CN105631545A - Photovoltaic power station generation capacity prediction method based on similar day analysis and prediction system thereof - Google Patents
Photovoltaic power station generation capacity prediction method based on similar day analysis and prediction system thereof Download PDFInfo
- Publication number
- CN105631545A CN105631545A CN201510992857.0A CN201510992857A CN105631545A CN 105631545 A CN105631545 A CN 105631545A CN 201510992857 A CN201510992857 A CN 201510992857A CN 105631545 A CN105631545 A CN 105631545A
- Authority
- CN
- China
- Prior art keywords
- index
- history
- generated energy
- similar day
- factor
- 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 45
- 238000004458 analytical method Methods 0.000 title abstract description 9
- 230000007613 environmental effect Effects 0.000 claims abstract description 34
- 238000010248 power generation Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000000611 regression analysis Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 14
- 238000007405 data analysis Methods 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 238000012314 multivariate regression analysis Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- VQLYBLABXAHUDN-UHFFFAOYSA-N bis(4-fluorophenyl)-methyl-(1,2,4-triazol-1-ylmethyl)silane;methyl n-(1h-benzimidazol-2-yl)carbamate Chemical compound C1=CC=C2NC(NC(=O)OC)=NC2=C1.C=1C=C(F)C=CC=1[Si](C=1C=CC(F)=CC=1)(C)CN1C=NC=N1 VQLYBLABXAHUDN-UHFFFAOYSA-N 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Photovoltaic Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a photovoltaic power station generation capacity prediction method based on similar day analysis and a prediction system thereof. The generation capacity prediction method comprises the following steps that step S1, historical environmental information and historical generation capacity data corresponding to the date of the location of a photovoltaic power station are collected; step S2, numeralization processing is performed on all the determined historical environmental factors in the foreseen environmental factors and the historical environmental information; step 3, then a similar day processing model is established according to the data after numeralization processing and the historical generation capacity data; and step S4, generation capacity prediction is performed through the similar day processing model. According to the generation capacity prediction method, similar day analysis is performed according to the historical generation capacity data and weather parameters of the photovoltaic power station based on big data analysis and multivariate regression analysis to seek all the historical environmental information similar to all the foreseen environmental factors so that prediction and assessment of medium and short term of power generation capacity of the photovoltaic power station can be realized, and thus the data basis is provided for production and scheduling of photovoltaic enterprises.
Description
Technical field
The invention belongs to photovoltaic power generation quantity prediction field, particularly relate to a kind of photovoltaic power station power generation amount Forecasting Methodology based on similar day analysis and pre-examining system.
Background technology
Photovoltaic generation occupies more and more important status with the advantage of clean and effective in utilization of new energy resources. China has also put into effect many policies in the application and popularization of photovoltaic power generation technology, and year, accumulative newly adding lustre to lied prostrate installation rapid development, but majority enterprise is based on the realization of photovoltaic power station power generation function, and system is transported the research still Shortcomings that dimension is monitored. The environmental factors in photovoltaic power station power generation amount and its location has much relations (such as irradiation, temperature, Air quality, weather pattern etc.), in conjunction with each environmental information, light is lied prostrate systems generate electricity amount predicts it is study less field present stage, and be the key and the prerequisite that realize utility power grid scheduling and produce adjustment to the prediction of generated energy, it is the important channel that enterprise realizes maximizing the benefits, also it is the big problem being badly in need of in field of photovoltaic power generation solving.
Summary of the invention
It is an object of the invention to provide the Forecasting Methodology of a kind of photovoltaic power station power generation amount based on similar day analysis and pre-examining system, to realize the prediction to photovoltaic power station power generation amount, the assessment produced for enterprise's light volt and scheduling offer reference.
In order to solve the problems of the technologies described above, the present invention provides the Forecasting Methodology of a kind of photovoltaic power station power generation amount analyzed based on similar day, comprises the steps:
Step S1, the history environment information corresponding with the date in location, collection photovoltaics power station, history generated energy data; Step S2, carries out numerical value process respectively to each history environment factor determined in the environmental factors predicted and history environment information; Step S3, then set up similar day transaction module according to the data after numerical valueization process and history generated energy data; And step S4, carry out generated energy prediction by similar day transaction module.
