CN113961620A

CN113961620A - Method and device for determining numerical weather forecast result

Info

Publication number: CN113961620A
Application number: CN202111217277.6A
Authority: CN
Inventors: 鲁晨鹏; 闫永刚
Original assignee: Sungrow Power Supply Co Ltd
Current assignee: Sungrow Power Supply Co Ltd
Priority date: 2021-10-19
Filing date: 2021-10-19
Publication date: 2022-01-21

Abstract

The application discloses a method and a device for determining a numerical weather forecast result, and relates to the technical field of photovoltaic power generation. The method comprises the following steps: acquiring an actually measured data sequence and a historical prediction data set of meteorological parameters in a preset historical time period; the historical prediction data set comprises N historical prediction data sequences acquired from N data sources; determining a target data sequence and other data sequences from the N historical prediction data sequences according to the similarity degree parameters of the historical prediction data sequences and the actually measured data sequences; determining the dynamic weights of the N data sources based on the deviation degree parameters of the other data sequences and the target data sequence; and determining the numerical weather forecast result of the meteorological parameters in the time period to be forecasted according to the current forecast data set and the dynamic weight of the meteorological parameters in the time period to be forecasted.

Description

Method and device for determining numerical weather forecast result

Technical Field

The embodiment of the application relates to the technical field of photovoltaic power generation, in particular to a method and a device for determining a numerical weather forecast result.

Background

With the wide application of photovoltaic power stations, prediction of photovoltaic power generation power becomes especially important. The photovoltaic power generation power is predicted, unknown power generation output can be changed into known power generation output, a countermeasure can be made in advance, the safety and the reliability of a power grid are improved, power generation can be brought into a scheduling plan according to the prediction result of the photovoltaic power generation power, and the economy of a power system is improved.

At present, the photovoltaic power generation power can be generally predicted according to a multi-source numerical weather forecast result and the operation parameters of a photovoltaic power station. Therefore, the accuracy of the prediction result of the photovoltaic power generation power is closely related to the accuracy of the numerical weather forecast result.

However, the quality of the numerical weather forecast results obtained from different data sources is uneven, and the numerical weather forecast result obtained from one data source may have a larger error than the numerical weather forecast results obtained from other data sources. Therefore, how to process the multi-source numerical weather forecast result to obtain a more accurate numerical weather forecast result becomes an urgent problem to be solved.

Disclosure of Invention

The application provides a method and a device for determining a numerical weather forecast result, which can determine a more accurate numerical weather forecast result, so that the accuracy of a prediction result of photovoltaic power generation power is improved.

In order to achieve the purpose, the technical scheme is as follows:

in a first aspect, the present application provides a method for determining a result of a numerical weather forecast, including: acquiring an actually measured data sequence and a historical prediction data set of meteorological parameters in a preset historical time period; the historical prediction data set comprises N historical prediction data sequences obtained from N data sources, wherein N is a positive integer; determining a target data sequence and other data sequences from the N historical prediction data sequences according to the similarity degree parameters of the historical prediction data sequences and the actually measured data sequences; determining the dynamic weights of the N data sources based on the deviation degree parameters of the other data sequences and the target data sequence; determining a numerical weather forecast result of the meteorological parameters in the time period to be predicted according to the current prediction data set and the dynamic weight of the meteorological parameters in the time period to be predicted; the current prediction data set includes N current prediction data sequences obtained from N data sources.

According to the technical scheme provided by the application, the N historical prediction data sequences obtained from the N data sources are compared with the actual measurement data sequences corresponding to the historical time periods (namely the preset historical time periods in the application), and the target data sequence with higher approaching degree with the actual measurement data sequences is determined according to the approaching degree of the N historical prediction data sequences and the actual measurement data sequences (namely the similarity parameters in the application). Then, based on the target data sequence, dynamic weights may be assigned to the N data sources according to the deviation degree parameter between the other data sequences and the target data sequence. Because the target data sequence is a data sequence with higher proximity to the measured data sequence, and the dynamic weight is determined according to the deviation degree parameter of other data sequences and the target data sequence, the dynamic weight can represent the proximity of each historical predicted data sequence and the measured data sequence. Therefore, the dynamic weights of the N data sources determined by the method can represent the accuracy of the data of each data source. The N current prediction data sequences acquired from the N data sources are weighted based on the dynamic weight to determine a numerical weather forecast result, so that the influence of errors of data acquired from the data sources on the numerical weather forecast result can be reduced. Therefore, the method and the device can determine a more accurate numerical weather forecast result, so that the accuracy of the prediction result of the photovoltaic power generation power is improved.

Optionally, in a possible design manner, the "determining the dynamic weights of the N data sources based on the parameter of the deviation degree between the other data sequences and the target data sequence" may include: acquiring initial weights of N data sources; determining the dynamic weight of the data source corresponding to the first data sequence according to the initial weight of the data source corresponding to the first data sequence and the deviation degree parameter of the first data sequence and the target data sequence; the first data sequence is any data sequence among other data sequences.

Optionally, in another possible design, the "determining the dynamic weights of the N data sources based on the parameter of the deviation degree between the other data sequences and the target data sequence" further includes: determining a total deviation degree parameter according to the deviation degree parameter of each data sequence in other data sequences and the target data sequence; and determining the dynamic weight of the data source corresponding to the target data sequence according to the initial weight and the total deviation degree parameter of the data source corresponding to the target data sequence.

