Wind and light prediction output curve determination method and device, electronic equipment and medium
By fitting and randomly adjusting the scenery prediction data, combined with standard error statistical indicators, the problems of overfitting and instability in the scenery prediction output curve are solved, and the accuracy of prediction and the generalization ability of the model are improved.
Patent Information
- Application Number
- CN202411587585.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-08
- Publication Date
- 2025-03-04
Smart Images
Figure CN119558455A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of wind and solar power prediction, and in particular to a method, device, electronic device and medium for determining a wind and solar power prediction output curve. Background Art
[0002] Wind and solar forecast refers to the future forecast of wind and solar power generation. Through wind and solar forecast, the wind and solar forecast data for a certain period of time in the future can be obtained. The wind and solar forecast data is usually periodic discrete data. After processing the wind and solar forecast data, the wind and solar forecast output curve can be obtained. The wind and solar forecast output curve describes the change law of the output power of wind and solar power generation over time. It is in seconds and continuous. Therefore, it is used as the input of simulation or scheduling systems.
[0003] In the related art, a 9th-order polynomial fitting can be performed on the basis of wind and solar prediction data to generate a wind and solar prediction output curve. However, using a 9th-order polynomial fitting will result in overfitting, which will cause the model's generalization ability on new data to deteriorate, that is, it performs well on training data but performs poorly on test data. Polynomial fitting is a black box model that is not easy to explain the relationship between the model's internal mechanisms and features. High-order polynomials provide good fit within the data range, but tend to diverge wildly outside the range, resulting in model instability. Ultimately, the accuracy of the wind and solar prediction output curve is low. Summary of the invention
[0004] In order to solve the above technical problems, the present application provides a method, device, electronic device and storage medium for determining a wind-solar predicted output curve.
[0005] According to a first aspect of the present application, a method for determining a wind-solar power forecast output curve is provided, comprising:
[0006] Obtaining wind and solar power forecast data at N moments in a future time period, fitting the wind and solar power forecast data, and obtaining a wind and solar power forecast output curve to be processed; N is an integer greater than 1;
[0007] Setting a random event adjustment parameter, and adjusting the wind-solar power forecast output curve to be processed according to the random event adjustment parameter to obtain a first wind-solar power forecast output curve;
[0008] Setting a random stretching or compression parameter, and adjusting the first wind-solar power prediction output curve according to the random stretching or compression parameter to obtain a second wind-solar power prediction output curve;
[0009] Setting a normal distribution random noise parameter, and adjusting the second wind-solar power prediction output curve according to the normal distribution random noise parameter to obtain a third wind-solar power prediction output curve;
[0010] According to the N wind-solar prediction data and the wind-solar prediction data corresponding to N moments in the third wind-solar prediction output curve, and using a standard error statistical indicator calculation method, determine the accuracy of the third wind-solar prediction output curve;
[0011] If the accuracy is less than the first accuracy threshold, or greater than the second accuracy threshold, return to the step of setting the random event adjustment parameter, and adjust the wind-solar power forecast output curve to be processed according to the random event adjustment parameter; the first accuracy threshold is less than the second accuracy threshold;
[0012] If the accuracy is greater than or equal to the first accuracy threshold and less than or equal to the second accuracy threshold, the third wind-solar power prediction output curve is used as the final wind-solar power prediction output curve.
[0013] Optionally, the method further comprises:
[0014] Cleaning the data exceeding the preset threshold in the third wind-solar power prediction output curve to obtain a fourth wind-solar power prediction output curve;
[0015] Using a filter to smooth the fourth wind-solar power prediction curve to obtain a fifth wind-solar power prediction curve;
[0016] The determining the accuracy of the third wind-solar prediction output curve according to the N wind-solar prediction data and the wind-solar prediction data corresponding to N moments in the third wind-solar prediction output curve and using a standard error statistical indicator calculation method specifically includes:
[0017] According to the N wind and solar power prediction data and the wind and solar power prediction data corresponding to N moments in the fifth wind and solar power prediction output curve, and using a standard error statistical indicator calculation method, determine the accuracy of the fifth wind and solar power prediction output curve;
[0018] The taking the third wind-solar power prediction output curve as the final wind-solar power prediction output curve specifically includes:
[0019] The fifth wind-solar power forecast curve is taken as the final wind-solar power forecast curve.
