Method, device, equipment and storage medium for solving future prediction errors of wind and solar resources

Abstract

The present invention discloses a method, device, equipment and storage medium for solving future prediction errors of wind and solar resources. The method comprises: based on a wind and solar prediction error regression model, according to historical wind and solar output data, respectively obtaining the absolute average values ​​of historical wind power and photovoltaic installed capacity proportions and historical wind and solar prediction error per unit values ​​in the daytime and nighttime periods of each season in a preset historical period, and then performing parameter regression fitting to obtain the wind power and photovoltaic installed capacity influence factors in the daytime and nighttime periods of each season; then obtaining the future prediction error values ​​in the daytime and nighttime periods of each season in a preset future period according to the preset future wind and solar output data and the wind power and photovoltaic installed capacity influence factors; when solving the future prediction error values ​​of wind and solar resources, the present invention takes into account the seasonal differences and day and night differences of wind and solar resources, as well as the influence of the number of wind power installed capacity and the number of photovoltaic installed capacity on the prediction error of wind and solar resources, so as to obtain accurate future prediction error values.

Description

Technical Field

[0001] The present invention relates to the field of renewable energy power generation technology, and in particular to a method, device, equipment and storage medium for solving future prediction errors of wind and solar resources. Background Art

[0002] The prediction error of new energy has an important impact on the operation of the power grid. As new energy resources, wind power resources and photovoltaic resources are collectively referred to as wind and solar resources. Their own randomness and volatility increase the difficulty of solving the future prediction error of wind and solar resources. The existing methods for solving the future prediction error of wind and solar resources usually do not take into account the distribution differences of wind and solar resources in different time periods, as well as the impact of wind power installed capacity and photovoltaic installed capacity on the prediction error of wind and solar resources, resulting in poor accuracy of the prediction error, which is difficult to provide reference for power grid dispatching. Summary of the invention

[0003] The present invention provides a method, device, equipment and storage medium for solving the future prediction error of wind and solar resources to solve the problem of poor accuracy in solving the future prediction error of wind and solar resources in the prior art. When fitting and solving the future prediction error of wind and solar resources, the seasonal differences and day and night differences of wind and solar resources, as well as the influence of the number of wind power installed capacity and the number of photovoltaic installed capacity on the wind and solar resource prediction error are fully considered, so as to obtain an accurate future prediction error value, so that a reference can be provided for power grid scheduling based on the future prediction error value.

[0004] In order to solve the above technical problems, a first aspect of an embodiment of the present invention provides a method for solving future prediction errors of wind and solar resources, comprising:

[0005] Based on the pre-acquired wind and solar forecast error regression model, according to the pre-acquired historical wind and solar output data, the historical wind power installed capacity ratio, the historical photovoltaic installed capacity ratio and the absolute average value of the historical wind and solar forecast error per unit value in the daytime and nighttime periods of each season in the preset historical period are obtained respectively;

[0006] Based on the wind-solar forecast error regression model, parameter regression fitting is performed according to the absolute average values ​​of the historical wind power installed capacity ratio, the historical photovoltaic installed capacity ratio and the historical wind-solar forecast error per unit value in the daytime and nighttime periods of each season in the preset historical period, to obtain the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor in the daytime and nighttime periods of each season;

[0007] Based on the wind and solar forecast error regression model, according to the preset future wind and solar output data, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor, the future forecast error value of the daytime and nighttime periods of each season in the preset future period is obtained;

[0008] The historical wind and solar power output data include the historical total installed capacity of wind power, the historical total installed capacity of photovoltaic power, the historical wind power output prediction error and the historical photovoltaic output prediction error in the preset historical period;

[0009] The future wind and solar power output data includes the future total wind power installed capacity and the future total photovoltaic installed capacity in the preset future period.

[0010] Preferably, the method specifically obtains the wind-solar forecast error regression model in advance through the following steps:

[0011] The wind and solar forecast error regression model is constructed according to the following expression:

[0012]

[0013] Among them, C w is the total installed capacity of wind power, C p is the total installed capacity of photovoltaic power, X is the proportion of wind power installed capacity, Y is the proportion of photovoltaic installed capacity, P wei is the wind power output prediction error in period i, P pei is the photovoltaic output prediction error in period i, N is the total number of periods, Z is the absolute average of the per-unit values ​​of the wind and solar prediction errors in each period, a is the wind power installed capacity impact factor, b is the photovoltaic installed capacity impact factor, and c is the constant term.

