CN116485046A - Photovoltaic output prediction method and device - Google Patents
Photovoltaic output prediction method and device Download PDFInfo
- Publication number
- CN116485046A CN116485046A CN202310738733.4A CN202310738733A CN116485046A CN 116485046 A CN116485046 A CN 116485046A CN 202310738733 A CN202310738733 A CN 202310738733A CN 116485046 A CN116485046 A CN 116485046A
- Authority
- CN
- China
- Prior art keywords
- snow covering
- snow
- photovoltaic
- state
- covering state
- 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 44
- 238000012549 training Methods 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000000556 factor analysis Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 16
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000010248 power generation Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000005855 radiation Effects 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Photovoltaic Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a photovoltaic output prediction method and a device, wherein the method comprises the following steps: acquiring numerical weather forecast data, and acquiring the numerical weather forecast data and snow covering thickness forecast data of a target photovoltaic station in a forecast time period from the numerical weather forecast data; obtaining the snow covering thickness in a predicted time period according to the snow covering thickness prediction data and the snow covering thickness prediction model; obtaining a snow covering state according to the snow covering thickness of the target photovoltaic station in the predicted time period and the snow covering state judging rule; according to the numerical weather forecast data and the snow covering state of the target photovoltaic station in the forecast time period, obtaining forecast input data, and according to the snow covering state of the target photovoltaic station in the forecast time period, obtaining a corresponding photovoltaic output forecast model; and predicting the photovoltaic output value of the target photovoltaic field station according to the predicted input data and the photovoltaic output prediction model. The photovoltaic output prediction method and the device provided by the embodiment of the invention improve the reliability of photovoltaic output value prediction.
Description
Technical Field
The invention relates to the technical field of new energy, in particular to a photovoltaic output prediction method and device.
Background
Along with the proposal of the peak reaching goal of carbon neutralization, the construction of a novel electric power system taking new energy as a dominant source is steadily carried out. And with the continuous promotion of the proportion of new energy power generation, new energy power generation such as wind power and photovoltaic power generation needs to be incorporated into electric power and electric quantity balance when planning a novel electric power system in the future.
In order to incorporate new energy generation into the power balance, it is necessary to predict the output power of the new energy generation. Photovoltaic power generation is a technology for directly converting light energy into electric energy by utilizing the photovoltaic effect of a semiconductor interface, and is affected by a snowfall factor, so that the prediction of the output power of the photovoltaic power generation by the snowfall factor is still under study, and therefore, how to consider the snowfall factor to predict the output power of a photovoltaic power station becomes an important subject to be solved in the field.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a photovoltaic output prediction method and device, which can at least partially solve the problems in the prior art.
In one aspect, the present invention provides a photovoltaic output prediction method, including:
acquiring numerical weather forecast data of a target photovoltaic station, and acquiring the numerical weather forecast data and snow covering thickness forecast data of the target photovoltaic station in a forecast time period from the numerical weather forecast data of the target photovoltaic station;
Obtaining the snow covering thickness of the target photovoltaic field station in a predicted time period according to the snow covering thickness prediction data and a snow covering thickness prediction model; wherein the snow cover thickness prediction model is pre-established;
obtaining the snow covering state of the target photovoltaic station in the predicted time period according to the snow covering thickness of the target photovoltaic station in the predicted time period and the snow covering state judging rule;
according to the numerical weather forecast data of the target photovoltaic field station in the forecast time period and the snow covering state of the target photovoltaic field station in the forecast time period, obtaining forecast input data of the target photovoltaic field station in the snow covering state, and according to the snow covering state of the target photovoltaic field station in the forecast time period, obtaining a photovoltaic output forecast model corresponding to the snow covering state; the photovoltaic output prediction model corresponding to the snow covering state is obtained in advance;
and predicting the photovoltaic output value of the target photovoltaic station according to the predicted input data of the target photovoltaic station in the snow covering state and the photovoltaic output prediction model corresponding to the snow covering state.
In another aspect, the present invention provides a photovoltaic output predicting apparatus, comprising:
The acquisition unit is used for acquiring numerical weather forecast data of a target photovoltaic station and acquiring numerical weather forecast data and snow covering thickness forecast data of the target photovoltaic station in a forecast time period from the numerical weather forecast data of the target photovoltaic station;
the first obtaining unit is used for obtaining the snow covering thickness of the target photovoltaic field station in a predicted time period according to the snow covering thickness prediction data and the snow covering thickness prediction model; wherein the snow cover thickness prediction model is pre-established;
the second obtaining unit is used for obtaining the snow covering state of the target photovoltaic station in the predicted time period according to the snow covering thickness of the target photovoltaic station in the predicted time period and the snow covering state judging rule;
the third obtaining unit is used for obtaining predicted input data of the target photovoltaic field station in a snow covering state according to the numerical weather forecast data of the target photovoltaic field station in a predicted time period and the snow covering state of the target photovoltaic field station in the predicted time period, and obtaining a photovoltaic output prediction model corresponding to the snow covering state according to the snow covering state of the target photovoltaic field station in the predicted time period; the photovoltaic output prediction model corresponding to the snow covering state is obtained in advance;
And the prediction unit is used for predicting the photovoltaic output value of the target photovoltaic station according to the predicted input data of the target photovoltaic station in the snow covering state and the photovoltaic output prediction model corresponding to the snow covering state.
In yet another aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the photovoltaic output predicting method according to any one of the embodiments described above when executing the program.
In yet another aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the photovoltaic output predicting method of any one of the embodiments described above.
According to the photovoltaic output prediction method and device provided by the embodiment of the invention, the numerical weather forecast data of the target photovoltaic station is obtained, and the numerical weather forecast data and the snow covering thickness prediction data of the target photovoltaic station in a prediction time period are obtained from the numerical weather forecast data of the target photovoltaic station; obtaining the snow covering thickness of the target photovoltaic field station in a predicted time period according to the snow covering thickness prediction data and a snow covering thickness prediction model; obtaining the snow covering state of the target photovoltaic station in the predicted time period according to the snow covering thickness of the target photovoltaic station in the predicted time period and the snow covering state judging rule; according to the numerical weather forecast data of the target photovoltaic field station in the forecast time period and the snow covering state of the target photovoltaic field station in the forecast time period, obtaining forecast input data of the target photovoltaic field station in the snow covering state, and according to the snow covering state of the target photovoltaic field station in the forecast time period, obtaining a photovoltaic output forecast model corresponding to the snow covering state; according to the predicted input data of the target photovoltaic station in the snow covered state and the photovoltaic output prediction model corresponding to the snow covered state, the photovoltaic output value of the target photovoltaic station is predicted, the prediction of the photovoltaic output value in the snow covered state is realized, and the reliability of the prediction of the photovoltaic output value is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a photovoltaic output prediction method according to a first embodiment of the present invention.