Optionally, in another possible design, after the "determining the result of the numerical weather forecast of the weather parameter in the time period to be predicted" is performed, the method may further include: updating the initial weights of the N data sources according to the dynamic weights of the N data sources; and readjusting the dynamic weights of the N data sources according to the updated initial weights of the N data sources, the numerical weather forecast result and the N current predicted data sequences.

Optionally, in another possible design manner, before the "determining the dynamic weights of the N data sources based on the parameter of the degree of deviation between the other data sequences and the target data sequence", the method may further include: determining a deviation degree parameter according to the relative difference value of each first similarity degree parameter and each second similarity degree parameter; each first similarity parameter is a similarity parameter between each data sequence in other data sequences and the measured data sequence, and the second similarity parameter is a similarity parameter between the target data sequence and the measured data sequence.

Optionally, in another possible design manner, the similarity degree parameter may be goodness of fit;

the "determining the target data sequence and the other data sequences from the N historical predicted data sequences according to the similarity parameter between the historical predicted data sequence and the measured data sequence" may include: determining an average value of all data in the first historical prediction data sequence; determining the goodness of fit of the first historical predicted data sequence and the actually measured data sequence according to the difference between the corresponding data of the first historical predicted data sequence and the actually measured data sequence and the difference between each data of the actually measured data sequence and the average value; the first historical predicted data sequence is any one of the N historical predicted data sequences;

the "determining the target data sequence and the other data sequences from the N historical predicted data sequences" may include: and determining a sequence with the highest goodness of fit with the measured data sequence in the N historical predicted data sequences as a target data sequence, and determining data sequences except the target data sequence in the N historical predicted data sequences as other data sequences.

Optionally, in another possible design, the meteorological parameter may include at least one of irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure, and the "determining the numerical weather forecast result of the meteorological parameter in the time period to be predicted" may include: and determining the numerical weather forecast result of at least one meteorological parameter of irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure in the time period to be predicted.

Optionally, in another possible design, after the "determining the result of the numerical weather forecast of the weather parameter in the time period to be predicted" is performed, the method may further include: and determining the predicted photovoltaic power generation power within the time period to be predicted according to the numerical weather forecast result of the meteorological parameters.

In a second aspect, the present application provides a device for determining a result of a numerical weather forecast, comprising: the device comprises an acquisition module and a determination module;

the acquisition module is used for acquiring an actually measured data sequence and a historical prediction data set of the meteorological parameters in a preset historical time period; the historical prediction data set comprises N historical prediction data sequences obtained from N data sources, wherein N is a positive integer;

the determining module is used for determining a target data sequence and other data sequences from the N historical prediction data sequences according to the similarity degree parameter between the historical prediction data sequence and the actually measured data sequence acquired by the acquiring module;

the determining module is further used for determining the dynamic weights of the N data sources based on the deviation degree parameters of the other data sequences and the target data sequence;

the determining module is further used for determining a numerical weather forecast result of the meteorological parameters in the time period to be predicted according to the current prediction data set and the dynamic weight of the meteorological parameters in the time period to be predicted; the current prediction data set includes N current prediction data sequences obtained from N data sources.

Optionally, in a possible design manner, the determining module is specifically configured to:

acquiring initial weights of N data sources; determining the dynamic weight of the data source corresponding to the first data sequence according to the initial weight of the data source corresponding to the first data sequence and the deviation degree parameter of the first data sequence and the target data sequence; the first data sequence is any data sequence among other data sequences.

Optionally, in another possible design manner, the determining module is further specifically configured to:

determining a total deviation degree parameter according to the deviation degree parameter of each data sequence in other data sequences and the target data sequence; and determining the dynamic weight of the data source corresponding to the target data sequence according to the initial weight and the total deviation degree parameter of the data source corresponding to the target data sequence.

Optionally, in another possible design, the device for determining a numerical weather forecast result provided by the present application may further include an updating module and an adjusting module;

the updating module is used for updating the initial weight of the N data sources according to the dynamic weight of the N data sources after the determining module determines the numerical weather forecast result of the weather parameters in the time period to be predicted;

and the adjusting module is used for readjusting the dynamic weights of the N data sources according to the initial weights of the N data sources, the numerical weather forecast results and the N current predicted data sequences updated by the updating module.

Optionally, in another possible design manner, the determining module is further configured to determine a deviation degree parameter according to a relative difference between each first similarity degree parameter and each second similarity degree parameter before determining the dynamic weights of the N data sources based on the deviation degree parameters of the other data sequences and the target data sequence; each first similarity parameter is a similarity parameter between each data sequence in other data sequences and the measured data sequence, and the second similarity parameter is a similarity parameter between the target data sequence and the measured data sequence.

Optionally, in another possible design manner, the similarity parameter may be a goodness of fit, and the determining module is further specifically configured to: determining an average value of all data in the first historical prediction data sequence; determining the goodness of fit of the first historical predicted data sequence and the actually measured data sequence according to the difference between the corresponding data of the first historical predicted data sequence and the actually measured data sequence and the difference between each data of the actually measured data sequence and the average value; the first historical predicted data sequence is any one of the N historical predicted data sequences;

the determining module is further specifically configured to: and determining a sequence with the highest goodness of fit with the measured data sequence in the N historical predicted data sequences as a target data sequence, and determining data sequences except the target data sequence in the N historical predicted data sequences as other data sequences.

Optionally, in another possible design, the meteorological parameter may include at least one of irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure;

the determining module is used for determining the numerical weather forecast result of at least one meteorological parameter of irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure in the time period to be predicted.

