CN117856222A - Photovoltaic output prediction method and device, electronic equipment and storage medium - Google Patents
Photovoltaic output prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117856222A CN117856222A CN202311749168.8A CN202311749168A CN117856222A CN 117856222 A CN117856222 A CN 117856222A CN 202311749168 A CN202311749168 A CN 202311749168A CN 117856222 A CN117856222 A CN 117856222A
- Authority
- CN
- China
- Prior art keywords
- weather
- data
- historical
- photovoltaic output
- weather data
- 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 63
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 9
- 239000000203 mixture Substances 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 238000009826 distribution Methods 0.000 description 7
- 238000010248 power generation Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 238000000053 physical method Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a photovoltaic output prediction method, a device, electronic equipment and a storage medium, wherein the photovoltaic output prediction method comprises the following steps: acquiring historical weather data and corresponding historical photovoltaic output data in a preset time period; clustering the historical weather data to obtain various weather types of the historical weather data; acquiring weather data of a target prediction day; determining pearson correlation coefficients between historical weather data under each weather type and weather data of a target prediction day; determining a target weather type of weather data of a target prediction day according to the pearson correlation coefficient; and inputting weather data of the target prediction day into a photovoltaic output prediction model corresponding to the target weather type to obtain a photovoltaic output prediction value, wherein the photovoltaic output prediction model is obtained based on a transducer model training. Therefore, the prediction accuracy of the photovoltaic output is improved.
Description
Technical Field
The application relates to the technical field of photovoltaic output prediction, in particular to a photovoltaic output prediction method, a device, electronic equipment and a storage medium.
Background
With the transformation of the current generation energy structure and the development of renewable energy sources, photovoltaic power generation systems are widely used in the global scope. However, the output power of a photovoltaic power generation system is affected by various factors, the most important of which is weather conditions and seasonal variations, and thus, accurate prediction of photovoltaic output is of great importance to improve the stability and economy of the power system.
At present, photovoltaic output prediction methods are mainly divided into two main categories: statistical methods and physical methods. The statistical method mainly comprises regression analysis, support vector regression, a neural network and the like, and the physical method mainly comprises a photovoltaic simulation and optimization method based on a meteorological model and the like. Although the statistical method has certain universality, a large amount of historical data is needed as a training sample, and the dynamic characteristic of weather change cannot be considered. The physical method considers the dynamic characteristics of weather changes, but requires accurate weather models and physical characteristics of photovoltaic cells, and has higher calculation complexity.
It can be seen that the existing photovoltaic output has the technical problem that accurate prediction is difficult.
Disclosure of Invention
The embodiment of the application aims to provide a photovoltaic output prediction method, a device, electronic equipment and a storage medium, which are used for solving the technical problem that the photovoltaic output is difficult to accurately predict in the prior art.
To achieve the above object, a first aspect of the present application provides a photovoltaic output prediction method, including:
acquiring historical weather data and corresponding historical photovoltaic output data in a preset time period;
clustering the historical weather data to obtain various weather types of the historical weather data;
acquiring weather data of a target prediction day;
determining pearson correlation coefficients between historical weather data under each weather type and weather data of a target prediction day;
determining a target weather type of weather data of a target prediction day according to the pearson correlation coefficient;
and inputting weather data of the target prediction day into a photovoltaic output prediction model corresponding to the target weather type to obtain a photovoltaic output prediction value, wherein the photovoltaic output prediction model is obtained based on a transducer model training.
In an embodiment of the present application, determining pearson correlation coefficients between historical weather data and weather data for a target prediction day for each weather type includes:
extracting a first solar irradiance of historical weather data under a plurality of weather types;
extracting a second solar irradiance of the weather data of the target prediction day;
a Pearson correlation coefficient between the historical weather data and the weather data of the target prediction day under each weather type is determined according to the first solar irradiance and the second solar irradiance.
In an embodiment of the present application, determining a target weather type of weather data of a target prediction day according to a pearson correlation coefficient includes:
and taking the weather type corresponding to the maximum pearson correlation coefficient as the target weather type of the weather data of the target prediction day.
In the embodiment of the application, the historical weather data are clustered to obtain multiple weather types of the historical weather data, including:
and clustering the historical weather data by using a mixed Gaussian model clustering algorithm to obtain various weather types of the historical weather data.
