CN113379143A - Typical meteorological year construction method, power generation amount prediction method and related device - Google Patents
Typical meteorological year construction method, power generation amount prediction method and related device Download PDFInfo
- Publication number
- CN113379143A CN113379143A CN202110700241.7A CN202110700241A CN113379143A CN 113379143 A CN113379143 A CN 113379143A CN 202110700241 A CN202110700241 A CN 202110700241A CN 113379143 A CN113379143 A CN 113379143A
- Authority
- CN
- China
- Prior art keywords
- meteorological
- data
- candidate
- typical
- weather
- 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
- 238000010248 power generation Methods 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000010276 construction Methods 0.000 title claims abstract description 39
- 239000011159 matrix material Substances 0.000 claims description 47
- 230000001186 cumulative effect Effects 0.000 claims description 24
- 238000012216 screening Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 6
- 230000000875 corresponding effect Effects 0.000 description 18
- 230000007774 longterm Effects 0.000 description 6
- 230000005855 radiation Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 241000321453 Paranthias colonus Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a construction method of a typical meteorological year, a generating capacity prediction method and a related device. In other words, the target meteorological parameters are determined according to the influence degree of the candidate meteorological parameters, and compared with a mode that a fixed number of meteorological parameters are manually selected according to experience, the accuracy of meteorological parameter determination can be improved. And then improving the accuracy of the typical meteorological year constructed based on the parameter values of the target meteorological parameters in the historical meteorological data, so that the accuracy of the photovoltaic power generation amount prediction for performing the power generation amount prediction operation according to the meteorological data of the typical meteorological year is also improved.
Description
Technical Field
The invention relates to the field of power generation amount prediction, in particular to a construction method of a typical meteorological year, a power generation amount prediction method and a related device.
Background
In recent years, photovoltaic power generation technology is rapidly developed, photovoltaic power generation amount is predicted in the photovoltaic power generation process, and important reference basis can be provided for investment decision, economic analysis, electrical equipment type selection and system access of a photovoltaic power station.
When the photovoltaic power generation amount is predicted, the accuracy of the prediction of the photovoltaic power generation amount is affected by meteorological data of an area where the photovoltaic power station is located, and if the accuracy of the meteorological data of the area where the photovoltaic power station is located is low, the accuracy of the prediction of the photovoltaic power generation amount is low.
Disclosure of Invention
In view of the above, the present invention provides a typical meteorological year construction method, a power generation amount prediction method, and a related apparatus, so as to solve the problem that if the accuracy of meteorological data of an area where a photovoltaic power station is located is low, the accuracy of photovoltaic power generation amount prediction is low.
In order to solve the technical problems, the invention adopts the following technical scheme:
a construction method of a typical weather year comprises the following steps:
acquiring historical meteorological data and a plurality of candidate meteorological parameters;
determining a weight value of each candidate meteorological parameter based on the historical meteorological data;
screening out candidate meteorological parameters meeting a preset influence degree rule according to the weighted values of the candidate meteorological parameters, and taking the candidate meteorological parameters as target meteorological parameters;
and constructing a typical meteorological year based on the parameter values of the target meteorological parameters in the historical meteorological data.
Optionally, the historical meteorological data includes parameter values of each candidate meteorological parameter within each preset time period in a preset historical time period;
determining a weight value for each of the candidate weather parameters based on the historical weather data, including:
constructing and obtaining a data matrix corresponding to each preset sub-time period in the preset historical time period; the data matrix comprises parameter values of each candidate meteorological parameter in each preset time period in the preset sub-time period;
carrying out data preprocessing operation on the data matrix to obtain a data matrix to be processed;
calculating the entropy of each candidate meteorological parameter corresponding to the data matrix to be processed;
and calculating the weight value of each candidate meteorological parameter according to the entropy of each candidate meteorological parameter.
Optionally, performing data preprocessing operation on the data matrix to obtain a data matrix to be processed, including:
and performing homodromous transformation processing and normalization processing on the parameter values of the candidate meteorological parameters in the data matrix to obtain a data matrix to be processed.
Optionally, screening out candidate meteorological parameters meeting a preset influence degree rule according to the weighted values of the candidate meteorological parameters, and using the candidate meteorological parameters as target meteorological parameters, including:
sorting the weighted values of the candidate meteorological parameters according to a preset sorting mode;
performing cumulative summation operation on the weighted values according to the sorting sequence, and stopping until the cumulative summation value meets a preset cumulative summation condition;
and acquiring candidate meteorological parameters corresponding to the weight values for the cumulative summation operation, and taking the candidate meteorological parameters as target meteorological parameters.
Optionally, constructing a typical weather year based on the parameter values of the target weather parameters in the historical weather data comprises:
and screening typical weather days from the historical weather data based on the parameter values of the target weather parameters in the historical weather data, and constructing the screened typical weather days to obtain typical weather years.
Optionally, the step of screening out typical weather days from the historical weather data based on the parameter values of the target weather parameters in the historical weather data comprises:
taking any one of the preset time periods as a target preset time period respectively;
calculating a distance value between the target time period and each non-target preset time period in each preset time period based on the historical meteorological data;
calculating the average value of all the distance values;
and screening out the preset time period with the minimum corresponding average value, and taking the preset time period as a typical meteorological day.
Optionally, calculating a distance value between the target time period and each non-target preset time period in the preset time periods based on the historical meteorological data includes:
acquiring first data and second data; the first data is the parameter value of the target meteorological parameter in the historical meteorological data within the target preset time period; the second data is the parameter value of the target meteorological parameter in the non-target preset time period in each preset time period in the historical meteorological data;
and calculating the distance value between the first data and the second data, and taking the distance value as the distance value between the target time period and the non-target preset time period.
Optionally, constructing the screened typical weather days to obtain typical weather years, including:
and constructing the screened typical weather days according to the time sequence to obtain the typical weather years.
A power generation amount prediction method comprising:
acquiring a typical meteorological year; the typical meteorological year is constructed based on the construction method of the typical meteorological year;
and performing power generation amount prediction operation according to the meteorological data of the typical meteorological year.
Optionally, performing an electric power generation amount prediction operation based on the meteorological data of the typical meteorological year, comprising:
and performing power generation amount prediction operation according to the meteorological data of the typical meteorological year and a preset power generation amount prediction mode to obtain predicted power generation amount data.
A typical weather year construction apparatus comprising:
the data acquisition module is used for acquiring historical meteorological data and a plurality of candidate meteorological parameters;
the weight value calculation module is used for determining the weight value of each candidate meteorological parameter based on the historical meteorological data;
the parameter screening module is used for screening out candidate meteorological parameters meeting a preset influence degree rule according to the weight values of the candidate meteorological parameters and taking the candidate meteorological parameters as target meteorological parameters;
and the year construction module is used for constructing a typical meteorological year based on the parameter values of the target meteorological parameters in the historical meteorological data.