[0020] Optionally, determining the accuracy of the third wind-solar prediction output curve according to the N wind-solar prediction data and the wind-solar prediction data corresponding to N moments in the third wind-solar prediction output curve and using a standard error statistical indicator calculation method includes:
[0021] Assume that the obtained wind and solar forecast data at the i-th moment is P Pi The wind power forecast data corresponding to the i-th moment in the third wind power forecast output curve is P Mi ; The startup capacity of wind and solar power generation at the i-th moment is Ci ;
[0022] According to the formula:
[0023] Determine the accuracy C of the third wind-solar power forecast curve R .
[0024] Optionally, the random event adjustment parameters include: probability, intensity and duration of the random event;
[0025] The adjusting the wind / solar power forecast output curve to be processed according to the random event adjustment parameter includes:
[0026] According to the probability, intensity and duration of the random event, the amplitude of the wind and solar power forecast output curve to be processed is adjusted; wherein the amplitude of the adjustment of the wind and solar power forecast output curve to be processed is positively correlated with the probability, intensity and duration of the random event.
[0027] According to a second aspect of the present application, a device for determining a wind-solar power forecast output curve is provided, comprising:
[0028] The module for determining the curve to be processed is used to obtain the wind and solar power forecast data at N moments in the future time period, and to fit the wind and solar power forecast data to obtain the wind and solar power forecast output curve to be processed; N is an integer greater than 1;
[0029] A first adjustment module, used for setting a random event adjustment parameter, and adjusting the to-be-processed wind-solar power forecast output curve according to the random event adjustment parameter to obtain a first wind-solar power forecast output curve;
[0030] a second adjustment module, used for setting a random stretching or compression parameter, and adjusting the first wind-solar power prediction output curve according to the random stretching or compression parameter to obtain a second wind-solar power prediction output curve;
[0031] A third adjustment module is used to set a normal distribution random noise parameter, and adjust the second wind-solar power prediction output curve according to the normal distribution random noise parameter to obtain a third wind-solar power prediction output curve;
[0032] An accuracy calculation module, used to determine the accuracy of the third wind-solar prediction output curve according to the N wind-solar prediction data and the wind-solar prediction data corresponding to N moments in the third wind-solar prediction output curve, and using a standard error statistical indicator calculation method;
[0033] A return module, used for returning to the first adjustment module if the accuracy rate output by the accuracy rate calculation module is less than a first accuracy rate threshold, or greater than a second accuracy rate threshold; the first accuracy rate threshold is less than the second accuracy rate threshold;
[0034] The final curve determination module is used to use the third wind-solar power prediction output curve as the final wind-solar power prediction output curve if the accuracy output by the accuracy calculation module is greater than or equal to the first accuracy threshold and less than or equal to the second accuracy threshold.
[0035] Optionally, the device further comprises:
[0036] A fourth adjustment module, used for cleaning the data exceeding a preset threshold in the third wind-solar power prediction output curve to obtain a fourth wind-solar power prediction output curve;
[0037] a fifth adjustment module, configured to use a filter to smooth the fourth wind-solar power prediction curve to obtain a fifth wind-solar power prediction curve;
[0038] The accuracy calculation module is specifically used to determine the accuracy of the fifth wind-solar prediction output curve according to the N wind-solar prediction data and the wind-solar prediction data corresponding to N moments in the fifth wind-solar prediction output curve, and using a standard error statistical indicator calculation method;
[0039] The final curve determination module is specifically configured to use the fifth wind-solar power prediction output curve as the final wind-solar power prediction output curve if the accuracy output by the accuracy calculation module is greater than or equal to the accuracy threshold.
[0040] Optionally, assuming that the obtained scenery prediction data at the i-th moment is P Pi The wind power forecast data corresponding to the i-th moment in the third wind power forecast output curve is P Mi ; The startup capacity of wind and solar power generation at the i-th moment is C i ; The accuracy calculation module is specifically used according to the formula:
[0041] Determine the accuracy C of the third wind-solar power forecast curve R .