Optionally, in another possible design, the determining module is further configured to determine, according to a numerical weather forecast result of the meteorological parameter, the predicted photovoltaic power generation power within the time period to be predicted.

In a third aspect, the present application provides a device for determining a result of a numerical weather forecast, comprising a memory, a processor, a bus and a communication interface; the memory is used for storing computer execution instructions, and the processor is connected with the memory through a bus; when the determination means of the numeric weather forecast result is operated, the processor executes the computer-executable instructions stored in the memory to cause the determination means of the numeric weather forecast result to perform the determination method of the numeric weather forecast result as provided in the above first aspect.

Optionally, the apparatus for determining a result of a numerical weather forecast may further include a transceiver, and the transceiver is configured to perform the steps of transceiving data, signaling or information under the control of the processor of the apparatus for determining a result of a numerical weather forecast, for example, acquiring a measured data sequence and a historical predicted data set of the weather parameters in a preset historical time period.

Further alternatively, the determination device for the numerical weather forecast result may be a physical machine for determining the numerical weather forecast result, or may be a part of the physical machine, for example, a system on a chip in the physical machine. The system-on-chip is adapted to support the determining means of the numeric weather forecast result to perform the functions referred to in the first aspect, such as receiving, sending or processing data and/or information referred to in the determining method of the numeric weather forecast result. The chip system includes a chip and may also include other discrete devices or circuit structures.

In a fourth aspect, the present application provides a computer-readable storage medium having instructions stored therein, which when executed by a computer, cause the computer to perform the method for determining a result of a numerical weather forecast as provided in the first aspect.

In a fifth aspect, the present application provides a computer program product comprising computer instructions which, when run on a computer, cause the computer to perform the method of determining a numerical weather forecast result as provided in the first aspect.

It should be noted that all or part of the computer instructions may be stored on the computer readable storage medium. The computer-readable storage medium may be packaged with the processor of the device for determining a numerical weather forecast result, or may be packaged separately from the processor of the device for determining a numerical weather forecast result, which is not limited in this application.

For the descriptions of the second, third, fourth and fifth aspects in this application, reference may be made to the detailed description of the first aspect; in addition, for the beneficial effects described in the second aspect, the third aspect, the fourth aspect and the fifth aspect, reference may be made to beneficial effect analysis of the first aspect, and details are not repeated here.

In the present application, the names of the above-mentioned determining means of the numerical weather forecast result do not limit the devices or the function modules themselves, and in actual implementation, the devices or the function modules may appear by other names. Insofar as the functions of the respective devices or functional modules are similar to those of the present application, they fall within the scope of the claims of the present application and their equivalents.

These and other aspects of the present application will be more readily apparent from the following description.

Drawings

Fig. 1 is a schematic flowchart of a method for determining a numerical weather forecast result according to an embodiment of the present disclosure;

fig. 2 is a schematic flowchart of another method for determining a numerical weather forecast result according to an embodiment of the present disclosure;

fig. 3 is a schematic flowchart of another method for determining a numerical weather forecast result according to an embodiment of the present application;

fig. 4 is a schematic flowchart of another method for determining a numerical weather forecast result according to an embodiment of the present application;

fig. 5 is a schematic flowchart of another method for determining a numerical weather forecast result according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a device for determining a numerical weather forecast result according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of another apparatus for determining a result of a numerical weather forecast according to an embodiment of the present application.

Detailed Description

The following describes in detail a method and an apparatus for determining a numerical weather forecast result according to an embodiment of the present application with reference to the drawings.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.

The terms "first" and "second" and the like in the description and drawings of the present application are used for distinguishing different objects or for distinguishing different processes for the same object, and are not used for describing a specific order of the objects.

Furthermore, the terms "including" and "having," and any variations thereof, as referred to in the description of the present application, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.

In the description of the present application, the meaning of "a plurality" means two or more unless otherwise specified.

At present, the photovoltaic power generation power can be generally predicted according to a multi-source numerical weather forecast result and the operation parameters of a photovoltaic power station. Therefore, the accuracy of the prediction result of the photovoltaic power generation power is closely related to the accuracy of the numerical weather forecast result. However, the quality of the numerical weather forecast results obtained from different data sources is uneven, and the numerical weather forecast result obtained from one data source may have a larger error than the numerical weather forecast results obtained from other data sources. Therefore, how to process the multi-source numerical weather forecast result to obtain a more accurate numerical weather forecast result becomes an urgent problem to be solved.

In view of the problems in the prior art, the embodiments of the present application provide a method for determining a result of a numerical weather forecast, and the method can determine a dynamic weight representing the accuracy of data of each data source by comparing a historical predicted data sequence with an actually measured data sequence. The numerical weather forecast result is determined based on the dynamic weight, so that the influence of errors of data acquired from each data source on the numerical weather forecast result can be reduced, and a more accurate numerical weather forecast result can be determined.

The method for determining the numerical weather forecast result provided by the embodiment of the application can be applied to a device for determining the numerical weather forecast result, and the device for determining the numerical weather forecast result can be a physical machine (such as a server) or a Virtual Machine (VM) deployed on the physical machine.

The following describes in detail a method for determining a numerical weather forecast result provided in the embodiment of the present application.

Referring to fig. 1, a method for determining a numerical weather forecast result provided in the embodiment of the present application includes S101 to S104:

s101, acquiring an actually measured data sequence and a historical prediction data set of the meteorological parameters in a preset historical time period.

The preset history period may be a period determined in advance by a human, and for example, the preset history period may be the past 24 hours.