An electric power generation amount prediction apparatus comprising:
the year acquisition module is used for acquiring typical meteorological years; the typical meteorological year is constructed based on the construction method of the typical meteorological year;
and the power generation amount prediction module is used for performing power generation amount prediction operation according to the meteorological data of the typical meteorological year.
A storage medium comprising a stored program, wherein the program, when executed, controls a device in which the storage medium is located to execute the above-described typical weather year construction method or the above-described power generation amount prediction method.
An electronic device, comprising: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to execute the above-described typical weather year construction method or to execute the above-described power generation amount prediction method.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a construction method of a typical meteorological year, a generating capacity prediction method and a related device. In other words, the target meteorological parameters are determined according to the influence degree of the candidate meteorological parameters, and compared with a mode that a fixed number of meteorological parameters are manually selected according to experience, the accuracy of meteorological parameter determination can be improved. And then improving the accuracy of the typical meteorological year constructed based on the parameter values of the target meteorological parameters in the historical meteorological data, so that the accuracy of the photovoltaic power generation amount prediction for performing the power generation amount prediction operation according to the meteorological data of the typical meteorological year is also improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flowchart of a method for constructing a typical weather year according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for constructing another typical weather year according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for constructing a typical weather year according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method for constructing a representative weather year according to an embodiment of the present invention;
fig. 5 is a flowchart of a method for predicting power generation according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a typical meteorological year building apparatus according to an embodiment of the present invention.
Fig. 7 is a schematic structural diagram of an electric power generation amount prediction apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In recent years, photovoltaic power generation serving as an important distributed energy technology is rapidly developed, and scientific and reasonable evaluation of power generation capacity of a power station can provide important reference basis for power station investment decision, economic analysis, electrical equipment type selection and system access. Especially, in the initial design stage of the photovoltaic power station, the power generation amount prediction has a crucial meaning for the evaluation of the economic benefit and the social benefit of the whole power station.
The power generation amount prediction of the photovoltaic power station can be influenced by a plurality of factors, such as photovoltaic array efficiency, inverter conversion efficiency, alternating current grid connection efficiency, meteorological data (such as temperature, wind speed, dust and snow), loss, equipment failure rate and the like, wherein the meteorological data is one of the most important influencing factors influencing the power generation amount prediction effect.
At present, because photovoltaic power generation is influenced by weather, environment and self component characteristics, the existing photovoltaic power station power generation amount estimation method generally needs more actual operation data of a local power station and weather data information provided by a weather station closest to the location of the power station.
However, in the research stage of feasibility of photovoltaic power station construction, the photovoltaic power station is mostly located in barren hilly lands far away from urban areas, local authoritative effective meteorological data and environmental parameters are generally lacked, and meanwhile, detailed resource data collection for independent household systems and other small power supply systems is not cost-effective. Therefore, how to obtain meteorological data to predict the power generation amount without meteorological data is an urgent problem to be solved by those skilled in the art.
The inventors found that Typical Meteorological annual Data (Typical Meteorological Year Data) can be used as Meteorological Data used when current Meteorological Data cannot be acquired. Wherein the Typical weather year is a hypothetical year consisting of 12 Typical Meteorological Months (TMM), and each of the Typical Meteorological months is selected to be a Month capable of representing a long-term climate characteristic. In the selection of the typical meteorological month, various factors need to be considered comprehensively, including the consistency of the meteorological parameters of the selected month and the data of a plurality of years in the aspects of average value, structure and the like.
Currently, there are several ways to implement when selecting a typical weather month. Such as:
1. danish method:
and comparing the standardized mean value and the standardized mean square error of the meteorological parameter residuals of a month in a year to select a typical meteorological year.
2. Filkenstein-Schafer (FS) statistical method generates a typical weather year (TMY) data set
3. And analyzing different energy systems by using a genetic algorithm to generate a typical meteorological year.
Regardless of the above approach, the inventors have discovered that currently, when generating a typical weather year, the main problems faced are:
1. the meteorological parameters and the parameter weights of the meteorological parameters are selected by manual experience.
Meteorological parameters selected by TMY data and parameter weights of the meteorological parameters lack reasonable selection bases, and most of the current methods use former experience parameters (such as meteorological characteristics four elements, dry-bulb humidity, dew-point temperature, wind speed and total radiation of a horizontal plane, proposed by Sandia national laboratory in the united states).
2. The idea of 'factorization' is mostly adopted in the process of processing TMY data, specifically, the method mainly examines the degree of closeness of a single meteorological parameter and the parameter to long-term data for many years, and analogizes to other parameters, and then selects a typical meteorological year by summing weighted values by using artificially-specified empirical parameter weights, so that the method is a single-factor processing strategy.
In this way, if the parameter weights of the selected meteorological parameters are inaccurate, the accuracy of the determined typical meteorological year is low. In addition, when a typical meteorological year is selected, each meteorological parameter is independently analyzed, and the incidence relation among the meteorological parameters is not considered, such as wind speed and wind direction which influence temperature and humidity.
The invention provides a generating capacity prediction method, which selects proper meteorological parameters according to an influence program of the meteorological parameters, and uniformly calculates the parameter values of the meteorological parameters when generating a typical meteorological year without independently calculating each meteorological parameter independently, thereby improving the accuracy of the generated typical meteorological year.
Furthermore, in the invention, the typical weather month is determined firstly, and then the typical weather year is constructed by the typical weather month, compared with the mode of firstly determining the typical weather month, the data is finer in fine granularity in the manner of constructing the typical weather month to obtain the typical weather year, so that the accuracy of the determined typical weather year is higher.
On the basis of the above, the embodiment of the invention provides an electric power generation amount prediction method applied to a processor, such as an electric power generation amount prediction processor, a server, and the like. Referring to fig. 1, the power generation amount prediction method may include:
and S11, acquiring historical meteorological data and a plurality of candidate meteorological parameters.
In practical applications, the plurality of candidate meteorological parameters may be all meteorological parameters affecting photovoltaic power generation, such as:
altitude, average cloud cover, maximum temperature, minimum temperature, average temperature, maximum dew point temperature, minimum dew point temperature, dew point average temperature, maximum relative humidity, minimum relative humidity, average relative humidity, relative humidity deviation, maximum wind speed, average wind speed deviation, average wind direction, average wind power, total radiation in a horizontal plane, direct radiation, scattered radiation, cloud cover coverage, precipitation probability, precipitation amount, atmospheric pressure, visibility, and ultraviolet index.
