Method and device for generating source-load coupled wind and solar power output scenarios

Abstract

The application discloses a kind of source-load coupling wind and light output scene generation method and device.Therein, the method includes: obtaining the load characteristic value of typical day load information in the region where new energy power station is located;According to load characteristic value, establish source-load coupling characteristic evaluation index;Based on source-load coupling characteristic evaluation index, generate the feature index set of wind and light output scene;The feature index set is clustered, and the feature index set of the wind and light output scene after clustering is obtained;According to the feature index set of the wind and light output scene after clustering, from the wind and light output scene of typical day, the target wind and light output scene is screened out.The application solves the technical problem that the wind and light output scene generation method in the related art mostly only considers the probability distribution characteristics of wind and light, with great randomness, resulting in wind and light output scene deviation will be transmitted to power system operation simulation calculation result, thereby affecting the power and energy balance result.

Description

Technical Field

[0001] This invention relates to the field of wind power generation technology, and more specifically, to a method and apparatus for generating a source-load coupled wind-solar power output scenario. Background Technology

[0002] The large-scale grid connection of new energy sources has introduced a large number of uncertainties. Traditional deterministic power balance calculation methods can no longer meet the needs of the system. Power balance methods based on operation simulation will play a more important role. Wind and solar power output scenarios are the main scenario boundaries of power balance methods based on operation simulation. How to obtain wind and solar power output scenarios that meet the needs of power balance analysis is the core of power balance methods based on operation simulation.

[0003] Most existing methods for generating wind and solar power output scenarios only consider the probability distribution characteristics of wind and solar power, or generate random wind and solar power scenarios based on Monte Carlo random simulation methods. They lack consideration of source-load coupling characteristics. On the one hand, they ignore the temporal characteristics of wind and solar power, resulting in the trend of wind and solar power output curves being inconsistent with historical scenarios. On the other hand, they ignore the cross-correlation between wind and solar power output sequences and load sequences, and do not consider the impact of source-load coupling characteristics on wind power output sequences.

[0004] The aforementioned methods for generating wind and solar power output scenarios mostly only consider the probability distribution characteristics of wind and solar power, which involves a large degree of randomness. As a result, deviations in wind and solar power output scenarios will be transmitted to the simulation calculation results of power system operation, thus affecting the power balance results. Currently, no effective solution has been proposed. Summary of the Invention

[0005] This invention provides a method and apparatus for generating source-load coupled wind and solar power output scenarios, which at least solves the technical problem that most wind and solar power output scenario generation methods in related technologies only consider the probability distribution characteristics of wind and solar power, which have a large degree of randomness. As a result, the deviation of wind and solar power output scenarios will be transmitted to the power system operation simulation calculation results, thereby affecting the power balance results.

[0006] According to one aspect of the present invention, a method for generating a source-load coupled wind and solar power output scenario is provided, comprising: obtaining load characteristic values ​​of typical daily load information within a region where a new energy power station is located, wherein the typical daily load information is the electricity consumption information of a typical day in the electricity consumption area corresponding to the new energy power station, the typical day is at least one day selected from the historical electricity consumption time period of the electricity consumption area according to a predetermined index, and the load characteristic values ​​include at least: daily load peak period, daily load trough period, and daily load mid-load period; establishing a source-load coupling characteristic evaluation index based on the load characteristic values; generating a set of characteristic indicators for the wind and solar power output scenario based on the source-load coupling characteristic evaluation index; clustering the set of characteristic indicators to obtain a clustered set of characteristic indicators for the wind and solar power output scenario; and selecting a target wind and solar power output scenario from the wind and solar power output scenarios of the typical day based on the clustered set of characteristic indicators for the wind and solar power output scenario.

[0007] Optionally, obtaining load characteristic values ​​of typical daily load information in the area where the new energy power station is located includes: collecting multiple historical daily load information of the power consumption area within the historical power consumption time period; analyzing the multiple historical daily load information to obtain historical load characteristic values ​​of the multiple historical daily load information; generating a daily load characteristic curve based on the historical load characteristic values ​​of the multiple historical daily load information; and obtaining the load characteristic values ​​based on the daily load characteristic curve and the daily load information.

[0008] Optionally, the load information of the plurality of historical days is analyzed to obtain the historical load characteristic values ​​of the plurality of historical day load information, including: determining the historical day load peak period of the plurality of historical day load information using a first formula, wherein the first formula is: T H ={t1|p L (t1)≥ρ p ·P Lmax}, T H P represents the historical daily peak load period. Lmax ρ represents the maximum daily load value among the multiple historical daily load information. p p is the coefficient for dividing peak hours. L (t1) represents the moment when the daily load value is greater than or equal to the product of the peak period division coefficient and the daily load maximum value, where t1 is a moment within the historical daily load peak period; the historical daily load trough period of the multiple historical daily load information is determined by a second formula, wherein the second formula is: T L ={t2|p L (t2)≤ρ b ·P Lmin}, T L P represents the historical daily load trough period. Lmaxρ represents the minimum daily load among the multiple historical daily load information. b p is the coefficient for dividing the trough period. L (t2) represents the moment when the daily load value is less than or equal to the product of the low-load period division coefficient and the daily load minimum value, where t2 is a moment within the historical daily load peak period; the historical daily load mid-load period of the multiple historical daily load information is determined by a third formula, wherein the third formula is: T M ={t3|ρ b ·P Lmin <p L (t3)<ρ p ·P Lmax}, T M p represents the historical daily load period. L (t3) represents the moment when the daily load value is less than or equal to the product of the valley period division coefficient and the daily minimum load value. t3 is the moment in the historical daily load waist load period.

[0009] Optionally, establishing a source-load coupling characteristic evaluation index based on the load characteristic value includes: generating a wind power-load coupling characteristic index system in the power consumption area, wherein the wind power-load coupling characteristic index system is an evaluation index of the coupling relationship between the output of the wind turbine generator and the power consumption end in the power consumption area; generating a photovoltaic-load coupling characteristic index system in the power consumption area, wherein the photovoltaic-load coupling characteristic index system is an evaluation index of the coupling relationship between the output of the photovoltaic generator and the power consumption end in the power consumption area; and determining the source-load coupling characteristic evaluation index based on the wind power-load coupling characteristic index system and the photovoltaic-load coupling characteristic index system.

[0010] Optionally, the wind power-load coupling characteristic index system includes at least: maximum wind power output during peak daily load, minimum wind power output during peak daily load, average wind power output during peak daily load, maximum wind power output during off-peak daily load, average wind power output during off-peak daily load, average wind power output during mid-load daily load, proportion of daily wind power generation, rate of change of maximum output during off-peak daily load, and rate of change of maximum wind power output during peak daily load.

[0011] Optionally, the average wind power output during the daily peak load period is obtained using a fourth formula, wherein the fourth formula is: P represents the average wind power output during the peak load period of the day. W (t) represents the wind power output at time t during the peak daily load period, N size (T H ) represents the daily peak load period T HThe number of time periods included; the average wind power output during the daily load off-peak period is obtained through the fifth formula, which is: P represents the average wind power output during the daily off-peak load period. W (t) represents the wind power output at time t during the peak daily load period, N size (T L ) represents the daily load trough period T. L The number of time periods included; the average wind power output during the daily load period is obtained through the sixth formula, which is: P represents the average wind power output during the day's mid-load period. W (t) represents the wind power output at time t during the peak daily load period, N size (T M ) represents the number of moments included in the daily load waist load period.

[0012] Optionally, the wind power-load coupling characteristic index system further includes: the rate of change of maximum output during the daily load off-peak period, the rate of change of maximum wind power output during the daily load peak period, and the anti-peak shaving coefficient, wherein the anti-peak shaving coefficient is obtained through the seventh formula, which is: R W The inverse peak adjustment coefficient is... Indicates the maximum net load for the entire day. L represents the minimum net load for the entire day. max L represents the maximum daily load for the entire day. min This indicates the minimum daily load for the entire day.