In this embodiment of the present application, before clustering the historical weather data to obtain multiple weather types of the historical weather data, the method further includes:
and carrying out data preprocessing on the historical weather data and the historical photovoltaic output data.
In an embodiment of the present application, performing data preprocessing on historical weather data and historical photovoltaic output data includes:
and carrying out outlier rejection and missing value reconstruction on the historical weather data and the historical photovoltaic output data.
In an embodiment of the present application, the training step of the photovoltaic output prediction model includes:
according to various weather types, training a plurality of preset models respectively by utilizing historical weather data and historical photovoltaic output data to obtain a plurality of photovoltaic output prediction models corresponding to the various weather types.
A second aspect of the present application provides a photovoltaic output predicting device, comprising:
a memory configured to store instructions; and
a processor configured to invoke instructions from a memory and when executing the instructions is capable of implementing the photovoltaic output prediction method according to any of the first aspects.
A third aspect of the present application provides an electronic device, comprising:
the photovoltaic output predicting device according to the second aspect.
A fourth aspect of the present application provides a machine-readable storage medium having stored thereon instructions for causing a machine to perform the photovoltaic output prediction method according to any one of the first aspects.
According to the technical scheme, the historical weather data are clustered, the historical weather data are divided into a plurality of weather types, and the photovoltaic output prediction models corresponding to different weather types can be established according to the historical weather data and the corresponding historical photovoltaic output data under different weather types, so that the rules and trends of the weather data of different weather types can be captured more accurately by the models; the method comprises the steps of determining a pearson correlation coefficient between historical weather data under each weather type and weather data of a target prediction day, so as to accurately judge the target weather type of the weather data of the target prediction day; the weather data of the target prediction day are input into the photovoltaic output prediction model corresponding to the target weather type, so that the influence of the weather type on the photovoltaic output can be considered more comprehensively, and the accuracy of the photovoltaic output prediction is improved.
Additional features and advantages of embodiments of the present application will be set forth in the detailed description that follows.
Drawings
The accompanying drawings are included to provide a further understanding of embodiments of the present application and are incorporated in and constitute a part of this specification, illustrate embodiments of the present application and together with the description serve to explain, without limitation, the embodiments of the present application. In the drawings:
FIG. 1 schematically illustrates a flow diagram of a photovoltaic output prediction method according to an embodiment of the present application;
fig. 2 schematically shows a schematic structural diagram of a photovoltaic output predicting device according to an embodiment of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the specific implementations described herein are only for illustrating and explaining the embodiments of the present application, and are not intended to limit the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present application based on the embodiments herein.
It should be noted that, in the embodiment of the present application, directional indications (such as up, down, left, right, front, and rear … …) are referred to, and the directional indications are merely used to explain the relative positional relationship, movement conditions, and the like between the components in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indications are correspondingly changed.
In addition, if there is a description of "first", "second", etc. in the embodiments of the present application, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be regarded as not exist and not within the protection scope of the present application.
Fig. 1 schematically shows a flow diagram of a photovoltaic output prediction method according to an embodiment of the present application. As shown in fig. 1, an embodiment of the present application provides a photovoltaic output prediction method, which may include the following steps.
Step 110: acquiring historical weather data and corresponding historical photovoltaic output data in a preset time period;
it should be noted that the photovoltaic output is affected by various weather information, such as solar irradiance, temperature, humidity, wind speed, air pressure, etc. When the solar irradiance is higher, the photovoltaic panel on the photovoltaic power station is subjected to stronger illumination, the photovoltaic output is larger, namely more electric energy is generated; the high temperature also reduces the conversion efficiency of the electric energy, so that the photovoltaic output is reduced; meanwhile, the humidity, the wind speed and the air pressure can also have certain influence on the power generation performance of the photovoltaic station, the high humidity can influence the working efficiency of electronic elements in the photovoltaic panel, the wind speed can influence the heat dissipation effect of the photovoltaic panel, and the air pressure change can influence the water vapor content in the atmosphere and the propagation of solar radiation. Therefore, the embodiment of the application acquires the historical weather data and the corresponding historical photovoltaic output data in the preset time period, and lays a data foundation for building the photovoltaic output prediction model for the subsequent embodiment.