The historical meteorological data comprises parameter values of the candidate meteorological parameters in each preset time period in the preset historical time period.
The preset historical time period may be the last thirty years, and the preset time period may be one day, that is, the parameter values of the candidate meteorological parameters are obtained in each day of the last thirty years.
TABLE 1 partial historical meteorological data
| Date | Longitude (G) | Latitude | Altitude (H) level | Mean cloud volume | … | Dew point average temperature | Maximum wind speed | Mean wind speed | Total radiation of horizontal plane |
| 1970-01-01 | 114.37 | 10.38 | 5 | 0.15 | … | 66.17 | 20 | 11.83 | 1076.64 |
| 1971-01-01 | 114.37 | 10.38 | 5 | 9.55 | … | 67.71 | 2 | 1.14 | 1111.17 |
| 1972-01-01 | 114.37 | 10.38 | 5 | 7.89 | … | 69 | 7 | 3.25 | 1106.05 |
| 1975-01-01 | 114.37 | 10.38 | 5 | 17.93 | … | 74.63 | 18 | 12 | 1106.1 |
| 1976-01-01 | 114.37 | 10.38 | 5 | 22.45 | … | 74.38 | 20 | 14.25 | 1103.69 |
| 1977-01-01 | 114.37 | 10.38 | 5 | 3.61 | … | 73.86 | 20 | 15 | 1106.67 |
| 1978-01-01 | 114.37 | 10.38 | 5 | 1.45 | … | 74.38 | 20 | 10.63 | 1085.31 |
| … | … | … | … | … | … | … | … | … | … |
| 2010-01-01 | 114.366 | 10.383 | 5 | 41.6456 | … | 75 | 11 | 10.3333 | 1784.107 |
| 2011-01-01 | 114.366 | 10.383 | 5 | 35.9577 | … | 74.8333 | 13 | 12.3333 | 1815.423 |
| 2012-01-01 | 114.366 | 10.383 | 5 | 7.1759 | … | 75.1667 | 13 | 10.3333 | 1821.303 |
| 2013-01-01 | 114.366 | 10.383 | 5 | 8.5737 | … | 76.375 | 11 | 9.75 | 1828.717 |
| 2014-01-01 | 114.366 | 10.383 | 5 | 24.3022 | … | 75.125 | 18 | 13.5 | 1820.187 |
| 2015-01-01 | 114.366 | 10.383 | 5 | 0.5809 | … | 75.625 | 11 | 8.5 | 1818.353 |
| 2016-01-01 | 114.366 | 10.383 | 5 | 8.61959 | … | 77.1429 | 7 | 6.57143 | 1821.947 |
| 2017-01-01 | 114.366 | 10.383 | 5 | 30.4382 | … | 76.25 | 7 | 4.875 | 1827.927 |
| 2018-01-01 | 114.366 | 10.383 | 5 | 22.1551 | … | 76.4286 | 13 | 10.4286 | 1832.893 |
| 2019-01-01 | 114.366 | 10.383 | 5 | 36.1352 | … | 76.25 | 11 | 9.5 | 1827.74 |
| 2020-01-01 | 114.366 | 10.383 | 5 | 32.2346 | … | 73.6 | 2 | 2 | 1624.56 |
Where the longitude and latitude in table 1 are used to identify a geographic location and are not candidate meteorological parameters.
Referring to table 1 above, a schematic of a portion of historical weather data is shown in table 1, where table 1 includes parameter values for each candidate weather parameter in month 1 of the year, which is the last 30 years. The number of other months in the last 30 years is similar.
The historical meteorological data and the candidate meteorological parameters can be stored in a database in advance, and can be acquired from the database when the acquisition requirement exists.
And S12, determining the weight value of each candidate meteorological parameter based on the historical meteorological data.
The weighted value in this embodiment is a basis for determining the target meteorological parameter.
And S13, screening out candidate meteorological parameters meeting the preset influence degree rule according to the weight values of the candidate meteorological parameters, and taking the candidate meteorological parameters as target meteorological parameters.
The target meteorological parameter in this embodiment is a candidate meteorological parameter that has a large influence on the photovoltaic power generation amount.
That is, in the present invention, not all weather parameter candidates are analyzed, but a better weather parameter candidate is selected and only the better weather parameter candidate is analyzed. As shown in Table 1, the preferred weather parameter candidates as selected may be:
altitude, average cloud cover, dew point average temperature, maximum wind speed, average wind speed, and total horizontal radiation.
S14, constructing a typical weather year based on the parameter values of the target weather parameters in the historical weather data.
Specifically, typical weather days are screened from the historical weather data based on parameter values of the target weather parameters in the historical weather data, and the screened typical weather days are constructed to obtain typical weather years.
Still taking the last 30 years as an example, since the parameter values of the candidate weather parameters for each day of the last 30 years are given in the historical weather data, the typical weather day can be selected from each day given in the historical weather data according to the parameter values of the target weather parameters.
Taking 1 month and 1 day as an example, in table 1, weather data of 1 month and 1 day of each year in the last 30 years is given, and one day is selected from 30 1 month and 1 day of the last 30 years as a typical weather day of 1 month and 1 day. Similarly, other dates are similar. Taking 365 days included in a year as an example, 365 typical weather days are selected. And then constructing the screened typical weather days according to the time sequence to obtain the typical weather years.
In this embodiment, historical meteorological data and a plurality of candidate meteorological parameters are obtained, a weight value of each candidate meteorological parameter is determined based on the historical meteorological data, and a candidate meteorological parameter meeting a preset influence degree rule is screened out according to the weight value of each candidate meteorological parameter and is used as a target meteorological parameter. In other words, the target meteorological parameters are determined according to the influence degree of the candidate meteorological parameters, and compared with a mode that a fixed number of meteorological parameters are manually selected according to experience, the accuracy of meteorological parameter determination can be improved. And then improving the accuracy of the typical meteorological year constructed based on the parameter values of the target meteorological parameters in the historical meteorological data, so that the accuracy of the photovoltaic power generation amount prediction for performing the power generation amount prediction operation according to the meteorological data of the typical meteorological year is also improved.
Further, typical weather days are screened from the historical weather data based on parameter values of the target weather parameters in the historical weather data, and the screened typical weather days are constructed to obtain typical weather years.