Further, the environmental factors of described precognition and each history environment factor include the irradiation index corresponding to photovoltaic electric station, weather pattern index, envrionment temperature exponential sum air quality index; Wherein
Described weather pattern index, it is divided into numerical value 1��7 according to different weather situation to the influence degree of irradiation index is fuzzy;
Described air quality index, it selects PM2.5 index.
Further, the method that data after processing according to numerical valueization in described step S3 and history generated energy data set up similar day transaction module comprises the steps:
Step S31, carries out multiple regression analysis to the numerical value of index corresponding in history environment factor, and determines that above-mentioned each index is respectively to the influence degree of history generated energy data;
Step S32, screens history environment information according to the environment factor of precognition, to obtain the similar day number of days of some days, and by the history generated energy data corresponding to this similar day number of days, as described similar day transaction module.
Further, the numerical value of index corresponding in history environment factor is carried out multiple regression analysis by described step S31, namely determines each factor of influence by multiple regression analysis,
Getting X1 and represent irradiation index, its factor of influence is COEFFICIENT K 1;
X2 represents weather pattern index, and its factor of influence is COEFFICIENT K 2;
X3 represents envrionment temperature index, and its factor of influence is COEFFICIENT K 3;
X4 represents PM2.5 index, and its factor of influence is COEFFICIENT K 4;
Further, described step S31 determining, above-mentioned each index is respectively to the influence degree of history generated energy data, namely the influence degree to photovoltaic power station power generation amount is drawn by each factor of influence, its method comprises: sorted by the absolute value of each factor of influence, to determine that each environmental factors is to the influence degree of history generated energy data; It is irradiation index for the influence degree of generated energy respectively by high to Low sequence > weather pattern index > envrionment temperature index > air quality index; Sorting by each factor of influence absolute value is | K1 | > | K2 | > | K3 | > | K4 |.
Further, history environment information is screened by described step S32 according to the environment factor predicted, comprise with the method for the similar day number of days obtaining some days: the pre-known information determining each influence factor by the environmental factors predicted, and history environment information is screened by environmental factors according to precognition one by one; Namely the big factor of influence degree is first screened, i.e. irradiation index, screen weather pattern index, envrionment temperature index, air quality index more successively, and regulate each screening scope, to filter out corresponding similar day number of days, set the history generated energy data from the similar day of the 1st day to n-th day is corresponding and distinguish E1, E2, E3 ... En.
Further, the method carrying out generated energy prediction by similar day transaction module in described step S4 comprises:
Above-mentioned similar day generated energy data make average treatment, to predict the prediction average of time generated energy E as correspondence, i.e. E=(E1+E2+E3+ ... + En)/n.
Again on the one hand, present invention also offers the pre-examining system of a kind of photovoltaic power station power generation amount analyzed based on similar day, comprising:
Data acquisition module, the history environment information corresponding with the date in location, collection photovoltaics power station, history generated energy data;
The numerical value module being connected with data acquisition module, its each history environment factor being suitable in the environmental factors to precognition and history environment information determining carries out numerical value process respectively;
Module set up by the model being connected with numerical value module, and it is suitable for the data after processing according to numerical valueization and history generated energy data set up similar day transaction module; And
Set up the output module that module is connected with model, it is suitable for carrying out generated energy prediction by similar day transaction module.
Further, the environmental factors of described precognition and each history environment factor include the irradiation index corresponding to photovoltaic electric station, weather pattern index, envrionment temperature exponential sum air quality index; Wherein
Described weather pattern index, it is divided into numerical value 1��7 according to different weather situation to the influence degree of irradiation index is fuzzy;
Described air quality index, it selects PM2.5 index.
Further, the data after processing in module set up according to numerical valueization by described model and history generated energy data set up similar day transaction module, namely the numerical value of index corresponding in history environment factor is carried out multiple regression analysis, and determine that above-mentioned each index is respectively to the influence degree of history generated energy data; And history environment information is screened by the environment factor according to precognition, to obtain the similar day number of days of some days, and by the history generated energy data corresponding to this similar day number of days, as described similar day transaction module.
The invention has the beneficial effects as follows, the Forecasting Methodology of the photovoltaic power station power generation amount based on similar day analysis provided by the invention and pre-examining system, similar day analysis is carried out according to photovoltaic electric station history generated energy data and weather parameter, based on big data analysis and multiple regression analysis, seek each history environment information close with each precognition environmental factors, realize the predicting and evaluating to photovoltaic electric station generated energy a middle or short term, for production and the scheduling of Guang Fu enterprise provides data basis; Meanwhile, the present invention does not need the generated energy prediction unit additionally increasing specialty in photovoltaic electric station, and cost is low, and application prospect is extensive.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the present invention is further described.