[0013] Optionally, the photovoltaic-load coupling characteristic index system in the power consumption area shall include at least: the maximum daily output of photovoltaic power, the average daily output of photovoltaic power, the average output of photovoltaic power during peak load periods, and the proportion of daily photovoltaic power generation.

[0014] Optionally, clustering the feature index set to obtain the clustered feature index set of the wind and solar power output scene includes: selecting multiple daily wind and solar power output scenes as initial cluster centers from all wind and solar power output scenes corresponding to the feature index set; determining the distance between all wind and solar power output scenes and each of the initial cluster centers; storing a predetermined number of wind and solar power output scenes with a distance less than a distance threshold into a scene set, and determining new cluster centers based on the wind and solar power output scenes in the scene set, until the maximum iteration is reached, to obtain the clustered feature index set of the wind and solar power output scene.

[0015] Optionally, a target wind and solar power output scenario is selected from the wind and solar power output scenarios of the typical day based on the feature index set of the clustered wind and solar power output scenarios, including at least one of the following: selecting multiple first wind and solar power output scenarios with the highest daily maximum net load based on the feature index set of the clustered wind and solar power output scenarios; selecting a second wind and solar power output scenario with the highest anti-peak shaving coefficient from each of the first wind and solar power output scenarios; selecting a third wind and solar power output scenario with the largest daily peak-valley difference from the second wind and solar power output scenarios based on the daily peak-valley difference; and determining the third wind and solar power output scenario as the target wind and solar power output scenario.

[0016] Optionally, the method for generating the source-load coupled wind and solar power output scenario further includes: determining an energy optimization strategy for the power consumption area in the future period after the historical power consumption time period based on the target wind and solar power output scenario, wherein the energy optimization strategy is used to optimize the power system; and optimizing the power system in the future period according to the energy optimization strategy.

[0017] According to another aspect of the present invention, an apparatus for generating a source-load coupled wind and solar power output scenario is also provided, comprising: an acquisition unit, configured to acquire load characteristic values ​​of typical daily load information within an area where a new energy power station is located, wherein the typical daily load information is the electricity consumption information of a typical day in the electricity consumption area corresponding to the new energy power station, the typical day is at least one day selected from the historical electricity consumption time period of the electricity consumption area according to a predetermined index, and the load characteristic values ​​include at least: daily load peak period, daily load trough period, and daily load mid-load period; an establishment unit, configured to establish a source-load coupling characteristic evaluation index based on the load characteristic values; a generation unit, configured to generate a set of characteristic indexes for a wind and solar power output scenario based on the source-load coupling characteristic evaluation indexes; a clustering unit, configured to cluster the set of characteristic indexes to obtain a clustered set of characteristic indexes for the wind and solar power output scenario; and a filtering unit, configured to filter out target wind and solar power output scenarios from the typical day's wind and solar power output scenarios based on the clustered set of characteristic indexes for the wind and solar power output scenarios.

[0018] Optionally, the acquisition unit includes: a collection module for collecting multiple historical daily load information of the electricity consumption area within the historical electricity consumption time period; an analysis module for analyzing the multiple historical daily load information to obtain historical load characteristic values ​​of the multiple historical daily load information; a first generation module for generating a daily load characteristic curve based on the historical load characteristic values ​​of the multiple historical daily load information; and an acquisition module for acquiring the load characteristic values ​​based on the daily load characteristic curve and the daily load information.

[0019] Optionally, the analysis module includes: a first determining submodule, configured to determine the historical daily load peak periods of the plurality of historical daily load information using a first formula, wherein the first formula is: T H ={t1|p L (t1)≥ρ p ·P Lmax}, T H P represents the peak load period of the historical days. Lmax ρ represents the maximum daily load value among the multiple historical daily load information. p p is the coefficient for dividing peak hours. L (t1) represents the moment when the daily load value is greater than or equal to the product of the peak period division coefficient and the daily load maximum value, where t1 is a moment within the historical daily load peak period; the second determining submodule is used to determine the historical daily load trough period of the multiple historical daily load information through a second formula, wherein the second formula is: T L ={t2|p L (t2)≤ρ b ·P Lmin}, T L P represents the historical daily load trough period. Lmax ρ represents the minimum daily load among the multiple historical daily load information. b p is the coefficient for dividing the trough period. L (t2) represents the moment when the daily load value is less than or equal to the product of the low-load period division coefficient and the daily load minimum value, where t2 is a moment within the historical daily load peak period; the third determining submodule is used to determine the historical daily load mid-load period of the multiple historical daily load information through a third formula, wherein the third formula is: T M ={t3|ρ b ·P Lmin <p L (t3)<ρ p ·P Lmax}, T M p represents the historical daily load period. L (t3) represents the moment when the daily load value is less than or equal to the product of the valley period division coefficient and the daily minimum load value. t3 is the moment in the historical daily load waist load period.

[0020] Optionally, the establishing unit includes: a second generation module, used to generate a wind power-load coupling characteristic index system in the power consumption area, wherein the wind power-load coupling characteristic index system is an evaluation index of the coupling relationship between the output of the wind turbine generator and the power consumption end in the power consumption area; a third generation module, used to generate a photovoltaic-load coupling characteristic index system in the power consumption area, wherein the photovoltaic-load coupling characteristic index system is an evaluation index of the coupling relationship between the output of the photovoltaic generator and the power consumption end in the power consumption area; and a first determining module, used to determine the source-load coupling characteristic evaluation index based on the wind power-load coupling characteristic index system and the photovoltaic-load coupling characteristic index system.

[0021] Optionally, the wind power-load coupling characteristic index system includes at least: maximum wind power output during peak daily load, minimum wind power output during peak daily load, average wind power output during peak daily load, maximum wind power output during off-peak daily load, average wind power output during off-peak daily load, average wind power output during mid-load daily load, proportion of daily wind power generation, rate of change of maximum output during off-peak daily load, and rate of change of maximum wind power output during peak daily load.

[0022] Optionally, the average wind power output during the daily peak load period is obtained using a fourth formula, wherein the fourth formula is: P represents the average wind power output during the peak load period of the day. W (t) represents the wind power output at time t during the peak daily load period, N size (T H ) represents the daily peak load period T H The number of time periods included; the average wind power output during the daily load off-peak period is obtained through the fifth formula, which is: P represents the average wind power output during the daily off-peak load period. W (t) represents the wind power output at time t during the peak daily load period, N size (T L ) represents the daily load trough period T. L The number of time periods included; the average wind power output during the daily load period is obtained through the sixth formula, which is: P represents the average wind power output during the day's mid-load period. W (t) represents the wind power output at time t during the peak daily load period, N size (T M ) represents the number of moments included in the daily load waist load period.

[0023] Optionally, the wind power-load coupling characteristic index system further includes: the rate of change of maximum output during the daily load off-peak period, the rate of change of maximum wind power output during the daily load peak period, and the anti-peak shaving coefficient, wherein the anti-peak shaving coefficient is obtained through the seventh formula, which is: R W The inverse peak adjustment coefficient is... Indicates the maximum net load for the entire day. L represents the minimum net load for the entire day. max L represents the maximum daily load for the entire day. min This indicates the minimum daily load for the entire day.

[0024] Optionally, the photovoltaic-load coupling characteristic index system in the power consumption area shall include at least: the maximum daily output of photovoltaic power, the average daily output of photovoltaic power, the average output of photovoltaic power during peak load periods, and the proportion of daily photovoltaic power generation.

[0025] Optionally, the clustering unit includes: a first selection module, used to select multiple daily wind and solar power output scenarios as initial cluster centers from all wind and solar power output scenarios corresponding to the feature index set; a second determination module, used to determine the distance between all wind and solar power output scenarios and each of the initial cluster centers; and a clustering module, used to store a predetermined number of wind and solar power output scenarios with distances less than a distance threshold into a scene set, and determine new cluster centers based on the wind and solar power output scenarios in the scene set, until the maximum iteration is reached, to obtain the feature index set of the clustered wind and solar power output scenarios.

