050517A (en) * | 2014-06-27 | 2014-09-17 | 哈尔滨工业大学 | Photovoltaic power generation forecasting method based on GRNN |
| CN104268659A (en) * | 2014-10-09 | 2015-01-07 | 国电南瑞科技股份有限公司 | Photovoltaic power station generated power super-short-term prediction method |
| CN106803128A (en) * | 2015-11-26 | 2017-06-06 | 华为技术有限公司 | The Forecasting Methodology and device of photovoltaic generation |
| CN105488592A (en) * | 2015-12-02 | 2016-04-13 | 国家电网公司 | Method for predicting generated energy of photovoltaic power station |
| CN105512763A (en) * | 2015-12-07 | 2016-04-20 | 河海大学常州校区 | Method and system for predicting photovoltaic power station middle-short term power generation |
| CN107909218A (en) * | 2017-12-06 | 2018-04-13 | 南通大学 | A kind of short-term method for forecasting photovoltaic power generation quantity |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020228568A1 (en) * | 2019-05-14 | 2020-11-19 | 京东方科技集团股份有限公司 | Method for training power generation amount prediction model of photovoltaic power station, power generation amount prediction method and device of photovoltaic power station, training system, prediction system and storage medium |
| CN110909916A (en) * | 2019-10-24 | 2020-03-24 | 国网辽宁省电力有限公司 | Entropy weight method based wind power generation monthly electric quantity interval prediction method |
| CN110909916B (en) * | 2019-10-24 | 2023-06-13 | 国网辽宁省电力有限公司 | Wind power generation month electric quantity interval prediction method based on entropy weight method |
| CN111680826A (en) * | 2020-05-14 | 2020-09-18 | 沂南力诺太阳能电力工程有限公司 | Photovoltaic power generation capacity prediction analysis method |
| CN114137357A (en) * | 2021-11-11 | 2022-03-04 | 国网江西省电力有限公司电力科学研究院 | Information interaction comprehensive power management method for power transmission line on-line monitoring device |
| CN114137357B (en) * | 2021-11-11 | 2024-06-04 | 国网江西省电力有限公司电力科学研究院 | Comprehensive power management method for information interaction type power transmission line on-line monitoring device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Random forest solar power forecast based on classification optimization | |
| Wu et al. | An intuitionistic fuzzy multi-criteria framework for large-scale rooftop PV project portfolio selection: Case study in Zhejiang, China | |
| CN110474339B (en) | Power grid reactive power control method based on deep power generation load prediction | |
| CN108960522A (en) | A kind of photovoltaic power generation quantity prediction analysis method | |
| CN113496311A (en) | Photovoltaic power station generated power prediction method and system | |
| CN103023065B (en) | Wind power short-term power prediction method based on relative error entropy evaluation method | |
| CN109858673A (en) | A kind of photovoltaic generating system power forecasting method | |
| CN110110912B (en) | Photovoltaic power multi-model interval prediction method | |
| Wang et al. | Comparative study of machine learning approaches for predicting short-term photovoltaic power output based on weather type classification | |
| CN111488896B (en) | Distribution line time-varying fault probability calculation method based on multi-source data mining | |
| CN106485093B (en) | Based on the solar irradiance time series synthetic method for improving Markov chain | |
| CN109978242A (en) | The photovoltaic power generation cluster power forecasting method and device of scale are risen based on statistics | |
| KR20140021179A (en) | Method and apparatus for predicting daily solar radiation level | |
| Sogabe et al. | Optimization of decentralized renewable energy system by weather forecasting and deep machine learning techniques | |
| KR20140087965A (en) | System for predicting energy producing quantity | |
| CN114792156A (en) | Photovoltaic output power prediction method and system based on curve characteristic index clustering | |
| CN109242200B (en) | Wind power interval prediction method of Bayesian network prediction model | |
| CN104915727B (en) | Various dimensions allomer BP neural network optical power ultra-short term prediction method | |
| Yang et al. | Sub-minute probabilistic solar forecasting for real-time stochastic simulations | |
| CN110135652B (en) | Long-term flood season runoff prediction method | |
| CN108694475B (en) | Short-time-scale photovoltaic cell power generation capacity prediction method based on hybrid model | |
| CN109919382A (en) | Consider the non-precision probability forecasting method of photovoltaic power climbing event and system that date periodicity influences | |
| CN105205572A (en) | Photovoltaic power generation output forecasting method based on EMD (Empirical Mode Decomposition) and Elman algorithm | |
| CN117277304A (en) | Photovoltaic power generation ultra-short-term power prediction method and system considering sunrise and sunset time | |
| Feng et al. | Peak operation optimization of cascade hydropower reservoirs and solar power plants considering output forecasting uncertainty |
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 |
Application publication date: 20181207 |
|
| RJ01 | Rejection of invention patent application after publication |