The historical predicted data set may include N historical predicted data sequences obtained from N data sources, N being a positive integer. Each historical prediction data sequence may include a plurality of historical prediction data, the plurality of historical prediction data may be historical prediction data acquired according to a preset sampling period, for example, one historical prediction data may be acquired every 15 minutes, and then the acquired historical prediction data are arranged according to an acquisition time sequence to obtain a historical prediction data sequence.

Illustratively, the historical prediction data set may be represented as { X }_i，1，X_i，2，...，X_i，n，...，X_i，N}. Wherein, the historical prediction data set comprises N historical prediction data sequences, X_i，nThe nth historical predicted data sequence in the historical predicted data set is represented, namely n represents the number of the data source. With X_i，nFor example, X_i，n＝{x_1，n，x_2，n，...，x_M，nAnd M represents the total data number (namely, the sampling point number) in each historical prediction data sequence, and i represents the ith data in the M data.

The N data sources may be providers of N numerical weather forecast results, that is, N historical prediction data sequences may be obtained from background servers of different vendors.

The measured data sequence may be a data sequence actually measured over a preset historical period of time. In a possible implementation mode, the photovoltaic power station is generally provided with various meteorological sensors, and the measurement data of the meteorological sensors can be directly obtained from the intranet server to obtain an actually measured data sequence. Similarly, the measured data sequence may include a plurality of measured data, the plurality of measured data may be measured data collected according to a preset sampling period, and the sampling period for collecting the measured data may be the same as the sampling period for collecting the historical predicted data. For example, one measured data may be acquired every 15 minutes, and then the acquired measured data may be arranged according to the sequence of the acquisition time to obtain a measured data sequence.

Illustratively, the measured data sequence may be represented as X_i＝{x₁，x₂，...，x_M}. Where M represents the total data number (i.e., the number of sampling points) in the measured data sequence, and i represents the ith data in the M data.

Optionally, if the measured data sequence cannot be obtained from the intranet server of the current photovoltaic power station (for example, the current photovoltaic power station is not provided with a meteorological sensor), the measured data sequence may be obtained from servers of other photovoltaic power stations or meteorological stations closest to the photovoltaic power station.

And S102, determining a target data sequence and other data sequences from the N historical predicted data sequences according to the similarity parameters of the historical predicted data sequences and the measured data sequences.

Wherein, the similarity parameter is used for representing the closeness degree of the historical prediction data sequence and the measured data sequence, and can be comparedAnd obtaining corresponding data in the historical prediction data sequence and the actually measured data sequence, wherein the corresponding data is the data obtained in the same sampling period. Illustratively, the nth historical prediction data sequence X is_i，n＝{x_1，n，x_2，n，...，x_M，nAnd the measured data sequence X_i＝{x₁，x₂，...，x_MWhen comparing, x can be compared_1，nAnd x₁Comparing and comparing x_2，nAnd x₂Carrying out comparison, and sequentially comparing until x is compared_M，nAnd x_MComparing, and determining X according to the comparison result of all data_i，nAnd X_iThe degree of similarity parameter.

Optionally, in the embodiment of the present application, the goodness of fit may be used as the similarity degree parameter. Taking any one of the N historical predicted data sequences (referred to as a first historical predicted data sequence in the description of the embodiment of the present application) as an example, an average value of all data in the first historical predicted data sequence may be determined, and then a goodness of fit between the first historical predicted data sequence and the measured data sequence may be determined according to a difference between corresponding data of the first historical predicted data sequence and the measured data sequence and a difference between each data of the measured data sequence and the average value; then, the historical predicted data sequence with the highest goodness of fit with the measured data sequence in the N historical predicted data sequences may be determined as the target data sequence, and the data sequences other than the target data sequence in the N historical predicted data sequences may be determined as other data sequences.

Illustratively, data sequence X is predicted with the nth history_i，n＝{x_1，n，x_2，n，...，x_M，nFor example, can be for X_i，nAveraging the data of each sampling point to obtain an average value

The measured data sequence X can then be determined_iEach data and mean value in

The sum of squares of the differences between

And, the nth historical predicted data sequence X can be determined_i，nWith measured data sequence X_iIs calculated by the sum of squares of the differences between corresponding data of

Thereafter, can be combined

And

and determining the goodness of fit of the first historical predicted data sequence and the measured data sequence. For example, X can be determined by expression (1)_i，nWith measured data sequence X_iGoodness of fit of

Similarly, a goodness-of-fit of each historical predicted data sequence in the set of historical predicted data to the measured data sequence may be determined. Illustratively, if the data sequence X is predicted historically_i，pGoodness of fit to measured data sequences

Highest, then the history can be predicted to data sequence X_i，pDetermining the data sequence as a target data sequence, and dividing X in the N historical prediction data sequences_i，pThe outer data sequences are determined to be the other data sequences. Where p represents the number of the data source with the highest goodness of fit.

S103, determining the dynamic weight of the N data sources based on the deviation degree parameter of the other data sequences and the target data sequence.

Because the target data sequence is determined by analyzing the similarity degree parameters of the N historical predicted data sequences and the actually measured data sequence, the approach degree of each historical predicted data sequence and the actually measured data sequence can be represented based on the dynamic weights of the N data sources determined by the deviation degree parameters of other data sequences and the target data sequence. It can be seen that, in the embodiment of the present application, dynamic weights are assigned to N data sources by comparing the closeness degrees of the historical predicted data sequences obtained from N data sources and the actually measured data sequences, so that a higher dynamic weight can be assigned to a data source corresponding to a historical predicted data sequence with a higher closeness degree of an actually measured data sequence, and a lower dynamic weight can be assigned to a data source corresponding to a historical predicted data sequence with a lower closeness degree of an actually measured data sequence. Therefore, when the numerical weather forecast result of the current prediction data sequence is determined according to the dynamic weight, the method and the device for predicting the numerical weather forecast result can reduce the influence of errors of data acquired at each data source on the numerical weather forecast result, and obtain a more accurate numerical weather forecast result.