Fig. 2 is a schematic diagram of estimating snow depth through GPS multipath reflection according to a second embodiment of the present invention.
Fig. 3 is a flowchart of a photovoltaic output prediction method according to a third embodiment of the present invention.
Fig. 4 is a flowchart of a photovoltaic output predicting method according to a fourth embodiment of the present invention.
Fig. 5 is a flowchart of a photovoltaic output predicting method according to a fifth embodiment of the present invention.
Fig. 6 is a schematic structural diagram of a photovoltaic output predicting device according to a sixth embodiment of the present invention.
Fig. 7 is a schematic structural diagram of a photovoltaic output predicting device according to a seventh embodiment of the present invention.
Fig. 8 is a schematic structural diagram of a photovoltaic output predicting device according to an eighth embodiment of the present invention.
Fig. 9 is a schematic structural diagram of a photovoltaic output predicting device according to a ninth embodiment of the present invention.
Fig. 10 is a schematic physical structure of an electronic device according to a tenth embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be arbitrarily combined with each other.
The following describes a specific implementation procedure of the photovoltaic output prediction method provided by the embodiment of the present invention, taking a server as an execution body as an example. The execution subject of the photovoltaic output prediction method provided by the embodiment of the invention is not limited to a server.
Fig. 1 is a flow chart of a photovoltaic output prediction method according to a first embodiment of the present invention, as shown in fig. 1, where the photovoltaic output prediction method according to the embodiment of the present invention includes:
s101, acquiring numerical weather forecast data of a target photovoltaic station, and acquiring numerical weather forecast data and snow covering thickness forecast data of the target photovoltaic station in a forecast time period from the numerical weather forecast data of the target photovoltaic station;
Specifically, the server may obtain numerical weather forecast (Numerical Weather Prediction, abbreviated NWP) data for the target photovoltaic site. NWP data includes meteorological factors such as irradiance, long wave radiation, short wave radiation, temperature, air pressure, humidity, precipitation, etc. From NWP data, numerical weather forecast data for the target photovoltaic field station over a predicted time period can be obtained. The prediction time period may be 1 day, 2 days, 3 days, 1 week, etc., and is set according to actual needs, which is not limited in the embodiment of the present invention. From NWP data, snow thickness prediction data may be obtained, where the snow thickness prediction data is time-series data, and may include meteorological factors such as snowfall, wind speed, humidity, and atmospheric temperature corresponding to a plurality of moments. The target photovoltaic station refers to a photovoltaic station for which photovoltaic output prediction is to be performed.
S102, obtaining the snow covering thickness of the target photovoltaic station in a predicted time period according to the snow covering thickness prediction data and a snow covering thickness prediction model; wherein the snow cover thickness prediction model is pre-established;
specifically, the server inputs the snow cover thickness prediction data into a snow cover thickness prediction model, and may output the snow cover thickness of the target photovoltaic station in a predicted period of time. The snow cover thickness of the target photovoltaic station in the predicted time period may include snow cover thicknesses corresponding to a plurality of moments in the predicted time period. Wherein the snow cover thickness prediction model is pre-established.
For example, the prediction time period is 1 day, and the snowfall amount, the wind speed, the humidity, and the atmospheric temperature corresponding to each whole point of 10 days before the prediction time period can be obtained as the snowfall thickness prediction data, which is input into the snowfall thickness prediction model, and the snowfall thickness corresponding to each whole point in the prediction time period is input.
In order to build the snow cover thickness prediction model, snow cover thickness training sample data can be collected, the snow cover thickness training sample data comprises snow fall amounts, wind speeds, humidity, atmospheric temperature at all time points in a historical time period and snow cover thicknesses corresponding to all time points, an original model is trained according to the snow cover thickness training sample data, and the snow cover thickness prediction model can be obtained through training. The raw model may employ a sequence-to-sequence model (Sequence to Sequence, simply Seq2 Seq) neural network model.
The snow covering thickness corresponding to each time point of the target photovoltaic field station in the historical time period can be acquired. A global positioning system (Global Positioning System, abbreviated as GPS) receiver is disposed at the target photovoltaic station, and each GPS receiver is disposed adjacent to the target photovoltaic station with a radius of five kilometers, covering the entire target photovoltaic station. The antenna heights of the individual GPS receivers can be measured. From the meteorological features of snow cover, GPS multipath reflection (GPS ⁃ multipath reflectometry, GPS ⁃ MR for short) can be used to estimate snow depth.
FIG. 2 is a schematic diagram of estimating the depth of snow by GPS multipath reflection, as shown in FIG. 2, the snow thickness at the collection point，/>The antenna height of the GPS receiver, which represents the distance of the antenna from the snow surface, also called vertical reflection distance, may be represented by the antenna position of each GPS receiver as an acquisition point. The GPS receiver may receive signal-to-noise ratio (signal to noise ratio, abbreviated as SNR) data, which may be used to express the strength of the signal received by the GPS receiver, and is mainly related to factors such as the transmission power of the satellite signal, the distance between the satellite and the receiver, the multipath effect, and the antenna gain. Frequency information of the SNR residual value may be extracted using a Lomb ⁃ Scargle spectral analysis method, and a Lomb-Scargle power spectrum may be expressed as frequencyfFunction of->Thereby obtaining the frequencyf. And then according to the formula->Can be calculated to obtainH，/>Indicating the wavelength of the light. And calculating the average value of the snow covering thickness of each acquisition point as the snow covering thickness of the acquisition time point.
S103, obtaining the snow covering state of the target photovoltaic station in the predicted time period according to the snow covering thickness of the target photovoltaic station in the predicted time period and the snow covering state judging rule;
specifically, the server can determine the snow covering state of the target photovoltaic station in the predicted time period according to the snow covering thickness of the target photovoltaic station in the predicted time period and the snow covering state judging rule. The snow covering state judging rule is preset and set according to actual needs, and the embodiment of the invention is not limited. The snow covering state can comprise before, during and after snow covering, and is set according to actual needs, and the embodiment of the invention is not limited.
It is understood that there may be at least one of the snow cover states of the target photovoltaic field station in the predicted period of time. For example, the predicted period is 24 hours in the future, the snow covered state of the first 12 hours is before the snow is covered, and the snow covered state of the second 12 hours is in the snow.
