CN110555220B - Calibration method and system of photoelectric conversion model - Google Patents
Calibration method and system of photoelectric conversion model Download PDFInfo
- Publication number
- CN110555220B CN110555220B CN201810554671.0A CN201810554671A CN110555220B CN 110555220 B CN110555220 B CN 110555220B CN 201810554671 A CN201810554671 A CN 201810554671A CN 110555220 B CN110555220 B CN 110555220B
- Authority
- CN
- China
- Prior art keywords
- radiation
- power
- data
- goodness
- value
- 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.)
- Active
Links
Images
Landscapes
- Photovoltaic Devices (AREA)
Abstract
A calibration method and system of a photoelectric conversion model comprise: obtaining a modeling data set based on the obtained total radiation data and power data; calculating a goodness-of-fit value based on the modeling data and a preset reference value; and determining a photoelectric conversion relation curve based on the goodness-of-fit value. According to the method, data optimization is carried out through correlation analysis, and abnormal point filtering is carried out through inspection of goodness of fit, so that a good model calibration effect is achieved.
Description
Technical Field
The invention relates to the field of solar energy utilization, in particular to a method and a system for calibrating a photoelectric conversion model.
Background
The new energy power prediction technology is an indispensable support technology in new energy power generation grid connection, and plays an important role in aspects of power grid optimization scheduling, power generation plan formulation, power station economic operation and the like. The short-term power prediction generally refers to new energy grid-connected power prediction for 72 hours in the future, effective short-term power prediction can provide decision support for optimal scheduling for an electric power department, reasonable arrangement, maintenance and overhaul of a power station are facilitated, competitiveness of intermittent new energy is improved, and the consumption level of new energy power generation is improved.
At present, short-term photovoltaic power generation prediction mainly comprises the following steps: the method comprises the steps of firstly predicting meteorological elements such as radiation and the like, and then predicting future photovoltaic output power through a photoelectric conversion model. In the prediction idea, the establishment of a photoelectric conversion model is an important link of short-term power prediction of photovoltaic power generation, and the establishment of the photoelectric conversion model is usually determined by a regression method based on historical actually-measured radiation data and power data. However, due to various factors, the prediction accuracy of the photoelectric conversion model is not high, and how to improve the accuracy of the short-term prediction of the photovoltaic power generation through the photoelectric conversion model has important significance.
Disclosure of Invention
In order to solve the above-mentioned deficiencies in the prior art, the present invention provides a method and a system for calibrating a photoelectric conversion model. In the process of photovoltaic power generation short-term prediction through a photoelectric conversion model, the influence of the quality of the historical measured data on the conversion of the radiation power is large, however, on one hand, the influence is caused by the quality of a sensor, the external environment and other factors; on the other hand, the problem of light abandon is serious at present, so that the historical accumulated data of the photovoltaic power station comprises a plurality of limited power data; the quality of measured data is often uneven, the existing photovoltaic power prediction method mostly relies on historical data for modeling, and if abnormal points of the historical data are not eliminated, a large prediction error is inevitably brought, so that the method for effectively filtering the abnormal data points has outstanding improvement on the accuracy of a photoelectric conversion model.
The technical scheme provided by the invention is as follows: a method for calibrating a photoelectric conversion model, comprising:
obtaining a modeling data set based on the obtained total radiation data and power data;
calculating a goodness-of-fit value based on the modeling data set and a preset reference value;
and determining a photoelectric conversion relation curve based on the goodness-of-fit value.