Specifically, historical weather data within a preset time period can be obtained from a weather station, and corresponding historical photovoltaic output data can be obtained from a photovoltaic power station. Weather stations typically record and provide historical weather data, including solar irradiance, temperature, humidity, wind speed, barometric pressure, etc., which may be obtained by accessing a website, API, or other data providing means of the weather station. The photovoltaic power station generally records data such as historical photovoltaic power generation capacity, historical photovoltaic power generation power, historical photovoltaic output and the like, wherein the historical photovoltaic output data refers to electric power data actually generated by the photovoltaic power station in a preset time period, and the electric power data can be obtained through a monitoring system or data recording device of the photovoltaic power station. The preset time period may be set according to actual requirements, which is not limited in the embodiment of the present application.
Step 120: clustering the historical weather data to obtain various weather types of the historical weather data;
it can be understood that clustering is an unsupervised learning method, and aims to divide samples in a data set into similar groups (or clusters), so that the similarity between samples in the same cluster is high, and the similarity between samples in different clusters is low. Common clustering methods comprise K-means clustering, hierarchical clustering, density clustering, gaussian mixture model clustering and the like, different clustering methods have respective advantages and applicable scenes when processing different data characteristics, distribution conditions and clustering requirements, and a proper clustering method can be selected according to actual requirements.
It should be noted that different weather types can have different effects on photovoltaic power generation, for example, the illumination conditions on sunny days and cloudy days are different, and factors such as wind speed, temperature and humidity can also affect the efficiency of the photovoltaic panel, so in order to more accurately predict the photovoltaic output data under different weather types, a photovoltaic output prediction model under different weather types needs to be established. Specifically, the historical weather data is clustered, the historical weather data can be divided into multiple weather types through clustering, and the photovoltaic output prediction model corresponding to different weather types can be established according to the historical weather data and the corresponding historical photovoltaic output data under different weather types, so that the model can capture the rules and trends of the weather data of different weather types more accurately, and the accuracy of photovoltaic output prediction is improved.
In the embodiment of the present application, step 120 includes:
and clustering the historical weather data by using a mixed Gaussian model clustering algorithm to obtain various weather types of the historical weather data.
It will be appreciated that the mixed gaussian model clustering (Gaussian Mixture Model, GMM) algorithm is a probabilistic model-based clustering method, assuming that the sample data is composed of a plurality of gaussian distributions, the core idea is to consider the samples in the dataset as being composed of a plurality of gaussian distributions, each gaussian distribution representing a cluster, and the distribution of sample points can be described by a combination of these gaussian distributions. In the training process, the mixed Gaussian model clustering algorithm is trained by using an expected maximum (Expectation Maximization, EM) algorithm, whether one model is well fitted is judged by observing the approach degree of the sampled probability value and the model probability value, then the expected value of data is calculated by the model, and the expected value is maximized by updating the mean value and the standard deviation of distribution, so that the clustering effect of the Gaussian mixture model is optimized. By utilizing the Gaussian mixture model clustering algorithm, the historical weather data can be effectively clustered, so that the historical weather data are divided into a plurality of weather types.
Step 130: acquiring weather data of a target prediction day;
specifically, the weather data of the target prediction day may be obtained from the numerical prediction results (Numerical Weather Prediction, NWP), where the weather data of the target prediction day includes characteristics such as solar irradiance, temperature, humidity, wind speed, air pressure, and the like, and the target prediction day is a date on which the photovoltaic output prediction is required, and may be set according to actual requirements, which is not limited in the embodiment of the present application.
Step 140: determining pearson correlation coefficients between historical weather data under each weather type and weather data of a target prediction day;
it will be appreciated that the pearson correlation coefficient (Pearson correlation coefficient) is a statistic used to measure the degree of linear correlation between two variables, and ranges from-1 to 1. It should be noted, however, that the pearson correlation coefficient measures only linear correlations and does not represent that there must be a causal or other nonlinear relationship between the two variables.
By determining the pearson correlation coefficient between the historical weather data under each weather type and the weather data of the target prediction day, the linear correlation between the historical weather data under each weather type and the weather data of the target prediction day can be obtained, so that the target weather type of the weather data of the target prediction day can be accurately judged.
In the embodiment of the present application, step 140 includes:
extracting a first solar irradiance of historical weather data under a plurality of weather types;
extracting a second solar irradiance of the weather data of the target prediction day;
a Pearson correlation coefficient between the historical weather data and the weather data of the target prediction day under each weather type is determined according to the first solar irradiance and the second solar irradiance.