S104, obtaining predicted input data of the target photovoltaic field station in a snow covering state according to numerical weather forecast data of the target photovoltaic field station in a predicted time period and the snow covering state of the target photovoltaic field station in the predicted time period, and obtaining a photovoltaic output prediction model corresponding to the snow covering state according to the snow covering state of the target photovoltaic field station in the predicted time period; the photovoltaic output prediction model corresponding to the snow covering state is obtained in advance;
specifically, the photovoltaic output prediction model adopted by the target photovoltaic station is different in different snow covering states, and the predicted input data adopted by the target photovoltaic station is also different. And the server selects predicted input data of the target photovoltaic field station in the snow covering state from numerical weather forecast data of the target photovoltaic field station in the predicted time period according to the snow covering state of the target photovoltaic field station in the predicted time period, and obtains a photovoltaic output prediction model corresponding to the snow covering state according to the snow covering state of the target photovoltaic field station. The photovoltaic output prediction model corresponding to the snow covering state is obtained in advance. The correspondence between the snow covered state and the predicted input data is also obtained in advance.
S105, predicting the photovoltaic output value of the target photovoltaic station according to the predicted input data corresponding to the target photovoltaic station and the photovoltaic output prediction model corresponding to the snow covering state.
Specifically, the server inputs the predicted input data of the target photovoltaic field station in the snow covered state into a photovoltaic output prediction model corresponding to the snow covered state, and can output a photovoltaic output value of the target photovoltaic field station in the snow covered state. And summing the photovoltaic output values of the target photovoltaic field station in each snow-covered state in the prediction time period to obtain a summation result, wherein the summation result is used as the photovoltaic output value of the target photovoltaic field station in the prediction time period.
For example, the predicted period is 24 hours in the future, the snow covered state of the first 12 hours is before the snow is covered, and the snow covered state of the second 12 hours is in the snow. Inputting predicted input data of a target photovoltaic station before snow covering into a photovoltaic output prediction model corresponding to the target photovoltaic station before snow covering to obtain a first photovoltaic output value; and inputting predicted input data of the target photovoltaic station under the snow covering into a photovoltaic output prediction model corresponding to the snow covering to obtain a second photovoltaic output value. And calculating the sum of the first photovoltaic output value and the second photovoltaic output value as the photovoltaic output value of the target photovoltaic field station for 24 hours in future.
According to the photovoltaic output prediction method provided by the embodiment of the invention, the numerical weather forecast data of the target photovoltaic field station is obtained, and the numerical weather forecast data and the snow covering thickness prediction data of the target photovoltaic field station in a prediction time period are obtained from the numerical weather forecast data of the target photovoltaic field station; obtaining the snow covering thickness of the target photovoltaic field station in a predicted time period according to the snow covering thickness prediction data and a snow covering thickness prediction model; obtaining the snow covering state of the target photovoltaic station in the predicted time period according to the snow covering thickness of the target photovoltaic station in the predicted time period and the snow covering state judging rule; according to the numerical weather forecast data of the target photovoltaic field station in the forecast time period and the snow covering state of the target photovoltaic field station in the forecast time period, obtaining forecast input data of the target photovoltaic field station in the snow covering state, and according to the snow covering state of the target photovoltaic field station in the forecast time period, obtaining a photovoltaic output forecast model corresponding to the snow covering state; according to the predicted input data of the target photovoltaic station in the snow covered state and the photovoltaic output prediction model corresponding to the snow covered state, the photovoltaic output value of the target photovoltaic station is predicted, the prediction of the photovoltaic output value in different snow covered states can be realized, and the reliability of the prediction of the photovoltaic output value is improved.
On the basis of the above embodiments, further, the snow cover state judgment rule includes:
if the continuously preset number of collected snow covering thicknesses indicate that the snow covering thickness is zero, the snow covering state is before snow covering;
if the continuously preset number of collected snow covering thicknesses indicate that the snow covering thickness is increased or kept unchanged, the snow covering state is in the snow covering state;
and if the snow covering thickness acquired by the continuous preset number shows that the snow covering thickness is reduced, the snow covering state is after the snow covering.
Specifically, the server acquires the snow covering thickness of the target photovoltaic field stations with the continuous preset number, and if the snow covering thickness of the continuous preset number is 0 or approximately 0, the snow covering thickness is zero, and the snow covering state of the target photovoltaic field stations is before snow covering. The snow covering thickness of approximately 0 means that the snow covering thickness is within a preset range, the preset range is set according to actual needs, and the embodiment of the invention is not limited. Such as setting the preset range to-0.01 mm to 0.01mm.
The server acquires the continuous preset number of snow covering thicknesses of the target photovoltaic field stations, and if the continuous preset number of snow covering thicknesses indicate that the snow covering thicknesses are increased or kept unchanged, the snow covering state of the target photovoltaic field stations is in the snow covering state. For example, the snow covering thickness of the target photovoltaic field station of 3 continuous whole points is d, and d is greater than zero, and then the snow covering state of the target photovoltaic field station is in snow. For example, the snow covering thicknesses of the target photovoltaic field stations of 3 continuous integral points are a, b and c respectively, c is greater than b, b is greater than a, and a is greater than 0, so that the snow covering state of the target photovoltaic field stations is in snow covering.
And the server acquires the continuous preset number of snow covering thicknesses of the target photovoltaic field stations, and if the continuous preset number of snow covering thicknesses indicate that the snow covering thicknesses are reduced, the snow covering state of the target photovoltaic field stations is after the snow covering. For example, the snow covering thickness of the target photovoltaic field station with 3 continuous whole points is a, b and c respectively, and c is smaller than b, and b is smaller than a, so that the snow covering state of the target photovoltaic field station is after the snow covering.
The preset number is set according to actual needs, and the embodiment of the invention is not limited. Such as setting the preset number to 3.
Fig. 3 is a schematic flow chart of a photovoltaic output prediction method according to a third embodiment of the present invention, as shown in fig. 3, further, based on the above embodiments, obtaining a photovoltaic output prediction model corresponding to the snow covered state includes:
s301, training sample data corresponding to the snow covering state is obtained;
specifically, the server acquires training sample data corresponding to the snow covering state. Training sample data corresponding to different snow covering states are different.
S302, training to obtain a photovoltaic output prediction model corresponding to the snow covering state according to training sample data corresponding to the snow covering state and an original model corresponding to the snow covering state.
Specifically, the server trains the original model corresponding to the snow covering state according to the training sample data corresponding to the snow covering state, and can train to obtain the photovoltaic output prediction model corresponding to the snow covering state. The original models corresponding to different snow covering states are different, and correspondingly, the photovoltaic output prediction models corresponding to different snow covering states are also different. For different snow covering states, different original models are adopted to establish a photovoltaic output prediction model, so that the accidental is avoided, and the prediction accuracy is improved.