Preferably, the calculating of the goodness-of-fit value based on the modeling data set and a preset reference value includes:
obtaining a radiation-power relational expression by adopting a least square polynomial fitting method based on the modeling data set;
drawing a radiation-power conversion relation curve according to the radiation-power relation by using total radiation data and power data in the modeling data set;
calculating a goodness-of-fit value based on the plotted radiation-power conversion relationship curve;
presetting a reference value according to the data dispersion degree, and obtaining a current goodness-of-fit value when the goodness-of-fit value is not less than the preset reference value;
otherwise, screening each discrete point in the drawn radiation-power conversion relation curve according to preset conditions, and then redrawing the radiation-power conversion relation curve;
calculating a goodness-of-fit value based on the re-plotted radiation-power conversion relationship curve;
and updating the goodness-of-fit value based on the goodness-of-fit value and a preset reference value.
Preferably, the radiation-power relation is as follows:
p(x)＝a 0 +a 1 x+...+a m x m
in the formula: x: total radiation data; p (x): power data; a is m : fitting the mth term coefficient of the polynomial; x is the number of m : fitting the mth term of the polynomial.
Preferably, after screening each discrete point in the radiation-power conversion relation curve according to a preset condition, the redrawing the radiation-power conversion relation curve includes:
calculating the relative error between the actual power and the fitting power value of each discrete point in the radiation-power conversion relation curve;
and screening out all discrete points of which the relative errors do not meet the preset condition, and then redrawing a radiation-power conversion curve.
Preferably, the updating the goodness-of-fit value based on the goodness-of-fit value and a preset reference value includes:
when the goodness-of-fit value is larger than a preset reference value, adjusting the preset condition, continuously drawing a radiation-power conversion relation curve and calculating the goodness-of-fit value;
and when the goodness-of-fit value is not less than a preset reference value, ending the circulation and updating the goodness-of-fit value.
Preferably, the goodness-of-fit value is calculated as:
in the formula: r is 2 : fitting goodness of fit values; y is i : an ith discrete point in a radiation-power conversion relation curve;
a mean of discrete points in a radiation-power conversion relationship curve; n: the number of discrete points in the radiation-power conversion relationship curve;
fitting power value of each discrete point.
Preferably, the obtaining a modeling data set based on the acquired total radiation data and power data includes:
processing total radiation data and power data acquired in advance to generate an initial sample;
analyzing radiation-power correlation coefficients by day in the initial sample using data correlations;
screening out a radiation-power correlation coefficient not smaller than a preset threshold value from the radiation-power correlation coefficients;
and taking the data corresponding to the screened radiation-power correlation coefficient as a modeling data set.
Preferably, the processing the pre-acquired total radiation data and power data to generate the initial sample includes:
and rejecting the data with radiation of 0 but not 0, the data with power of 0 but not 0, the irregular data with power and radiation of 0, and the data beyond a preset range in the total radiation data and the power data to generate an initial sample.
Based on the same inventive concept, the invention provides a calibration system of a photoelectric conversion model, which comprises:
the data set module is used for obtaining a modeling data set based on the obtained total radiation data and power data;
the calculation module is used for calculating a goodness-of-fit value based on the modeling data set and a preset reference value;
and the determining module is used for determining the photoelectric conversion relation curve based on the goodness-of-fit value.
Preferably, the calculation module includes:
the first calculation unit is used for obtaining a radiation-power relational expression by adopting a least square polynomial fitting method based on the modeling data set;
the primary drawing unit is used for drawing a radiation-power conversion relation curve according to the radiation-power relation by using the total radiation data and the power data in the modeling data set;
a second calculation unit for calculating a goodness-of-fit value based on the plotted radiation-power conversion relationship curve;
the judging unit is used for presetting a reference value according to the data dispersion degree, and obtaining the current goodness-of-fit value when the goodness-of-fit value is not less than the preset reference value;
the redrawing unit is used for screening each discrete point in the drawn radiation-power conversion relation curve according to preset conditions and redrawing the radiation-power conversion relation curve;
a third calculation unit for calculating a goodness-of-fit value based on the re-plotted radiation-power conversion relation curve;
and the updating unit is used for updating the goodness-of-fit value based on the goodness-of-fit value and a preset reference value.