[0014] Preferably, the pre-acquired wind / solar forecast error regression model is based on the pre-acquired historical wind / solar output data to obtain the historical wind power installed capacity ratio, the historical photovoltaic installed capacity ratio and the absolute average value of the historical wind / solar forecast error per unit value in the daytime and nighttime periods of each season in the preset historical period, specifically including:

[0015] Based on the pre-acquired wind and solar forecast error regression model, according to the pre-acquired historical wind and solar output data, the absolute average values ​​of the first historical wind power installed capacity ratio, the first historical photovoltaic installed capacity ratio and the first historical wind and solar forecast error per unit value in the daytime period of each season in the preset historical period are obtained;

[0016] Based on the wind and solar power prediction error regression model, according to the historical total wind power installed capacity and the historical wind power output prediction error in the preset historical period, the absolute average values ​​of the second historical wind power installed capacity ratio, the second historical photovoltaic installed capacity ratio and the second historical wind and solar power prediction error per unit value in the night period of each season in the preset historical period are obtained, wherein the second historical photovoltaic installed capacity ratio is zero.

[0017] Preferably, the wind-solar forecast error regression model is based on preset future wind-solar output data, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor to obtain the future forecast error values ​​for the daytime and nighttime periods of each season in the preset future period, specifically including:

[0018] Based on the wind-solar forecast error regression model, according to the preset future wind-solar output data, the future wind power installed capacity ratio and the future photovoltaic installed capacity ratio in the daytime and nighttime periods of each season in the preset future period are respectively obtained;

[0019] Based on the wind-solar forecast error regression model, according to the future wind power installed capacity proportion, the future photovoltaic installed capacity proportion, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor, the future forecast error values ​​for the day and night time periods of each season in the preset future time period are obtained.

[0020] A second aspect of an embodiment of the present invention provides a device for solving future prediction errors of wind and solar resources, comprising:

[0021] A data acquisition module is used to obtain the historical wind power installed capacity ratio, historical photovoltaic installed capacity ratio and absolute average value of the historical wind power forecast error per unit value in the daytime and nighttime periods of each season in a preset historical period based on a pre-acquired wind power forecast error regression model and pre-acquired historical wind power output data;

[0022] A parameter regression fitting module is used to perform parameter regression fitting based on the wind-solar forecast error regression model, and to obtain the wind power installed capacity impact factor and photovoltaic installed capacity impact factor in the daytime and nighttime periods of each season in the preset historical period according to the historical wind power installed capacity proportion, historical photovoltaic installed capacity proportion and the absolute average value of the historical wind-solar forecast error per unit value.

[0023] A future prediction error value acquisition module is used to obtain the future prediction error values ​​of the daytime and nighttime periods of each season in a preset future period based on the wind-solar prediction error regression model, according to preset future wind-solar output data, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor;

[0024] The historical wind and solar power output data include the historical total installed capacity of wind power, the historical total installed capacity of photovoltaic power, the historical wind power output prediction error and the historical photovoltaic output prediction error in the preset historical period;

[0025] The future wind and solar power output data includes the future total wind power installed capacity and the future total photovoltaic installed capacity in the preset future period.

[0026] Preferably, the device for solving the future prediction error of wind and solar resources further includes a wind and solar prediction error regression model acquisition module, which is used to:

[0027] The wind and solar forecast error regression model is constructed according to the following expression:

[0028]

[0029] Among them, C w is the total installed capacity of wind power, C p is the total installed capacity of photovoltaic power, X is the proportion of wind power installed capacity, Y is the proportion of photovoltaic installed capacity, P wei is the wind power output prediction error in period i, P pei is the photovoltaic output prediction error in period i, N is the total number of periods, Z is the absolute average of the per-unit values ​​of the wind and solar prediction errors in each period, a is the wind power installed capacity impact factor, b is the photovoltaic installed capacity impact factor, and c is the constant term.