[0026] Optionally, the filtering unit includes at least one of the following: a second selection module, configured to select multiple first wind and solar power output scenarios with the highest daily maximum net load based on the clustered set of characteristic indicators of the wind and solar power output scenarios; a third selection module, configured to select a second wind and solar power output scenario with the highest anti-peak shaving coefficient from each of the first wind and solar power output scenarios; a fourth selection module, configured to select a third wind and solar power output scenario with the largest daily peak-valley difference from the second wind and solar power output scenarios based on the daily peak-valley difference; and a third determination module, configured to determine the third wind and solar power output scenario as the target wind and solar power output scenario.

[0027] Optionally, the device for generating the source-load coupled wind and solar power output scenario further includes: a determining unit, configured to determine an energy optimization strategy for the power consumption area in the future period after the historical power consumption time period based on the target wind and solar power output scenario, wherein the energy optimization strategy is used for power system optimization; and an optimization unit, configured to optimize the power system in the future period according to the energy optimization strategy.

[0028] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes the method for generating a source-load coupled wind-solar power output scenario as described in any one of the above embodiments.

[0029] According to another aspect of the present invention, a processor is also provided, the processor being configured to run a program, wherein the program, when running, executes the method for generating a source-load coupled wind-solar power output scenario as described in any of the preceding embodiments.

[0030] In this embodiment of the invention, load characteristic values ​​of typical daily load information within the area where the new energy power station is located are obtained. The typical daily load information refers to the electricity consumption information of the electricity consumption area corresponding to the new energy power station on a typical day. A typical day is at least one day selected from the historical electricity consumption time period of the electricity consumption area according to predetermined indicators. The load characteristic values ​​include at least: daily peak load period, daily low load period, and daily mid-load period. A source-load coupling characteristic evaluation index is established based on the load characteristic values. A set of characteristic indicators for wind and solar power output scenarios is generated based on the source-load coupling characteristic evaluation index. The set of characteristic indicators is clustered to obtain a clustered set of characteristic indicators for wind and solar power output scenarios. Target wind and solar power output scenarios are selected from the wind and solar power output scenarios of typical days based on the clustered set of characteristic indicators for wind and solar power output scenarios. Through the above-mentioned technical solution of the present invention, the original wind and solar power output scenarios are transformed into a set of feature indicators. By clustering and filtering the feature indicators, a probabilistic wind and solar power output scenario is obtained. This ensures that the generated wind and solar power output scenario meets the source-load coupling characteristics and can meet the diverse needs of new energy power output scenarios in power system operation and planning. In turn, it solves the technical problem that most wind and solar power output scenario generation methods in related technologies only consider the probability distribution characteristics of wind and solar power, which has a large degree of randomness. The resulting deviation in wind and solar power output scenario will be transmitted to the power system operation simulation calculation results, thereby affecting the power balance results. Attached Figure Description

[0031] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0032] Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of generating a source-load coupled wind and solar power output scene according to an embodiment of the present invention.

[0033] Figure 2 This is a flowchart of a method for generating a source-load coupled wind and solar power output scenario according to an embodiment of the present invention;

[0034] Figure 3This is a diagram illustrating the typical daily load characteristics according to an embodiment of the present invention;

[0035] Figure 4 This is a flowchart of an optional source-load coupled wind and solar power output scenario generation method according to an embodiment of the present invention;

[0036] Figure 5 This is a schematic diagram of a device for generating a source-load coupled wind and solar power output scene according to an embodiment of the present invention. Detailed Implementation

[0037] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0039] As described in the background section, most existing methods for generating wind and solar power output scenarios only consider the probability distribution characteristics of wind and solar power, or generate random wind and solar power scenarios based on Monte Carlo random simulation methods. They lack consideration for source-load coupling characteristics. On the one hand, they ignore the temporal characteristics of wind and solar power, leading to inconsistencies between the wind and solar power output curves and historical scenarios. On the other hand, they ignore the cross-correlation between the wind and solar power output sequence and the load sequence, failing to consider the impact of source-load coupling characteristics on the wind power output sequence. The deviations in wind and solar power output scenarios caused by these problems will be transmitted to the power system operation simulation calculation results, thereby affecting the power balance results. In the embodiments of this invention, a method and apparatus for generating source-load coupled wind and solar power output scenarios, a computer-readable storage medium, and a processor are provided.

[0040] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0041] The methods and embodiments provided in this invention can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of generating a source-load coupled wind and solar power output scene according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0042] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the source-load coupling wind and solar power output scenario generation method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one instance, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0043] According to an embodiment of the present invention, a method embodiment for generating a source-load coupled wind and solar power output scenario is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0044] Figure 2 This is a flowchart of a method for generating a source-load coupled wind-solar power output scenario according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes the following steps:

[0045] Step S202: Obtain the load characteristic value of typical daily load information in the area where the new energy power station is located. The typical daily load information is the electricity consumption information of the electricity consumption area corresponding to the new energy power station on a typical day. The typical day is at least one day selected from the historical electricity consumption time period of the electricity consumption area according to predetermined indicators. The load characteristic value includes at least the daily load peak period, the daily load trough period, and the daily load mid-load period.

[0046] Optionally, the aforementioned typical day can be selected from at least one day in a historical time period according to predetermined indicators. For example, when making power system plans, the day with the highest electricity load in the province that year can be selected as the typical day; or, for example, the day with the highest electricity load in each month of the province that year can be selected as the typical day.

[0047] In this embodiment, based on the historical operating experience of the power system, the daily load characteristics of a large-scale power system are generally "double-peak" characteristics, namely the morning peak and the evening peak.

[0048] Step S204: Establish source-load coupling characteristic evaluation index based on load characteristic values.

[0049] Step S206: Generate a set of feature indicators for wind and solar power output scenarios based on the source-load coupling characteristic evaluation index.

[0050] Step S208: Cluster the feature index set to obtain the clustered feature index set of the wind and solar power output scenario.

[0051] Step S210: Select target wind and solar power output scenarios from the wind and solar power output scenarios of typical days based on the feature index set of clustered wind and solar power output scenarios.

[0052] As can be seen from the above, in this embodiment of the invention, load characteristic values ​​of typical daily load information in the area where the new energy power station is located can be obtained. The typical daily load information refers to the electricity consumption information of the electricity consumption area corresponding to the new energy power station on a typical day. A typical day is at least one day selected from the historical electricity consumption time period of the electricity consumption area according to predetermined indicators. The load characteristic values ​​include at least: daily load peak period, daily load valley period, and daily load mid-load period. A source-load coupling characteristic evaluation index is established based on the load characteristic values. A set of characteristic indicators for wind and solar power output scenarios is generated based on the source-load coupling characteristic evaluation index. The set of characteristic indicators is clustered to obtain a clustered set of characteristic indicators for wind and solar power output scenarios. Target wind and solar power output scenarios are selected from the wind and solar power output scenarios of typical days based on the clustered set of characteristic indicators for wind and solar power output scenarios. This achieves the goal of transforming the original wind and solar power output scenarios into a set of characteristic indicators. By clustering and selecting the characteristic indicators, a probabilistic wind and solar power output scenario is obtained, ensuring that the generated wind and solar power output scenario meets the source-load coupling characteristics and can meet the diverse needs of new energy power output scenarios in power system operation and planning.

[0053] Therefore, the technical solution described in the above embodiments of the present invention solves the technical problem that most wind and solar power output scenario generation methods in related technologies only consider the probability distribution characteristics of wind and solar power, which have a large degree of randomness. As a result, the deviation of wind and solar power output scenarios will be transmitted to the power system operation simulation calculation results, thereby affecting the power balance results.