[0042] Optionally, the random event adjustment parameters include: probability, intensity and duration of the random event;
[0043] The first adjustment module is specifically used to set random event adjustment parameters, and adjust the amplitude of the wind and solar power forecast output curve to be processed according to the probability, intensity and duration of the random event; wherein the amplitude of the adjustment of the wind and solar power forecast output curve to be processed is positively correlated with the probability, intensity and duration of the random event.
[0044] According to a third aspect of the present application, an electronic device is provided, comprising: a processor, wherein the processor is configured to execute a computer program stored in a memory, wherein the computer program implements the method described in the first aspect when executed by the processor.
[0045] According to a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first aspect is implemented.
[0046] According to a fifth aspect of the present application, a computer program product is provided. When the computer program product is run on a computer, the computer is enabled to execute the method described in the first aspect.
[0047] Compared with the prior art, the technical solution provided by the embodiments of the present application has the following advantages:
[0048] By fitting the wind and solar power prediction data, the wind and solar power prediction output curve to be processed is obtained. On the basis of the wind and solar power prediction output curve to be processed, the random event adjustment parameters, random stretching or compression parameters, and normal distribution random noise parameters are adjusted. From an objective point of view, random events are added to simulate weather changes and other processing methods to enhance the mutation and randomness of the wind and solar power prediction output curve. Finally, the accuracy of the wind and solar power prediction output curve is calculated using the standard error statistical indicator calculation method, and the accuracy parameters are calibrated to improve the accuracy of the wind and solar power prediction output curve. Compared with the method of using data fitting and adding random disturbances based only on the data level, the embodiment of the present application can ensure the accuracy of the final wind and solar power prediction output curve, and at the same time, it is more interpretable. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0050] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0051] Figure 1 A flow chart of a method for determining a wind-solar power forecast output curve in an embodiment of the present application;
[0052] Figure 2 A schematic diagram of the structure of a device for determining a wind-solar power prediction output curve in an embodiment of the present application;
[0053] Figure 3A schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION
[0054] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.
[0055] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only part of the embodiments of the present application, rather than all of the embodiments.
[0056] The wind and solar output curve includes the wind power output curve and the photovoltaic output curve. The wind power output curve refers to the curve of the average power generation capacity of the wind turbine generator set under different wind speed conditions within a certain time range. It is usually displayed in the form of a curve with wind speed as the horizontal axis and power generation capacity as the vertical axis. The wind power output curve has the following characteristics:
[0057] 1) Nonlinear changes: When the wind speed is lower than the rated wind speed, the power generation capacity of the wind turbine is low; when the wind speed reaches the rated wind speed, the power generation capacity reaches the maximum; when the wind speed exceeds the rated wind speed, the power generation capacity will gradually decrease. This nonlinear change makes it difficult to predict the power generation capacity of the wind turbine under different wind speed conditions.
[0058] 2) Highly dependent on wind speed: The power generation capacity of wind turbines is highly dependent on wind speed.
[0059] 3) Rated wind speed: refers to the wind speed at which the wind turbine can operate at rated power. At the rated wind speed, the wind turbine's power generation capacity reaches its maximum value.
[0060] The photovoltaic output curve refers to the curve in which the output power of photovoltaic cells changes with the light intensity. As the weather and light conditions change, the output of photovoltaic cells will also change. The photovoltaic output curve is an inverted U-shaped curve. When the light intensity is low, the output power of photovoltaic cells is also relatively low. As the light intensity increases, the output power of photovoltaic cells will also increase until it reaches a peak point. When the light intensity continues to increase, the output power of photovoltaic cells will gradually decrease until it eventually reaches 0. The peak point of the photovoltaic output curve is usually called the maximum power point (MPP), at which the output power of the photovoltaic cell is the highest.
[0061] Wind and solar forecast refers to the future forecast of wind and solar power generation. The wind and solar forecast output curve refers to the wind and solar output curve for a period of time in the future, which can help the power system to dispatch and plan. How to obtain a continuous wind and solar forecast output curve that is close to actual weather changes based on wind and solar forecast data is the basis for related research such as simulation and dispatch of wind and solar power generation.