[0030] Preferably, the data acquisition module is used to obtain the historical wind power installed capacity ratio, historical photovoltaic installed capacity ratio and absolute average value of the historical wind power forecast error per unit value in the daytime and nighttime periods of each season in the preset historical period based on the pre-acquired wind power forecast error regression model and the pre-acquired historical wind power output data, specifically including:

[0031] Based on the pre-acquired wind and solar forecast error regression model, according to the pre-acquired historical wind and solar output data, the absolute average values ​​of the first historical wind power installed capacity ratio, the first historical photovoltaic installed capacity ratio and the first historical wind and solar forecast error per unit value in the daytime period of each season in the preset historical period are obtained;

[0032] Based on the wind and solar power prediction error regression model, according to the historical total wind power installed capacity and the historical wind power output prediction error in the preset historical period, the absolute average values ​​of the second historical wind power installed capacity ratio, the second historical photovoltaic installed capacity ratio and the second historical wind and solar power prediction error per unit value in the night period of each season in the preset historical period are obtained, wherein the second historical photovoltaic installed capacity ratio is zero.

[0033] Preferably, the future prediction error value acquisition module is used to obtain the future prediction error values ​​of the daytime and nighttime periods of each season in the preset future period based on the wind-solar prediction error regression model, according to the preset future wind-solar output data, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor, specifically including:

[0034] Based on the wind-solar forecast error regression model, according to the preset future wind-solar output data, the future wind power installed capacity ratio and the future photovoltaic installed capacity ratio in the daytime and nighttime periods of each season in the preset future period are respectively obtained;

[0035] Based on the wind-solar forecast error regression model, according to the future wind power installed capacity proportion, the future photovoltaic installed capacity proportion, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor, the future forecast error values ​​for the day and night time periods of each season in the preset future time period are obtained.

[0036] A third aspect of an embodiment of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for solving future prediction errors of wind and solar resources as described in any one of the first aspects is implemented.

[0037] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method for solving future prediction errors of wind and solar resources as described in any one of the first aspects.

[0038] Compared with the prior art, the beneficial effect of the embodiments of the present invention is that, when fitting and solving the future prediction errors of wind and solar resources, the seasonal differences and day and night differences of wind and solar resources, as well as the influence of the number of wind power installed capacity and photovoltaic installed capacity on the prediction errors of wind and solar resources are fully considered, thereby obtaining an accurate future prediction error value, so that a reference can be provided for power grid scheduling based on the future prediction error value. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flow chart of a method for solving future prediction errors of wind and solar resources provided by an embodiment of the present invention;

[0040] Figure 2 It is a structural schematic diagram of a device for solving future prediction errors of wind and solar resources provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] See also Figure 1 The first aspect of the embodiment of the present invention provides a flow chart of a method for solving future prediction errors of wind and solar resources, including steps S1 to S3, which are as follows:

[0043] Step S1, based on the pre-acquired wind and solar power prediction error regression model and according to the pre-acquired historical wind and solar power output data, obtain the absolute average values ​​of the historical wind power installed capacity ratio, the historical photovoltaic installed capacity ratio and the historical wind and solar power prediction error per unit value in the daytime and nighttime periods of each season in the preset historical period.

[0044] It should be noted that the historical wind and solar power output data includes the historical total installed capacity of wind power, the historical total installed capacity of photovoltaic power, the historical wind power output prediction error and the historical photovoltaic output prediction error in the preset historical period.

[0045] It is worth noting that in order to analyze the relationship between the installed number of wind power and photovoltaic power and the wind and solar power prediction error, the embodiment of the present invention adopts a linear regression model for parameter fitting, and reflects the correlation between the installed number of wind power and photovoltaic power and the wind and solar power prediction error size through the parameter size.

[0046] Preferably, the method specifically obtains the wind-solar forecast error regression model in advance through the following steps:

[0047] The wind and solar forecast error regression model is constructed according to the following expression:

[0048]

[0049] Among them, C w is the total installed capacity of wind power, C p is the total installed capacity of photovoltaic power, X is the proportion of wind power installed capacity, Y is the proportion of photovoltaic installed capacity, P wei is the wind power output prediction error in period i, P pei is the photovoltaic output prediction error in period i, N is the total number of periods, Z is the absolute average of the per-unit values ​​of the wind and solar prediction errors in each period, a is the wind power installed capacity impact factor, b is the photovoltaic installed capacity impact factor, and c is the constant term.