[0054] In step S202 of the present invention, optionally, obtaining the load characteristic value of typical daily load information in the area where the new energy power station is located includes: collecting multiple historical daily load information of the power consumption area within a historical power consumption period; analyzing the multiple historical daily load information to obtain the historical load characteristic value of the multiple historical daily load information; generating a daily load characteristic curve based on the historical load characteristic value of the multiple historical daily load information; and obtaining the load characteristic value based on the daily load characteristic curve and the daily load information.

[0055] In this embodiment, multiple historical daily load information of new energy power plants within a historical time period, such as one year, can be collected and analyzed to obtain historical load characteristic values ​​of multiple historical daily load information. A daily load characteristic curve is generated based on the historical load characteristic values ​​of multiple historical daily load information, thereby obtaining load characteristic values ​​based on the daily load characteristic curve and daily load information.

[0056] In the above embodiments, optionally, the historical load characteristic values ​​of multiple historical days are analyzed to obtain the historical load characteristic values ​​of the multiple historical days, including: determining the historical daily load peak periods of the multiple historical days using a first formula, wherein the first formula is: T H ={t1|p L(t1)≥ρ p ·P Lmax}, T H P represents the historical daily peak load period. Lmax ρ represents the maximum daily load value among multiple historical daily load data. p p is the coefficient for dividing peak hours. L (t1) represents the moment when the daily load value is greater than or equal to the product of the peak period division factor and the maximum daily load value. t1 is a moment within the historical daily load peak period. The historical daily load trough period is determined by the second formula, where the second formula is: T L ={t2|p L (t2)≤ρ b ·P Lmin}, T L P represents the historical daily load trough period. Lmax ρ represents the minimum daily load value among multiple historical daily load data. b p is the coefficient for dividing the trough period. L (t2) represents the moment when the daily load value is less than or equal to the product of the off-peak period division factor and the daily minimum load value. t2 is a moment within the historical daily load peak period. The historical daily load mid-load period for multiple historical daily load information is determined by the third formula, where the third formula is: T M ={t3|ρ b ·P Lmin <p L (t3)<ρ p ·P Lmax}, T M p represents the historical daily load period. L (t3) indicates the moment when the daily load value is less than or equal to the product of the low-end period division coefficient and the daily minimum load value. t3 is the moment in the historical daily load mid-load period.

[0057] In this embodiment, the historical daily load peak period, historical daily load trough period, and historical daily load mid-load period can be obtained through the above formulas. Wherein, the above ρ... p Generally, ρ is taken as 0.85-0.9. bGenerally, a value of 1.05-1.2 is used. According to the above embodiments of the present invention, a source-load coupling characteristic evaluation index is established based on the load characteristic value, including: generating a wind power-load coupling characteristic index system in the power consumption area, wherein the wind power-load coupling characteristic index system is an evaluation index of the coupling relationship between the output of wind turbine units and the power consumption end in the power consumption area; generating a photovoltaic-load coupling characteristic index system in the power consumption area, wherein the photovoltaic-load coupling characteristic index system is an evaluation index of the coupling relationship between the output of photovoltaic units and the power consumption end in the power consumption area; and determining the source-load coupling characteristic evaluation index based on the wind power-load coupling characteristic index system and the photovoltaic-load coupling characteristic index system.

[0058] This embodiment can establish a wind power-load coupling characteristic evaluation index system and a photovoltaic-load coupling characteristic index system in the power consumption area, thereby determining the wind and solar power output characteristic indexes based on the wind power-load coupling characteristic evaluation index system and the photovoltaic-load coupling characteristic index system in the power consumption area.

[0059] Figure 3 This is a diagram illustrating the typical daily load characteristics according to an embodiment of the present invention, such as... Figure 3 As shown, the reference values ​​for the daily peak load time are: ρ p ·P Lmax Reference value for the lowest daily load: ρ b ·P Lmin Changes over time.

[0060] The following explains the evaluation index system for wind power-load coupling characteristics and the photovoltaic-load coupling characteristic index system for power consumption areas.

[0061] The wind power-load coupling characteristic index system includes at least the following: maximum wind power output during peak load period, minimum wind power output during peak load period, average wind power output during peak load period, maximum wind power output during off-peak load period, average wind power output during off-peak load period, average wind power output during mid-load period, wind power daily power generation ratio, rate of change of maximum output during off-peak load period, and rate of change of maximum wind power output during peak load period.

[0062] The above-mentioned peak wind power output during the peak load period This refers to the system's ability to allow higher wind power output during peak daily load periods, primarily affecting the system's power balance. This is determined by the formula... It means that P W (t) represents the wind power output at time t.

[0063] The minimum output of wind power during the above-mentioned peak load period It primarily affects system reliability and the output plans of new energy and conventional generating units. This is expressed by the following formula.

[0064] The average wind power output during the peak daily load period mentioned above is obtained through the fourth formula, which is: P represents the average wind power output during peak daily load periods. W (t) represents the wind power output at time t during the peak daily load period, N size (T H ) represents the peak daily load period T H The number of time periods included; the average wind power output during the daily off-peak load period is obtained through the fifth formula, which is: P represents the average wind power output during the off-peak hours of the day. W (t) represents the wind power output at time t during the peak daily load period, N size (T L ) represents the period of lowest daily load, T L The number of time periods included; the average wind power output during the daily load mid-load period is obtained through the sixth formula, which is: P represents the average wind power output during the mid-load period of the day. W (t) represents the wind power output at time t during the peak daily load period, N size (T M () represents the number of moments included in the daily load waist load period.

[0065] The average wind power output during peak load periods mentioned above reflects the amount of electricity generated by wind power during these periods. Maximum wind power output during off-peak load periods is also shown. Minimum output It reflects the system's peak-shaving demand and affects the amount of wind power absorbed and the amount of wind power curtailed. This is expressed by the following formula: Average wind power output during off-peak hours This reflects the amount of electricity generated by wind power during the off-peak hours of the day. Average wind power output during the mid-load period of the day. It reflects the amount of electricity generated by wind power during the mid-load period of the day.

[0066] The above-mentioned daily wind power generation ratio λ W This represents the proportion of wind power generation to total load during the day. When wind power output increases, thermal power units need to reduce their output to maintain system power balance. Due to the limited self-regulation capacity of the units, the higher the proportion of wind power generation, the greater the impact on renewable energy consumption and the system's peak-shaving capacity. This is expressed by the following formula: In the formula, L(t) represents the load value at time t.

[0067] Based on the above indicators, three indicators can be derived: the rate of change of wind power maximum output during the daily load trough period, the rate of change of wind power peak shaving during the daily load mid-load period, and the rate of change of wind power peak shaving during the daily load mid-load period. These indicators more comprehensively reflect the inherent resource characteristics of wind power and the coupling relationship between wind power and load.

[0068] According to the above embodiments of the present invention, the wind power-load coupling characteristic index system further includes: the rate of change of maximum output during the daily load off-peak period, the rate of change of maximum wind power output during the daily load peak period, and the anti-peak shaving coefficient, wherein the anti-peak shaving coefficient is obtained by the seventh formula, which is: R W This is the anti-peak adjustment coefficient. Indicates the maximum net load for the entire day. L represents the minimum net load for the entire day. max L represents the maximum daily load for the entire day. min This indicates the minimum daily load for the entire day.

[0069] The above-mentioned rate of change of maximum wind power output during off-peak and peak load periods This represents the maximum rate of change in wind power output during peak and off-peak periods, reflecting to some extent the fluctuation characteristics and trends of the wind power output curve. It can be expressed by the following formula:

[0070] The above-mentioned anti-peak modulation coefficient R W The anti-peak coefficient reflects the degree to which the direction of wind power change is opposite to the direction of load change throughout the day. The larger the anti-peak coefficient, the greater the difference between the direction of wind power change and load change, the more severe the degree of anti-peak shaving in the system, and the greater the pressure on peak shaving throughout the day.

[0071] The net load at time L can be expressed by formula L. net (t)=L(t)-P W (t) represents the maximum daily net load for the entire day. Through formula This indicates the minimum net load for the entire day. Through formula Indicates. L max L min These represent the maximum and minimum daily loads, respectively; T D This indicates all time periods throughout the day.