[0062] The existing wind and solar output curve processing method is mainly based on the data level, using data fitting and adding random disturbances. The accuracy cannot be guaranteed and the interpretability is not strong. In the embodiment of the present application, based on the wind and solar forecast data, random events are added to simulate the impact of weather changes on wind and solar output (for example, a cloud suddenly floats in the sky, and the photovoltaic output will drop sharply), providing a modeling method for wind and solar output curves that is more in line with weather changes.
[0063] Figure 1 This is a flow chart of a method for determining a wind-solar power forecast output curve in an embodiment of the present application, which may include the following steps:
[0064] Step S102, obtaining wind and solar power prediction data at N moments in a future time period, fitting the wind and solar power prediction data, and obtaining a wind and solar power prediction output curve to be processed; N is an integer greater than 1.
[0065] The future time period may be a certain day in the future, two days, etc. The N moments may be moments determined according to a preset time interval. For example, if the future time period is a certain day in the future and the preset time interval is 15 minutes, then 96 moments of wind and solar power prediction data can be obtained on a certain day in the future. The present application does not limit the fitting method of the N wind and solar power prediction data. For example, the cubic spline method may be used to fit the N wind and solar power prediction data to obtain a smooth curve as the wind and solar power prediction output curve to be processed.
[0066] Step S104, setting random event adjustment parameters, and adjusting the wind-solar power forecast output curve to be processed according to the random event adjustment parameters to obtain a first wind-solar power forecast output curve.
[0067] Since the wind and solar power forecast data is an average value over a period of time, the overall performance is smooth, while actual weather changes are often drastic. In the embodiment of the present application, by adding random events to enhance the mutation of simulated weather, the mutation of the wind and solar power forecast output curve can be more accurately reflected, and the extensive exploratory nature of generated training data can be improved, thereby improving the flexibility and accuracy of prediction and scheduling. Specifically, the random event adjustment parameters can be set, and the wind and solar power forecast output curve to be processed can be adjusted according to the random event adjustment parameters.
[0068] Optionally, the random event adjustment parameters may include: the probability, intensity and duration of the occurrence of the random event. A random event may be, for example, a cloud suddenly floating in the sky, a sudden rain in the sky, etc. It should be noted that both the wind power output curve and the photovoltaic output curve can be adjusted by the random event adjustment parameters. Since the output power of the wind and photovoltaic output curves is directly related to the wind force and light intensity respectively, the light intensity over a period of time is relatively stable, while the wind force changes more randomly. Therefore, compared with the photovoltaic output curve, the accuracy of the wind power output curve can be better improved after adding random events.
[0069] After setting the random event adjustment parameters, the amplitude of the wind-solar forecast output curve to be processed can be adjusted according to the probability, intensity and duration of the random event; wherein, the amplitude of the adjustment of the wind-solar forecast output curve to be processed is positively correlated with the probability, intensity and duration of the random event. For example, adjusting the probability of a random event can randomly adjust the number of random events and the time of their occurrence. Adjusting the intensity can randomly adjust the power corresponding to the random event point (increase or decrease at multiples of speed). Adjusting the duration means randomly adjusting the duration of the random event, using logarithmic and other attenuation methods within the duration.
[0070] Step S106, setting a random stretching or compression parameter, and adjusting the first wind-solar power prediction curve according to the random stretching or compression parameter to obtain a second wind-solar power prediction curve.
[0071] After adjusting the wind-solar forecast output curve to be processed through random event adjustment parameters, in order to prevent positive or negative deviations in the first wind-solar forecast output curve, the first wind-solar forecast output curve can be further adjusted through random stretching or compression parameters to improve the accuracy of prediction and scheduling.
[0072] Step S108, setting a normal distribution random noise parameter, and adjusting the second wind-solar power prediction output curve according to the normal distribution random noise parameter to obtain a third wind-solar power prediction output curve.
[0073] Taking into account the randomness of the wind and solar power output curve, by adding normally distributed random noise parameters, the model can better reflect the volatility of the actual wind and solar power output curve, thereby improving the accuracy of prediction and scheduling.
[0074] Step S110, according to N wind-solar prediction data and wind-solar prediction data corresponding to N moments in the third wind-solar prediction output curve, and using a standard error statistical indicator calculation method, determine the accuracy of the third wind-solar prediction output curve.