[0050] It is worth noting that the i period mentioned above can be a certain hour in a certain day in a preset historical period, and is not specifically limited here.

[0051] The embodiment of the present invention divides the historical wind and solar power output data into seasons and daytime and nighttime periods, and uses the wind and solar prediction error regression model to solve the absolute average values ​​of the historical wind power installed capacity ratio, the historical photovoltaic installed capacity ratio and the historical wind and solar prediction error per-unit value in the daytime and nighttime periods of each season in the preset historical period. Specifically, according to the seasonal differences in wind and solar resources, the wind and solar prediction error regression model can be used to solve the absolute average values ​​of the historical wind power installed capacity ratio, the historical photovoltaic installed capacity ratio and the historical wind and solar prediction error per-unit value in the four seasons of spring, summer, autumn and winter. Considering the day and night differences in photovoltaic output, the above formula (1) needs to divide the solution process of the absolute average values ​​of the historical wind power installed capacity ratio, the historical photovoltaic installed capacity ratio and the historical wind and solar prediction error per-unit value into two periods of day and night.

[0052] Preferably, the pre-acquired wind / solar forecast error regression model is based on the pre-acquired historical wind / solar output data to obtain the historical wind power installed capacity ratio, the historical photovoltaic installed capacity ratio and the absolute average value of the historical wind / solar forecast error per unit value in the daytime and nighttime periods of each season in the preset historical period, specifically including:

[0053] Based on the pre-acquired wind and solar forecast error regression model, according to the pre-acquired historical wind and solar output data, the absolute average values ​​of the first historical wind power installed capacity ratio, the first historical photovoltaic installed capacity ratio and the first historical wind and solar forecast error per unit value in the daytime period of each season in the preset historical period are obtained;

[0054] Based on the wind and solar power prediction error regression model, according to the historical total wind power installed capacity and the historical wind power output prediction error in the preset historical period, the absolute average values ​​of the second historical wind power installed capacity ratio, the second historical photovoltaic installed capacity ratio and the second historical wind and solar power prediction error per unit value in the night period of each season in the preset historical period are obtained, wherein the second historical photovoltaic installed capacity ratio is zero.

[0055] It is understandable that when solving the absolute average values ​​of historical wind power installed capacity ratio, historical wind power installed capacity ratio, and historical wind and solar power forecast error per unit value in the daytime period, the photovoltaic output needs to be considered. Therefore, according to the historical total wind power installed capacity and the historical total photovoltaic installed capacity in the preset historical period, the absolute average values ​​of historical wind power installed capacity ratio, historical wind power installed capacity ratio, and historical wind and solar power forecast error per unit value in the daytime period are solved according to formula (1).

[0056] When solving the absolute average of the historical wind power installed capacity ratio, historical wind power installed capacity ratio, and historical wind-solar forecast error per unit value in the night period, the photovoltaic output does not need to be considered. Therefore, in the process of solving the problem using the wind-solar forecast error regression model, the historical photovoltaic output forecast error and the historical photovoltaic total installed capacity are both set to 0, which mainly affects the solution of Y and Z. Formula (1) changes to the following formula (2):

[0057]

[0058] As an optional embodiment, the preset historical period can be a certain five years in the past, such as 2014 to 2018. Since the total number of wind power installed capacity and the total number of photovoltaic installed capacity are different in each year, when the wind-solar power prediction error regression model is used to process the historical wind-solar power output data of the five years, the absolute average values ​​of five groups of wind power installed capacity percentage, wind power installed capacity percentage and wind-solar power prediction error standard value are finally obtained as the absolute average values ​​of wind power installed capacity percentage, wind power installed capacity percentage and wind-solar power prediction error standard value of the preset historical period.

[0059] Step S2, based on the wind and solar power prediction error regression model, parameter regression fitting is performed according to the absolute average values ​​of the historical wind power installed capacity ratio, historical photovoltaic installed capacity ratio and historical wind and solar power prediction error per unit value in the daytime and nighttime periods of each season in the preset historical period, to obtain the wind power installed capacity impact factor and photovoltaic installed capacity impact factor in the daytime and nighttime periods of each season.