Optionally, before determining the dynamic weights of the N data sources based on the deviation degree parameter between the other data sequences and the target data sequence, the method for determining the result of the numerical weather forecast provided in the embodiment of the present application may further include: and determining a deviation degree parameter according to the relative difference value of each first similarity degree parameter and each second similarity degree parameter.

The first similarity degree parameter is a similarity degree parameter between each data sequence in other data sequences and the actually measured data sequence, and the second similarity degree parameter is a similarity degree parameter between the target data sequence and the actually measured data sequence.

Taking the similarity degree parameter as the goodness of fit, if used

Indicating the goodness of fit of any one of the other data sequences to the measured data sequence

Representing the goodness of fit of the target data sequence and the measured data sequence, the deviation degree parameter of other data sequences and the target data sequence can be determined by the relative difference value epsilon_nIndicates, illustratively, the relative difference e_nIt can be determined from expression (2):

optionally, when determining the dynamic weights of the N data sources, the initial weights of the N data sources may be obtained first; the dynamic weight of the data source corresponding to the first data sequence can then be determined according to the initial weight of the data source corresponding to the first data sequence and the parameter of the degree of deviation of the first data sequence from the target data sequence. The first data sequence is any data sequence in other data sequences.

In one possible implementation, the initial weights of the N data sources may be the same, and the initial weight w_nIt can be determined from expression (3):

exemplary, if w'_nRepresenting a dynamic weight, e, of a data source to which the first data sequence corresponds_nRepresenting the deviation degree parameter of the first data sequence and the target data sequence, w 'can be determined according to expression (4)'_n：

Optionally, when determining the dynamic weight of the data source corresponding to the target data sequence, a total deviation degree parameter may be determined according to a deviation degree parameter between each data sequence in the other data sequences and the target data sequence; then, the dynamic weight of the data source corresponding to the target data sequence can be determined according to the initial weight and the total deviation degree parameter of the data source corresponding to the target data sequence.

Illustratively, the total deviation parameter may be

In this case, m represents the number of each of the other data sequences, and N-1 represents the total number of the other data sequences. The total parameter of the degree of deviation can be determined according to expression (5):

wherein the content of the first and second substances,

indicating the goodness of fit of the mth other data sequence to the measured data sequence,

indicating the goodness of fit of the target data sequence to the measured data sequence.

After the total deviation degree parameter is determined, the dynamic weight w 'of the data source corresponding to the target data sequence can be determined according to the expression (6)'_n：

And S104, determining the numerical weather forecast result of the meteorological parameters in the time period to be predicted according to the current prediction data set and the dynamic weight of the meteorological parameters in the time period to be predicted.

Wherein the current prediction data set comprises N current prediction data sequences obtained from N data sources. The time period to be predicted may be a time period after the current time determined in advance by human.

After the dynamic weight is determined, if a numerical weather forecast result of the weather parameters in the time period to be predicted needs to be determined, the numerical weather forecast result can be obtained from N data sourcesN current predicted data sequences are then determined based on the N current predicted data sequences and the dynamic weights. It is understood that the numerical weather forecast result is also a data sequence, and for example, the data sequence X 'corresponding to the numerical weather forecast result of the weather parameter in the time period to be predicted can be determined according to expression (7)'_j：

Wherein, X_j，n＝{x_1，n，x_2，n，...，x_Y，n}，X_j，nThe nth data sequence in the N current predicted data sequences is represented, that is, N represents the number of the data source, Y represents the total data number (that is, the number of sampling points) in each current predicted data sequence, and j represents the jth data in the Y data sequences.

Optionally, the meteorological parameters may include at least one of irradiance, wind speed, wind direction, humidity, rainfall and barometric pressure. It is understood that, in practical applications, the meteorological parameters may also include other parameters, such as wind power level, and the like, which are not limited in the embodiments of the present application. Taking the meteorological parameters including irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure as an example, the numerical weather forecast results of irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure in the time period to be forecasted can be respectively determined according to the mode of determining the numerical weather forecast results.

The method for determining the numerical weather forecast result provided by the embodiment of the application can be applied to a scene for predicting the photovoltaic power generation power. Optionally, after the numerical weather forecast result of the meteorological parameter is determined, the predicted photovoltaic power generation power within the time period to be predicted can be determined according to the numerical weather forecast result of the meteorological parameter.

For example, the predicted photovoltaic power generation power in the time period to be predicted can be determined according to numerical weather forecast results of irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure. The method for predicting the photovoltaic power generation power is determined according to the numerical weather forecast result, and reference may be made to related descriptions in the prior art, which is not repeated herein in the embodiments of the present application.

Optionally, after determining a numerical weather forecast result of the weather parameter in the time period to be predicted, the embodiment of the application may further update the initial weights of the N data sources according to the dynamic weights of the N data sources; and then, the dynamic weights of the N data sources can be readjusted according to the updated initial weights of the N data sources, the numerical weather forecast result and the N current predicted data sequences.