Compared with the closest prior art, the technical scheme provided by the invention has the following beneficial effects:
according to the technical scheme provided by the invention, a modeling data set is obtained based on the acquired total radiation data and power data; calculating a goodness-of-fit value based on the modeling data and a preset reference value; and determining a photoelectric conversion relation curve based on the goodness-of-fit value, carrying out data optimization through correlation analysis and carrying out abnormal point filtering through inspection of goodness-of-fit so as to achieve a better model calibration effect.
The technical scheme provided by the invention is suitable for the region with frequent electricity limitation, eliminates the influence of electricity limitation data on a photoelectric conversion model, and improves the short-term photovoltaic prediction precision.
The technical scheme provided by the invention can realize automatic processing, has strong operability and is suitable for a photovoltaic short-term power prediction system.
Drawings
FIG. 1 is a general flow diagram of the calibration method of the present invention;
FIG. 2 is a detailed flowchart of a calibration method according to an embodiment of the present invention;
FIG. 3 is a raw radiation-power scatter plot of a power plant according to an embodiment of the present invention;
FIG. 4 is a graph of radiation-power relationship after correlation verification in an embodiment of the present invention;
FIG. 5 is a diagram illustrating a result of a cyclic check according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating a comparison of predicted results according to an embodiment of the present invention.
Detailed Description
For a better understanding of the present invention, reference is made to the following description taken in conjunction with the accompanying drawings and examples.
Example 1
Fig. 1 is a general flowchart of a method for calibrating a photoelectric conversion model in this embodiment, including:
s1, obtaining a modeling data set based on the obtained total radiation data and power data;
s2, calculating a goodness-of-fit value based on the modeling data and a preset reference value;
and S3, determining a photoelectric conversion relation curve based on the goodness-of-fit value.
Fig. 2 is a detailed flowchart of the calibration method in the embodiment of the present invention, which takes the calibration method of the photoelectric conversion model suitable for photovoltaic short-term power prediction as an example, and includes the following specific steps:
step 1: extracting meteorological observation data and historical power data of the photovoltaic power station, carrying out integrity inspection, and removing missing and unreasonable data to serve as an initial sample;
wherein, meteorological observation data mainly refer to historical total radiation data, and unreasonable data includes following several: radiation is 0 and power is not 0, power is 0 and radiation is not 0, both power and radiation are 0, irregular data and data out of reasonable range.
And 2, step: analyzing data correlation, calculating historical daily radiation-power corresponding correlation coefficients, and screening historical complete day data with better radiation-power correlation as input data of the step 3;
further, data optimization by correlation analysis includes: selecting total radiation and power data of a whole historical day, calculating a radiation-power correlation coefficient R of the data of the whole day according to a strong correlation characteristic between the total radiation and photovoltaic power generation power, and calculating the R according to the following formula;
in the formula: x represents the total radiation data and X represents the total radiation data,
represents the average of the total radiation data, Y represents the power data,
represents the average of the power data.
Determining a correlation judgment standard R according to requirements and experience ref Selecting the radiation-power correlation coefficient R to be greater than or equal to the reference value R ref The complete day data of (3) is used as modeling initial selection data, and the modeling initial selection data is used as input data of the step (3).
And step 3: preliminarily drawing a radiation-power conversion curve according to the radiation-power conversion relation based on a least square polynomial fitting method by using the input data obtained in the step 2, wherein the method specifically comprises the following steps:
performing first least squares polynomial fitting on the input data to obtain a radiation-power relation:
p(x)＝a 0 +a 1 x+...+a m x m
in the formula: x represents total radiation data, p (x) represents power data, a m An m-th term coefficient representing a fitting polynomial; x is the number of m Representing the mth term of the fitted polynomial.
And preliminarily drawing a radiation-power conversion curve according to the radiation-power relation by using total radiation data and power data in the input data.