In the above embodiments, a simple description of determining the target meteorological parameters is given, and a specific implementation process thereof is now described. In this embodiment, if the information entropy of a certain meteorological parameter is smaller, it indicates that the variation degree of the meteorological parameter is larger, the amount of the provided information is larger, and the weight of the information is larger; according to the scheme, the objective weights of various meteorological parameters required by TMY data are determined by means of the thought (particularly by using an entropy weight method), and then core meteorological parameters are selected preferably according to the contribution rate of each parameter, wherein the parameters are called as target meteorological parameters in the embodiment.
Specifically, referring to fig. 2, step S12 may include:
and S21, constructing and obtaining a data matrix corresponding to each preset sub-time period in the preset historical time period.
The data matrix comprises parameter values of the candidate meteorological parameters in each preset time period in the preset sub-time period.
The preset sub-period may be one year, that is, for each year in the preset historical period (such as each year in the last 30 years mentioned above), a corresponding data matrix is constructed. The data matrix includes parameter values for each candidate weather parameter for each day of the year:
assuming that there are s historical meteorological years (e.g., the last 30 years mentioned above), each historical meteorological year has n days, and m candidate meteorological indexes (as shown in table 1), the data matrix is constructed as follows:
by the construction method, S data matrixes can be constructed and obtained.
And S22, performing data preprocessing operation on the data matrix to obtain a data matrix to be processed.
The preset preprocessing operation in this embodiment includes homotrending transformation processing and normalization processing, that is, homotrending transformation processing and normalization processing are performed on parameter values of each candidate meteorological parameter in the data matrix, so as to obtain a data matrix to be processed.
Taking the maximum temperature and the average wind speed as examples, the higher the maximum temperature is, the larger the power generation amount is, that is, the maximum temperature is positively correlated with the power generation amount, and the smaller the average wind speed is, the larger the power generation amount is, that is, the average wind speed is negatively correlated with the power generation amount.
That is, the influence of the maximum temperature and the average wind speed on the power generation amount are opposite, and the influence of different candidate meteorological parameters on the power generation amount needs to be unified, so that the influence is in a forward direction or in a reverse direction.
In this embodiment, the same forward matrix is constructed, i.e. for X described abovesThe adjustment is made so that it becomes a forward-identical matrix. The specific adjustment process is as follows:
for the candidate meteorological parameters, the parameter identifiers are preset for the candidate meteorological parameters, the parameter identifiers can be absolute indicators and relative indicators, for example, the highest temperature is an absolute indicator, the average relative humidity is a relative indicator, and each candidate meteorological parameter has a corresponding parameter identifier.
Then, for the absolute index, the reciprocal method is adopted: 1/x; aiming at the relative indexes, adopting a difference method: 1-x, and obtaining a homoforward matrix after homotrend transformation processing, wherein the homoforward matrix is as follows:
after the homonymous matrix is obtained, non-dimensionalization processing is performed, in an embodiment of the present invention, normalization processing is performed on the homonymous matrix, and an adopted normalization processing method may be:
(1)z-score；
(2) a minimum maximization;
(3) relative average method.
In this embodiment, a relative average method may be selected to obtain a to-be-processed data matrix:
wherein the content of the first and second substances,
and S23, calculating the entropy of each candidate meteorological parameter corresponding to the data matrix to be processed.
Specifically, according to the to-be-processed matrix, the entropy of each candidate meteorological parameter is calculated, and a specific calculation formula is as follows:
wherein k is an adjusting coefficient, k is 1/ln (n × s), s is the number of historical meteorological years, n is the number of days of each historical meteorological year, m is the number of candidate meteorological indexes, z is a set of weather indexes, and the set of weather indexes is used for determining the weather indexesijThe normalized value of the jth candidate meteorological parameter on the ith day is the data in the to-be-processed data matrix.
And S24, calculating the weight value of each candidate meteorological parameter according to the entropy of each candidate meteorological parameter.
Specifically, according to the entropy of each candidate meteorological parameter, a calculation formula for calculating the weight value of each candidate meteorological parameter is as follows:
wherein m is the number of candidate meteorological indexes, H (x)j) As entropy of the candidate meteorological parameters, djThe candidate meteorological parameters are weighted values.
Therefore, the weight value set of each candidate meteorological parameter that can be obtained specifically includes:
D＝(d1,d2,...,dm)。
in another implementation manner of the present invention, in step S13, "the candidate weather parameters meeting the preset influence degree rule are screened out according to the weight values of the candidate weather parameters, and the candidate weather parameters with larger influence program are screened out from the candidate weather parameters as the target weather parameters. The specific implementation process refers to fig. 3.
Referring to fig. 3, step S13 may include:
and S31, sorting the weighted values of the candidate meteorological parameters according to a preset sorting mode.
In a specific implementation process, the weight values of the candidate meteorological parameters are sorted from large to small, namely, the candidate meteorological parameters are arranged in front of the candidate meteorological parameters with larger weight values and are arranged behind the candidate meteorological parameters with smaller weight values.
And S32, performing cumulative summation operation on the weight values according to the sorting sequence, and stopping until the cumulative summation value meets the preset cumulative summation condition.
The preset cumulative summation condition in this embodiment may be that a ratio of the cumulative summation value to a sum of all the weight values is greater than a preset threshold, and the preset threshold may be 0.85.
For example, assume that the weight values in descending order are 0.5, 0.3, 0.17, 0.02, 0.01. First, a value of 0.5+0.3 is calculated to be 0.8, and if the sum of all weight values is 1, 0.8/1 is 0.8 and is less than 0.85.
At this point, the cumulative summation is continued, and a value of 0.5+0.3+0.17 is calculated as 0.97, and 0.97/1 is 0.97 and greater than 0.85, at which point the cumulative summation operation may be stopped.
In practical applications, step S42 can also be implemented by a formula, specifically,
wherein m is the number of candidate meteorological parameters, DjRepresenting a ratio of the cumulative sum to the sum of all weight values exceeding 85% after descending order. The candidate meteorological parameters corresponding to the weight values for the cumulative summation operation can be screened out to obtain the candidate meteorological parameters with the cumulative contribution degree of more than 85% for determining the subsequent typical meteorological year.
And S33, acquiring candidate meteorological parameters corresponding to the weight values for the cumulative summation operation, and taking the candidate meteorological parameters as target meteorological parameters.
Specifically, in the above embodiment, the weighting values for performing the cumulative summation operation are 0.5, 0.3, and 0.17, and if the candidate meteorological parameters corresponding to the three weighting values are the maximum wind speed, the average wind speed, and the dew point average temperature, it is described that the three candidate meteorological parameters are parameters having a large influence on the power generation amount, and at this time, the three parameters are taken as the target meteorological parameters.