[0060] Specifically, after solving in step S1 to obtain the absolute average values ​​of historical wind power installed capacity ratios, historical photovoltaic installed capacity ratios and historical wind-solar prediction error per-unit values ​​in the daytime and nighttime periods of each season in the preset historical period, the wind-solar prediction error regression model is used to perform parameter regression fitting according to the absolute average values ​​of historical wind power installed capacity ratios, historical photovoltaic installed capacity ratios and historical wind-solar prediction error per-unit values ​​in the daytime and nighttime periods of each season in the preset historical period to obtain the wind power installed capacity impact factor, photovoltaic installed capacity impact factor and a constant term in the daytime and nighttime periods of each season in the preset historical period.

[0061] It should be noted that the wind power installed capacity impact factor represents the impact factor of wind power installed capacity on the wind and solar power forecast error, and the photovoltaic installed capacity impact factor represents the impact factor of photovoltaic installed capacity on the wind and solar power forecast error. Since the wind and solar power forecast error regression model performs parameter regression fitting by season and time period based on the historical wind and solar power output data of the preset historical period, the wind power installed capacity impact factor and photovoltaic installed capacity impact factor obtained by fitting have seasonal characteristics and day and night output characteristics.

[0062] Furthermore, the embodiment of the present invention adopts the determination coefficient R 2 Evaluate the effect of model parameter fitting, determination coefficient R 2 Generally used in regression models to evaluate the degree of agreement between predicted values ​​and actual values. The closer the value is to 1, the better the regression fitting effect. 2 When the value is greater than 0.8, the regression fitting effect is considered to be good. 2 It reflects how much percentage of the dependent variable can be explained by the control variable. The embodiment of the present invention uses the average of the absolute average values ​​of all wind and solar forecast error per unit values ​​in a preset historical period as the fitting error benchmark to observe whether the wind and solar forecast error obtained by fitting is greater or less than the mean benchmark error. The details are as follows:

[0063]

[0064] Among them, R 2 is the coefficient of determination, z is the absolute average of the per-unit values ​​of the wind power forecast error in each year in the preset historical period, is the average of the absolute averages of all wind and solar forecast error per unit values ​​in the preset historical period, is the future forecast error value for each year in the preset future period.

[0065] Step S3, based on the wind-solar forecast error regression model, according to the preset future wind-solar output data, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor, obtain the future forecast error value of the daytime and nighttime periods of each season in the preset future period.

[0066] It should be noted that the future wind and solar power output data includes the future total wind power installed capacity and the future total photovoltaic installed capacity in the preset future period.

[0067] Preferably, the wind-solar forecast error regression model is based on preset future wind-solar output data, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor to obtain the future forecast error values ​​for the daytime and nighttime periods of each season in the preset future period, specifically including:

[0068] Based on the wind-solar forecast error regression model, according to the preset future wind-solar output data, the future wind power installed capacity ratio and the future photovoltaic installed capacity ratio in the daytime and nighttime periods of each season in the preset future period are respectively obtained;

[0069] Based on the wind-solar forecast error regression model, according to the future wind power installed capacity proportion, the future photovoltaic installed capacity proportion, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor, the future forecast error values ​​for the day and night time periods of each season in the preset future time period are obtained.

[0070] Specifically, the embodiment of the present invention plans the total installed number of wind power and the total installed number of photovoltaic power in a future year in advance, and then obtains the future total installed number of wind power X and the future installed number of photovoltaic power Y in the daytime and nighttime periods of each season in the future year based on the wind and solar prediction error regression model according to formula (1).

[0071] Based on the wind-solar forecast error regression model, the wind power installed capacity impact factor a, photovoltaic installed capacity impact factor b and constant term c of the daytime and nighttime periods of each season obtained by fitting in step S2, combined with the future wind power total installed capacity proportion X and future photovoltaic installed capacity proportion Y of the daytime and nighttime periods of each season in the future year, according to the formula: Get the future forecast error values ​​for the daytime and nighttime periods of each season in the future year

[0072] A method for solving the future prediction error of wind and solar resources provided by an embodiment of the present invention fully considers the seasonal differences and day-night differences of wind and solar resources, as well as the influence of the number of wind power installed capacity and the number of photovoltaic installed capacity on the prediction error of wind and solar resources when fitting and solving the future prediction error of wind and solar resources, thereby obtaining an accurate future prediction error fitting result, so that the prediction error can be accurately analyzed according to the fitting result, providing a reference for power grid scheduling.