[0072] In this embodiment of the invention, the rate of change of wind power peak shaving during the daily load mid-load period is... This reflects the peak-shaving capacity of wind power output during periods of low load, as it follows load changes. The larger the absolute value, the greater the difference between the rate of change of wind power output and load, and the greater the peak-shaving pressure during the system's mid-load period. (Based on the formula...) Indicated. In the formula, These represent the maximum and minimum wind power output during the day's mid-load period, respectively. These represent the daily maximum and minimum loads during the waist load period, respectively.

[0073] In this embodiment of the invention, the daily peak-valley difference in wind power output ΔP W Through formula It means that, in the formula, The maximum wind power output for the entire day is expressed by the formula. express; This represents the minimum wind power output for the entire day, expressed by the formula... Indicates ΔP W This indicates the peak-to-valley difference in wind power output throughout the day.

[0074] In this embodiment of the invention, the photovoltaic-load coupling characteristic index system in the new energy power station includes at least: the maximum daily output of photovoltaic power, the average daily output of photovoltaic power, the average output of photovoltaic power during peak load periods, and the proportion of daily photovoltaic power generation.

[0075] The above-mentioned maximum daily output of photovoltaic power P Vmax This reflects the highest daily output level of photovoltaic power generation, affecting the peak-shaving demand of photovoltaic power generation, and is expressed by the formula... It means that, in the formula, P V (t) represents the photovoltaic output at time t. The above-mentioned average daily photovoltaic output P Vavg : Reflects the daily power generation of photovoltaics, expressed by the formula The above refers to the average output during peak daily photovoltaic load periods. Average output during waist load The impact of photovoltaic power output on the consumption of new energy sources is reflected in the following ways. This indicates that the aforementioned daily photovoltaic power generation accounts for λ. V This represents the proportion of daily photovoltaic (PV) power generation to total load. Similar to the principle when wind power output increases, a higher proportion of PV power generation has a greater impact on the absorption of new energy sources. This is expressed by the following formula:

[0076] The above indicators reflect the coupling between new energy sources and loads well. Combining the inherent resource characteristics of new energy sources, a new energy output model considering the source-load coupling characteristics is established to generate probabilistic new energy output scenarios.

[0077] According to the above embodiments of the present invention, clustering the feature index set to obtain the clustered feature index set of the wind and solar power output scene includes: selecting multiple daily wind and solar power output scenes as initial cluster centers from all wind and solar power output scenes corresponding to the feature index set; determining the distance between all wind and solar power output scenes and each initial cluster center; storing a predetermined number of wind and solar power output scenes with a distance less than a distance threshold into a scene set, and determining new cluster centers based on the wind and solar power output scenes in the scene set, until the maximum iteration is reached, to obtain the clustered feature index set of the wind and solar power output scene.

[0078] In this embodiment, a set of wind power output characteristic indices that consider source-load coupling characteristics can be defined: In the formula, λ W and R W It mainly affects the peak-shaving balance of the system; and The main impact is on the system's power balance; ΔP W It primarily affects the volatility of wind power. A set of photovoltaic output characteristic indices considering source-load coupling characteristics is defined: In the formula, λ V The main impact is on the peak-shaving balance of the system; P Vmax It mainly affects the power balance of the system; P Vavg It mainly affects the power balance of the system.

[0079] Furthermore, the k-means clustering algorithm can be used to cluster the wind and solar power index set. Taking wind power as an example, K daily power generation scenarios are selected as the initial cluster centers {μ1,μ2,...,μ3} from the sample set D of all wind power daily power generation scenarios. K}, initialize the cluster partition C to The input is the sample set D = {x1, x2, ..., x} of all wind power generation scenarios. m}, where K is the number of clusters and K is the maximum number of iterations. The output is the cluster partition C = {C1, C2, ..., C}. K For i = 1, 2, ..., m, calculate the scene sample x. i With each cluster center μ j The distance between (j = 1, 2, ..., K) is: d ij =||x i -μ j ||, will the scene sample x i Reduced to the smallest d ij The corresponding scene set category j is determined, and the cluster is updated to C. j =C j ∪{x i For each predefined category, recalculate the center point of all scene samples for each category. And the calculated μ j As the new cluster center, repeat steps S42-S43 until the maximum number of iterations is reached, then terminate the iteration.

[0080] According to the above embodiments of the present invention, a target wind and solar power output scenario is selected from the wind and solar power output scenarios of a typical day based on the feature index set of the clustered wind and solar power output scenarios, including at least one of the following: selecting multiple first wind and solar power output scenarios with the highest daily maximum net load based on the feature index set of the clustered wind and solar power output scenarios; selecting a second wind and solar power output scenario with the highest anti-peak shaving coefficient from each of the first wind and solar power output scenarios; selecting a third wind and solar power output scenario with the largest daily peak-valley difference from the second wind and solar power output scenarios based on the daily peak-valley difference; and determining the third wind and solar power output scenario as the target wind and solar power output scenario.

[0081] In this embodiment, it can be based on the maximum net load. To select, choose the curves with the highest net load values, specifically the top 50% of the curves: L net (t)=L(t)-P(t), In the formula, L net (t) represents the net load at time t. T represents the maximum net load for the entire day; D This represents all time periods throughout the day; alternatively, it can be selected based on the anti-peak shaving coefficient R, choosing the top 50% of curves with the highest anti-peak shaving coefficients from the curves selected above: L net (t)=L(t)-P(t), In the formula, L net (t) represents the net load at time t; These represent the maximum and minimum net load for the entire day, respectively; L max L min These represent the maximum and minimum daily loads, respectively; T D This represents all time periods throughout the day; and can be selected based on the sunrise power peak-to-valley difference ΔP, choosing the curve with the largest peak-to-valley difference from the curves selected above: In the formula, Indicates the maximum output of wind / solar power throughout the day; ΔP represents the minimum output of wind / solar power throughout the day; ΔP represents the peak-to-valley difference in wind / solar power output throughout the day.

[0082] Figure 4 This is a flowchart of an optional power system optimization method based on wind and solar power output scenarios according to an embodiment of the present invention, such as... Figure 4As shown, firstly, based on the typical daily load characteristic curve, the typical daily load peak, valley, and mid-load periods are divided. Then, based on the typical daily load peak, valley, and mid-load periods, a source-load coupling characteristic evaluation index system is established. Next, based on the established source-load coupling characteristic evaluation index, a set of characteristic indicators for wind and solar power output scenarios is constructed. Finally, based on the characteristic indicator set of the power output scenarios, a clustering algorithm is used to cluster the wind and solar indicator set, and based on the wind and solar scenarios obtained from the clustering, scenario screening is performed to generate probabilistic typical daily scenarios at different time scales. Thus, based on the source-load coupling characteristics of the new power system, the original wind and solar power output scenarios are transformed into a set of characteristic indicators. By clustering and screening the characteristic indicators, probabilistic scenarios of wind and solar power output are obtained, ensuring that the generated wind and solar power output scenarios meet the source-load coupling characteristics and can meet the diverse needs of new energy power output scenarios in power system operation and planning.

[0083] According to the above embodiments of the present invention, the method for generating the source-load coupled wind and solar power output scenario further includes: determining the energy optimization strategy for the future power consumption area after determining the historical power consumption time period based on the target wind and solar power output scenario, wherein the energy optimization strategy is used to optimize the power system; and optimizing the power system according to the energy optimization strategy in the future time period.

[0084] In this embodiment, after obtaining the target wind and solar power output scenario, the renewable energy absorption capacity in the future period can be analyzed based on the obtained target wind and solar power output scenario, laying the foundation for the future planning of the power system.