After determining the numerical weather forecast result of the weather parameters in the time period to be predicted, the dynamic weight may be re-adjusted according to the prediction result, that is, the dynamic weight determined in the embodiment of the present application is not a fixed value but a variable. Therefore, the determined numerical weather forecast result is more accurate along with the increase of the prediction times, so that the accuracy of the prediction result of the photovoltaic power generation power can be further improved.

In the technical scheme provided by the embodiment of the application, by comparing N historical predicted data sequences obtained from N data sources with measured data sequences of corresponding historical time periods (namely, preset historical time periods in the application), a target data sequence with a higher degree of proximity to the measured data sequences is determined according to the degree of proximity of the N historical predicted data sequences and the measured data sequences (namely, similarity parameters in the application). Then, based on the target data sequence, dynamic weights may be assigned to the N data sources according to the deviation degree parameter between the other data sequences and the target data sequence. Because the target data sequence is a data sequence with higher proximity to the measured data sequence, and the dynamic weight is determined according to the deviation degree parameter of other data sequences and the target data sequence, the dynamic weight can represent the proximity of each historical predicted data sequence and the measured data sequence. Therefore, the dynamic weights of the N data sources determined in the embodiment of the present application can represent the accuracy of the data of the N data sources. The N current prediction data sequences acquired from the N data sources are weighted based on the dynamic weight to determine a numerical weather forecast result, so that the influence of errors of data acquired from the data sources on the numerical weather forecast result can be reduced. Therefore, the method and the device for predicting the photovoltaic power generation power can determine a more accurate numerical weather forecast result, and accuracy of a prediction result of the photovoltaic power generation power is improved.

In addition, the actually measured photovoltaic power generation power is not only influenced by the numerical weather forecast result, but also influenced by other factors such as power grid power limitation, equipment failure, operation and maintenance, dust accumulation, shadow loss and the like. Therefore, when the dynamic weight is determined, the dynamic weight is obtained by comparing the N historical predicted data sequences and the measured data sequences obtained from the N data sources, instead of comparing the photovoltaic power generation power predicted according to the N historical predicted data sequences and the measured photovoltaic power generation power. Therefore, the interference of other non-meteorological factors on the determined dynamic weight result can be avoided, and the determined dynamic weight is more reasonable.

In summary of the above description, as shown in fig. 2, step S103 in fig. 1 may be replaced with S1031-S1034:

and S1031, obtaining the initial weights of the N data sources.

S1032, determining the dynamic weight of the data source corresponding to the first data sequence according to the initial weight of the data source corresponding to the first data sequence and the deviation degree parameter of the first data sequence and the target data sequence.

And S1033, determining a total deviation degree parameter according to the deviation degree parameter of each data sequence in other data sequences and the target data sequence.

S1034, determining the dynamic weight of the data source corresponding to the target data sequence according to the initial weight and the total deviation degree parameter of the data source corresponding to the target data sequence.

It is to be understood that, in the embodiment of the present application, the sequence of step S1033 and step S1032 is not limited, and the sequence of step S1034 and step S1032 is not limited, and step S1033 and step S1034 may be performed before step S1032, or may be performed after step S1032, as long as step S1034 is performed after step S1033.

Optionally, as shown in fig. 3, after step S104 in fig. 1, the method for determining a numerical weather forecast result according to the embodiment of the present application may further include S105 to S106:

and S105, updating the initial weight of the N data sources according to the dynamic weight of the N data sources.

And S106, readjusting the dynamic weights of the N data sources according to the updated initial weights of the N data sources, the numerical weather forecast result and the N current prediction data sequences.

Alternatively, as shown in fig. 4, step S102 in fig. 1 may be replaced with S1021-S1023:

and S1021, determining the average value of all data in the first historical prediction data sequence.

And S1022, determining the goodness of fit of the first historical predicted data sequence and the actually measured data sequence according to the difference value between the corresponding data of the first historical predicted data sequence and the actually measured data sequence and the difference value between each data of the actually measured data sequence and the average value.

And S1023, after the goodness of fit between each historical predicted data sequence and the actually measured data sequence is determined, determining the historical predicted data sequence with the highest goodness of fit with the actually measured data sequence as a target data sequence, and determining the data sequences except the target data sequence in the N historical predicted data sequences as other data sequences.

Optionally, as shown in fig. 5, an embodiment of the present application further provides a method for determining a result of a numerical weather forecast, including S501-S505:

s501, respectively obtaining an actually measured data sequence and a historical prediction data set of irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure in a preset historical time period.

S502, according to the similarity degree parameters of the historical prediction data sequence and the actually measured data sequence, determining a target data sequence and other data sequences from N historical prediction data sequences corresponding to irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure respectively.

And S503, respectively determining the dynamic weights of the N data sources of the irradiation, the wind speed, the wind direction, the humidity, the rainfall and the atmospheric pressure based on the deviation degree parameters of the other data sequences and the target data sequence.

S504, according to the current prediction data set and the dynamic weight of the meteorological parameters in the time period to be predicted, numerical weather forecast results of irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure in the time period to be predicted are respectively determined.

And S505, determining the predicted photovoltaic power generation power in the time period to be predicted according to numerical weather forecast results of irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure.

As shown in fig. 6, an embodiment of the present application further provides a device for determining a numerical weather forecast result, where the device for determining a numerical weather forecast result may include: an acquisition module 11 and a determination module 12.

The obtaining module 11 executes S101 in the above method embodiment, and the determining module 12 executes S102, S103, and S104 in the above method embodiment.