[0073] See also Figure 2 According to a second aspect of an embodiment of the present invention, a device for solving future prediction errors of wind and solar resources is provided, comprising:

[0074] The data acquisition module 201 is used to obtain the historical wind power installed capacity ratio, the historical photovoltaic installed capacity ratio and the absolute average value of the historical wind power prediction error per unit value in the daytime and nighttime periods of each season in the preset historical period based on the pre-acquired wind power prediction error regression model and the pre-acquired historical wind power output data;

[0075] A parameter regression fitting module 202 is used to perform parameter regression fitting based on the wind-solar forecast error regression model, and to obtain the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor in the daytime and nighttime periods of each season in the preset historical period according to the historical wind power installed capacity ratio, the historical photovoltaic installed capacity ratio and the absolute average value of the historical wind-solar forecast error per unit value.

[0076] The future prediction error value acquisition module 203 is used to obtain the future prediction error value of the daytime and nighttime periods of each season in the preset future period based on the wind-solar prediction error regression model, according to the preset future wind-solar output data, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor;

[0077] The historical wind and solar power output data include the historical total installed capacity of wind power, the historical total installed capacity of photovoltaic power, the historical wind power output prediction error and the historical photovoltaic output prediction error in the preset historical period;

[0078] The future wind and solar power output data includes the future total wind power installed capacity and the future total photovoltaic installed capacity in the preset future period.

[0079] Preferably, the wind and solar resource future prediction error solving device further includes a wind and solar prediction error regression model acquisition module 204, which is used to:

[0080] The wind and solar forecast error regression model is constructed according to the following expression:

[0081]

[0082] Among them, C w is the total installed capacity of wind power, C p is the total installed capacity of photovoltaic power, X is the proportion of wind power installed capacity, Y is the proportion of photovoltaic installed capacity, P wei is the wind power output prediction error in period i, P pei is the photovoltaic output prediction error in period i, N is the total number of periods, Z is the absolute average of the per-unit values ​​of the wind and solar prediction errors in each period, a is the wind power installed capacity impact factor, b is the photovoltaic installed capacity impact factor, and c is the constant term.

[0083] Preferably, the data acquisition module 201 is used to obtain the historical wind power installed capacity ratio, historical photovoltaic installed capacity ratio and absolute average value of the historical wind power forecast error per unit value in the daytime and nighttime periods of each season in the preset historical period based on the pre-acquired wind power forecast error regression model and the pre-acquired historical wind power output data, specifically including:

[0084] Based on the pre-acquired wind and solar forecast error regression model, according to the pre-acquired historical wind and solar output data, the absolute average values ​​of the first historical wind power installed capacity ratio, the first historical photovoltaic installed capacity ratio and the first historical wind and solar forecast error per unit value in the daytime period of each season in the preset historical period are obtained;

[0085] Based on the wind and solar power prediction error regression model, according to the historical total wind power installed capacity and the historical wind power output prediction error in the preset historical period, the absolute average values ​​of the second historical wind power installed capacity ratio, the second historical photovoltaic installed capacity ratio and the second historical wind and solar power prediction error per unit value in the night period of each season in the preset historical period are obtained, wherein the second historical photovoltaic installed capacity ratio is zero.

[0086] Preferably, the future prediction error value acquisition module 203 is used to obtain the future prediction error values ​​of the daytime and nighttime periods of each season in the preset future period based on the wind-solar prediction error regression model, according to the preset future wind-solar output data, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor, specifically including:

[0087] Based on the wind-solar forecast error regression model, according to the preset future wind-solar output data, the future wind power installed capacity ratio and the future photovoltaic installed capacity ratio in the daytime and nighttime periods of each season in the preset future period are respectively obtained;

[0088] Based on the wind-solar forecast error regression model, according to the future wind power installed capacity proportion, the future photovoltaic installed capacity proportion, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor, the future forecast error values ​​for the day and night time periods of each season in the preset future time period are obtained.

[0089] It should be noted that a device for solving future prediction errors of wind and solar resources provided in an embodiment of the present invention can implement all processes of the method for solving future prediction errors of wind and solar resources described in any of the above embodiments. The functions of each module in the device and the technical effects achieved are respectively the same as the functions and technical effects achieved by the method for solving future prediction errors of wind and solar resources described in the above embodiments, and will not be repeated here.