[0085] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0086] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0087] According to embodiments of the present invention, an apparatus for generating a source-load coupled wind-solar power output scenario is also provided for implementing the above-described method for generating such a scenario. Figure 5 This is a schematic diagram of a device for generating a source-load coupled wind and solar power output scene according to an embodiment of the present invention, as shown below. Figure 5 As shown, the device includes: an acquisition unit 501, a creation unit 503, a generation unit 505, a clustering unit 507, and a filtering unit 509. Among them,

[0088] The acquisition unit 501 is used to acquire the load characteristic value of typical daily load information in the area where the new energy power station is located. The typical daily load information is the electricity consumption information of the electricity consumption area corresponding to the new energy power station on a typical day. The typical day is at least one day selected from the historical electricity consumption time period of the electricity consumption area according to predetermined indicators. The load characteristic value includes at least the daily load peak period, the daily load trough period, and the daily load mid-load period.

[0089] Unit 503 is established to create an evaluation index for source-load coupling characteristics based on load characteristic values.

[0090] The generation unit 505 is used to generate a set of feature indicators for wind and solar power output scenarios based on the source-load coupling characteristic evaluation index.

[0091] Clustering unit 507 is used to cluster the set of feature indicators to obtain the set of feature indicators of the wind and solar power output scene after clustering.

[0092] The filtering unit 509 is used to filter out target wind and solar power output scenarios from the wind and solar power output scenarios of a typical day based on the feature index set of the clustered wind and solar power output scenarios.

[0093] It should be noted that the above-mentioned acquisition unit 501, establishment unit 503, generation unit 505, clustering unit 507 and filtering unit 509 correspond to steps S202 to S210 in the above embodiments. The five units and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments.

[0094] As can be seen from the above, in the scheme described in the above embodiments of the present invention, the load characteristic value of typical daily load information in the area where the new energy power station is located can be obtained by the acquisition unit. The typical daily load information is the electricity consumption information of a typical day in the electricity consumption area corresponding to the new energy power station. The typical day is at least one day selected from the historical electricity consumption time period of the electricity consumption area according to predetermined indicators. The load characteristic value includes at least: daily load peak period, daily load valley period, and daily load mid-load period. Then, the establishment unit establishes a source-load coupling characteristic evaluation index based on the load characteristic value; and the generation unit generates wind power based on the source-load coupling characteristic evaluation index. The system generates a set of characteristic indicators for solar power output scenarios. It then uses clustering units to cluster these characteristic indicators, resulting in a clustered set of characteristic indicators for the solar power output scenarios. A filtering unit then selects target solar power output scenarios from typical day solar power output scenarios based on the clustered set of characteristic indicators. This process transforms the original solar power output scenarios into a set of characteristic indicators. By clustering and filtering these indicators, the system obtains probabilistic solar power output scenarios, ensuring that the generated scenarios meet the source-load coupling characteristics and can satisfy the diverse needs of new energy power output scenarios in power system operation and planning.

[0095] Therefore, the technical solution described in the above embodiments of the present invention solves the technical problem that most wind and solar power output scenario generation methods in related technologies only consider the probability distribution characteristics of wind and solar power, which have a large degree of randomness. As a result, the deviation of wind and solar power output scenarios will be transmitted to the power system operation simulation calculation results, thereby affecting the power balance results.

[0096] Optionally, the acquisition unit includes: an acquisition module for acquiring multiple historical daily load information of the electricity consumption area within a historical electricity consumption period; an analysis module for analyzing the multiple historical daily load information to obtain historical load characteristic values ​​of the multiple historical daily load information; a first generation module for generating a daily load characteristic curve based on the historical load characteristic values ​​of the multiple historical daily load information; and an acquisition module for acquiring load characteristic values ​​based on the daily load characteristic curve and the daily load information.

[0097] Optionally, the analysis module includes: a first determination submodule, used to determine the historical daily load peak periods of multiple historical daily load information through a first formula, wherein the first formula is: T H ={t1|p L (t1)≥ρ p ·P Lmax}, T H P represents the historical daily peak load period. Lmax ρ represents the maximum daily load value among multiple historical daily load data. p p is the coefficient for dividing peak hours. L(t1) represents the moment when the daily load value is greater than or equal to the product of the peak period division coefficient and the maximum daily load value; t1 is a moment within the historical daily load peak period. The second determining submodule is used to determine the historical daily load trough period of multiple historical daily load information through the second formula, where the second formula is: T L ={t2|p L (t2)≤ρ b ·P Lmin}, T L P represents the historical daily load trough period. Lmax ρ represents the minimum daily load value among multiple historical daily load data. b p is the coefficient for dividing the trough period. L (t2) represents the moment when the daily load value is less than or equal to the product of the low-load period division coefficient and the daily minimum load value; t2 is a moment within the historical daily load peak period; the third determination submodule is used to determine the historical daily load mid-load period of multiple historical daily load information through the third formula, where the third formula is: T M ={t3|ρ b ·P Lmin <p L (t3)<ρ p ·P Lmax}, T M p represents the historical daily load period. L (t3) indicates the moment when the daily load value is less than or equal to the product of the low-end period division coefficient and the daily minimum load value. t3 is the moment in the historical daily load mid-load period.

[0098] Optionally, the establishment unit includes: a second generation module for generating a wind power-load coupling characteristic index system in the power consumption area, wherein the wind power-load coupling characteristic index system is an evaluation index of the coupling relationship between the output of wind turbine units and the power consumption end in the power consumption area; a third generation module for generating a photovoltaic-load coupling characteristic index system in the power consumption area, wherein the photovoltaic-load coupling characteristic index system is an evaluation index of the coupling relationship between the output of photovoltaic units and the power consumption end in the power consumption area; and a first determination module for determining the source-load coupling characteristic evaluation index based on the wind power-load coupling characteristic index system and the photovoltaic-load coupling characteristic index system.

[0099] Optionally, the wind power-load coupling characteristic index system shall include at least the following: maximum wind power output during peak load period, minimum wind power output during peak load period, average wind power output during peak load period, maximum wind power output during off-peak load period, average wind power output during off-peak load period, average wind power output during mid-load period, proportion of daily wind power generation, rate of change of maximum output during off-peak load period, and rate of change of maximum wind power output during peak load period.

[0100] Optionally, the average wind power output during peak daily load periods is obtained using the fourth formula, which is: P represents the average wind power output during peak daily load periods. W (t) represents the wind power output at time t during the peak daily load period, N size (T H ) represents the peak daily load period T H The number of time periods included; the average wind power output during the daily off-peak load period is obtained through the fifth formula, which is: P represents the average wind power output during the off-peak hours of the day. W (t) represents the wind power output at time t during the peak daily load period, N size (T L ) represents the period of lowest daily load, T L The number of time periods included; the average wind power output during the daily load mid-load period is obtained through the sixth formula, which is: P represents the average wind power output during the mid-load period of the day. W (t) represents the wind power output at time t during the peak daily load period, N size (T M () represents the number of moments included in the daily load waist load period.

[0101] Optionally, the wind power-load coupling characteristic index system also includes: the rate of change of maximum output during the daily load off-peak period, the rate of change of maximum wind power output during the daily load peak period, and the anti-peak shaving coefficient. The anti-peak shaving coefficient is obtained through the seventh formula, which is: R W This is the anti-peak adjustment coefficient. Indicates the maximum net load for the entire day. L represents the minimum net load for the entire day. max L represents the maximum daily load for the entire day. min This indicates the minimum daily load for the entire day.

[0102] Optionally, the photovoltaic-load coupling characteristic index system in the power consumption area shall include at least: the maximum daily output of photovoltaic power, the average daily output of photovoltaic power, the average output of photovoltaic power during peak load periods, and the proportion of daily photovoltaic power generation.

[0103] Optionally, the clustering unit includes: a first selection module, used to select multiple daily wind and solar power output scenarios as initial cluster centers from all wind and solar power output scenarios corresponding to the feature index set; a second determination module, used to determine the distance between all wind and solar power output scenarios and each initial cluster center; and a clustering module, used to store a predetermined number of wind and solar power output scenarios with a distance less than a distance threshold into a scene set, and determine new cluster centers based on the wind and solar power output scenarios in the scene set, until the maximum iteration is reached, to obtain the feature index set of the clustered wind and solar power output scenarios.