Fig. 1 is the schema of the Forecasting Methodology of the generated energy of the present invention.
Embodiment
In conjunction with the accompanying drawings, the present invention is further detailed explanation. These accompanying drawings are the schematic diagram of simplification, and the basic structure of the present invention is only described with illustration, and therefore it only shows the formation relevant with the present invention.
Embodiment 1
As shown in Figure 1, the Forecasting Methodology of a kind of photovoltaic power station power generation amount analyzed based on similar day of the present invention, it is characterised in that, comprise the steps:
Step S1, the history environment information corresponding with the date in location, collection photovoltaics power station, history generated energy data;
Step S2, carries out numerical value process respectively to each history environment factor determined in the environmental factors predicted and history environment information;
Step S3, then set up similar day transaction module according to the data after numerical valueization process and history generated energy data; And
Step S4, carries out generated energy prediction by similar day transaction module.
The environmental factors of described precognition is obtained by weather-forecast.
Concrete, the environmental factors of described precognition and each history environment factor include the irradiation index corresponding to photovoltaic electric station (irradiation that namely in photovoltaic electric station, light volt system obtains), weather pattern index, envrionment temperature exponential sum air quality index; Wherein, described weather pattern index, it is divided into numerical value 1��7 according to different weather situation to the influence degree of irradiation index is fuzzy; Described air quality index, it selects PM2.5 index.
The concrete corresponding table of numerical valueization process is as shown in table 1.
Table 1 weather pattern numerical value synopsis
Preferably, the method that data after processing according to numerical valueization in described step S3 and history generated energy data set up similar day transaction module comprises the steps:
Step S31, carries out multiple regression analysis to the numerical value of index corresponding in history environment factor in Matlab, judges that above-mentioned each index is respectively to the influence degree of history generated energy data in conjunction with StepwiseRegression module;
Step S32, screens history environment information according to the environment factor of precognition, to obtain the similar day number of days of some days, and by the history generated energy data corresponding to this similar day number of days, as described similar day transaction module.
The numerical value of index corresponding in history environment factor is carried out multiple regression analysis by described step S31, namely
Each factor of influence is determined by multiple regression analysis,
Getting X1 and represent irradiation index, its factor of influence is COEFFICIENT K 1;
X2 represents weather pattern index, and its factor of influence is COEFFICIENT K 2;
X3 represents envrionment temperature index, and its factor of influence is COEFFICIENT K 3;
X4 represents PM2.5 index, and its factor of influence is COEFFICIENT K 4;
Concrete, by gathering, corresponding history environment factor (such as the data of a year) is solved each factor of influence K1��K4 by StepwiseRegression module in Matlab. Concrete result is as shown in table 2.
The corresponding table of each environmental factors processing mode of table 2
Preferably, determining that above-mentioned each index is respectively to the influence degree of history generated energy data, namely draws the influence degree to photovoltaic power station power generation amount by each factor of influence in described step S31, its method comprises:
In conjunction with StepwiseRegression module in Matlab, the absolute value of each factor of influence is sorted, to determine that each environmental factors is to the influence degree of history generated energy data.
It is irradiation index for the influence degree of generated energy respectively by high to Low sequence > weather pattern index > envrionment temperature index > air quality index; Namely
Being sorted by each factor of influence absolute value is | K1 | > | K2 | > | K3 | > | K4 |.
History environment information is screened according to the environment factor predicted by described step S32, comprises with the method for the similar day number of days obtaining some days:
The pre-known information of each influence factor is determined, and history environment information is screened by environmental factors according to precognition one by one by the environmental factors predicted; Namely
First screen the big factor of influence degree, i.e. irradiation index, screen weather pattern index, envrionment temperature index, air quality index more successively, and regulate each screening scope, to filter out corresponding similar day number of days, set the history generated energy data from the similar day of the 1st day to n-th day is corresponding and distinguish E1, E2, E3 ... En.
The method carrying out generated energy prediction by similar day transaction module in described step S4 comprises:
Above-mentioned similar day generated energy data make average treatment, to predict the prediction average of time generated energy E as correspondence, i.e. E=(E1+E2+E3+ ... + En)/n.