[0075] The N wind-solar prediction data represent actual data, and the wind-solar prediction data corresponding to the N moments in the third wind-solar prediction output curve represent the prediction data obtained after the wind-solar prediction output curve is generated. The closer the prediction data is to the actual data, the higher the accuracy of the generated third wind-solar prediction output curve. Therefore, the accuracy of the third wind-solar prediction output curve can be calculated based on the actual data and the prediction data.
[0076] Optionally, the accuracy can be calculated according to the error statistical index calculation method in Appendix D of GB / T40607 to accurately evaluate the accuracy of the third wind-solar power forecast output curve. Assume that the wind-solar power forecast data obtained at the i-th moment is P Pi , the wind power forecast data corresponding to the i-th moment in the third wind power forecast output curve is P Mi ; The startup capacity of wind and solar power generation at the i-th moment is C i The startup capacity of wind and solar power generation usually refers to the total capacity of wind and solar generator sets actually connected to the grid and operating in a wind and solar power plant at a specific time point or time period, which can be a known constant.
[0077] According to the formula:
[0078] Determine the accuracy of the third wind and solar power forecast output curve C R .
[0079] Step S112, determining whether the accuracy is greater than or equal to a first accuracy threshold and less than or equal to a second accuracy threshold.
[0080] If the accuracy is less than the first accuracy threshold, or greater than the second accuracy threshold, it means that the accuracy of the third wind-solar power prediction curve is low, that is, the accuracy is too low or too high, and the third wind-solar power prediction curve is considered inaccurate, and the process returns to step S104 to readjust the wind-solar power prediction curve to be processed; if the accuracy is greater than or equal to the first accuracy threshold, and less than or equal to the second accuracy threshold, it means that the accuracy of the third wind-solar power prediction curve has met the requirements, and step S114 is executed. The first accuracy threshold is less than the second accuracy threshold, for example, the first accuracy threshold can be 85%, and the second accuracy threshold can be 95%.
[0081] It should be noted that after returning to step S104, one or more of the random event adjustment parameters, random stretching or compression parameters, and normal distribution random noise parameters may be reset according to the obtained third wind-solar predicted output curve. For example, the random event adjustment parameters may be kept unchanged, and the random stretching or compression parameters and the normal distribution random noise parameters may be reset. Alternatively, the random event adjustment parameters, random stretching or compression parameters, and the normal distribution random noise parameters may also be reset.
[0082] Step S114: taking the third wind-solar power prediction output curve as the final wind-solar power prediction output curve.
[0083] In some embodiments, after obtaining the third wind-solar predicted output curve, the data exceeding the preset threshold in the third wind-solar predicted output curve may be cleaned to obtain a fourth wind-solar predicted output curve, so that the error that the actual wind-solar power exceeds the rated power can be avoided. In addition, the fourth wind-solar predicted output curve is smoothed using a filter to obtain a fifth wind-solar predicted output curve. For example, using a Savitzky-Golay filter to smooth the curve after adding noise can better retain the characteristics and trends of the data.
[0084] Accordingly, the accuracy of the fifth wind-solar prediction output curve can be determined based on the N wind-solar prediction data and the wind-solar prediction data corresponding to N moments in the fifth wind-solar prediction output curve, and using the standard error statistical indicator calculation method. If the accuracy is less than the first accuracy threshold, or greater than the second accuracy threshold, return to step S104; if the accuracy is greater than or equal to the first accuracy threshold, and less than or equal to the second accuracy threshold, the fifth wind-solar prediction output curve is used as the final wind-solar prediction output curve.
[0085] The method for determining the wind-solar forecast output curve of the embodiment of the present application obtains the wind-solar forecast output curve to be processed by fitting the wind-solar forecast data. On the basis of the wind-solar forecast output curve to be processed, the wind-solar forecast output curve is adjusted by random event adjustment parameters, random stretching or compression parameters, and normal distribution random noise parameters. From an objective point of view, the wind-solar forecast output curve is enhanced by adding random events to simulate weather changes and other processing methods. The data exceeding the preset threshold can also be cleaned and smoothed using a filter to improve the accuracy of the wind-solar forecast output curve. Finally, the accuracy of the wind-solar forecast output curve is calculated using the standard error statistical indicator calculation method, and the accuracy parameter is checked to improve the accuracy of the wind-solar forecast output curve. Compared with the method of using data fitting and adding random disturbances based only on the data level, the embodiment of the present application can ensure the accuracy of the wind-solar forecast output curve finally obtained, and at the same time, it is more interpretable.