[0104] Optionally, the filtering unit includes at least one of the following: a second selection module, used to select multiple first wind and solar power output scenarios with the highest daily maximum net load based on the feature index set of clustered wind and solar power output scenarios; a third selection module, used to select the second wind and solar power output scenario with the highest anti-peak shaving coefficient from each of the first wind and solar power output scenarios; a fourth selection module, used to select the third wind and solar power output scenario with the largest daily peak-valley difference from the second wind and solar power output scenarios based on the daily peak-valley difference; and a third determination module, used to determine the third wind and solar power output scenario as the target wind and solar power output scenario.

[0105] Optionally, the device for generating the source-load coupled wind and solar power output scenario further includes: a determining unit, used to determine the energy optimization strategy for the future power consumption area after the historical power consumption period based on the target wind and solar power output scenario, wherein the energy optimization strategy is used for power system optimization; and an optimization unit, used to optimize the power system in the future period according to the energy optimization strategy.

[0106] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes the method for generating a source-load coupled wind-solar power output scenario as described above.

[0107] Optionally, in this embodiment, the computer-readable storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any communication device in a group of communication devices.

[0108] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: obtaining load characteristic values ​​of typical daily load information in the area where the new energy power station is located, wherein the typical daily load information is the electricity consumption information of the electricity consumption area corresponding to the new energy power station on a typical day, and the typical day is at least one day selected from the historical electricity consumption time period of the electricity consumption area according to predetermined indicators, and the load characteristic values ​​include at least: daily load peak period, daily load trough period, and daily load mid-load period; establishing source-load coupling characteristic evaluation indicators based on the load characteristic values; generating a set of characteristic indicators for wind and solar power output scenarios based on the source-load coupling characteristic evaluation indicators; clustering the set of characteristic indicators to obtain a set of characteristic indicators for clustered wind and solar power output scenarios; and selecting target wind and solar power output scenarios from the wind and solar power output scenarios of typical days based on the set of characteristic indicators for clustered wind and solar power output scenarios.

[0109] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: collecting multiple historical daily load information of the electricity consumption area within a historical electricity consumption period; analyzing the multiple historical daily load information to obtain historical load characteristic values ​​of the multiple historical daily load information; generating a daily load characteristic curve based on the historical load characteristic values ​​of the multiple historical daily load information; and obtaining load characteristic values ​​based on the daily load characteristic curve and the daily load information.

[0110] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining the historical daily load peak periods of multiple historical daily load information using a first formula, wherein the first formula is: T H ={t1|p L (t1)≥ρ p ·P Lmax}, T H P represents the historical daily peak load period. Lmax ρ represents the maximum daily load value among multiple historical daily load data. p p is the coefficient for dividing peak hours. L (t1) represents the moment when the daily load value is greater than or equal to the product of the peak period division factor and the maximum daily load value. t1 is a moment within the historical daily load peak period. The historical daily load trough period is determined by the second formula, where the second formula is: T L ={t2|p L (t2)≤ρ b ·P Lmin}, T L P represents the historical daily load trough period. Lmax ρ represents the minimum daily load value among multiple historical daily load data. b p is the coefficient for dividing the trough period. L (t2) represents the moment when the daily load value is less than or equal to the product of the off-peak period division factor and the daily minimum load value. t2 is a moment within the historical daily load peak period. The historical daily load mid-load period for multiple historical daily load information is determined by the third formula, where the third formula is: T M ={t3|ρ b ·P Lmin <p L (t3)<ρ p ·P Lmax}, T M p represents the historical daily load period. L (t3) indicates the moment when the daily load value is less than or equal to the product of the low-end period division coefficient and the daily minimum load value. t3 is the moment in the historical daily load mid-load period.

[0111] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: generating a wind power-load coupling characteristic index system in the power consumption area, wherein the wind power-load coupling characteristic index system is an evaluation index of the coupling relationship between the output of wind turbine units and the power consumption end in the power consumption area; generating a photovoltaic-load coupling characteristic index system in the power consumption area, wherein the photovoltaic-load coupling characteristic index system is an evaluation index of the coupling relationship between the output of photovoltaic units and the power consumption end in the power consumption area; and determining the source-load coupling characteristic evaluation index based on the wind power-load coupling characteristic index system and the photovoltaic-load coupling characteristic index system.

[0112] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: selecting multiple daily wind and solar power output scenarios as initial cluster centers from all wind and solar power output scenarios corresponding to the feature index set; determining the distance between all wind and solar power output scenarios and each initial cluster center; storing a predetermined number of wind and solar power output scenarios with a distance less than a distance threshold into a scene set, and determining new cluster centers based on the wind and solar power output scenarios in the scene set, until the maximum iteration is reached, to obtain the feature index set of the clustered wind and solar power output scenarios.

[0113] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: selecting multiple first wind and solar power output scenarios with the highest daily maximum net load based on the feature index set of clustered wind and solar power output scenarios; selecting the second wind and solar power output scenario with the highest anti-peak shaving coefficient from each of the first wind and solar power output scenarios; selecting the third wind and solar power output scenario with the largest daily peak-valley difference from the second wind and solar power output scenarios based on the daily peak-valley difference; and determining the third wind and solar power output scenario as the target wind and solar power output scenario.

[0114] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining an energy optimization strategy for the future electricity consumption area based on the historical electricity consumption time period according to the target wind and solar power output scenario, wherein the energy optimization strategy is used to optimize the power system; and optimizing the power system according to the energy optimization strategy in the future time period.

[0115] According to another aspect of the present invention, a processor is also provided, which is used to run a program, wherein the program executes the method for generating a source-load coupled wind-solar power output scenario as described above.

[0116] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0117] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0118] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0119] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0121] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0122] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for generating a source-load coupled wind-solar power output scenario, characterized in that, include: The load characteristic value of typical daily load information in the area where the new energy power station is located is obtained. The typical daily load information is the electricity consumption information of a typical day in the electricity consumption area corresponding to the new energy power station. The typical day is at least one day selected from the historical electricity consumption time period of the electricity consumption area according to a predetermined index. The load characteristic value includes at least: daily load peak period, daily load trough period and daily load mid-load period. Establish an evaluation index for source-load coupling characteristics based on the aforementioned load characteristic values; A set of feature indicators for wind and solar power output scenarios is generated based on the evaluation index of source-load coupling characteristics. Cluster the set of feature indicators to obtain the clustered set of feature indicators for the wind and solar power output scenario. Based on the clustered set of characteristic indicators of the solar power output scenarios, target solar power output scenarios are selected from the solar power output scenarios of the typical day. The process of obtaining load characteristic values ​​of typical daily load information in the area where the new energy power station is located includes: collecting multiple historical daily load information of the power consumption area within the historical power consumption time period; analyzing the multiple historical daily load information to obtain historical load characteristic values ​​of the multiple historical daily load information; generating a daily load characteristic curve based on the historical load characteristic values ​​of the multiple historical daily load information; and obtaining the load characteristic values ​​based on the daily load characteristic curve and the daily load information. The analysis of the multiple historical daily load information to obtain historical load characteristic values ​​includes: determining the historical daily load peak periods of the multiple historical daily load information using a first formula, wherein the first formula is: , This indicates the peak load period of the historical days. This represents the maximum daily load value among the multiple historical daily load information. Divide the peak period into coefficients. This indicates the time when the daily load value is greater than or equal to the product of the peak period division factor and the maximum daily load value. It refers to the time within the historical daily load peak period; the historical daily load trough period of the multiple historical daily load information is determined by a second formula, wherein the second formula is: , This indicates the historical daily load trough period. This represents the minimum daily load among the multiple historical daily load data. The coefficient for dividing the low-end period. This indicates the time when the daily load value is less than or equal to the product of the off-peak period division coefficient and the daily minimum load value. It refers to the time within the historical daily load peak period; the historical daily load mid-load period of the multiple historical daily load information is determined by a third formula, wherein the third formula is: , This indicates the historical daily load period. This indicates the time when the daily load value is less than or equal to the product of the off-peak period division coefficient and the daily minimum load value. It refers to a moment within the historical daily load period.