Embodiment 2
On embodiment 1 basis, the present embodiment 2 provides the pre-examining system of a kind of photovoltaic power station power generation amount analyzed based on similar day, comprising:
Data acquisition module, the history environment information corresponding with the date in location, collection photovoltaics power station, history generated energy data;
The numerical value module being connected with data acquisition module, its each history environment factor being suitable in the environmental factors to precognition and history environment information determining carries out numerical value process respectively;
Module set up by the model being connected with numerical value module, and it is suitable for the data after processing according to numerical valueization and history generated energy data set up similar day transaction module; And
Set up the output module that module is connected with model, it is suitable for carrying out generated energy prediction by similar day transaction module.
Further, the environmental factors of described precognition and each history environment factor include the irradiation index corresponding to photovoltaic electric station, weather pattern index, envrionment temperature exponential sum air quality index; Wherein
Described weather pattern index, it is divided into numerical value 1��7 according to different weather situation to the influence degree of irradiation index is fuzzy;
Described air quality index, it selects PM2.5 index.
Further, the data after processing in module set up according to numerical valueization by described model and history generated energy data set up similar day transaction module, namely the numerical value of index corresponding in history environment factor is carried out multiple regression analysis, and determine that above-mentioned each index is respectively to the influence degree of history generated energy data; And history environment information is screened by the environment factor according to precognition, to obtain the similar day number of days of some days, and by the history generated energy data corresponding to this similar day number of days, as described similar day transaction module.
About the detailed operation method steps of each module see the associated viscera of embodiment 1.
Embodiment 3
On the basis of embodiment 1 and embodiment 2, it is illustrated by concrete example.
Matlab emulation is carried out, through to each history environment factor multiple regression analysis, obtaining the sequence of described influence factor absolute value for Guang Fu enterprise of Changzhou city one 1 year project data, i.e. influence degree sequence, i.e. K1=135.983, K2=-8.873, K3=13.542, K4=-3.516.
Wherein, each influence factor is calculated as follows: write multiple regression analysis program in matlab, project data over the years for the enterprise collected (comprising: irradiation index, weather pattern index, envrionment temperature exponential sum air quality index) is imported with matrix, selects the array mode of the Different Effects factor to obtain above-mentioned each influence coefficient numerical value in StepwiseRegression module.
It can thus be seen that the influence degree sequence of generated energy is by each environmental factors: | K1 | > | K3 | > | K2 | > | K4 |, namely it is irradiation index by high to Low sequence respectively > envrionment temperature index > weather pattern index > air quality index.
Certain day each environment index of precognition is as follows respectively: irradiation index is 5.97, and envrionment temperature index is 24.5, and weather pattern index is 4, and air quality index is 35. By generated energy influence degree by screening item by item to the little historical data to accumulative a year greatly, obtain the history environment data similar to this precognition environmental aspect and history generated energy data. Again these some days similar day generated energy data are averaged, obtain the prediction generated energy of this precognition day. Specific as follows:
First screen irradiation index, and to get screening scope be K1 �� 1.0; Screening envrionment temperature index, and to get screening scope be K3 �� 2.0; Screening weather pattern index, and to get screening scope be K2 �� 1; Finally screening Air quality is K4 �� 15; Final screening obtains 5 days similar day generated energy data, such as table 3:
| Total daily generation (kwh) | Irradiation (MJ/m2) | Average daily temperature (DEG C) | Weather pattern | Air quality (PM2.5) |
| 701.901 | 5.9853 | 23.5 | 3 | 59 |
| 753.878 | 5.9847 | 23.5 | 3 | 58 |
| 1019.704 | 6.7602 | 24 | 3 | 60 |
| 802 | 6.4206 | 23.5 | 3 | 69 |
| 1281.875 | 6.4182 | 24.5 | 4 | 58 |
Above-mentioned similar day generated energy data are averaging number, as the prediction average of this precognition date generated energy E, i.e. E=(E1+E2+E3+ ... + En)/n
=(701.901+753.878+1019.704+802+1281.875) �� 5=911.8716kwh.