For example, the original model may employ a polynomial model before the snow-covered state is snow-covered. In the snow covering state, the original model can adopt a neural network model. After the snow covering state is snow covering, the original model can adopt a time sequence prediction model.
Fig. 4 is a flow chart of a photovoltaic output prediction method according to a fourth embodiment of the present invention, as shown in fig. 4, further, based on the above embodiments, the obtaining training sample data corresponding to the snow covered state includes:
s401, acquiring historical photovoltaic output data, historical numerical weather forecast data and snow covering state data of the target photovoltaic station;
Specifically, historical photovoltaic output data and historical numerical weather forecast data of the target photovoltaic station can be collected, and historical snow covering states of the target photovoltaic station can be collected. The server can acquire historical photovoltaic output data, historical numerical weather forecast data and snow covering states of the target photovoltaic station. Wherein the historical photovoltaic output data includes an output power of the target photovoltaic field station. The snow cover state data is past snow cover state of the target photovoltaic field station, and can comprise three states before snow cover, during snow cover and after snow cover, and corresponding starting time and ending time respectively.
S402, splitting photovoltaic output data and historical numerical weather forecast data of the target photovoltaic station according to the snow covering state data to obtain photovoltaic output data, historical numerical weather forecast data and time periods corresponding to different snow covering states;
specifically, the server splits the photovoltaic output data and the historical numerical weather forecast data of the target photovoltaic station according to the snow covering state data, so that the photovoltaic output data and the historical numerical weather forecast data corresponding to different snow covering states can be obtained, and the duration time of the different snow covering states is counted to serve as the corresponding time period of the different snow covering states.
S403, analyzing key meteorological factors for historical photovoltaic output data and historical numerical weather forecast data corresponding to each snow covering state to obtain the key meteorological factors corresponding to each snow covering state;
specifically, for each snow covering state, the server analyzes the historical numerical weather forecast data for key weather factors, and finds out weather factors which play a leading role in the historical photovoltaic output data as the key weather factors corresponding to each snow covering state. The key meteorological factors corresponding to different snow covering states can be different. Wherein, the critical meteorological factor analysis can adopt an drift diameter coefficient analysis method.
The drift diameter coefficient analysis method is used for analyzing the linear relation between the dependent variable and the independent variables on the basis of a multivariable linear regression equation, and the relation between the historical photovoltaic output data and the historical numerical weather forecast data is expressed as follows:
wherein y represents the historical photovoltaic output,representing regression coefficients->Represents the ith weather factor in the historical numerical weather forecast data, and n represents the total number of weather factors in the historical numerical weather forecast data.
The larger indicates the corresponding +.>The greater the degree of influence on y.
S404, if the snow covering state is before snow covering, acquiring key meteorological factors and photovoltaic output data corresponding to the snow covering state as training sample data corresponding to the snow covering state; and if the snow covering state is not before the snow covering, acquiring key meteorological factors, photovoltaic output data, time period and snow covering thickness corresponding to the snow covering state as training sample data corresponding to the snow covering state.
Specifically, if the snow covering state is before snow covering, the server acquires key meteorological factors corresponding to the before snow covering as training sample data corresponding to the before snow covering. If the snow covering state is not before the snow covering, for example, before the snow covering is neutral and after the snow covering is finished, the server acquires key meteorological factors, photovoltaic output data, time periods and snow covering thickness corresponding to the snow covering state as training sample data corresponding to each snow covering state. The photovoltaic output data corresponding to the snow covered state can be used as a training label.
Fig. 5 is a flowchart of a photovoltaic output prediction method according to a fifth embodiment of the present invention, as shown in fig. 5, further, based on the foregoing embodiments, the obtaining, according to the numerical weather forecast data of the target photovoltaic station and the snow covering state of the target photovoltaic station, prediction input data corresponding to the target photovoltaic station includes:
s501, acquiring weather input data corresponding to the snow covering state of the target photovoltaic station in a predicted time period from numerical weather forecast data of the target photovoltaic station in the predicted time period according to key weather factors corresponding to the snow covering state of the target photovoltaic station;
Specifically, the server may query and obtain weather input data corresponding to the snow covering state of the target photovoltaic station in the predicted time period from the numerical weather forecast data of the target photovoltaic station in the predicted time period according to the key weather factors corresponding to the snow covering state of the target photovoltaic station. The key meteorological factors corresponding to the snow covering state of the target photovoltaic station are obtained in advance.
S502, if the snow covering state is before snow covering, weather input data corresponding to the snow covering state is used as the prediction input data; and if the snow covering state is not before the snow covering, taking weather input data corresponding to the snow covering state, a time period corresponding to the snow covering state and the snow covering thickness in the time period corresponding to the snow covering state as the prediction input data.
Specifically, if the snow-covered state is before snow is covered, the server uses weather input data corresponding to the snow-covered state as the predicted input data. If the snow cover state is not before the snow cover, such as during the snow cover or after the snow cover, the server takes the meteorological input data corresponding to the snow cover state, the time period corresponding to the snow cover state and the snow cover thickness in the time period corresponding to the snow cover state as the prediction input data. The snow cover thickness within the snow cover state correspondence period may include a snow cover thickness corresponding to each time within the snow cover state correspondence period.
For example, the snow-covered state is before snow covering, the weather input data corresponding to the snow-covered state is irradiance, and the photovoltaic output prediction model corresponding to the snow-covered state is:
wherein, the liquid crystal display device comprises a liquid crystal display device,the value of the photovoltaic output is indicated,xindicating irradiance, ++>， />Is a constant value, and is used for the treatment of the skin,jis an integer of the number of the times,Mis a positive integer.
And inputting irradiance into the photovoltaic output prediction model corresponding to the snow covered state, and outputting the photovoltaic output value of the target photovoltaic station.
On the basis of the above embodiments, further, the snow covering states are multiple, and the photovoltaic output prediction models corresponding to different snow covering states are different.
For example, the snow-covered state includes three kinds of before snow covering, during snow covering, and after snow covering. The photovoltaic output prediction model corresponding to the snow covering can be obtained through training of a polynomial model. The corresponding photovoltaic output prediction model in the snow covering can be obtained by training a neural network model. The corresponding photovoltaic output prediction model after snow covering can be obtained by training a time sequence prediction model.