[0086] Corresponding to the above method embodiment, the present application embodiment also provides a device for determining a wind-solar power forecast output curve, see Figure 2 , the wind and solar power forecast output curve determination device 200 includes:
[0087] The module 202 for determining the curve to be processed is used to obtain the wind and solar power prediction data at N moments in the future time period, and to fit the wind and solar power prediction data to obtain the wind and solar power prediction output curve to be processed; N is an integer greater than 1;
[0088] The first adjustment module 204 is used to set a random event adjustment parameter, and adjust the wind and solar power forecast output curve to be processed according to the random event adjustment parameter to obtain a first wind and solar power forecast output curve;
[0089] The second adjustment module 206 is used to set a random stretching or compression parameter, and adjust the first wind-solar power prediction curve according to the random stretching or compression parameter to obtain a second wind-solar power prediction curve;
[0090] The third adjustment module 208 is used to set the normal distribution random noise parameter, and adjust the second wind-solar power prediction output curve according to the normal distribution random noise parameter to obtain the third wind-solar power prediction output curve;
[0091] The accuracy calculation module 210 is used to determine the accuracy of the third wind-solar prediction output curve according to the N wind-solar prediction data and the wind-solar prediction data corresponding to N moments in the third wind-solar prediction output curve, and using a standard error statistical indicator calculation method;
[0092] A return module 212, configured to return to the first adjustment module 204 if the accuracy rate output by the accuracy rate calculation module 210 is less than the first accuracy rate threshold, or greater than the second accuracy rate threshold;
[0093] The final curve determination module 214 is used to use the third wind-solar power prediction output curve as the final wind-solar power prediction output curve if the accuracy output by the accuracy calculation module 210 is greater than or equal to the first accuracy threshold and less than or equal to the second accuracy threshold.
[0094] Optionally, the wind / solar power forecast output curve determination device 200 further includes:
[0095] A fourth adjustment module is used to clean the data exceeding the preset threshold in the third wind-solar power prediction output curve to obtain a fourth wind-solar power prediction output curve;
[0096] a fifth adjustment module, configured to use a filter to smooth the fourth wind-solar power prediction output curve to obtain a fifth wind-solar power prediction output curve;
[0097] The accuracy calculation module 210 is specifically used to determine the accuracy of the fifth wind-solar prediction output curve according to the N wind-solar prediction data and the wind-solar prediction data corresponding to N moments in the fifth wind-solar prediction output curve, and using the standard error statistical indicator calculation method;
[0098] The final curve determination module 214 is specifically configured to use the fifth wind-solar power prediction output curve as the final wind-solar power prediction output curve if the accuracy output by the accuracy calculation module is greater than or equal to the accuracy threshold.
[0099] Optionally, assuming that the obtained scenery prediction data at the i-th moment is PPi , the wind power forecast data corresponding to the i-th moment in the third wind power forecast output curve is P Mi ; The startup capacity of wind and solar power generation at the i-th moment is C i ; Accuracy calculation module 210, specifically used according to the formula:
[0100]
[0101] Determine the accuracy of the third wind and solar power forecast output curve C R .
[0102] Optionally, the random event adjustment parameters include: probability, intensity and duration of the random event;
[0103] The first adjustment module 204 is specifically used to set the random event adjustment parameters, and adjust the amplitude of the wind and solar power forecast output curve to be processed according to the probability, intensity and duration of the random event; wherein the amplitude of the adjustment of the wind and solar power forecast output curve to be processed is positively correlated with the probability, intensity and duration of the random event.
[0104] The specific details of each module or unit in the above device have been described in detail in the corresponding method, so they will not be repeated here.
[0105] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.
[0106] An embodiment of the present application also provides an electronic device, including: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the above-mentioned method for determining the wind and solar power predicted output curve in this example implementation.