Compared with other Forecasting Methodology, Forecasting Methodology based on the photovoltaic power station power generation amount of similar day analysis utilizes Matlab to carry out data analysis, the similar day generated energy data obtained by matlab or excel etc., and can be carried out equal value process by data screening, thus obtain the generated energy of precognition. This Forecasting Methodology by historical data is carried out Analysis and Screening, to realize the prediction to generated energy. This screening process simple and fast, has certain predicated error, but the production planning and dispatching of power netwoks to enterprise can play certain guidance and reference role.
Therefore, the present invention is especially applicable to predicting a middle or short term to photo-voltaic power generation station generated energy, and prediction effect is very good.
Taking the above-mentioned desirable embodiment according to the present invention as enlightenment, by above-mentioned description, relevant staff in the scope not deviateing this invention technological thought, can carry out various change and amendment completely. The content that the technical scope of this invention is not limited on specification sheets, it is necessary to determine its technical scope according to right.
Claims (10)
1. the Forecasting Methodology of the photovoltaic power station power generation amount analyzed based on similar day, it is characterised in that, comprise the steps:
Step S1, the history environment information corresponding with the date in location, collection photovoltaics power station, history generated energy data;
Step S2, carries out numerical value process respectively to each history environment factor determined in the environmental factors predicted and history environment information;
Step S3, data and history generated energy data after processing according to numerical valueization set up similar day transaction module; And
Step S4, carries out generated energy prediction by similar day transaction module.
2. Forecasting Methodology according to claim 1, it is characterised in that,
The environmental factors of described precognition and each history environment factor include the irradiation index corresponding to photovoltaic electric station, weather pattern index, envrionment temperature exponential sum air quality index; Wherein
Described weather pattern index, it is divided into numerical value 1��7 according to different weather situation to the influence degree of irradiation index is fuzzy;
Described air quality index, it selects PM2.5 index.
3. Forecasting Methodology according to claim 2, it is characterised in that, the method that data after processing according to numerical valueization in described step S3 and history generated energy data set up similar day transaction module comprises the steps:
Step S31, carries out multiple regression analysis to the numerical value of index corresponding in history environment factor, and determines that above-mentioned each index is respectively to the influence degree of history generated energy data;
Step S32, screens history environment information according to the environment factor of precognition, to obtain the similar day number of days of some days, and by the history generated energy data corresponding to this similar day number of days, as described similar day transaction module.
4. Forecasting Methodology according to claim 3, it is characterised in that, the numerical value of index corresponding in history environment factor is carried out multiple regression analysis by described step S31, namely
Each factor of influence is determined by multiple regression analysis,
Getting X1 and represent irradiation index, its factor of influence is COEFFICIENT K 1;
X2 represents weather pattern index, and its factor of influence is COEFFICIENT K 2;
X3 represents envrionment temperature index, and its factor of influence is COEFFICIENT K 3;
X4 represents PM2.5 index, and its factor of influence is COEFFICIENT K 4.
5. Forecasting Methodology according to claim 4, it is characterised in that, described step S31 determining, above-mentioned each index is respectively to the influence degree of history generated energy data, namely draws the influence degree to photovoltaic power station power generation amount by each factor of influence, its method comprises:
The absolute value of each factor of influence is sorted, to determine that each environmental factors is to the influence degree of history generated energy data;
It is irradiation index for the influence degree of generated energy respectively by high to Low sequence > weather pattern index > envrionment temperature index > air quality index; Namely
Being sorted by each factor of influence absolute value is | K1 | > | K2 | > | K3 | > | K4 |.
6. Forecasting Methodology according to claim 5, it is characterised in that, history environment information is screened according to the environment factor predicted by described step S32, comprises with the method for the similar day number of days obtaining some days:
The pre-known information of each influence factor is determined, and history environment information is screened by environmental factors according to precognition one by one by the environmental factors predicted; Namely
First screen the big factor of influence degree, i.e. irradiation index, screen weather pattern index, envrionment temperature index, air quality index more successively, and regulate each screening scope, to filter out corresponding similar day number of days, set the history generated energy data from the similar day of the 1st day to n-th day is corresponding and distinguish E1, E2, E3 ... En.
7. Forecasting Methodology according to claim 6, it is characterised in that, the method carrying out generated energy prediction by similar day transaction module in described step S4 comprises:
Above-mentioned similar day generated energy data make average treatment, to predict the prediction average of time generated energy E as correspondence, i.e. E=(E1+E2+E3+ ... + En)/n.