Calculating a goodness-of-fit value based on the plotted radiation-power conversion curve;
presetting a reference value according to the data dispersion degree, and obtaining a current goodness-of-fit value when the goodness-of-fit value is not less than the preset reference value;
otherwise, executing step (4).
The least squares fitting method in this embodiment reflects the functional relationship between the independent variables and the dependent variables by minimizing the sum of the squares of the errors and finding the best functional match.
Let the function y = f (x) at point x 1 ,...,x n The function value of (a) is y 1 ,...,y n Then the objective of the least squares polynomial fitting method is to solve the polynomial p (x) = a 0 +a 1 x+...+a m x m ∈Π m (m +1 < n) so that the sum of squares of errors
And minimum.
Existing facility
To a j Calculating the partial derivative, and making the partial derivative be 0, we can obtain:
and (5) finishing the equation to obtain:
solving the equation system to obtain a 0 ,a 1 ,......,a m Finally, a least squares fitting polynomial is obtained:
p(x)＝a 0 +a 1 x+...+a m x m 。
and 4, step 4: calculating relative error of each discrete point based on the last curve, screening out large error value points, redrawing radiation-power relation curve, and calculating goodness-of-fit value R 2 The method comprises the following steps:
calculating the relative error delta between the actual power and the fitting power value of each discrete point by using the radiation data in the input data;
determining an upper bound judgment standard delta according to the distribution condition of the discrete points on the two sides of the fitting curve up And a lower bound criterion δ down ；
If delta i ＞δ up Or delta i ＜δ down Then the point is screened out and the radiation power relationship curve, δ, is re-fitted on the basis of the previous time i Representing the relative error of the ith discrete point;
calculate goodness of fit value R as follows 2 ：
In the formula: let y i Is the ith discrete point in the radiation-power conversion relation curve, and the mean value is
n represents the number of discrete points,
the fitting power value for each discrete point is indicated.
And 5: goodness of fit R 2 Judging, if the relative error judgment standard of the discrete point is not reached to the preset reference value, adjusting the relative error judgment standard of the discrete point, repeating the step 4, if the relative error judgment standard of the discrete point is reached to the reference value, finishing the calibration of the photoelectric conversion relation curve, comprising:
determining reference value of goodness of fit according to data dispersion degree
Calculating goodness of fit R 2 Value, if
Ending circulation, and outputting the current goodness-of-fit value and a corresponding radiation-power conversion relation curve;
otherwise, adjusting the upper bound judgment standard delta up And a lower bound criterion δ down Repeating the abnormal point elimination of the step 4And (4) outputting a radiation power relation curve until the goodness of fit reaches the requirement.
And finally, obtaining the photoelectric conversion model meeting the requirements.
Example 2
Taking a certain photovoltaic power station in Xinjiang as an example, actually measured radiation and power data of the certain photovoltaic power station in Xinjiang for one month are read, and under the condition that electricity is limited frequently in the area, a radiation-power relation curve is fitted by a least square polynomial, so that data scatter points and the relation curve are obtained and are shown in figure 3.
Wherein, radiation-power relation: p = -2E-05x 2 +0.0297x-0.0327；
Goodness of fit: r is 2 ＝0.8232。
Data in the graph show that in a section with high irradiance, corresponding output power is distributed in a scattered manner, and when a radiation-power conversion relation is calibrated, curve deviation is inevitably caused, so that the subsequent prediction precision is reduced.
The photoelectric conversion model is re-calibrated by using the calibration method in the present embodiment.
Through correlation verification, selecting complete day data with a radiation-power correlation coefficient larger than 0.9, screening 9 days to meet the correlation requirement, and re-calibrating a radiation-power conversion relation to obtain a curve shown in fig. 4, wherein the radiation-power relation is as follows: p = -1E-05x 2 +0.0323x-0.713；
Goodness of fit: r 2 ＝0.8677。
Through cyclic verification, discrete large value points are removed, and a final radiation-power conversion relation is obtained as shown in fig. 5, wherein the radiation-power relation is as follows: p = -1E-05x 2 +0.0351x-0.9302; the goodness of fit of the curve reaches 0.9429.