It should be noted that solar irradiance is one of the main driving factors of photovoltaic power generation, and power output generally increases with the increase of solar irradiance, because the conversion efficiency of photovoltaic cells to sunlight is closely related to irradiance, when solar irradiance is higher, the photovoltaic panel on the photovoltaic site is more strongly illuminated, and the photovoltaic output is larger, so that the embodiments of the present application determine the pearson correlation coefficient between the historical weather data under each weather type and the weather data of the target prediction day according to the solar irradiance which is most closely related to the photovoltaic output.
Specifically, first solar irradiance of historical weather data under various weather types and second solar irradiance of weather data of a target prediction day are extracted, and according to the first solar irradiance and the second solar irradiance, pearson correlation coefficients between the historical weather data under each weather type and the weather data of the target prediction day are calculated through the following formula:
wherein ρ is i Representing the pearson correlation coefficient, X, between historical weather data for the ith weather type and weather data for the target prediction day i Representing a first solar irradiance, X, in historical weather data for an ith weather type i Representing an average of the first solar irradiance in the historical weather data for the ith weather type, Y representing the second solar irradiance of the weather data for the target prediction day, and Y representing an average of the second solar irradiance of the weather data for the target prediction day.
Step 150: determining a target weather type of weather data of a target prediction day according to the pearson correlation coefficient;
it should be noted that the pearson correlation coefficient has a value ranging from-1 to 1. When the pearson correlation coefficient is 1, the two variables have a complete positive linear relation, namely the two variables are increased in proportion; when the pearson correlation coefficient is-1, the complete negative linear relation exists between the two variables, namely the two variables are inversely proportional to increase; when the pearson correlation coefficient is 0, it indicates that there is no linear relationship between the two variables; when the pearson correlation coefficient is between 0 and 1, the larger the pearson correlation coefficient is, the stronger the positive linear relationship between the two variables is represented; when the pearson correlation coefficient is between-1 and 0, the smaller the pearson correlation coefficient, the stronger the negative linear relationship between the two variables. According to the pearson correlation coefficient, the target weather type of the weather data of the target prediction day is determined, and the weather type of the weather data of the target prediction day can be accurately judged.
In an embodiment of the present application, step 150 includes:
and taking the weather type corresponding to the maximum pearson correlation coefficient as the target weather type of the weather data of the target prediction day.
It should be noted that, because the value range of the pearson correlation coefficient is between-1 and 1, the closer the value is to 1, the stronger the positive linear relationship between the two variables is indicated, and the embodiment of the application is to accurately determine the target weather type of the weather data on the target prediction day, so that the weather type of the historical weather data with the strongest positive correlation with the weather data on the target prediction day is selected as the target weather type of the weather data on the target prediction day, that is, the weather type corresponding to the largest pearson correlation coefficient is selected as the target weather type of the weather data on the target prediction day, so that the accuracy of determining the weather type of the weather data on the target prediction day is improved.
Step 160: and inputting weather data of the target prediction day into a photovoltaic output prediction model corresponding to the target weather type to obtain a photovoltaic output prediction value, wherein the photovoltaic output prediction model is obtained based on a transducer model training.
It will be appreciated that the transducer model is a deep learning architecture, originally used for natural language processing (Natural Language Processing, NLP) tasks, but is also widely used in other fields. The transducer model abandons the traditional cyclic neural network and convolutional neural network structure, and adopts a self-attention mechanism to realize the processing of sequence data, and the structure is unique in that the transducer model is not dependent on position information or fixed window size any more, but can process the relation among all positions in a sequence at the same time, thereby greatly improving the parallel computing capacity of the model. And by introducing components such as encoder-decoder structure, multi-head attention mechanism, feedforward neural network and the like, the transducer model has strong semantic understanding and generating capability.