[0107] Reference Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. The specific embodiment of the present application does not limit the specific implementation of the electronic device.
[0108] like Figure 3 As shown, the electronic device may include: a processor 302 , a communication interface 304 , a memory 306 , and a communication bus 308 .
[0109] The processor 302 , the communication interface 304 , and the memory 306 communicate with each other via a communication bus 308 .
[0110] The communication interface 304 is used to communicate with other electronic devices or servers.
[0111] The processor 302 is used to execute the program 310, and specifically can execute the relevant steps in the above method embodiment.
[0112] Specifically, the program 310 may include program codes, which include computer operation instructions.
[0113] The processor 302 may be a central processing unit, or a specific integrated circuit, or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.
[0114] The memory 306 is used to store the program 310. The memory 306 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
[0115] The program 310 can be specifically used to enable the processor 302 to execute the steps in the above-mentioned embodiment of the method for determining the wind-solar power forecast output curve.
[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding process descriptions in the aforementioned method embodiments and will not be repeated here.
[0117] A computer-readable storage medium is also provided in an embodiment of the present application, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned method for determining the wind and solar power forecast output curve is implemented.
[0118] It should be noted that the computer-readable storage medium shown in the present application may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, radio frequency, etc., or any suitable combination of the above.
[0119] In an embodiment of the present application, a computer program product is also provided. When the computer program product is run on a computer, the computer executes the above-mentioned method for determining the wind and solar power prediction output curve.
[0120] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0121] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for determining a wind and solar power forecast output curve, characterized in that: include: Obtaining wind and solar power forecast data at N moments in a future time period, fitting the wind and solar power forecast data, and obtaining a wind and solar power forecast output curve to be processed; N is an integer greater than 1; Setting a random event adjustment parameter, and adjusting the wind-solar power forecast output curve to be processed according to the random event adjustment parameter to obtain a first wind-solar power forecast output curve; Setting a random stretching or compression parameter, and adjusting the first wind-solar power prediction output curve according to the random stretching or compression parameter to obtain a second wind-solar power prediction output curve; Setting a normal distribution random noise parameter, and adjusting the second wind-solar power prediction output curve according to the normal distribution random noise parameter to obtain a third wind-solar power prediction output curve; According to the N wind-solar prediction data and the wind-solar prediction data corresponding to N moments in the third wind-solar prediction output curve, and using a standard error statistical indicator calculation method, determine the accuracy of the third wind-solar prediction output curve; If the accuracy is less than the first accuracy threshold, or greater than the second accuracy threshold, return to the step of setting the random event adjustment parameter, and adjust the wind-solar power forecast output curve to be processed according to the random event adjustment parameter; the first accuracy threshold is less than the second accuracy threshold; If the accuracy is greater than or equal to the first accuracy threshold and less than or equal to the second accuracy threshold, the third wind-solar power prediction output curve is used as the final wind-solar power prediction output curve.
2. The method according to claim 1, characterized in that The method further comprises: Cleaning the data exceeding the preset threshold in the third wind-solar power prediction output curve to obtain a fourth wind-solar power prediction output curve; Using a filter to smooth the fourth wind-solar power prediction curve to obtain a fifth wind-solar power prediction curve; The determining the accuracy of the third wind-solar prediction output curve according to the N wind-solar prediction data and the wind-solar prediction data corresponding to N moments in the third wind-solar prediction output curve and using a standard error statistical indicator calculation method specifically includes: According to the N wind and solar power prediction data and the wind and solar power prediction data corresponding to N moments in the fifth wind and solar power prediction output curve, and using a standard error statistical indicator calculation method, determine the accuracy of the fifth wind and solar power prediction output curve; The taking the third wind-solar power prediction output curve as the final wind-solar power prediction output curve specifically includes: The fifth wind-solar power forecast curve is taken as the final wind-solar power forecast curve.
3. The method according to claim 1, characterized in that The determining the accuracy of the third wind-solar prediction output curve according to the N wind-solar prediction data and the wind-solar prediction data corresponding to N moments in the third wind-solar prediction output curve and using a standard error statistical indicator calculation method includes: Assume that the obtained wind and solar forecast data at the i-th moment is P Pi The wind power forecast data corresponding to the i-th moment in the third wind power forecast output curve is P Mi ; The startup capacity of wind and solar power generation at the i-th moment is C i ; According to the formula: Determine the accuracy C of the third wind-solar power forecast curve R .