Specifically, the obtaining module 11 is configured to obtain an actually measured data sequence and a historical prediction data set of the meteorological parameters in a preset historical time period; the historical prediction data set comprises N historical prediction data sequences obtained from N data sources, wherein N is a positive integer;

a determining module 12, configured to determine a target data sequence and other data sequences from the N historical predicted data sequences according to a similarity parameter between the historical predicted data sequence acquired by the acquiring module 11 and the actually measured data sequence;

the determining module 12 is further configured to determine dynamic weights of the N data sources based on a deviation degree parameter of the other data sequences from the target data sequence;

the determining module 12 is further configured to determine a numerical weather forecast result of the meteorological parameters in the time period to be predicted according to the current prediction data set and the dynamic weight of the meteorological parameters in the time period to be predicted; the current prediction data set includes N current prediction data sequences obtained from N data sources.

Optionally, in a possible design, the determining module 12 is specifically configured to:

Optionally, in another possible design, the determining module 12 is further specifically configured to:

the updating module is used for updating the initial weights of the N data sources according to the dynamic weights of the N data sources after the determining module 12 determines the numerical weather forecast result of the weather parameters in the time period to be predicted;

Optionally, in another possible design manner, the determining module 12 is further configured to determine a deviation degree parameter according to a relative difference between each first similarity degree parameter and each second similarity degree parameter before determining the dynamic weights of the N data sources based on the deviation degree parameters of the other data sequences and the target data sequence; each first similarity parameter is a similarity parameter between each data sequence in other data sequences and the measured data sequence, and the second similarity parameter is a similarity parameter between the target data sequence and the measured data sequence.

Optionally, in another possible design manner, the similarity parameter may be a goodness of fit, and the determining module 12 is further specifically configured to: determining an average value of all data in the first historical prediction data sequence; determining the goodness of fit of the first historical predicted data sequence and the actually measured data sequence according to the difference between the corresponding data of the first historical predicted data sequence and the actually measured data sequence and the difference between each data of the actually measured data sequence and the average value; the first historical predicted data sequence is any one of the N historical predicted data sequences;

the determining module 12 is further specifically configured to: and determining a sequence with the highest goodness of fit with the measured data sequence in the N historical predicted data sequences as a target data sequence, and determining data sequences except the target data sequence in the N historical predicted data sequences as other data sequences.

Optionally, in another possible design, the meteorological parameter may include at least one of irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure; the determining module 12 is configured to determine a numerical weather forecast result of at least one weather parameter of irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure in a time period to be predicted.

Optionally, in another possible design, the determining module 12 is further configured to determine the predicted photovoltaic power generation power within the time period to be predicted according to a numerical weather forecast result of at least one weather parameter.

Optionally, the device for determining a numerical weather forecast result may further include a storage module, where the storage module is configured to store a program code of the device for determining a numerical weather forecast result, and the like.

As shown in fig. 7, the embodiment of the present application further provides a device for determining the result of the numerical weather forecast, which includes a memory 41, processors 42(42-1 and 42-2), a bus 43 and a communication interface 44; the memory 41 is used for storing computer execution instructions, and the processor 42 is connected with the memory 41 through a bus 43; when the determination device of the numeric weather forecast result operates, the processor 42 executes computer-executable instructions stored in the memory 41 to cause the determination device of the numeric weather forecast result to perform the determination method of the numeric weather forecast result as provided in the above-described embodiment.

In particular implementations, processor 42 may include one or more Central Processing Units (CPUs), such as CPU0 and CPU1 shown in FIG. 7, as one embodiment. And as an example, the means for determining the numerical weather forecast result may include a plurality of processors 42, such as processor 42-1 and processor 42-2 shown in fig. 7. Each of the processors 42 may be a single-Core Processor (CPU) or a multi-Core Processor (CPU). Processor 42 may refer herein to one or more devices, circuits, and/or processing cores that process data (e.g., computer program instructions).

The memory 41 may be, but is not limited to, a read-only memory 41 (ROM) or other type of static storage device that can store static information and instructions, a Random Access Memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory 41 may be self-contained and coupled to the processor 42 via a bus 43. The memory 41 may also be integrated with the processor 42.

In a specific implementation, the memory 41 is used for storing data in the present application and computer-executable instructions corresponding to software programs for executing the present application. The processor 42 may perform various functions of the determination means by running or executing software programs stored in the memory 41, and calling data stored in the memory 41, the numerical weather forecast result.

The communication interface 44 is any device, such as a transceiver, for communicating with other devices or communication networks, such as a control system, a Radio Access Network (RAN), a Wireless Local Area Network (WLAN), and the like. The communication interface 44 may include a receiving unit implementing a receiving function and a transmitting unit implementing a transmitting function.

The bus 43 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an extended ISA (enhanced industry standard architecture) bus, or the like. The bus 43 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 7, but this is not intended to represent only one bus or type of bus.

As an example, in conjunction with fig. 6, the acquiring module in the device for determining a numeric weather forecast result implements the same function as that implemented by the receiving unit in fig. 7, the determining module in the device for determining a numeric weather forecast result implements the same function as that implemented by the processor in fig. 7, and the storing module in the device for determining a numeric weather forecast result implements the same function as that implemented by the memory in fig. 7.

For the explanation of the related contents in this embodiment, reference may be made to the above method embodiments, which are not described herein again.

Through the above description of the embodiments, it is clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device may be divided into different functional modules to complete all or part of the above described functions. For the specific working processes of the system, the apparatus and the unit described above, reference may be made to the corresponding processes in the foregoing method embodiments, and details are not described here again.