[0090] A third aspect of an embodiment of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for solving future prediction errors of wind and solar resources as described in any embodiment of the first aspect is implemented.

[0091] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory. The terminal device may also include an input / output device, a network access device, a bus, etc.

[0092] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0093] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0094] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method for solving future prediction errors of wind and solar resources as described in any embodiment of the first aspect.

[0095] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary hardware platform, and of course can also be implemented entirely by hardware. Based on such an understanding, all or part of the contribution of the technical solution of the present invention to the background technology can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present invention or certain parts of the embodiments.

[0096] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for solving future prediction errors of wind and solar resources, characterized in that: include: Based on the pre-acquired wind and solar forecast error regression model, according to the pre-acquired historical wind and solar output data, the historical wind power installed capacity ratio, the historical photovoltaic installed capacity ratio and the absolute average value of the historical wind and solar forecast error per unit value in the daytime and nighttime periods of each season in the preset historical period are obtained respectively; Based on the wind-solar forecast error regression model, parameter regression fitting is performed according to the absolute average values ​​of the historical wind power installed capacity ratio, the historical photovoltaic installed capacity ratio and the historical wind-solar forecast error per unit value in the daytime and nighttime periods of each season in the preset historical period, to obtain the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor in the daytime and nighttime periods of each season; Based on the wind and solar forecast error regression model, according to the preset future wind and solar output data, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor, the future forecast error value of the daytime and nighttime periods of each season in the preset future period is obtained; The historical wind and solar power output data include the historical total installed capacity of wind power, the historical total installed capacity of photovoltaic power, the historical wind power output prediction error and the historical photovoltaic output prediction error in the preset historical period; The future wind and solar power output data includes the future total wind power installed capacity and the future total photovoltaic installed capacity in the preset future period.

2. The method for solving the future prediction error of wind and solar resources according to claim 1, characterized in that: The method specifically obtains the wind and solar power prediction error regression model in advance through the following steps: The wind and solar forecast error regression model is constructed according to the following expression: Among them, C w is the total installed capacity of wind power, C p is the total installed capacity of photovoltaic power, X is the proportion of wind power installed capacity, Y is the proportion of photovoltaic installed capacity, P wei is the wind power output prediction error in period i, P pei is the photovoltaic output prediction error in period i, N is the total number of periods, Z is the absolute average of the per-unit values ​​of the wind and solar prediction errors in each period, a is the wind power installed capacity impact factor, b is the photovoltaic installed capacity impact factor, and c is the constant term.

3. The method for solving the future prediction error of wind and solar resources according to claim 2, characterized in that: The wind and solar power forecast error regression model based on the pre-acquired historical wind and solar power output data obtained in advance respectively obtains the historical wind power installed capacity ratio, the historical photovoltaic installed capacity ratio and the absolute average value of the historical wind and solar power forecast error per unit value in the daytime and nighttime periods of each season in the preset historical period, specifically including: Based on the pre-acquired wind and solar forecast error regression model, according to the pre-acquired historical wind and solar output data, the absolute average values ​​of the first historical wind power installed capacity ratio, the first historical photovoltaic installed capacity ratio and the first historical wind and solar forecast error per unit value in the daytime period of each season in the preset historical period are obtained; Based on the wind and solar power prediction error regression model, according to the historical total wind power installed capacity and the historical wind power output prediction error in the preset historical period, the absolute average values ​​of the second historical wind power installed capacity ratio, the second historical photovoltaic installed capacity ratio and the second historical wind and solar power prediction error per unit value in the night period of each season in the preset historical period are obtained, wherein the second historical photovoltaic installed capacity ratio is zero.

4. The method for solving the future prediction error of wind and solar resources according to claim 3, characterized in that: The method based on the wind-solar forecast error regression model, according to the preset future wind-solar output data, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor, obtains the future forecast error value of the daytime and nighttime periods of each season in the preset future period, specifically including: Based on the wind-solar forecast error regression model, according to the preset future wind-solar output data, the future wind power installed capacity ratio and the future photovoltaic installed capacity ratio in the daytime and nighttime periods of each season in the preset future period are respectively obtained; Based on the wind-solar forecast error regression model, according to the future wind power installed capacity proportion, the future photovoltaic installed capacity proportion, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor, the future forecast error values ​​for the day and night time periods of each season in the preset future time period are obtained.