4. The method according to claim 1, characterized in that: The random event adjustment parameters include: probability, intensity and duration of random event occurrence; The adjusting the wind / solar power forecast output curve to be processed according to the random event adjustment parameter includes: According to the probability, intensity and duration of the random event, the amplitude of the wind and solar power forecast output curve to be processed is adjusted; wherein the amplitude of the adjustment of the wind and solar power forecast output curve to be processed is positively correlated with the probability, intensity and duration of the random event.
5. A device for determining a wind and solar power forecast output curve, characterized in that: The device comprises: The module for determining the curve to be processed is used to obtain the wind and solar power forecast data at N moments in the future time period, and to fit the wind and solar power forecast data to obtain the wind and solar power forecast output curve to be processed; N is an integer greater than 1; A first adjustment module, used for setting a random event adjustment parameter, and adjusting the to-be-processed wind-solar power forecast output curve according to the random event adjustment parameter to obtain a first wind-solar power forecast output curve; a second adjustment module, used for setting a random stretching or compression parameter, and adjusting the first wind-solar power prediction output curve according to the random stretching or compression parameter to obtain a second wind-solar power prediction output curve; A third adjustment module is used to set a normal distribution random noise parameter, and adjust the second wind-solar power prediction output curve according to the normal distribution random noise parameter to obtain a third wind-solar power prediction output curve; An accuracy calculation module, used to determine the accuracy of the third wind-solar prediction output curve according to the N wind-solar prediction data and the wind-solar prediction data corresponding to N moments in the third wind-solar prediction output curve, and using a standard error statistical indicator calculation method; A return module, used for returning to the first adjustment module if the accuracy rate output by the accuracy rate calculation module is less than a first accuracy rate threshold, or greater than a second accuracy rate threshold; the first accuracy rate threshold is less than the second accuracy rate threshold; The final curve determination module is used to use the third wind-solar power prediction output curve as the final wind-solar power prediction output curve if the accuracy output by the accuracy calculation module is greater than or equal to the first accuracy threshold and less than or equal to the second accuracy threshold.
6. The device according to claim 5, characterized in that The device also includes: A fourth adjustment module, used for cleaning the data exceeding a preset threshold in the third wind-solar power prediction output curve to obtain a fourth wind-solar power prediction output curve; a fifth adjustment module, configured to use a filter to smooth the fourth wind-solar power prediction curve to obtain a fifth wind-solar power prediction curve; The accuracy calculation module is specifically used to determine the accuracy of the fifth wind-solar prediction output curve according to the N wind-solar prediction data and the wind-solar prediction data corresponding to N moments in the fifth wind-solar prediction output curve, and using a standard error statistical indicator calculation method; The final curve determination module is specifically configured to use the fifth wind-solar power prediction output curve as the final wind-solar power prediction output curve if the accuracy output by the accuracy calculation module is greater than or equal to the accuracy threshold.
7. The device according to claim 5, characterized in that Assume that the obtained wind and solar forecast data at the i-th moment is P Pi The wind power forecast data corresponding to the i-th moment in the third wind power forecast output curve is P Mi ; The startup capacity of wind and solar power generation at the i-th moment is C i ; The accuracy calculation module is specifically used according to the formula: Determine the accuracy C of the third wind-solar power forecast curve R .
8. The device according to claim 5, characterized in that The random event adjustment parameters include: probability, intensity and duration of random event occurrence; The first adjustment module is specifically used to set random event adjustment parameters, and adjust the amplitude of the wind and solar power forecast output curve to be processed according to the probability, intensity and duration of the random event; wherein the amplitude of the adjustment of the wind and solar power forecast output curve to be processed is positively correlated with the probability, intensity and duration of the random event.
9. An electronic device, characterized in that: include: A processor, wherein the processor is used to execute a computer program stored in a memory, wherein the computer program, when executed by the processor, implements the method according to any one of claims 1 to 4.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.