8. the pre-examining system of the photovoltaic power station power generation amount analyzed based on similar day, it is characterised in that, comprising:
Data acquisition module, the history environment information corresponding with the date in location, collection photovoltaics power station, history generated energy data;
The numerical value module being connected with data acquisition module, its each history environment factor being suitable in the environmental factors to precognition and history environment information determining carries out numerical value process respectively;
Module set up by the model being connected with numerical value module, and it is suitable for the data after processing according to numerical valueization and history generated energy data set up similar day transaction module; And
Set up the output module that module is connected with model, it is suitable for carrying out generated energy prediction by similar day transaction module.
9. the pre-examining system of photovoltaic power station power generation amount according to claim 8, it is characterised in that,
The environmental factors of described precognition and each history environment factor include the irradiation index corresponding to photovoltaic electric station, weather pattern index, envrionment temperature exponential sum air quality index; Wherein
Described weather pattern index, it is divided into numerical value 1��7 according to different weather situation to the influence degree of irradiation index is fuzzy;
Described air quality index, it selects PM2.5 index.
10. pre-examining system according to claim 9, it is characterised in that,
The data after processing in module set up according to numerical valueization by described model and history generated energy data set up similar day transaction module, namely
The numerical value of index corresponding in history environment factor is carried out multiple regression analysis, and determines that above-mentioned each index is respectively to the influence degree of history generated energy data; And
History environment information is screened by the environment factor according to precognition, to obtain the similar day number of days of some days, and by the history generated energy data corresponding to this similar day number of days, as described similar day transaction module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510992857.0A CN105631545A (en) | 2015-12-25 | 2015-12-25 | Photovoltaic power station generation capacity prediction method based on similar day analysis and prediction system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510992857.0A CN105631545A (en) | 2015-12-25 | 2015-12-25 | Photovoltaic power station generation capacity prediction method based on similar day analysis and prediction system thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105631545A true CN105631545A (en) | 2016-06-01 |
Family
ID=56046452
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510992857.0A Pending CN105631545A (en) | 2015-12-25 | 2015-12-25 | Photovoltaic power station generation capacity prediction method based on similar day analysis and prediction system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105631545A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106934482A (en) * | 2016-09-20 | 2017-07-07 | 威德大学产学协力团 | Using 24 hours electric power demand forecasting devices and electric power demand forecasting method of the temperature for temporally dividing |
| JP2018148741A (en) * | 2017-03-08 | 2018-09-20 | 中国電力株式会社 | Photovoltaic power output prediction device considering snow cover |
| CN109884896A (en) * | 2019-03-12 | 2019-06-14 | 河海大学常州校区 | A kind of photovoltaic tracking system optimization tracking based on similar day irradiation prediction |
| CN112149861A (en) * | 2019-06-28 | 2020-12-29 | 北京天诚同创电气有限公司 | Operation and maintenance task scheduling method and device for photovoltaic power station group |
| CN113052386A (en) * | 2021-03-29 | 2021-06-29 | 国网电子商务有限公司 | Distributed photovoltaic daily generated energy prediction method and device based on random forest algorithm |
| CN114094570A (en) * | 2021-11-05 | 2022-02-25 | 国能浙江余姚燃气发电有限责任公司 | Method and device for predicting power generation gas consumption of gas turbine unit |
| CN116151509A (en) * | 2023-02-13 | 2023-05-23 | 国家电投集团数字科技有限公司 | Power information management method and system based on data fusion |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390200A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power station electricity generation output power forecasting method based on similar days |
| CN103390199A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power generation capacity/power prediction device |
-
2015
- 2015-12-25 CN CN201510992857.0A patent/CN105631545A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390200A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power station electricity generation output power forecasting method based on similar days |
| CN103390199A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power generation capacity/power prediction device |