Fig. 6 is a schematic structural diagram of a photovoltaic output predicting device according to a sixth embodiment of the present invention, as shown in fig. 6, the photovoltaic output predicting device according to the embodiment of the present invention includes an obtaining unit 601, a first obtaining unit 602, a second obtaining unit 603, a third obtaining unit 604, and a predicting unit 605, where:
The acquiring unit 601 is configured to acquire numerical weather forecast data of a target photovoltaic station, and acquire numerical weather forecast data and snow covering thickness prediction data of the target photovoltaic station in a prediction time period from the numerical weather forecast data of the target photovoltaic station; the first obtaining unit 602 is configured to obtain a snow coverage thickness of the target photovoltaic station in a predicted period of time according to the snow coverage thickness prediction data and a snow coverage thickness prediction model; wherein the snow cover thickness prediction model is pre-established; the second obtaining unit 603 is configured to obtain a snow coverage state of the target photovoltaic station in the predicted time period according to the snow coverage thickness and the snow coverage state judging rule of the target photovoltaic station in the predicted time period; the third obtaining unit 604 is configured to obtain predicted input data of the target photovoltaic field station in a snow covered state according to the numerical weather forecast data of the target photovoltaic field station in a predicted time period and the snow covered state of the target photovoltaic field station in the predicted time period, and obtain a photovoltaic output prediction model corresponding to the snow covered state according to the snow covered state of the target photovoltaic field station in the predicted time period; the photovoltaic output prediction model corresponding to the snow covering state is obtained in advance; the prediction unit 605 is configured to predict a photovoltaic output value of the target photovoltaic station according to predicted input data of the target photovoltaic station in a snow covered state and a photovoltaic output prediction model corresponding to the snow covered state.
The acquisition unit 601 may acquire numerical weather forecast (Numerical Weather Prediction, abbreviated NWP) data of the target photovoltaic station. NWP data includes meteorological factors such as irradiance, long wave radiation, short wave radiation, temperature, air pressure, humidity, precipitation, etc. From NWP data, numerical weather forecast data for the target photovoltaic field station over a predicted time period can be obtained. The prediction time period may be 1 day, 2 days, 3 days, 1 week, etc., and is set according to actual needs, which is not limited in the embodiment of the present invention. From NWP data, snow thickness prediction data may be obtained, which is time-series data and may include meteorological factors such as snowfall, wind speed, humidity, and atmospheric temperature corresponding to a plurality of times. The target photovoltaic station refers to a photovoltaic station for which photovoltaic output prediction is to be performed.
The first obtaining unit 602 inputs the snow cover thickness prediction data into a snow cover thickness prediction model, and may output the snow cover thickness of the target photovoltaic station in a predicted period of time. The snow cover thickness of the target photovoltaic station in the predicted time period may include snow cover thicknesses corresponding to a plurality of moments in the predicted time period. Wherein the snow cover thickness prediction model is pre-established.
The second obtaining unit 603 can determine the snow covering state of the target photovoltaic station in the predicted period according to the snow covering thickness of the target photovoltaic station in the predicted period and the snow covering state determination rule. The snow covering state judging rule is preset and set according to actual needs, and the embodiment of the invention is not limited. The snow covering state can comprise before, during and after snow covering, and is set according to actual needs, and the embodiment of the invention is not limited.
The photovoltaic output prediction model adopted by the target photovoltaic station is different in different snow covering states, and the predicted input data adopted by the target photovoltaic station is also different. The third obtaining unit 604 selects, according to the snow covering state of the target photovoltaic field station in the predicted time period, predicted input data of the target photovoltaic field station in the snow covering state from numerical weather forecast data of the target photovoltaic field station in the predicted time period, and obtains a photovoltaic output prediction model corresponding to the snow covering state according to the snow covering state of the target photovoltaic field station. The photovoltaic output prediction model corresponding to the snow covering state is obtained in advance. The correspondence between the snow covered state and the predicted input data is also obtained in advance.
The prediction unit 605 inputs the predicted input data of the target photovoltaic station in the snow covered state into the photovoltaic output prediction model corresponding to the snow covered state, and can output the photovoltaic output value of the target photovoltaic station in the snow covered state. And summing the photovoltaic output values of the target photovoltaic field station in each snow-covered state in the prediction time period to obtain a summation result, wherein the summation result is used as the photovoltaic output value of the target photovoltaic field station in the prediction time period.
According to the photovoltaic output prediction device provided by the embodiment of the invention, the numerical weather forecast data of the target photovoltaic field station is obtained, and the numerical weather forecast data and the snow covering thickness prediction data of the target photovoltaic field station in a prediction time period are obtained from the numerical weather forecast data of the target photovoltaic field station; obtaining the snow covering thickness of the target photovoltaic field station in a predicted time period according to the snow covering thickness prediction data and a snow covering thickness prediction model; obtaining the snow covering state of the target photovoltaic station in the predicted time period according to the snow covering thickness of the target photovoltaic station in the predicted time period and the snow covering state judging rule; according to the numerical weather forecast data of the target photovoltaic field station in the forecast time period and the snow covering state of the target photovoltaic field station in the forecast time period, obtaining forecast input data of the target photovoltaic field station in the snow covering state, and according to the snow covering state of the target photovoltaic field station in the forecast time period, obtaining a photovoltaic output forecast model corresponding to the snow covering state; according to the predicted input data of the target photovoltaic station in the snow covered state and the photovoltaic output prediction model corresponding to the snow covered state, the photovoltaic output value of the target photovoltaic station is predicted, the prediction of the photovoltaic output value in different snow covered states can be realized, and the reliability of the prediction of the photovoltaic output value is improved.
On the basis of the above embodiments, further, the snow cover state judgment rule includes:
if the continuous preset number of snow covering thicknesses indicate that the snow covering thickness is zero, the snow covering state is before snow covering;
if the continuous preset number of snow covering thicknesses indicate that the snow covering thickness is increased or kept unchanged, the snow covering state is in the snow covering state;
if the continuous preset number of snow covering thicknesses indicate that the snow covering thickness is reduced, the snow covering state is after the snow covering.
Fig. 7 is a schematic structural diagram of a photovoltaic output predicting device according to a seventh embodiment of the present invention, as shown in fig. 7, further, based on the foregoing embodiments, the photovoltaic output predicting device according to the embodiment of the present invention further includes a sample acquiring unit 606 and a training unit 607, where:
the sample acquiring unit 606 is configured to acquire training sample data corresponding to the snow covered state; the training unit 607 is configured to train and obtain the photovoltaic output prediction model corresponding to the snow covered state according to the training sample data corresponding to the snow covered state and the original model corresponding to the snow covered state.