2. The method for generating a source-load coupled wind-solar power output scenario according to claim 1, characterized in that, Based on the load characteristic values, an evaluation index for source-load coupling characteristics is established, including: Generate a wind power-load coupling characteristic index system in the power consumption area, wherein the wind power-load coupling characteristic index system is an evaluation index of the coupling relationship between the output of wind turbine units and the power consumption end in the power consumption area; Generate a photovoltaic-load coupling characteristic index system in the power consumption area, wherein the photovoltaic-load coupling characteristic index system is an evaluation index of the coupling relationship between the output of photovoltaic units and the power consumption end in the power consumption area; The source-load coupling characteristic evaluation index is determined based on the wind power-load coupling characteristic index system and the photovoltaic-load coupling characteristic index system.

3. The method for generating a source-load coupled wind-solar power output scenario according to claim 2, characterized in that, The wind power-load coupling characteristic index system includes at least the following: maximum wind power output during peak load period, minimum wind power output during peak load period, average wind power output during peak load period, maximum wind power output during off-peak load period, average wind power output during off-peak load period, average wind power output during mid-load period, daily wind power generation ratio, rate of change of maximum wind power output during off-peak load period, and rate of change of maximum wind power output during peak load period.

4. The method for generating a source-load coupled wind-solar power output scenario according to claim 3, characterized in that, The average wind power output during the peak daily load period is obtained through the fourth formula, wherein the fourth formula is: , The average wind power output during the peak load period of the day. The wind power output at time t during the peak daily load period. The daily peak load period The number of time periods included; the average wind power output during the daily load off-peak period is obtained through the fifth formula, which is: , The average wind power output during the daily off-peak load period is [missing information]. The wind power output at time t during the peak daily load period. The daily load off-peak period The number of time periods included; the average wind power output during the daily load period is obtained through the sixth formula, which is: , The average wind power output during the aforementioned daily load period is [missing information]. The wind power output at time t during the peak daily load period. The number of moments included in the daily load waist load period.

5. The method for generating a source-load coupled wind-solar power output scenario according to claim 2, characterized in that, The wind power-load coupling characteristic index system also includes: the rate of change of maximum output during the daily load off-peak period, the rate of change of maximum wind power output during the daily load peak period, and the anti-peak shaving coefficient. The anti-peak shaving coefficient is obtained through the seventh formula, which is: , The inverse peak adjustment coefficient is... Indicates the maximum net load for the entire day. These represent the minimum net load for the entire day. This indicates the maximum daily load for the entire day. This indicates the minimum daily load for the entire day.

6. The method for generating a source-load coupled wind-solar power output scenario according to claim 2, characterized in that, The photovoltaic-load coupling characteristic index system in the power consumption area includes at least: the maximum daily output of photovoltaic power, the average daily output of photovoltaic power, the average output of photovoltaic power during peak load periods, and the proportion of daily photovoltaic power generation.

7. The method for generating a source-load coupled wind-solar power output scenario according to claim 1, characterized in that, Clustering the set of feature indicators yields a clustered set of feature indicators for the wind and solar power output scenario, including: Multiple daily wind and solar power output scenarios are selected from all wind and solar power output scenarios corresponding to the set of feature indicators as initial cluster centers; Determine the distance between each of the aforementioned wind and solar power output scenarios and each of the initial cluster centers; A predetermined number of wind and solar power output scenarios with a distance less than a distance threshold are stored in a scene set. New cluster centers are determined based on the wind and solar power output scenarios in the scene set, until the maximum iteration is reached, and a set of feature indicators of the clustered wind and solar power output scenarios is obtained.

8. The method for generating a source-load coupled wind-solar power output scenario according to claim 5, characterized in that, Based on the clustered set of feature indicators of the solar power output scenarios, target solar power output scenarios are selected from the solar power output scenarios of the typical day, including at least one of the following: Based on the clustered set of characteristic indicators of the wind and solar power output scenarios, select multiple first wind and solar power output scenarios with the highest daily maximum net load. Select the second wind and solar power output scenario with the highest anti-peak-shaving coefficient from each of the first wind and solar power output scenarios; Based on the difference between the peak and valley levels of the daily power output, select the third wind and solar power output scenario with the largest difference between the peak and valley levels of the daily power output from the second wind and solar power output scenario; The third wind and solar power output scenario is determined as the target wind and solar power output scenario.

9. The method for generating a source-load coupled wind-solar power output scenario according to any one of claims 1 to 8, characterized in that, Also includes: Based on the target wind and solar power output scenario, an energy optimization strategy for the electricity consumption area in the future period after the historical electricity consumption period is determined, wherein the energy optimization strategy is used for power system optimization; The power system will be optimized according to the energy optimization strategy during the future period.

10. A device for generating a source-load coupled wind-solar power output scenario, characterized in that, include: The acquisition unit is used to acquire load characteristic values ​​of typical daily load information in the area where the new energy power station is located. The typical daily load information is the electricity consumption information of a typical day in the electricity consumption area corresponding to the new energy power station. The typical day is at least one day selected from the historical electricity consumption time period of the electricity consumption area according to a predetermined index. The load characteristic values ​​include at least: daily load peak period, daily load trough period, and daily load mid-load period. A unit is established to establish an evaluation index for source-load coupling characteristics based on the load characteristic values. The generation unit is used to generate a set of feature indicators for wind and solar power output scenarios based on the source-load coupling characteristic evaluation index. Clustering unit, used to cluster the set of feature indicators to obtain the clustered set of feature indicators of the wind and solar power output scenario; The filtering unit is used to filter out target wind and solar power output scenarios from the wind and solar power output scenarios of the typical day based on the feature index set of the clustered wind and solar power output scenarios. The acquisition unit includes: a collection module for collecting multiple historical daily load information of the electricity consumption area within the historical electricity consumption time period; an analysis module for analyzing the multiple historical daily load information to obtain historical load characteristic values ​​of the multiple historical daily load information; a first generation module for generating a daily load characteristic curve based on the historical load characteristic values ​​of the multiple historical daily load information; and an acquisition module for acquiring the load characteristic values ​​based on the daily load characteristic curve and the daily load information. The analysis module includes a first determination submodule, used to determine the historical daily load peak periods of the plurality of historical daily load information using a first formula, wherein the first formula is: , This indicates the peak load period of the historical days. This represents the maximum daily load value among the multiple historical daily load information. Divide the peak period into coefficients. This indicates the time when the daily load value is greater than or equal to the product of the peak period division factor and the maximum daily load value. It is a time within the historical daily load peak period; the second determining submodule is used to determine the historical daily load trough period of the multiple historical daily load information through a second formula, wherein the second formula is: , This indicates the historical daily load trough period. This represents the minimum daily load among the multiple historical daily load data. The coefficient for dividing the low-end period. This indicates the time when the daily load value is less than or equal to the product of the off-peak period division coefficient and the daily minimum load value. It is a time within the historical daily load peak period; the third determining submodule is used to determine the historical daily load mid-load period of the multiple historical daily load information through a third formula, wherein the third formula is: , This indicates the historical daily load period. This indicates the time when the daily load value is less than or equal to the product of the off-peak period division coefficient and the daily minimum load value. It refers to a moment within the historical daily load period.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program executes the method for generating a source-load coupled wind-solar power output scenario as described in any one of claims 1 to 9.

12. A processor, characterized in that, The processor is used to run a program, wherein the program executes the method for generating a source-load coupled wind and solar power output scenario as described in any one of claims 1 to 9.

Images