If the preset threshold is set according to the actual application scenario, the target weather parameters selected according to the preset threshold also vary according to the actual application scenario, and for example, 3, 4, 5,6, and other candidate weather parameters may be selected as the target weather parameters.
In the embodiment, a determination process for determining the target meteorological parameters is provided, the objective weight of each meteorological parameter is determined by using an entropy weight method, the core TMY data meteorological parameters are preferably selected according to the factor contribution rate (85%), the science and rationality of parameter selection are improved, and compared with a mode of manually selecting the meteorological parameters according to experience, the data calculation is simplified, and the data making efficiency is improved.
In another implementation of the present invention, the typical weather year TMY data is processed from typical weather days, so in this embodiment, the typical weather year is obtained by preferentially determining the typical weather month and then constructing the typical weather month to obtain the typical weather year.
The typical weather day in the present embodiment is determined by the distance (e.g., minimum average Minkowski (Minkowski) distance, euclidean distance, etc.) between each target weather parameter and each target weather parameter on a certain day of the month of the year (such dates are 1970-01-01, 1971-01-01 … … 2020-01, and these dates are referred to as candidate weather days in table 1), and the smaller the distance, the smaller the degree of point dispersion, and the closer to the historical long-term average, the candidate weather day can be regarded as the typical weather day. The specific implementation of obtaining a typical weather day will now be described.
Specifically, referring to fig. 4, a specific implementation process of the above "screening out typical weather days from the historical weather data based on the parameter values of the target weather parameters in the historical weather data" is provided, and may include:
and S41, taking any one of the preset time periods as a target preset time period.
Wherein, the preset time period is one day, and each day is respectively taken as a target preset time period.
And S42, calculating the distance value between the target time period and each non-target preset time period in each preset time period based on the historical meteorological data.
In practical application, the first data and the second data can be acquired; the first data is the parameter value of the target meteorological parameter in the historical meteorological data within the target preset time period; the second data is the parameter value of the target meteorological parameter in the non-target preset time period in each preset time period in the historical meteorological data;
then, a distance value between the first data and the second data is calculated and used as a distance value between the target time period and the non-target preset time period.
Specifically, the distance value, such as the minimum average Minkowski distance, is calculated as:
wherein p generally takes the value of 2; a represents the number of target meteorological parameters; dist (X, Y) represents the Minkowski distance between the candidate weather day X and all other candidate weather days, as exemplified by the candidate weather day being 1970-01-01, as follows:
calculating the distance value of the parameter value of the target meteorological parameter on days 01-01 of each year 1970-01-01 and (1970-2020), such as calculating the distance value of 1970-01-01 and 1971-01-01, i.e. calculating the distance value of the parameter value of the target meteorological parameter
(iii) distance values of {5,0.15, 66.17,20,11.83,1076.64} from {5,9.55,67.71,2,1.14,1111.17 }.
Then for each candidate weather day, 29 distance values from another 29 of the last 30 years may be calculated.
And S43, calculating the average value of all the distance values.
And S44, screening out the preset time period with the minimum corresponding average value, and taking the preset time period as a typical weather day.
That is, for each weather day candidate, the 29 calculated distance values are averaged.
Where Y { Y, m, d } represents the candidate weather day for the minimum average Minkowski distance.
If the same minimum minkowski distance value exists as a result of the calculation, either one is selected.
In this embodiment, the candidate weather day having the smallest distance from the other candidate weather days is selected and used as the typical weather day, so that the typical weather day obtained by the screening can represent the long-term historical average value, the accuracy of the selected typical weather day is high, and the typical weather year can be obtained based on the determined typical weather day.
In addition, the existing TMY data processing method mainly examines the closeness degree of a single meteorological parameter and multi-year long-term data of the meteorological parameter, and analogizes to other meteorological parameters, then carries out weighted value summation by using artificially specified empirical parameter weight to select a typical meteorological month, and finally constructs to obtain the typical meteorological year. In addition, each meteorological parameter is independently calculated, the incidence relation among the meteorological parameters is ignored, in the invention, the typical meteorological day is determined through the minimum average Minkowski (Minkowski) distance, when the distance is calculated, a plurality of meteorological parameters are uniformly calculated, a single meteorological parameter is not split, the error influence caused by the fact that the traditional method adopts subjective weight weighted summation is avoided, the incidence relation among the meteorological parameters is considered, the smaller the obtained distance is, the smaller the discrete degree of the indication point is, the closer the discrete degree is to the long-term historical average value is, the higher the accuracy of the determined typical meteorological day is, and the complex and tedious calculation in the TMY data processing process is simplified.
Alternatively, on the basis of the above embodiment of the method for constructing the typical meteorological year, another embodiment of the present invention provides a method for predicting power generation, specifically, referring to fig. 5, which may include:
and S51, acquiring a typical weather year.
The typical weather year is constructed based on the construction method of the typical weather year, and weather data of each day in the typical weather year are acquired after the typical weather year is obtained.
And S52, performing power generation amount prediction operation according to the meteorological data of the typical meteorological year.
In practical application, according to the meteorological data of the typical meteorological year, the power generation amount prediction operation is carried out according to a preset power generation amount prediction mode, and predicted power generation amount data are obtained.
The preset power generation amount prediction mode can be set by a technician according to an actual application scene.
In this embodiment, the accuracy of the typical weather year obtained based on the construction method of the typical weather year is high, and further, according to the weather data of the typical weather year, the accuracy of the photovoltaic power generation amount prediction of the accuracy of the power generation amount prediction operation is also improved.
Alternatively, on the basis of the above embodiment of the method for building a typical meteorological year, another embodiment of the present invention provides a device for building a typical meteorological year, and with reference to fig. 6, the device may include:
the data acquisition module 11 is used for acquiring historical meteorological data and a plurality of candidate meteorological parameters;
a weight value calculating module 12, configured to determine a weight value of each candidate meteorological parameter based on the historical meteorological data;
the parameter screening module 13 is configured to screen out candidate meteorological parameters meeting a preset influence degree rule according to the weight values of the candidate meteorological parameters, and use the candidate meteorological parameters as target meteorological parameters;
a year construction module 14, configured to construct a typical weather year based on the parameter values of the target weather parameters in the historical weather data.
Further, the historical meteorological data comprises parameter values of each candidate meteorological parameter in each preset time period in a preset historical time period;
the weight value calculation module 12 includes:
the matrix construction submodule is used for constructing and obtaining a data matrix corresponding to each preset sub-time period in the preset historical time periods; the data matrix comprises parameter values of each candidate meteorological parameter in each preset time period in the preset sub-time period;
the matrix processing submodule is used for carrying out data preprocessing operation on the data matrix to obtain a data matrix to be processed;
the entropy calculation submodule is used for calculating the entropy of each candidate meteorological parameter corresponding to the data matrix to be processed;
and the weight value determining submodule is used for calculating the weight value of each candidate meteorological parameter according to the entropy of each candidate meteorological parameter.