The conversion curve is applied to predict 2 days in the future, the source data is predicted by adopting the same numerical value, and the obtained prediction result is shown in fig. 6.
The prediction result shows that the overall prediction result of the prediction method of the uncorrected photoelectric conversion model is low, the variation trend and the actual measurement deviation are large, the photoelectric conversion model can be effectively corrected by applying the method, the prediction precision of the unlimited time period is improved, and the overall trend is consistent with the actual measurement power.
Based on the same inventive concept, the invention also provides a calibration system of the photoelectric conversion model, which comprises:
the data set module is used for obtaining a modeling data set based on the obtained total radiation data and power data;
the calculation module is used for calculating a goodness-of-fit value based on the modeling data set and a preset reference value;
and the determining module is used for determining the photoelectric conversion relation curve based on the goodness-of-fit value.
In an embodiment, the calculation module comprises:
the first calculation unit is used for obtaining a radiation-power relational expression by adopting a least square polynomial fitting method based on the modeling data set;
the primary drawing unit is used for drawing a radiation-power conversion relation curve according to the radiation-power relation by using the total radiation data and the power data in the modeling data set;
a second calculation unit for calculating a goodness-of-fit value based on the plotted radiation-power conversion relationship curve;
the judging unit is used for presetting a reference value according to the data dispersion degree, and obtaining the current goodness-of-fit value when the goodness-of-fit value is not less than the preset reference value;
the redrawing unit is used for filtering each discrete point in the drawn radiation-power conversion relation curve according to a preset condition and redrawing the radiation-power conversion relation curve;
a third calculation unit for calculating a goodness-of-fit value based on the re-plotted radiation-power conversion relation curve;
and the updating unit is used for updating the goodness-of-fit value based on the goodness-of-fit value and a preset reference value.
In an embodiment, the determining module includes:
the first determining unit is used for presetting a reference value according to the data dispersion degree, and ending circulation to obtain the current goodness-of-fit value when the goodness-of-fit value is not less than the preset reference value;
and the second determining unit is used for adjusting the preset condition when the goodness-of-fit value is greater than a preset reference value, continuously drawing a radiation-power conversion relation curve and calculating the goodness-of-fit value until the goodness-of-fit value is not less than the preset reference value.
In an embodiment, the data set module includes:
the initial sample unit is used for processing pre-acquired total radiation data and power data to generate an initial sample;
an analysis unit for analyzing a radiation-power correlation coefficient by day using data correlation in the initial sample;
the screening unit is used for screening out the radiation-power correlation coefficient which is not less than a preset threshold value from the radiation-power correlation coefficient;
and the data set unit is used for screening out data corresponding to the radiation-power correlation coefficient and taking the data as a modeling data set.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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 application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. 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.
The present invention is not limited to the above embodiments, and any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are included in the scope of the claims of the present invention which are filed as the application.
Claims (8)
1. A method for calibrating a photoelectric conversion model, comprising:
obtaining a modeling data set based on the obtained total radiation data and power data;
calculating a goodness-of-fit value based on the modeling data set and a preset reference value;
determining a photoelectric conversion relation curve based on the goodness-of-fit value;
calculating a goodness-of-fit value based on the modeling data set and a preset reference value, comprising:
obtaining a radiation-power relational expression by adopting a least square polynomial fitting method based on the modeling data set;
drawing a radiation-power conversion relation curve according to the radiation-power relation by using the total radiation data and the power data in the modeling data set;
calculating a goodness-of-fit value based on the plotted radiation-power conversion relationship curve;
presetting a reference value according to the data dispersion degree, and obtaining a current goodness-of-fit value when the goodness-of-fit value is not less than the preset reference value;
otherwise, screening each discrete point in the drawn radiation-power conversion relation curve according to preset conditions, and then redrawing the radiation-power conversion relation curve;
calculating a goodness-of-fit value again based on the re-plotted radiation-power conversion relationship curve;
updating a goodness-of-fit value based on the goodness-of-fit value and the reference value;
the step of re-drawing the radiation-power conversion relation curve after screening each discrete point in the drawn radiation-power conversion relation curve according to a preset condition comprises:
calculating the relative error between the actual power and the fitting power value of each discrete point in the radiation-power conversion relation curve;
and screening out all discrete points of which the relative errors do not meet the preset conditions, and then redrawing a radiation-power conversion curve.