Non-Patent Citations (2)
| Title |
|---|
| 傅美平等: "基于相似日和最小二乘支持向量机的光伏发电短期预测", 《电力***保护与控制》 * |
| 沈金荣等: "Study on the Photovoltaic Power Generation Prediction Methods Based on Comprehensive Regression Analysis of Environmental Factors", 《PREPRINTS OF THE 5TH INTERNATIONAL CONFERENCE ON ELECTRIC UTILITY DEREGULATION AND RESTRUCTURING AND POWER TECHNOLOGIES》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106934482A (en) * | 2016-09-20 | 2017-07-07 | 威德大学产学协力团 | Using 24 hours electric power demand forecasting devices and electric power demand forecasting method of the temperature for temporally dividing |
| JP2018148741A (en) * | 2017-03-08 | 2018-09-20 | 中国電力株式会社 | Photovoltaic power output prediction device considering snow cover |
| CN109884896A (en) * | 2019-03-12 | 2019-06-14 | 河海大学常州校区 | A kind of photovoltaic tracking system optimization tracking based on similar day irradiation prediction |
| CN112149861A (en) * | 2019-06-28 | 2020-12-29 | 北京天诚同创电气有限公司 | Operation and maintenance task scheduling method and device for photovoltaic power station group |
| CN113052386A (en) * | 2021-03-29 | 2021-06-29 | 国网电子商务有限公司 | Distributed photovoltaic daily generated energy prediction method and device based on random forest algorithm |
| CN113052386B (en) * | 2021-03-29 | 2023-07-04 | 国网数字科技控股有限公司 | Random forest algorithm-based distributed photovoltaic daily power generation amount prediction method and device |
| CN114094570A (en) * | 2021-11-05 | 2022-02-25 | 国能浙江余姚燃气发电有限责任公司 | Method and device for predicting power generation gas consumption of gas turbine unit |
| CN114094570B (en) * | 2021-11-05 | 2024-05-10 | 国能浙江余姚燃气发电有限责任公司 | Method and device for predicting power generation gas consumption of gas turbine unit |
| CN116151509A (en) * | 2023-02-13 | 2023-05-23 | 国家电投集团数字科技有限公司 | Power information management method and system based on data fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105631545A (en) | Photovoltaic power station generation capacity prediction method based on similar day analysis and prediction system thereof | |
| Wu et al. | An intuitionistic fuzzy multi-criteria framework for large-scale rooftop PV project portfolio selection: Case study in Zhejiang, China | |
| Han et al. | A PV power interval forecasting based on seasonal model and nonparametric estimation algorithm | |
| Li et al. | Identifying the driving forces of national and regional CO2 emissions in China: based on temporal and spatial decomposition analysis models | |
| Yu et al. | A novel methodology for knowledge discovery through mining associations between building operational data | |
| CN109376951B (en) | Photovoltaic probability prediction method | |
| CN113496311A (en) | Photovoltaic power station generated power prediction method and system | |
| CN105373971A (en) | Method of building energy efficiency management on the basis of big data | |
| CN105069527A (en) | Zone area reasonable line loss prediction method based on data mining technology | |
| CN103441535A (en) | Day-ahead power generation plan photovoltaic power generation receiving capability analysis method based on SCED | |
| CN102147839A (en) | Method for forecasting photovoltaic power generation quantity | |
| CN104376371B (en) | A kind of distribution based on topology is layered load forecasting method | |
| Chen et al. | A multi-objective optimization strategy for building carbon emission from the whole life cycle perspective | |
| An et al. | Short term effect evaluation model of rural energy construction revitalization based on ID3 decision tree algorithm | |
| CN113344449A (en) | Method for predicting monthly-scale industrial water demand | |
| CN105512763A (en) | Method and system for predicting photovoltaic power station middle-short term power generation | |
| CN106786800A (en) | Based on big data Economic Dispatch analysis method of the treatment containing photovoltaic generation | |
| Zakovorotnyi et al. | Building energy data analysis by clustering measured daily profiles | |
| CN109902743A (en) | A kind of Wind turbines output power predicting method | |
| Wang et al. | Prediction and comparison of urban electricity consumption based on grey system theory: A case study of 30 southern China cities | |
| CN116826745B (en) | Layered and partitioned short-term load prediction method and system in power system background | |
| Wu et al. | The confrontation and symbiosis of green and development: Coupling coordination analysis between carbon emissions and spatial development in urban agglomerations of China | |
| Guo et al. | Spatio-temporal differentiation and driving factors of industrial ecology of restricted development zone from adaptive perspective: a case study of shandong, China | |
| Li et al. | The research of urban rail transit sectional passenger flow prediction method | |
| Qiao et al. | Development of small hydropower in China 1990–2015: Province-domain patterns of temporal-spatial evolution |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160601 |
|
| RJ01 | Rejection of invention patent application after publication |