Further, the matrix processing submodule is specifically configured to:
and performing homodromous transformation processing and normalization processing on the parameter values of the candidate meteorological parameters in the data matrix to obtain a data matrix to be processed.
Further, the parameter screening module 13 includes:
the sorting submodule is used for sorting the weighted values of the candidate meteorological parameters according to a preset sorting mode;
the summation submodule is used for carrying out cumulative summation operation on the weighted values according to the sorting sequence until the cumulative summation value meets a preset cumulative summation condition;
and the parameter selection submodule is used for acquiring candidate meteorological parameters corresponding to the weight values for performing the cumulative summation operation and taking the candidate meteorological parameters as the target meteorological parameters.
Further, the year construction module 14 is specifically configured to:
and screening typical weather days from the historical weather data based on the parameter values of the target weather parameters in the historical weather data, and constructing the screened typical weather days to obtain typical weather years.
Further, the year construction module 14 includes:
the period determination submodule is used for respectively taking any one preset time period in each preset time period as a target preset time period;
the distance calculation submodule is used for calculating a distance value between the target time period and each non-target preset time period in each preset time period based on the historical meteorological data;
the average value calculation submodule is used for calculating the average value of all the distance values;
and the weather day determining submodule is used for screening out the preset time period with the minimum corresponding average value and taking the preset time period as a typical weather day.
Further, the distance calculation submodule is specifically configured to:
acquiring first data and second data; the first data is the parameter value of the target meteorological parameter in the historical meteorological data within the target preset time period; the second data is the parameter value of the target meteorological parameter in the non-target preset time period in each preset time period in the historical meteorological data;
and calculating the distance value between the first data and the second data, and taking the distance value as the distance value between the target time period and the non-target preset time period.
Further, the year construction module 14 includes:
and the weather year determining submodule is used for constructing the screened typical weather days according to the time sequence to obtain the typical weather years.
In this embodiment, historical meteorological data and a plurality of candidate meteorological parameters are obtained, a weight value of each candidate meteorological parameter is determined based on the historical meteorological data, and a candidate meteorological parameter meeting a preset influence degree rule is screened out according to the weight value of each candidate meteorological parameter and is used as a target meteorological parameter. In other words, the target meteorological parameters are determined according to the influence degree of the candidate meteorological parameters, and compared with a mode that a fixed number of meteorological parameters are manually selected according to experience, the accuracy of meteorological parameter determination can be improved. And then improving the accuracy of the typical meteorological year constructed based on the parameter values of the target meteorological parameters in the historical meteorological data, so that the accuracy of the photovoltaic power generation amount prediction for performing the power generation amount prediction operation according to the meteorological data of the typical meteorological year is also improved.
It should be noted that, for the working processes of each module and sub-module in this embodiment, please refer to the corresponding description in the above embodiments, which is not described herein again.
Alternatively, on the basis of the embodiment of the electric power generation amount prediction method described above, another embodiment of the present invention provides an electric power generation amount prediction device, and referring to fig. 7, may include:
a year acquiring module 21 for acquiring a typical weather year; the typical weather year is constructed based on the construction method of the typical weather year as claimed in any one of claims 1 to 8;
and the power generation amount prediction module 22 is used for performing power generation amount prediction operation according to the meteorological data of the typical meteorological year.
Further, the power generation amount prediction module 22 is specifically configured to:
and performing power generation amount prediction operation according to the meteorological data of the typical meteorological year and a preset power generation amount prediction mode to obtain predicted power generation amount data.
In this embodiment, the accuracy of the typical weather year obtained based on the construction method of the typical weather year is high, and further, according to the weather data of the typical weather year, the accuracy of the photovoltaic power generation amount prediction of the accuracy of the power generation amount prediction operation is also improved.
It should be noted that, for the working process of each module in this embodiment, please refer to the corresponding description in the above embodiments, which is not described herein again.
Optionally, on the basis of the above embodiments of the typical weather year construction method and apparatus, another embodiment of the present invention provides a storage medium, where the storage medium includes a stored program, and when the program runs, a device in which the storage medium is located is controlled to execute the above typical weather year construction method.
Optionally, on the basis of the above embodiment of the method and apparatus for building a typical weather year, another embodiment of the present invention provides an electronic device, including: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to execute the typical weather year construction method described above.
In this embodiment, historical meteorological data and a plurality of candidate meteorological parameters are obtained, a weight value of each candidate meteorological parameter is determined based on the historical meteorological data, and a candidate meteorological parameter meeting a preset influence degree rule is screened out according to the weight value of each candidate meteorological parameter and is used as a target meteorological parameter. In other words, the target meteorological parameters are determined according to the influence degree of the candidate meteorological parameters, and compared with a mode that a fixed number of meteorological parameters are manually selected according to experience, the accuracy of meteorological parameter determination can be improved. And then improving the accuracy of the typical meteorological year constructed based on the parameter values of the target meteorological parameters in the historical meteorological data, so that the accuracy of the photovoltaic power generation amount prediction for performing the power generation amount prediction operation according to the meteorological data of the typical meteorological year is also improved.
Alternatively, on the basis of the embodiments of the above-described electric power generation amount prediction method and apparatus, another embodiment of the present invention provides a storage medium including a stored program, wherein the electric power generation amount prediction method is executed by a device on which the storage medium is controlled when the program is run.
Alternatively, on the basis of the embodiments of the power generation amount prediction method and apparatus, another embodiment of the present invention provides an electronic device, including: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to execute the above-described power generation amount prediction method.
In this embodiment, the accuracy of the typical weather year obtained based on the construction method of the typical weather year is high, and further, according to the weather data of the typical weather year, the accuracy of the photovoltaic power generation amount prediction of the accuracy of the power generation amount prediction operation is also improved.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (14)
1. A typical meteorological year construction method is characterized by comprising the following steps:
acquiring historical meteorological data and a plurality of candidate meteorological parameters;
determining a weight value of each candidate meteorological parameter based on the historical meteorological data;
screening out candidate meteorological parameters meeting a preset influence degree rule according to the weighted values of the candidate meteorological parameters, and taking the candidate meteorological parameters as target meteorological parameters;
and constructing a typical meteorological year based on the parameter values of the target meteorological parameters in the historical meteorological data.