Specifically, after the target weather type of the weather data of the target prediction day is obtained through the steps, the weather data of the target prediction day is input into a photovoltaic output prediction model corresponding to the target weather type, and a photovoltaic output prediction value corresponding to the weather data of the target prediction day can be obtained, wherein the photovoltaic output prediction model is obtained based on a Transformer model training. The transducer model can simultaneously consider information of different positions in the input sequence, and is beneficial to capturing possible long-term dependence in the photovoltaic output data; because the transducer model contains a self-attention mechanism, different attention weights can be distributed in the whole input sequence, global information can be better captured, and the method is very important for the mode and rule with frequent change in the photovoltaic output prediction; meanwhile, the transducer model can adapt to data of different frequencies and time sequences, has strong universality, and enables the prediction of the photovoltaic output data on different time scales to be carried out; because the weather data of the target prediction day comprises solar irradiance, temperature, humidity, wind speed, air pressure and other characteristics, the multi-head attention mechanism of the transducer model can process the relation between different characteristics, and more comprehensive information capture is provided. Compared with the method for predicting the photovoltaic output by using a unified photovoltaic output prediction model to predict the weather data of the target prediction day, the method for predicting the photovoltaic output by using the photovoltaic output prediction model under different weather types is more targeted, and the influence of the weather types on the photovoltaic output can be considered more comprehensively, so that the accuracy of the photovoltaic output prediction is improved.
In the embodiment of the present application, before step 120, the method further includes:
and carrying out data preprocessing on the historical weather data and the historical photovoltaic output data.
It should be noted that the problem that the scale difference between the missing value, the abnormal value or the characteristic is too large may exist in the historical weather data and the historical photovoltaic output data, and the training and learning processes of the photovoltaic output prediction model may be directly interfered, so that the prediction accuracy of the photovoltaic output prediction model is affected, and therefore, the data preprocessing needs to be performed on the historical weather data and the historical photovoltaic output data. The data preprocessing generally comprises abnormal value rejection, missing value reconstruction, feature extraction, standardization and other operations, noise and redundant information in historical weather data and historical photovoltaic output data can be reduced through the data preprocessing operations, original data are converted into features which are more meaningful and more representative of problems, so that the generalization capability of a photovoltaic output prediction model is improved, and features with different scales are scaled to the same range, so that the photovoltaic output prediction model is easier to learn, higher-quality and more reliable data are provided for the photovoltaic output prediction model, and the prediction accuracy of the photovoltaic output prediction model is improved.
In an embodiment of the present application, performing data preprocessing on historical weather data and historical photovoltaic output data includes:
and carrying out outlier rejection and missing value reconstruction on the historical weather data and the historical photovoltaic output data.
It should be noted that, due to various uncertainty problems, such as communication faults, equipment anomalies, artificial electricity limiting, and the like, measured data of the photovoltaic power station may include a large amount of anomaly data, and these anomaly data may seriously affect parameter estimation of the prediction model, so that the prediction accuracy is low, the prediction deviation is large, and the like. Therefore, prior to building a photovoltaic output prediction model using historical weather data and historical photovoltaic output data, these anomaly data need to be identified and rejected, and common methods for detecting anomalies include standard deviation methods, box-line graph methods, local outlier factor (Local Outlier Factor, LOF) algorithms, and the like.
Specifically, the embodiment of the application detects an outlier in historical weather data and historical photovoltaic output data by adopting a local outlier factor algorithm, wherein the local outlier factor algorithm is an algorithm commonly used for detecting outliers (outliers), for each data point, the local density between each data point and k nearest neighbor data points is calculated, the local density refers to the number of nearest neighbor points which are closer to a target point, then the LOF score of each data point is calculated and is used for representing the ratio of the local density of the target point to the local densities of the k nearest neighbors of the target point, if the LOF score is close to 1, the local density of the data point is similar to that of the nearest neighbor points, the data point is judged to be not the outlier, and if the LOF score is larger than 1, the local density of the data point is relatively lower, and the data point is judged to be the outlier.
It should be noted that due to the reasons of unit light rejection, maintenance, extreme weather conditions, external electromagnetic interference or equipment failure, etc. during operation of the photovoltaic power station, a large amount of incomplete data may exist in the original data. In order not to affect the learning process of the prediction model, it is necessary to reconstruct the missing values. Common missing value reconstruction methods include interpolation, multiple interpolation, random forest regression and the like, and suitable missing value reconstruction methods can be selected according to actual requirements, and the embodiment of the application is not limited to the above.
By carrying out outlier rejection and missing value reconstruction on the historical weather data and the historical photovoltaic output data, the quality and reliability of the data for training the photovoltaic output prediction model are guaranteed, so that the photovoltaic output prediction model can learn effective modes and rules from the data better, and the prediction accuracy of the photovoltaic output is improved.
In an embodiment of the present application, the training step of the photovoltaic output prediction model includes:
according to various weather types, training a plurality of preset models respectively by utilizing historical weather data and historical photovoltaic output data to obtain a plurality of photovoltaic output prediction models corresponding to the various weather types.