Fig. 8 is a schematic structural diagram of a photovoltaic output predicting device according to an eighth embodiment of the present invention, as shown in fig. 8, further, based on the above embodiments, the sample obtaining unit 606 includes a first obtaining subunit 6061, a splitting subunit 6062, an analyzing subunit 6063, and a second obtaining subunit 6064, wherein:
The first obtaining subunit 6061 is configured to obtain historical photovoltaic output data, historical numerical weather forecast data, and snow coverage status data of the target photovoltaic station; the splitting sub-unit 6062 is used for splitting the photovoltaic output data and the historical value weather forecast data of the target photovoltaic station according to the snow covering state data to obtain the photovoltaic output data, the historical value weather forecast data and the time period corresponding to different snow covering states; the analysis subunit 6063 is configured to perform key weather factor analysis on the historical photovoltaic output data and the historical numerical weather forecast data corresponding to each snow-covered state, so as to obtain key weather factors corresponding to each snow-covered state; the second obtaining subunit 6064 is configured to use, if the snow covered state is before snow covering, weather input data corresponding to the snow covered state as the predicted input data; and if the snow covering state is not before the snow covering, taking meteorological input data corresponding to the snow covering state, the prediction time period and the snow covering thickness of the target photovoltaic station in the prediction time period as the prediction input data.
Fig. 9 is a schematic structural diagram of a photovoltaic output predicting device according to a ninth embodiment of the present invention, as shown in fig. 9, further, based on the above embodiments, the third obtaining unit 604 includes an obtaining subunit 6041 and a third obtaining subunit 6042, wherein:
The obtaining subunit 6041 is configured to obtain weather input data corresponding to the snow covering state of the target photovoltaic station in the predicted time period from the numerical weather forecast data of the target photovoltaic station in the predicted time period according to the key weather factors corresponding to the snow covering state of the target photovoltaic station; the third obtaining subunit 6042 is configured to use, if the snow covered state is before snow covering, weather input data corresponding to the snow covered state as the predicted input data; and if the snow covering state is not before the snow covering, taking weather input data corresponding to the snow covering state, a time period corresponding to the snow covering state and the snow covering thickness in the time period corresponding to the snow covering state as the prediction input data.
On the basis of the above embodiments, further, the snow covering states are multiple, and the photovoltaic output prediction models corresponding to different snow covering states are different.
The embodiment of the apparatus provided in the embodiment of the present invention may be specifically used to execute the processing flow of each method embodiment, and the functions thereof are not described herein again, and may refer to the detailed description of the method embodiments.
Fig. 10 is a schematic physical structure of an electronic device according to a tenth embodiment of the present invention, as shown in fig. 10, the electronic device may include: a processor 1001, a communication interface (Communications Interface) 1002, a memory 1003, and a communication bus 1004, wherein the processor 1001, the communication interface 1002, and the memory 1003 perform communication with each other through the communication bus 1004. The processor 1001 may call logic instructions in the memory 1003 to perform the following method: acquiring numerical weather forecast data of a target photovoltaic station, and acquiring the numerical weather forecast data and snow covering thickness forecast data of the target photovoltaic station in a forecast time period from the numerical weather forecast data of the target photovoltaic station; obtaining the snow covering thickness of the target photovoltaic field station in a predicted time period according to the snow covering thickness prediction data and a snow covering thickness prediction model; wherein the snow cover thickness prediction model is pre-established; obtaining the snow covering state of the target photovoltaic station in the predicted time period according to the snow covering thickness of the target photovoltaic station in the predicted time period and the snow covering state judging rule; according to the numerical weather forecast data of the target photovoltaic field station in the forecast time period and the snow covering state of the target photovoltaic field station in the forecast time period, obtaining forecast input data of the target photovoltaic field station in the snow covering state, and according to the snow covering state of the target photovoltaic field station in the forecast time period, obtaining a photovoltaic output forecast model corresponding to the snow covering state; the photovoltaic output prediction model corresponding to the snow covering state is obtained in advance; and predicting the photovoltaic output value of the target photovoltaic station according to the predicted input data of the target photovoltaic station in the snow covering state and the photovoltaic output prediction model corresponding to the snow covering state.
Further, the logic instructions in the memory 1003 described above may be implemented in the form of software functional units and sold or used as a separate product, and may be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The present embodiment discloses a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, are capable of performing the methods provided by the above-described method embodiments, for example comprising: acquiring numerical weather forecast data of a target photovoltaic station, and acquiring the numerical weather forecast data and snow covering thickness forecast data of the target photovoltaic station in a forecast time period from the numerical weather forecast data of the target photovoltaic station; obtaining the snow covering thickness of the target photovoltaic field station in a predicted time period according to the snow covering thickness prediction data and a snow covering thickness prediction model; wherein the snow cover thickness prediction model is pre-established; obtaining the snow covering state of the target photovoltaic station in the predicted time period according to the snow covering thickness of the target photovoltaic station in the predicted time period and the snow covering state judging rule; according to the numerical weather forecast data of the target photovoltaic field station in the forecast time period and the snow covering state of the target photovoltaic field station in the forecast time period, obtaining forecast input data of the target photovoltaic field station in the snow covering state, and according to the snow covering state of the target photovoltaic field station in the forecast time period, obtaining a photovoltaic output forecast model corresponding to the snow covering state; the photovoltaic output prediction model corresponding to the snow covering state is obtained in advance; and predicting the photovoltaic output value of the target photovoltaic station according to the predicted input data of the target photovoltaic station in the snow covering state and the photovoltaic output prediction model corresponding to the snow covering state.