2. The method of constructing according to claim 1, wherein the historical meteorological data includes parameter values for each candidate meteorological parameter for each preset time period in a preset historical time period;
determining a weight value for each of the candidate weather parameters based on the historical weather data, including:
constructing and obtaining a data matrix corresponding to each preset sub-time period in the preset historical time period; the data matrix comprises parameter values of each candidate meteorological parameter in each preset time period in the preset sub-time period;
carrying out data preprocessing operation on the data matrix to obtain a data matrix to be processed;
calculating the entropy of each candidate meteorological parameter corresponding to the data matrix to be processed;
and calculating the weight value of each candidate meteorological parameter according to the entropy of each candidate meteorological parameter.
3. The construction method according to claim 2, wherein performing data preprocessing operation on the data matrix to obtain a data matrix to be processed comprises:
and performing homodromous transformation processing and normalization processing on the parameter values of the candidate meteorological parameters in the data matrix to obtain a data matrix to be processed.
4. The construction method according to claim 1, wherein the screening out the candidate meteorological parameters meeting the preset influence degree rule according to the weight values of the candidate meteorological parameters, and using the candidate meteorological parameters as the target meteorological parameters comprises:
sorting the weighted values of the candidate meteorological parameters according to a preset sorting mode;
performing cumulative summation operation on the weighted values according to the sorting sequence, and stopping until the cumulative summation value meets a preset cumulative summation condition;
and acquiring candidate meteorological parameters corresponding to the weight values for the cumulative summation operation, and taking the candidate meteorological parameters as target meteorological parameters.
5. The method of constructing according to claim 2, wherein constructing a typical weather year based on the parameter values of the target weather parameters in the historical weather data comprises:
and screening typical weather days from the historical weather data based on the parameter values of the target weather parameters in the historical weather data, and constructing the screened typical weather days to obtain typical weather years.
6. The construction method according to claim 5, wherein the step of screening out typical weather days from the historical weather data based on the parameter values of the target weather parameters in the historical weather data comprises:
taking any one of the preset time periods as a target preset time period respectively;
calculating a distance value between the target time period and each non-target preset time period in each preset time period based on the historical meteorological data;
calculating the average value of all the distance values;
and screening out the preset time period with the minimum corresponding average value, and taking the preset time period as a typical meteorological day.
7. The method of constructing according to claim 6, wherein calculating a distance value between the target time period and each of the respective preset time periods other than the target preset time period based on the historical meteorological data comprises:
acquiring first data and second data; the first data is the parameter value of the target meteorological parameter in the historical meteorological data within the target preset time period; the second data is the parameter value of the target meteorological parameter in the non-target preset time period in each preset time period in the historical meteorological data;
and calculating the distance value between the first data and the second data, and taking the distance value as the distance value between the target time period and the non-target preset time period.
8. The construction method according to claim 5, wherein constructing the screened typical weather day into a typical weather year comprises:
and constructing the screened typical weather days according to the time sequence to obtain the typical weather years.
9. A power generation amount prediction method characterized by comprising:
acquiring a typical meteorological year; the typical weather year is constructed based on the construction method of the typical weather year as claimed in any one of claims 1 to 8;
and performing power generation amount prediction operation according to the meteorological data of the typical meteorological year.
10. The electric power generation amount prediction method according to claim 9, wherein performing an electric power generation amount prediction operation based on the meteorological data of the typical meteorological year includes:
and performing power generation amount prediction operation according to the meteorological data of the typical meteorological year and a preset power generation amount prediction mode to obtain predicted power generation amount data.
11. A typical weather year construction apparatus comprising:
the data acquisition module is used for acquiring historical meteorological data and a plurality of candidate meteorological parameters;
the weight value calculation module is used for determining the weight value of each candidate meteorological parameter based on the historical meteorological data;
the parameter screening module is used for screening out candidate meteorological parameters meeting a preset influence degree rule according to the weight values of the candidate meteorological parameters and taking the candidate meteorological parameters as target meteorological parameters;
and the year construction module is used for constructing a typical meteorological year based on the parameter values of the target meteorological parameters in the historical meteorological data.
12. An electric power generation amount prediction apparatus characterized by comprising:
the year acquisition module is used for acquiring typical meteorological years; the typical weather year is constructed based on the construction method of the typical weather year as claimed in any one of claims 1 to 8;
and the power generation amount prediction module is used for performing power generation amount prediction operation according to the meteorological data of the typical meteorological year.
13. A storage medium characterized by comprising a stored program, wherein the apparatus on which the storage medium is placed is controlled to execute the typical meteorological year construction method according to any one of claims 1 to 8 or the electric power generation amount prediction method according to any one of claims 9 to 10 when the program is executed.
14. An electronic device, comprising: a memory and a processor;
wherein the memory is used for storing programs;
a processor calls a program and is used to perform the method of construction of a typical weather year according to any one of claims 1 to 8 or to perform the method of power generation prediction according to any one of claims 9 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110700241.7A CN113379143A (en) | 2021-06-23 | 2021-06-23 | Typical meteorological year construction method, power generation amount prediction method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110700241.7A CN113379143A (en) | 2021-06-23 | 2021-06-23 | Typical meteorological year construction method, power generation amount prediction method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113379143A true CN113379143A (en) | 2021-09-10 |
Family
ID=77578816