Specifically, according to the historical weather data and the corresponding historical photovoltaic output prediction data under the various weather types obtained in the embodiment, training is performed on the plurality of preset models to obtain a plurality of photovoltaic output prediction models corresponding to the various weather types, and photovoltaic output prediction can be performed by using the photovoltaic output prediction models under different weather types more pertinently, influences of the weather types on photovoltaic output can be considered more comprehensively, so that accuracy of photovoltaic output prediction is improved.
According to the photovoltaic output prediction method provided by the embodiment of the application, the historical weather data are clustered to be divided into multiple weather types, and the photovoltaic output prediction model corresponding to different weather types can be built according to the historical weather data and the corresponding historical photovoltaic output data under different weather types, so that the model can capture the rules and trends of the weather data of different weather types more accurately; the method comprises the steps of determining a pearson correlation coefficient between historical weather data under each weather type and weather data of a target prediction day, so as to accurately judge the target weather type of the weather data of the target prediction day; the weather data of the target prediction day are input into the photovoltaic output prediction model corresponding to the target weather type, so that the influence of the weather type on the photovoltaic output can be considered more comprehensively, and the accuracy of the photovoltaic output prediction is improved.
Fig. 2 schematically shows a schematic structural diagram of a photovoltaic output predicting device according to an embodiment of the present application. As shown in fig. 2, an embodiment of the present application provides a photovoltaic output prediction apparatus, which may include:
a memory 210 configured to store instructions; and
the processor 220 is configured to call instructions from the memory 210 and when executing the instructions is capable of implementing the photovoltaic output prediction method provided by the above embodiments.
Specifically, in embodiments of the present application, the processor 220 may be configured to:
acquiring historical weather data and corresponding historical photovoltaic output data in a preset time period;
clustering the historical weather data to obtain various weather types of the historical weather data;
acquiring weather data of a target prediction day;
determining pearson correlation coefficients between historical weather data under each weather type and weather data of a target prediction day;
determining a target weather type of weather data of a target prediction day according to the pearson correlation coefficient;
and inputting weather data of the target prediction day into a photovoltaic output prediction model corresponding to the target weather type, wherein the photovoltaic output prediction model is trained based on a transducer model.
It can be understood that the photovoltaic output prediction device provided in the embodiment of the present application can implement each process of the photovoltaic output prediction method in the method embodiment, and can achieve the same technical effect, so that repetition is avoided, and no further description is provided here.
The embodiment of the application also provides an electronic device, which may include:
the photovoltaic output predicting device according to the above embodiment.
It can be appreciated that the electronic device provided in the embodiments of the present application includes the photovoltaic output prediction apparatus according to the above embodiments, and may achieve the same technical effects, so that repetition is avoided and no further description is provided herein.
The embodiment of the application further provides a machine-readable storage medium, on which instructions are stored, where the instructions are configured to enable a machine to execute the photovoltaic output prediction method described in the above method embodiment, and achieve the same technical effects, so that repetition is avoided, and no further description is given here.
It will be appreciated by those skilled in the art that 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), 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.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (10)
1. A method of photovoltaic output prediction, the method comprising:
acquiring historical weather data and corresponding historical photovoltaic output data in a preset time period;
clustering the historical weather data to obtain multiple weather types of the historical weather data;
acquiring weather data of a target prediction day;
determining pearson correlation coefficients between the historical weather data and the weather data for the target prediction day for each of the weather types;
determining a target weather type of the weather data of the target prediction day according to the pearson correlation coefficient;
and inputting the weather data of the target prediction day into a photovoltaic output prediction model corresponding to the target weather type to obtain a photovoltaic output predicted value, wherein the photovoltaic output prediction model is obtained based on a transducer model training.
2. The method of claim 1, wherein said determining pearson correlation coefficients between the historical weather data and the weather data for the target prediction day for each of the weather types comprises:
extracting a first solar irradiance of the historical weather data for the plurality of weather types;
extracting a second solar irradiance of the weather data for the target prediction day;
determining pearson correlation coefficients between the historical weather data and the weather data for the target predicted day for each of the weather types based on the first solar irradiance and the second solar irradiance.
3. The method of claim 1, wherein determining the target weather type of the weather data for the target prediction day based on the pearson correlation coefficient comprises:
and taking the weather type corresponding to the maximum pearson correlation coefficient as a target weather type of weather data of the target prediction day.