The present embodiment provides a computer-readable storage medium storing a computer program that causes the computer to execute the methods provided by the above-described method embodiments, for example, including: acquiring numerical weather forecast data of a target photovoltaic station, and acquiring the numerical weather forecast data and snow covering thickness forecast data of the target photovoltaic station in a forecast time period from the numerical weather forecast data of the target photovoltaic station; obtaining the snow covering thickness of the target photovoltaic field station in a predicted time period according to the snow covering thickness prediction data and a snow covering thickness prediction model; wherein the snow cover thickness prediction model is pre-established; obtaining the snow covering state of the target photovoltaic station in the predicted time period according to the snow covering thickness of the target photovoltaic station in the predicted time period and the snow covering state judging rule; according to the numerical weather forecast data of the target photovoltaic field station in the forecast time period and the snow covering state of the target photovoltaic field station in the forecast time period, obtaining forecast input data of the target photovoltaic field station in the snow covering state, and according to the snow covering state of the target photovoltaic field station in the forecast time period, obtaining a photovoltaic output forecast model corresponding to the snow covering state; the photovoltaic output prediction model corresponding to the snow covering state is obtained in advance; and predicting the photovoltaic output value of the target photovoltaic station according to the predicted input data of the target photovoltaic station in the snow covering state and the photovoltaic output prediction model corresponding to the snow covering state.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In the description of the present specification, reference to the terms "one embodiment," "one particular embodiment," "some embodiments," "for example," "an example," "a particular example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (14)
1. A method of photovoltaic output prediction, comprising:
acquiring numerical weather forecast data of a target photovoltaic station, and acquiring the numerical weather forecast data and snow covering thickness forecast data of the target photovoltaic station in a forecast time period from the numerical weather forecast data of the target photovoltaic station;
obtaining the snow covering thickness of the target photovoltaic field station in a predicted time period according to the snow covering thickness prediction data and a snow covering thickness prediction model; wherein the snow cover thickness prediction model is pre-established;
obtaining the snow covering state of the target photovoltaic station in the predicted time period according to the snow covering thickness of the target photovoltaic station in the predicted time period and the snow covering state judging rule;
according to the numerical weather forecast data of the target photovoltaic field station in the forecast time period and the snow covering state of the target photovoltaic field station in the forecast time period, obtaining forecast input data of the target photovoltaic field station in the snow covering state, and according to the snow covering state of the target photovoltaic field station in the forecast time period, obtaining a photovoltaic output forecast model corresponding to the snow covering state; the photovoltaic output prediction model corresponding to the snow covering state is obtained in advance;
And predicting the photovoltaic output value of the target photovoltaic station according to the predicted input data of the target photovoltaic station in the snow covering state and the photovoltaic output prediction model corresponding to the snow covering state.
2. The method according to claim 1, wherein the snow cover state judgment rule includes:
if the continuous preset number of snow covering thicknesses indicate that the snow covering thickness is zero, the snow covering state is before snow covering;
if the continuous preset number of snow covering thicknesses indicate that the snow covering thickness is increased or kept unchanged, the snow covering state is in the snow covering state;
if the continuous preset number of snow covering thicknesses indicate that the snow covering thickness is reduced, the snow covering state is after the snow covering.
3. The method of claim 1, wherein obtaining a photovoltaic output prediction model corresponding to the snow covered state comprises:
acquiring training sample data corresponding to the snow covering state;
and training to obtain a photovoltaic output prediction model corresponding to the snow covering state according to the training sample data corresponding to the snow covering state and the original model corresponding to the snow covering state.
4. A method according to claim 3, wherein said obtaining training sample data corresponding to said snow covered status comprises:
Acquiring historical photovoltaic output data, historical numerical weather forecast data and snow covering state data of the target photovoltaic station;
splitting the photovoltaic output data and the historical numerical weather forecast data of the target photovoltaic station according to the snow covering state data to obtain photovoltaic output data, historical numerical weather forecast data and time periods corresponding to different snow covering states;
carrying out key meteorological factor analysis on historical photovoltaic output data and historical numerical weather forecast data corresponding to each snow covering state to obtain key meteorological factors corresponding to each snow covering state;
if the snow covering state is before the snow covering, acquiring key meteorological factors and photovoltaic output data corresponding to the snow covering state as training sample data corresponding to the snow covering state; and if the snow covering state is not before the snow covering, acquiring key meteorological factors, photovoltaic output data, time period and snow covering thickness corresponding to the snow covering state as training sample data corresponding to the snow covering state.
5. The method of claim 1, wherein the obtaining predicted input data for the target photovoltaic field station in the snow covered state based on the numerical weather forecast data for the target photovoltaic field station in the predicted time period and the snow covered state of the target photovoltaic field station in the predicted time period comprises:
According to key meteorological factors corresponding to the snow covering state of the target photovoltaic station, meteorological input data corresponding to the snow covering state of the target photovoltaic station in a predicted time period are obtained from numerical weather forecast data of the target photovoltaic station in the predicted time period;
if the snow covering state is before snow covering, weather input data corresponding to the snow covering state is used as the prediction input data; and if the snow covering state is not before the snow covering, taking weather input data corresponding to the snow covering state, a time period corresponding to the snow covering state and the snow covering thickness in the time period corresponding to the snow covering state as the prediction input data.
6. The method according to any one of claims 1 to 5, wherein the plurality of snow cover states are different, and the photovoltaic output prediction models corresponding to the different snow cover states are different.
7. A photovoltaic output predicting device, comprising:
the acquisition unit is used for acquiring numerical weather forecast data of a target photovoltaic station and acquiring numerical weather forecast data and snow covering thickness forecast data of the target photovoltaic station in a forecast time period from the numerical weather forecast data of the target photovoltaic station;
The first obtaining unit is used for obtaining the snow covering thickness of the target photovoltaic field station in a predicted time period according to the snow covering thickness prediction data and the snow covering thickness prediction model; wherein the snow cover thickness prediction model is pre-established;
the second obtaining unit is used for obtaining the snow covering state of the target photovoltaic station in the predicted time period according to the snow covering thickness of the target photovoltaic station in the predicted time period and the snow covering state judging rule;
the third obtaining unit is used for obtaining predicted input data of the target photovoltaic field station in a snow covering state according to the numerical weather forecast data of the target photovoltaic field station in a predicted time period and the snow covering state of the target photovoltaic field station in the predicted time period, and obtaining a photovoltaic output prediction model corresponding to the snow covering state according to the snow covering state of the target photovoltaic field station in the predicted time period; the photovoltaic output prediction model corresponding to the snow covering state is obtained in advance;
and the prediction unit is used for predicting the photovoltaic output value of the target photovoltaic station according to the predicted input data of the target photovoltaic station in the snow covering state and the photovoltaic output prediction model corresponding to the snow covering state.
8. The apparatus according to claim 7, wherein the snow cover state judgment rule includes:
if the continuous preset number of snow covering thicknesses indicate that the snow covering thickness is zero, the snow covering state is before snow covering;
if the continuous preset number of snow covering thicknesses indicate that the snow covering thickness is increased or kept unchanged, the snow covering state is in the snow covering state;
if the continuous preset number of snow covering thicknesses indicate that the snow covering thickness is reduced, the snow covering state is after the snow covering.
9. The apparatus as recited in claim 7, further comprising:
the sample acquisition unit is used for acquiring training sample data corresponding to the snow covering state;
and the training unit is used for training and obtaining the photovoltaic output prediction model corresponding to the snow covering state according to the training sample data corresponding to the snow covering state and the original model corresponding to the snow covering state.