5. A device for solving future prediction errors of wind and solar resources, characterized in that: include: A data acquisition module is used to obtain the historical wind power installed capacity ratio, historical photovoltaic installed capacity ratio and absolute average value of the historical wind power forecast error per unit value in the daytime and nighttime periods of each season in a preset historical period based on a pre-acquired wind power forecast error regression model and pre-acquired historical wind power output data; A parameter regression fitting module is used to perform parameter regression fitting based on the wind-solar forecast error regression model, and to obtain the wind power installed capacity impact factor and photovoltaic installed capacity impact factor in the daytime and nighttime periods of each season in the preset historical period according to the historical wind power installed capacity proportion, historical photovoltaic installed capacity proportion and the absolute average value of the historical wind-solar forecast error per unit value. A future prediction error value acquisition module is used to obtain the future prediction error values ​​of the daytime and nighttime periods of each season in a preset future period based on the wind-solar prediction error regression model, according to preset future wind-solar output data, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor; The historical wind and solar power output data include the historical total installed capacity of wind power, the historical total installed capacity of photovoltaic power, the historical wind power output prediction error and the historical photovoltaic output prediction error in the preset historical period; The future wind and solar power output data includes the future total wind power installed capacity and the future total photovoltaic installed capacity in the preset future period.

6. The device for solving the future prediction error of wind and solar resources according to claim 5, characterized in that: It also includes a wind and solar forecast error regression model acquisition module, which is used to: The wind and solar forecast error regression model is constructed according to the following expression: Among them, C w is the total installed capacity of wind power, C p is the total installed capacity of photovoltaic power, X is the proportion of wind power installed capacity, Y is the proportion of photovoltaic installed capacity, P wei is the wind power output prediction error in period i, P pei is the photovoltaic output prediction error in period i, N is the total number of periods, Z is the absolute average of the per-unit values ​​of the wind and solar prediction errors in each period, a is the wind power installed capacity impact factor, b is the photovoltaic installed capacity impact factor, and c is the constant term.

7. The device for solving the future prediction error of wind and solar resources according to claim 6, characterized in that: The data acquisition module is used to obtain the historical wind power installed capacity ratio, historical photovoltaic installed capacity ratio and absolute average value of the historical wind power forecast error per unit value in the daytime and nighttime periods of each season in the preset historical period based on the pre-acquired wind power forecast error regression model and the pre-acquired historical wind power output data, specifically including: Based on the pre-acquired wind and solar forecast error regression model, according to the pre-acquired historical wind and solar output data, the absolute average values ​​of the first historical wind power installed capacity ratio, the first historical photovoltaic installed capacity ratio and the first historical wind and solar forecast error per unit value in the daytime period of each season in the preset historical period are obtained; Based on the wind and solar power prediction error regression model, according to the historical total wind power installed capacity and the historical wind power output prediction error in the preset historical period, the absolute average values ​​of the second historical wind power installed capacity ratio, the second historical photovoltaic installed capacity ratio and the second historical wind and solar power prediction error per unit value in the night period of each season in the preset historical period are obtained, wherein the second historical photovoltaic installed capacity ratio is zero.

8. The device for solving the future prediction error of wind and solar resources according to claim 7, characterized in that: The future prediction error value acquisition module is used to obtain the future prediction error values ​​of the daytime and nighttime periods of each season in the preset future period based on the wind-solar prediction error regression model, according to the preset future wind-solar output data, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor, specifically including: Based on the wind-solar forecast error regression model, according to the preset future wind-solar output data, the future wind power installed capacity ratio and the future photovoltaic installed capacity ratio in the daytime and nighttime periods of each season in the preset future period are respectively obtained; Based on the wind-solar forecast error regression model, according to the future wind power installed capacity proportion, the future photovoltaic installed capacity proportion, the wind power installed capacity impact factor and the photovoltaic installed capacity impact factor, the future forecast error values ​​for the day and night time periods of each season in the preset future time period are obtained.

9. A terminal device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method for solving the future prediction error of wind and solar resources as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method for solving future prediction errors of wind and solar resources according to any one of claims 1 to 4.

Images