The embodiment of the present application further provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are executed by a computer, the computer is enabled to execute the method for determining the result of the numerical weather forecast provided in the foregoing embodiment.

The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM), a register, a hard disk, an optical fiber, a CD-ROM, an optical storage device, a magnetic storage device, any suitable combination of the foregoing, or any other form of computer readable storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuit (ASIC). In embodiments of the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The above description is only an embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for determining a result of a numerical weather forecast, comprising:

acquiring an actually measured data sequence and a historical prediction data set of meteorological parameters in a preset historical time period; the historical prediction data set comprises N historical prediction data sequences obtained from N data sources, wherein N is a positive integer;

determining a target data sequence and other data sequences from the N historical predicted data sequences according to the similarity degree parameter of the historical predicted data sequences and the actually measured data sequences;

determining dynamic weights of the N data sources based on deviation degree parameters of the other data sequences and the target data sequence;

determining a numerical weather forecast result of the meteorological parameters in the time period to be predicted according to the current prediction data set of the meteorological parameters in the time period to be predicted and the dynamic weight; the current prediction data set includes N current prediction data sequences obtained from the N data sources.

2. The method for determining the result of numerical weather forecast of claim 1, wherein said determining the dynamic weight of said N data sources based on the parameter of the degree of deviation of said other data sequences from said target data sequence comprises:

acquiring initial weights of the N data sources;

determining the dynamic weight of the data source corresponding to the first data sequence according to the initial weight of the data source corresponding to the first data sequence and the deviation degree parameter of the first data sequence and the target data sequence; the first data sequence is any data sequence in the other data sequences.

3. The method of determining a numerical weather forecast result according to claim 2, wherein said determining the dynamic weight of said N data sources based on the parameter of the degree of deviation of said other data series from said target data series further comprises:

determining a total deviation degree parameter according to the deviation degree parameter of each data sequence in the other data sequences and the target data sequence;

and determining the dynamic weight of the data source corresponding to the target data sequence according to the initial weight of the data source corresponding to the target data sequence and the total deviation degree parameter.

4. The method for determining the numerical weather forecast result according to claim 2, wherein after said determining the numerical weather forecast result of said weather parameter in said time period to be predicted, said method further comprises:

updating the initial weights of the N data sources according to the dynamic weights of the N data sources;

and readjusting the dynamic weights of the N data sources according to the updated initial weights of the N data sources, the numerical weather forecast result and the N current predicted data sequences.

5. The method of determining numerical weather forecast results of claim 1, wherein before said determining dynamic weights for said N data sources based on a parameter of degree of deviation of said other data sequences from said target data sequence, said method further comprises:

determining the deviation degree parameter according to the relative difference value of each first similarity degree parameter and each second similarity degree parameter; each first similarity parameter is a similarity parameter between each of the other data sequences and the measured data sequence, and the second similarity parameter is a similarity parameter between the target data sequence and the measured data sequence.

6. The method of determining numerical weather forecast result according to claim 1, wherein said similarity parameter is goodness-of-fit;

the parameter of the similarity degree between the historical prediction data sequence and the measured data sequence comprises: determining an average value of all data in the first historical prediction data sequence; determining a goodness-of-fit of the first historical predicted data sequence and the measured data sequence according to a difference between corresponding data of the first historical predicted data sequence and the measured data sequence and a difference between each data of the measured data sequence and the average value; the first historical predicted data sequence is any one of the N historical predicted data sequences;

the determining a target data sequence and other data sequences from the N historical predicted data sequences comprises: and determining a sequence with the highest goodness of fit with the measured data sequence in the N historical predicted data sequences as the target data sequence, and determining data sequences except the target data sequence in the N historical predicted data sequences as the other data sequences.

7. The method of determining numerical weather forecast result according to claim 1, wherein said meteorological parameters include at least one of irradiation, wind speed, wind direction, humidity, rainfall and atmospheric pressure,

the determining the numerical weather forecast result of the weather parameters in the time period to be predicted includes: and determining a numerical weather forecast result of at least one meteorological parameter of the irradiation, the wind speed, the wind direction, the humidity, the rainfall and the atmospheric pressure in the time period to be predicted.

8. The method for determining the result of a numerical weather forecast according to any one of claims 1-7, wherein after determining the result of a numerical weather forecast for said weather parameter during said time period to be predicted, the method further comprises:

and determining the predicted photovoltaic power generation power in the time period to be predicted according to the numerical weather forecast result of the meteorological parameters.

9. An apparatus for determining a result of a numerical weather forecast, comprising:

the determining module is used for determining a target data sequence and other data sequences from the N historical predicted data sequences according to the similarity degree parameter between the historical predicted data sequence and the actually measured data sequence acquired by the acquiring module;

the determining module is further configured to determine dynamic weights of the N data sources based on a deviation degree parameter of the other data sequences from the target data sequence;

the determining module is further configured to determine a numerical weather forecast result of the meteorological parameters in the time period to be predicted according to the current prediction data set of the meteorological parameters in the time period to be predicted and the dynamic weight; the current prediction data set includes N current prediction data sequences obtained from the N data sources.

10. A device for determining the result of numerical weather forecast is characterized by comprising a memory, a processor, a bus and a communication interface; the memory is used for storing computer execution instructions, and the processor is connected with the memory through the bus;

when the device for determining the numerical weather forecast result is operated, the processor executes the computer-executable instructions stored in the memory to cause the device for determining the numerical weather forecast result to perform the method for determining the numerical weather forecast result according to any one of claims 1 to 8.