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110700241.7A Pending CN113379143A (en) | 2021-06-23 | 2021-06-23 | Typical meteorological year construction method, power generation amount prediction method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113379143A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073791A (en) * | 2011-01-12 | 2011-05-25 | 东南大学 | Local solar energy resource abundance evaluating system for design of photovoltaic power station |
| US20130066569A1 (en) * | 2011-09-13 | 2013-03-14 | Kabushiki Kaisha Toshiba | Power generation predicting apparatus and method thereof |
| JP2014063372A (en) * | 2012-09-21 | 2014-04-10 | Toshiba Corp | Apparatus and method for predicting power generation capacity |
| WO2014155482A1 (en) * | 2013-03-25 | 2014-10-02 | 中国電力株式会社 | Power generation prediction device, and power generation prediction method and program |
| CN104123682A (en) * | 2014-07-28 | 2014-10-29 | 国家电网公司 | Distribution network fault risk assessment method based on meteorology influence factors |
| CN108197744A (en) * | 2018-01-02 | 2018-06-22 | 华北电力大学（保定） | A kind of determining method and system of photovoltaic generation power |
| CN109948281A (en) * | 2019-03-29 | 2019-06-28 | 上海电力学院 | It is effectively identified based on weather pattern and the straight of combined prediction dissipates separated modeling method |
| CN110133755A (en) * | 2019-04-19 | 2019-08-16 | 上海电力学院 | Separated modeling forecast Control Algorithm is directly dissipated under more weather patterns based on GRA-LMBP weight |
| CN110781577A (en) * | 2019-09-16 | 2020-02-11 | 北京工业大学 | Method and device for generating typical meteorological year when meteorological elements are missing |
| 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 |
| CN111160625A (en) * | 2019-12-10 | 2020-05-15 | 中铁电气化局集团有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
| CN111311169A (en) * | 2019-11-12 | 2020-06-19 | 上海朗绿建筑科技股份有限公司 | Urban outdoor environment analysis method and system, storage medium and electronic equipment |
| CN112365176A (en) * | 2020-11-18 | 2021-02-12 | 西安建筑科技大学 | Energy-saving analysis weather year calculation method, system, device and storage medium |
-
2021
- 2021-06-23 CN CN202110700241.7A patent/CN113379143A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073791A (en) * | 2011-01-12 | 2011-05-25 | 东南大学 | Local solar energy resource abundance evaluating system for design of photovoltaic power station |
| US20130066569A1 (en) * | 2011-09-13 | 2013-03-14 | Kabushiki Kaisha Toshiba | Power generation predicting apparatus and method thereof |
| JP2014063372A (en) * | 2012-09-21 | 2014-04-10 | Toshiba Corp | Apparatus and method for predicting power generation capacity |
| WO2014155482A1 (en) * | 2013-03-25 | 2014-10-02 | 中国電力株式会社 | Power generation prediction device, and power generation prediction method and program |
| CN104123682A (en) * | 2014-07-28 | 2014-10-29 | 国家电网公司 | Distribution network fault risk assessment method based on meteorology influence factors |
| CN108197744A (en) * | 2018-01-02 | 2018-06-22 | 华北电力大学（保定） | A kind of determining method and system of photovoltaic generation power |
| CN109948281A (en) * | 2019-03-29 | 2019-06-28 | 上海电力学院 | It is effectively identified based on weather pattern and the straight of combined prediction dissipates separated modeling method |
| CN110133755A (en) * | 2019-04-19 | 2019-08-16 | 上海电力学院 | Separated modeling forecast Control Algorithm is directly dissipated under more weather patterns based on GRA-LMBP weight |
| CN110781577A (en) * | 2019-09-16 | 2020-02-11 | 北京工业大学 | Method and device for generating typical meteorological year when meteorological elements are missing |
| 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 |
| CN111311169A (en) * | 2019-11-12 | 2020-06-19 | 上海朗绿建筑科技股份有限公司 | Urban outdoor environment analysis method and system, storage medium and electronic equipment |
| CN111160625A (en) * | 2019-12-10 | 2020-05-15 | 中铁电气化局集团有限公司 | Power load prediction method, power load prediction device, computer equipment and storage medium |
| CN112365176A (en) * | 2020-11-18 | 2021-02-12 | 西安建筑科技大学 | Energy-saving analysis weather year calculation method, system, device and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| 李燕青;杜莹莹;: ""基于最优相似度与IMEA-RBFNN的短期光伏发电功率预测"", 《华北电力大学学报(自然科学版)》, no. 05, pages 29 - 35 * |
| 杨小山等: "面向城市热环境的典型气象日确定方法", 《环境科学与技术》, vol. 42, no. 01, 15 January 2019 (2019-01-15), pages 231 - 236 * |
| 王华;: ""南海地区典型气象年生成方法对比研究"", 《中国优秀硕士学位论文全文数据库（工程科技Ⅱ辑）》, no. 2019, pages 038 - 233 * |
| 田启明;许和明;袁亚洲;张中丹;秦学林;邱云翔;: ""光热电站太阳能资源典型年选取方法及验证的探讨"", 《电力勘测设计》, no. 08, pages 61 - 66 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ohunakin et al. | Generation of a typical meteorological year for north–east, Nigeria | |
| CN112285807B (en) | Meteorological information prediction method and device | |
| CN109685257A (en) | A kind of photovoltaic power generation power prediction method based on Support vector regression | |
| CN112381137B (en) | New energy power system reliability assessment method, device, equipment and storage medium | |
| Pawlowski et al. | Application of time-series methods to disturbance estimation in predictive control problems | |
| CN116882847B (en) | Installation quality detection method and system for photovoltaic module | |
| Nazeri-Tahroudi et al. | Estimation of dew point temperature in different climates of Iran using support vector regression | |
| CN116663786B (en) | Wind-solar resource assessment method and device, electronic equipment and storage medium | |
| CN113222245A (en) | Method and system for checking monthly electric quantity and electricity charge abnormity of residential user and storage medium | |
| CN108764300A (en) | A kind of big data cluster analysis method of fixed type photovoltaic power generation system optimum angle of incidence | |
| CN113379143A (en) | Typical meteorological year construction method, power generation amount prediction method and related device | |
| CN116050666B (en) | Photovoltaic power generation power prediction method for irradiation characteristic clustering | |
| CN110648011B (en) | Feeder line short-term load prediction method considering photovoltaic users | |
| CN110059871B (en) | Photovoltaic power generation power prediction method | |
| CN116307220A (en) | Roof photovoltaic power prediction method and device and electronic equipment | |
| CN116050636A (en) | Output prediction method, device, equipment and medium of photovoltaic power station | |
| Jogunuri et al. | Artificial intelligence methods for solar forecasting for optimum sizing of PV systems: A review | |
| CN115983478A (en) | Distributed photovoltaic power generation power prediction analysis method, system, terminal and medium | |
| CN116484998A (en) | Distributed photovoltaic power station power prediction method and system based on meteorological similar day | |
| CN114925929A (en) | Building load prediction method and device based on degree days | |
| CN115563848A (en) | Distributed photovoltaic total radiation prediction method and system based on deep learning | |
| KR20180023078A (en) | Prediction method of generation quantity in solar energy generation using weather information | |
| CN115510767B (en) | Regional air temperature prediction method based on depth space-time network | |
| CN115587644B (en) | Photovoltaic power station performance parameter prediction method, device, equipment and medium | |
| Karume et al. | Correlation between sunshine hours and climatic parameters at four locations in Uganda |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221221 Address after: Room 214-49, Block B, Phase III (South District), Huguang Road Independent Innovation Industrial Base, Shushan New Industrial Park, Shushan District, Hefei City, Anhui Province, 230088 Applicant after: Hefei Zero Carbon Technology Co.,Ltd. Address before: 230088 No. 1699 Xiyou Road, Hefei High-tech Zone, Anhui Province Applicant before: SUNGROW POWER SUPPLY Co.,Ltd. |