2. A calibration method according to claim 1, wherein the radiation-power relationship is as follows:
p(x)＝a 0 +a 1 x+...+a m x m
in the formula: x: total radiation data; p (x): power data; a is m : fitting the mth term coefficient of the polynomial; x is a radical of a fluorine atom m : fitting the mth term of the polynomial.
3. A calibration method according to claim 1 wherein said updating the goodness-of-fit value based on the goodness-of-fit value and a preset reference value comprises:
when the goodness-of-fit value is larger than a preset reference value, adjusting the preset condition, continuously drawing a radiation-power conversion relation curve and calculating the goodness-of-fit value;
and when the goodness-of-fit value is not less than a preset reference value, ending the cycle and updating the goodness-of-fit value.
4. A calibration method according to claim 1 wherein the goodness-of-fit value is calculated as:
in the formula: r 2 : fitting goodness of fit values; y is i : an ith discrete point in a radiation-power conversion relation curve;
a mean of discrete points in a radiation-power conversion relationship curve; n: the number of discrete points in the radiation-power conversion relationship curve;
fitting power value of each discrete point.
5. A calibration method according to claim 1, wherein the deriving a modeling dataset based on the acquired total radiation data and power data comprises:
processing total radiation data and power data acquired in advance to generate an initial sample;
analyzing radiation-power correlation coefficients on a daily basis in the initial sample using data correlations;
screening out a radiation-power correlation coefficient not less than a preset threshold value from the radiation-power correlation coefficients;
and the data corresponding to the screened radiation-power correlation coefficient is used as a modeling data set.
6. A calibration method according to claim 5, wherein the processing of pre-acquired total radiation data and power data to generate initial samples comprises:
and rejecting the data with radiation of 0 but not 0, the data with power of 0 but not 0, the irregular data with power and radiation of 0, and the data beyond a preset range in the total radiation data and the power data to generate an initial sample.
7. A rating system of a photoelectric conversion model using the rating method of a photoelectric conversion model according to any one of claims 1 to 6, comprising:
a data set module for obtaining a modeling data set based on the obtained total radiation data and power data;
the calculation module is used for calculating a goodness-of-fit value based on the modeling data set and a preset reference value;
and the determining module is used for determining a photoelectric conversion relation curve based on the goodness-of-fit value.