4. The method of claim 1, wherein clustering the historical weather data to obtain a plurality of weather types for the historical weather data comprises:
and clustering the historical weather data by using a Gaussian mixture model clustering algorithm to obtain various weather types of the historical weather data.
5. The method of claim 1, further comprising, prior to clustering the historical weather data to obtain a plurality of weather types for the historical weather data:
and carrying out data preprocessing on the historical weather data and the historical photovoltaic output data.
6. The method of claim 5, wherein the data preprocessing the historical weather data and the historical photovoltaic output data comprises:
and carrying out outlier rejection and missing value reconstruction on the historical weather data and the historical photovoltaic output data.
7. The method of claim 1, wherein the training step of the photovoltaic output prediction model comprises:
and respectively training a plurality of preset models by utilizing the historical weather data and the historical photovoltaic output data according to the plurality of weather types to obtain a plurality of photovoltaic output prediction models corresponding to the plurality of weather types.
8. A photovoltaic output predicting device, comprising:
a memory configured to store instructions; and
a processor configured to invoke the instructions from the memory and when executing the instructions is capable of implementing the photovoltaic output prediction method according to any of claims 1 to 7.
9. An electronic device, comprising:
the photovoltaic output predicting device of claim 8.
10. A machine-readable storage medium having stored thereon instructions for causing a machine to perform the photovoltaic output prediction method according to any of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311749168.8A CN117856222A (en) | 2023-12-18 | 2023-12-18 | Photovoltaic output prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311749168.8A CN117856222A (en) | 2023-12-18 | 2023-12-18 | Photovoltaic output prediction method and device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117856222A true CN117856222A (en) | 2024-04-09 |
Family
ID=90539207
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311749168.8A Pending CN117856222A (en) | 2023-12-18 | 2023-12-18 | Photovoltaic output prediction method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117856222A (en) |
-
2023
- 2023-12-18 CN CN202311749168.8A patent/CN117856222A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111091233B (en) | Short-term wind power prediction modeling method for wind power plant | |
CN114792156B (en) | Photovoltaic output power prediction method and system based on curve characteristic index clustering | |
CN113988477A (en) | Photovoltaic power short-term prediction method and device based on machine learning and storage medium | |
CN114330934A (en) | Model parameter self-adaptive GRU new energy short-term power generation power prediction method | |
CN116629416A (en) | Photovoltaic power station power prediction method and device | |
CN115936177A (en) | Photovoltaic output power prediction method and system based on neural network | |
CN116014722A (en) | Sub-solar photovoltaic power generation prediction method and system based on seasonal decomposition and convolution network | |
CN115689055A (en) | Short-term solar irradiance prediction method and device | |
CN117933531A (en) | Distributed photovoltaic power generation power prediction system and method | |
CN113111592A (en) | Short-term wind power prediction method based on EMD-LSTM | |
CN115907131B (en) | Method and system for constructing electric heating load prediction model in northern area | |
CN117154680A (en) | Wind power prediction method based on non-stationary transducer model | |
CN116070458A (en) | New wind power plant scene generation method based on RAC-GAN | |
CN117856222A (en) | Photovoltaic output prediction method and device, electronic equipment and storage medium | |
CN113780643A (en) | Photovoltaic power station short-term output prediction method based on case reasoning | |
Yang et al. | A hybrid vmd-based ARIMA-LSTM model for day-ahead pv prediction and uncertainty analysis | |
CN118069717B (en) | Time sequence data characteristic prediction method based on cyclic neural network | |
Katranji et al. | Short-Term Wind Speed Prediction for Saudi Arabia via 1D-CNN | |
Ji et al. | Short-Term Wind Power Output Prediction Based on Temporal Graph Convolutional Networks | |
CN117829822B (en) | Power transformer fault early warning method and system | |
CN117688367B (en) | Wind power generation ultra-short term power prediction method and device based on instant learning | |
CN116342077B (en) | New energy power transfer learning prediction method suitable for data-missing station | |
CN117633456B (en) | Marine wind power weather event identification method and device based on self-adaptive focus loss | |
Li et al. | A failure assessment method of island distribution lines based on model‐data hybrid drive | |
CN118349855A (en) | Multi-model photovoltaic power prediction method, equipment and storage medium |
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 |