10. The apparatus of claim 9, wherein the sample acquisition unit comprises:
the first acquisition subunit is used for acquiring historical photovoltaic output data, historical numerical weather forecast data and snow covering state data of the target photovoltaic station;
the splitting subunit is used for splitting the photovoltaic output data and the historical numerical weather forecast data of the target photovoltaic station according to the snow covering state data to obtain the photovoltaic output data, the historical numerical weather forecast data and the time period corresponding to different snow covering states;
The analysis subunit is used for carrying out key meteorological factor analysis on the historical photovoltaic output data and the historical numerical weather forecast data corresponding to each snow covering state to obtain key meteorological factors corresponding to each snow covering state;
the second acquisition subunit is used for acquiring key meteorological factors and photovoltaic output data corresponding to the snow covering state as training sample data corresponding to the snow covering state if the snow covering state is before the snow covering; and if the snow covering state is not before the snow covering, acquiring key meteorological factors, photovoltaic output data, time period and snow covering thickness corresponding to the snow covering state as training sample data corresponding to the snow covering state.
11. The apparatus of claim 7, wherein the third obtaining unit comprises:
the obtaining subunit is used for obtaining weather input data corresponding to the snow covering state of the target photovoltaic station in the predicted time period from the numerical weather forecast data of the target photovoltaic station in the predicted time period according to the key weather factors corresponding to the snow covering state of the target photovoltaic station;
the third acquisition subunit is used for taking the meteorological input data corresponding to the snow covering state as the prediction input data if the snow covering state is before the snow covering; and if the snow covering state is not before the snow covering, taking weather input data corresponding to the snow covering state, a time period corresponding to the snow covering state and the snow covering thickness in the time period corresponding to the snow covering state as the prediction input data.
12. The apparatus according to any one of claims 7 to 11, wherein the snow cover state is plural, and the photovoltaic output prediction model corresponding to different snow cover states is different.
13. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any one of claims 1 to 6 when the computer program is executed by the processor.
14. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310738733.4A CN116485046A (en) | 2023-06-21 | 2023-06-21 | Photovoltaic output prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310738733.4A CN116485046A (en) | 2023-06-21 | 2023-06-21 | Photovoltaic output prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116485046A true CN116485046A (en) | 2023-07-25 |
Family
ID=87212272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310738733.4A Pending CN116485046A (en) | 2023-06-21 | 2023-06-21 | Photovoltaic output prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116485046A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220723A (en) * | 2017-04-20 | 2017-09-29 | 华北电力大学 | A kind of predicting power of photovoltaic plant method |
| CN112688306A (en) * | 2020-12-01 | 2021-04-20 | 重庆大学 | Photovoltaic cycle output scene prediction method based on weather forecast and historical power data combined drive |
| CN114021420A (en) * | 2021-12-17 | 2022-02-08 | 国网河南省电力公司南阳供电公司 | Distributed photovoltaic ultra-short-term power generation prediction method and system |
| CN114999117A (en) * | 2022-06-29 | 2022-09-02 | 洛阳腾飞市政工程有限公司 | Monitoring and early warning method, system, terminal and medium for ice and snow conditions on airport pavement |
| CN115935215A (en) * | 2023-01-06 | 2023-04-07 | 国网山东省电力公司威海供电公司 | Power transmission line icing early warning method and system based on deep learning in extreme weather |
-
2023
- 2023-06-21 CN CN202310738733.4A patent/CN116485046A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220723A (en) * | 2017-04-20 | 2017-09-29 | 华北电力大学 | A kind of predicting power of photovoltaic plant method |
| CN112688306A (en) * | 2020-12-01 | 2021-04-20 | 重庆大学 | Photovoltaic cycle output scene prediction method based on weather forecast and historical power data combined drive |
| CN114021420A (en) * | 2021-12-17 | 2022-02-08 | 国网河南省电力公司南阳供电公司 | Distributed photovoltaic ultra-short-term power generation prediction method and system |
| CN114999117A (en) * | 2022-06-29 | 2022-09-02 | 洛阳腾飞市政工程有限公司 | Monitoring and early warning method, system, terminal and medium for ice and snow conditions on airport pavement |
| CN115935215A (en) * | 2023-01-06 | 2023-04-07 | 国网山东省电力公司威海供电公司 | Power transmission line icing early warning method and system based on deep learning in extreme weather |
Non-Patent Citations (1)
| Title |
|---|
| 牛海霞 等: "光伏组件表面积雪及阴天对其发电量预测实验研究", 包头职业技术学院学报, vol. 18, no. 2, pages 8 - 10 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109580003B (en) | Method for estimating near-ground atmospheric temperature by thermal infrared data of stationary meteorological satellite | |
| CN106526708B (en) | A kind of intelligent early-warning analysis method of the meteorological strong convective weather based on machine learning | |
| CN110705772B (en) | Regional power grid wind power generation power prediction optimization method and device | |
| CN109636032B (en) | Precipitation forecast method, system, terminal and storage medium based on multi-mode integration | |
| CN110555561A (en) | Medium-and-long-term runoff ensemble forecasting method | |
| CN102682207A (en) | Ultrashort combined predicting method for wind speed of wind power plant | |
| CN111428942B (en) | Line icing thickness prediction method for extracting micro-terrain factors based on variable grid technology | |
| CN111047109A (en) | Quantitative prediction method for regional air temperature change | |
| CN110737876B (en) | Regional power grid photovoltaic power prediction optimization method and device | |
| CN111551964A (en) | Water vapor observation method based on navigation satellite system | |
| CN116595394A (en) | Training method of wind speed correction model, wind speed prediction method, wind speed prediction equipment and medium | |
| CN113435630A (en) | Basin hydrological forecasting method and system with self-adaptive runoff yield mode | |
| CN104200082A (en) | Typhoon landing prediction method | |
| CN113298311A (en) | Forest fire danger level prediction method, device, equipment and readable storage medium | |
| KR101556463B1 (en) | Methods, system, and program of estimating human and property losses by using gust and downpour indices of typhoons | |
| CN114564487A (en) | Meteorological raster data updating method combining forecast prediction | |
| CN116485046A (en) | Photovoltaic output prediction method and device | |
| CN116931129A (en) | Short-term precipitation prediction method, device, equipment and medium based on multi-mode set | |
| CN116167211A (en) | Wind field prediction system and method for complex terrain area of power grid power transmission channel | |
| KR101870743B1 (en) | Tidal flat experience index forecasting apparatus and the method thereof | |
| CN114821361A (en) | Method and device for calculating snow depth, computer equipment and readable storage medium | |
| CN109146175B (en) | Power transmission line icing real-time estimation and prediction method using Kalman filtering | |
| KR20180102842A (en) | Sea fishing index forecasting apparatus and the method thereof | |
| CN108876041B (en) | Polar sea ice area prediction method and device based on causal influence network algorithm | |
| JP2004198188A (en) | Device and method for discriminating and predicting road surface condition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230725 |