8. The rating system of claim 7, wherein the calculation module comprises:
the first calculation unit is used for obtaining a radiation-power relational expression by adopting a least square polynomial fitting method based on the modeling data set;
the primary drawing unit is used for drawing a radiation-power conversion relation curve according to the radiation-power relation by using the total radiation data and the power data in the modeling data set;
a second calculation unit for calculating a goodness-of-fit value based on the plotted radiation-power conversion relation curve;
the judging unit is used for presetting a reference value according to the data dispersion degree, and obtaining the current goodness-of-fit value when the goodness-of-fit value is not less than the preset reference value;
the redrawing unit is used for screening each discrete point in the drawn radiation-power conversion relation curve according to preset conditions and redrawing the radiation-power conversion relation curve;
a third calculation unit for calculating a goodness-of-fit value based on the re-plotted radiation-power conversion relation curve;
and the updating unit is used for updating the goodness-of-fit value based on the goodness-of-fit value and a preset reference value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810554671.0A CN110555220B (en) | 2018-05-31 | 2018-05-31 | Calibration method and system of photoelectric conversion model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810554671.0A CN110555220B (en) | 2018-05-31 | 2018-05-31 | Calibration method and system of photoelectric conversion model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110555220A CN110555220A (en) | 2019-12-10 |
| CN110555220B true CN110555220B (en) | 2022-10-25 |
Family
ID=68734681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810554671.0A Active CN110555220B (en) | 2018-05-31 | 2018-05-31 | Calibration method and system of photoelectric conversion model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110555220B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570126A (en) * | 2021-07-15 | 2021-10-29 | 远景智能国际私人投资有限公司 | Method, device and system for predicting power generation power of photovoltaic power station |
| CN114049010B (en) * | 2021-11-15 | 2024-06-18 | 无锡英臻科技股份有限公司 | Household photovoltaic power station installed capacity estimation method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103970719A (en) * | 2013-01-30 | 2014-08-06 | 华为技术有限公司 | Fitting method and fitting device |
| CN105590027A (en) * | 2015-12-17 | 2016-05-18 | 国网冀北电力有限公司 | Identification method for photovoltaic power abnormal data |
-
2018
- 2018-05-31 CN CN201810554671.0A patent/CN110555220B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103970719A (en) * | 2013-01-30 | 2014-08-06 | 华为技术有限公司 | Fitting method and fitting device |
| CN105590027A (en) * | 2015-12-17 | 2016-05-18 | 国网冀北电力有限公司 | Identification method for photovoltaic power abnormal data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110555220A (en) | 2019-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106779223B (en) | Photovoltaic system power generation real-time prediction method and device | |
| CN116089846A (en) | New energy settlement data anomaly detection and early warning method based on data clustering | |
| CN108319131B (en) | Unit peak regulation capacity evaluation method based on data mining | |
| CN110555220B (en) | Calibration method and system of photoelectric conversion model | |
| CN114004139A (en) | Photovoltaic power generation power prediction method | |
| CN102521080B (en) | Computer data recovery method for electricity-consumption information collecting system for power consumers | |
| CN111103565A (en) | Data transformation method and system based on intelligent electric energy meter metering error analysis | |
| CN117008479B (en) | Carbon emission optimization control method and system based on biomass gasification furnace | |
| CN117220597B (en) | Quick frequency response rate monitoring system of photovoltaic power station | |
| CN109670652A (en) | A kind of failure prediction method of photovoltaic module | |
| JP2018007347A (en) | Performance evaluation method of photovoltaic power generation | |
| CN112700050B (en) | Method and system for predicting ultra-short-term 1 st point power of photovoltaic power station | |
| CN108268963B (en) | Self-correction-inspection photovoltaic power short-term prediction method | |
| CN115455359A (en) | Automatic correction and distribution fitting method for small-batch error data | |
| CN109388863B (en) | ARIMA model-based distributed photovoltaic output power prediction method | |
| CN107808209B (en) | Wind power plant abnormal data identification method based on weighted kNN distance | |
| CN117595231A (en) | Intelligent power grid distribution management system and method thereof | |
| CN114819391B (en) | Photovoltaic power generation power prediction method and system based on historical data set time span optimization | |
| JP6548955B2 (en) | Support system for power generation estimation learning in photovoltaic power generation | |
| CN113632025A (en) | Methods, systems, and computer program products for assessing energy consumption in an industrial environment | |
| CN115081681B (en) | Wind power prediction method based on propset algorithm | |
| CN112801388A (en) | Power load prediction method and system based on nonlinear time series algorithm | |
| JP2019208350A (en) | Diagnostic device for photovoltaic power generation facility | |
| Müller et al. | A framework to calculate uncertainties for lifetime energy yield predictions of PV systems | |
| CN114547829A (en) | Theoretical power calculation method and system for wind power plant |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |