Power transaction declaration strategy adjustment method and device and computer equipment

Abstract

The invention relates to the technical field of electricity transaction, and discloses an electricity transaction declaration strategy adjustment method and device and computer equipment. Firstly, target sample data corresponding to a target time period is determined; acquiring time point sample data of any time point from the target sample data for any time point; performing a first type of clustering operation based on the time point sample data to obtain a first clustering result at any time point, and performing a second type of clustering operation based on the time point sample data to obtain a second clustering result at any time point; and finally, according to a first inter-cluster difference condition corresponding to the first clustering result and a second inter-cluster difference condition corresponding to the second clustering result, adjusting the initial declaration strategy of any time point to obtain a target declaration strategy of any time point. By clustering the time point sample data, the risk in the time point sample data is accurately evaluated, and the initial declaration strategy is optimized according to the evaluation result, so that a more accurate decision is made in the dynamic and changeable power market.

Description

Technical Field

[0001] The present application relates to the technical field of power trading, and in particular to a method, device and computer equipment for adjusting power trading declaration strategy. Background Art

[0002] In the day-ahead trading of the spot power market, power sellers need to declare the amount of electricity. In related technologies, the declared amount of electricity is determined based on the day-ahead forecast of electricity combined with the corresponding declaration strategy. When backtesting using a set of declaration strategies, it is usually found that the cumulative return graph shows different drawdown periods.

[0003] Therefore, the method of determining power transaction declaration strategies in related technologies needs to be improved to reduce potential risks. Summary of the invention

[0004] The present application provides a method, device and computer equipment for adjusting the electricity trading declaration strategy, which solves the technical problem that the electricity declaration strategy in the related technology needs to be adjusted, so as to improve the matching between the electricity declaration strategy and the actual situation, and achieves the technical effect of reducing the potential risks in electricity declaration.

[0005] In order to achieve the above objectives, the main technical solutions adopted in this application include:

[0006] In a first aspect, an embodiment of the present application provides a method for adjusting a power transaction declaration strategy, the method comprising:

[0007] Determine target sample data corresponding to a target time period; wherein the target sample data is used to characterize the supply and demand situation of the power market in multiple time periods related to the target time period, and the target time period is divided into multiple time points;

[0008] For any time point, obtaining the time point sample data of the any time point from the target sample data;

[0009] Performing a first type of clustering operation based on the time point sample data to obtain a first clustering result at any time point;

[0010] Performing a second type of clustering operation based on the time point sample data to obtain a second clustering result at any time point;

[0011] The initial declaration strategy at any time point is adjusted according to the first inter-cluster difference situation corresponding to the first clustering result and the second inter-cluster difference situation corresponding to the second clustering result to obtain the target declaration strategy at any time point.

[0012] Optionally, performing a first type of clustering operation based on the time point sample data to obtain a first clustering result at any time point includes:

[0013] A partitioning clustering operation is performed on a specified portion of the time point sample data to obtain the first clustering result.

[0014] Optionally, performing a second type of clustering operation based on the time point sample data to obtain a second clustering result at any time point includes:

[0015] A density-based clustering operation is performed on all data in the time point sample data to obtain the second clustering result.

[0016] Optionally, the first clustering result includes a first clustering cluster and a second clustering cluster; and the difference between the first clusters is determined by:

[0017] Determining price difference correlation data and silhouette coefficient between the first cluster and the second cluster;

[0018] The first inter-cluster difference is determined according to the price difference related data and the silhouette coefficient.

[0019] Optionally, the second clustering result includes a plurality of third clustering clusters; and the difference between the second clusters is determined by:

[0020] Determining price difference correlation data and silhouette coefficients between any two of the plurality of third clusters;

[0021] The difference between the second clusters is determined according to the price difference related data and the silhouette coefficient between the two clusters.

[0022] Optionally, adjusting the initial declaration strategy at any time point according to the first inter-cluster difference situation corresponding to the first clustering result and the second inter-cluster difference situation corresponding to the second clustering result to obtain the target declaration strategy at any time point includes:

[0023] Generate the first risk characterization data at any time point according to the first inter-cluster differences;

[0024] Generate the second risk characterization data at any time point according to the difference between the second clusters;

[0025] The initial declaration strategy is adjusted based on the first risk characterization data and the second risk characterization data to obtain the target declaration strategy.

[0026] Optionally, the first risk characterization data and the second risk characterization data are respectively represented in the form of risk labels, and the initial declaration strategy includes an initial risk coefficient; and the initial declaration strategy is adjusted based on the first risk characterization data and the second risk characterization data to obtain the target declaration strategy, including:

[0027] Determine the number of risk tags;

[0028] Adjusting the initial gap between the initial risk coefficient and the reference coefficient according to the number of the risk labels to obtain an adjusted gap;

[0029] The difference between the initial risk coefficient and the adjusted gap is used as the target risk coefficient; wherein the target declaration strategy includes the target risk coefficient.

[0030] Optionally, the determining target sample data corresponding to the target time period includes:

[0031] Obtain historical sample data for the first specified number of days before the target time period;

[0032] Determine a bidding space, and determine similar sample data of the target time period according to the bidding space;

[0033] The target sample data is constructed according to the historical sample data and the similar sample data.

[0034] In a second aspect, an embodiment of the present application provides a device for adjusting a power transaction declaration strategy, the device comprising:

[0035] A target sample data determination module is used to determine the target sample data corresponding to the target time period; wherein the target sample data is used to characterize the supply and demand situation of the power market in multiple time periods related to the target time period, and the target time period is divided into multiple time points;

[0036] A time point sample data acquisition module, used for acquiring the time point sample data of any time point from the target sample data;

[0037] A first clustering module, used for performing a first type of clustering operation based on the time point sample data to obtain a first clustering result at any time point;

[0038] A second clustering module, used for performing a second type of clustering operation based on the time point sample data to obtain a second clustering result at any time point;

[0039] A strategy adjustment module is used to adjust the initial declaration strategy at any time point according to the first inter-cluster difference situation corresponding to the first clustering result and the second inter-cluster difference situation corresponding to the second clustering result to obtain the target declaration strategy at any time point.

[0040] In a third aspect, an embodiment of the present application provides a computer device, including:

[0041] A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method described in any of the above embodiments by executing the computer instructions.

[0042] In the embodiment of the present application, the target sample data corresponding to the target time period is first determined; then, for any time point, the time point sample data of any time point is obtained from the target sample data; then, a first type of clustering operation is performed based on the time point sample data to obtain a first clustering result at any time point, and a second type of clustering operation is performed based on the time point sample data to obtain a second clustering result at any time point; finally, the initial declaration strategy at any time point is adjusted according to the difference between the first clusters corresponding to the first clustering result and the difference between the second clusters corresponding to the second clustering result, to obtain the target declaration strategy at any time point. By clustering the time point sample data, accurately assessing the risks therein, and adjusting the initial declaration strategy according to the risk assessment results, more accurate decisions can be made in the dynamic and changing power market. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 A flow chart of a method for adjusting a power transaction declaration strategy provided in an embodiment of this specification;

[0045] Figure 2 A flow chart of a method for adjusting a power transaction declaration strategy provided in an embodiment of this specification;

[0046] Figure 3 A flow chart of a method for adjusting a power transaction declaration strategy provided in an embodiment of this specification;

[0047] Figure 4 A flow chart of a method for adjusting a power transaction declaration strategy provided in an embodiment of this specification;

[0048] Figure 5 A flow chart of a method for adjusting a power transaction declaration strategy provided in an embodiment of this specification;

[0049] Figure 6 A flow chart of a method for adjusting a power transaction declaration strategy provided in an embodiment of this specification;

[0050] Figure 7A flow chart of a method for adjusting a power transaction declaration strategy provided in an embodiment of this specification;

[0051] Figure 8 A schematic diagram of a power transaction declaration strategy adjustment device provided in an embodiment of this specification;

[0052] Fig. 9 A schematic diagram of the structure of a computer device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0054] In the day-ahead transaction in the spot power market, power sales companies need to declare the amount of electricity at each point in time. In the related art, the declared amount of electricity is obtained by multiplying a coefficient on the basis of the day-ahead forecast of the electricity. The coefficient is used to adjust the forecasted amount of electricity to obtain the amount of electricity settled at the day-ahead price in the spot power trading market. When the day-ahead price at a certain point in time predicted by the forecast is lower than the real-time price, it is hoped that the declared amount of electricity will be increased, and the coefficient will be greater than 1; when the day-ahead price at a certain point in time predicted by the forecast is higher than the real-time price, it is hoped that the declared amount of electricity will be reduced, and the coefficient will be less than 1. For example, please refer to Table 1, the initial declaration strategy at each point in time can be this coefficient.

[0055] Table 1 Example of the relationship between initial declared electricity, predicted electricity and initial declared strategy

[0056] Time 00:15 00:30 … 07:00 … 09:00 09:15 … Predicted power consumption 10000 9000 … 50000 … 60000 60000 … Initial filing strategy 1.1 1.1 … 1 … 0.9 0.95 … Initial declared electricity 11000 9900 … 50000 … 54000 57000 …

[0057] When power sales companies use the initial declaration strategy for backtesting, they often find that the cumulative profit graph shows different drawdown periods, which may be caused by some entities in the power trading market suddenly changing their bidding behavior. Therefore, identifying the scenarios where bidding behavior changes and adjusting the initial power declaration strategy accordingly can effectively reduce potential risks.

[0058] In this embodiment, a method for adjusting the power transaction declaration strategy is proposed. Figure 1 , methods include:

[0059] S101. Determine target sample data corresponding to a target time period.

[0060] The target time period may be the time period required for power trading declaration, such as 1 day, or other time lengths, such as half a day, 6 hours, etc.

[0061] The target sample data is used to characterize the supply and demand situation of the electricity market in multiple time periods related to the target time period. The target time period can be divided into a time period of every 15 minutes, or it can be 30 minutes or 60 minutes, etc.

[0062] Specifically, the target sample data may include boundary condition data, namely load conditions, wind power output, photovoltaic output, and weather data closely related to supply and demand conditions. The boundary condition data can be obtained from the historical boundary condition data released by the trading center, and the weather data can be obtained from relevant databases.

[0063] S102. For any time point, obtain time point sample data at any time point from the target sample data.

[0064] The time point sample data may be a set of sample data corresponding to each time point.

[0065] In this embodiment, the time point sample data is composed of similar sample data and historical sample data. Specifically, for any time point, the closest m data can be selected as similar sample data according to the bidding space of the target sample data (bidding space = load situation - wind power output - photovoltaic output) and the degree of proximity to the bidding space of the time point in the target time period. In addition, the data of the corresponding time point in the n time periods closest to the target time period can also be selected as historical sample data.

[0066] S103: Perform a specified type of clustering operation suitable for at least part of the data on at least part of the time point sample data to obtain a corresponding plurality of clustering results.

[0067] The specified type of clustering operation may be to select a suitable clustering algorithm to group the data according to the selected data and analysis objectives.

[0068] Specifically, the specified type of clustering operation can be to cluster part of the data in the time point sample data, such as clustering any three data among the load conditions, wind power output, photovoltaic output and weather data. The purpose of the clustering operation is to determine the changes in electricity supply and demand between clusters, as well as the differences in electricity prices. If the electricity price difference between clusters is large when the electricity supply and demand changes little, it means that under the current boundary conditions, some market players may have changed their quotation strategies, resulting in large price fluctuations. From the perspective that there may be two quotation strategies, robust and aggressive, in the electricity trading market, it can be set to cluster the time point sample data into two clusters.

[0069] Furthermore, we can consider not setting the number of clusters, but instead using a clustering algorithm to discover clusters in the time point sample data in order to further explore the details of market behavior. Clustering can utilize more data, such as all data, namely load conditions, wind power output, photovoltaic output and weather data.

[0070] In some embodiments, performing a specified type of clustering operation suitable for at least part of the data in the time point sample data to obtain a corresponding plurality of clustering results may include: selecting a plurality of partial sample data from the time point sample data, and determining a first type of clustering operation corresponding to each partial sample data; selecting all sample data from the time point sample data, and determining a second type of clustering operation corresponding to all sample data; performing a corresponding first type of clustering operation on each partial sample data to obtain a first clustering result at any time point; performing a second type of clustering operation on all sample data to obtain a second clustering result at any time point; wherein the plurality of clustering results include a first clustering result for each partial sample data and a second clustering result for all sample data.

[0071] S104. Adjust the initial declaration strategy at any point in time according to the inter-cluster differences corresponding to each clustering result in the multiple clustering results to obtain the target declaration strategy at any point in time.

[0072] The inter-cluster difference can be the price difference between clusters in each clustering result, or the supply and demand difference between clusters. The target declaration strategy is obtained by adjusting the initial declaration strategy according to the clustering results. The power sales company can obtain the target declared power according to the predicted power and the target declaration strategy.

[0073] Specifically, the purpose of the clustering operation is to determine the changes in power supply and demand between clusters, as well as the differences in electricity prices. If the electricity prices between clusters differ greatly when the power supply and demand do not change much, it means that under the current boundary conditions, market players may have changed their bidding strategies, resulting in large price fluctuations and increased risks in electricity price forecasting, which may cause losses to power sales companies. Therefore, the initial reporting strategy needs to be adjusted at this point in time.

[0074] In this embodiment, the difference in electricity prices can be determined by comparing the mean absolute price difference between the two clusters. When the mean absolute price difference (MAPD) ​​between the two clusters is greater than the preset price difference threshold, it indicates that the price difference under the clustering condition is unstable. Otherwise, it indicates that the price difference is stable. Furthermore, the degree of supply and demand differentiation between the two clusters can be compared by the silhouette coefficient. If the silhouette coefficient is less than the preset silhouette coefficient threshold, it indicates that the supply and demand situation between the two clusters is not much different. Otherwise, it indicates that the supply and demand situation between the two clusters is relatively large.

[0075] For the above clustering operation, four clustering results of two clusters are obtained. If, in any clustering result, the difference in the average absolute price difference between the two clusters is greater than the preset price difference threshold, and the silhouette coefficient is less than the preset silhouette coefficient threshold, a "risky" mark is made for the clustering result, otherwise no mark is required. For a clustering result of multiple clusters obtained above, if the silhouette coefficients of any two clusters are less than the preset silhouette coefficient threshold, and there is a pair or more pairs of clusters whose difference in the average absolute price difference is greater than the preset price difference threshold, a "risky" mark is made for the clustering result, otherwise no mark is required. Exemplarily, the statistics of the clustering results at any time point are shown in Table 2. Different weights are assigned to each clustering result according to its importance. The risky clustering result enters 1 in the "Is there a risk" column, otherwise enter 0. It can be understood that by adding the weights corresponding to the risky clustering results, the risk assessment result at that time point can be obtained, and the initial declaration strategy can be adjusted according to the risk assessment result.

[0076] In this embodiment, the corresponding relationship between the risk assessment result and the adjustment rate is shown in Table 3. The relationship between the target declaration strategy and the initial declaration strategy can be: target declaration strategy = initial declaration strategy - (initial declaration strategy - 1) * adjustment rate. According to the initial declaration strategy and the adjustment rate corresponding to the risk assessment result in Table 3, the target declaration strategy can be obtained. Please refer to Table 4. Finally, according to the target declared electricity = predicted electricity * target declaration strategy, the target declared electricity can be obtained.

[0077] Table 2 Clustering result statistics example table

[0078] Cluster name Clustering Data Weight Is there a risk? Core supply and demand relationship1 Load conditions, wind power output, photovoltaic output, weather data 0.35 1 Core Supply and Demand Relationship 2 Load conditions, wind power output, photovoltaic output 0.35 1 Auxiliary supply and demand relationship 1 Load conditions, wind power output, weather data 0.1 1 Auxiliary supply and demand relationship 2 Load conditions, photovoltaic output, weather data 0.1 0 Auxiliary supply and demand relationship 3 Wind power output, photovoltaic output, weather data 0.1 0

[0079] Table 3 Example of the relationship between risk assessment results and adjustment rates

[0080] Risk Assessment Results Adjustment rate y<0.1 0 0.1≤y<0.2 5％ 0.2≤y<0.3 10％ 0.3≤y<0.5 15％ 0.5≤y<0.7 30％ 0.7≤y<0.9 50％ y≥0.9 60％

[0081] Table 4 Example of initial declaration strategy adjustment

[0082] Time 00:15 00:30 … 07:00 … 09:00 09:15 … Predicted power consumption 10000 9000 … 50000 … 60000 60000 … Initial filing strategy 1.1 1.1 … 1 … 0.9 0.95 … Risk Assessment Results 0.2 0.3 … 0.5 … 0.7 0.9 … Target reporting strategy 1.09 1.085 … 1 … 0.95 0.98 … Target declared electricity 10900 9765 … 50000 … 57000 58800 …

[0083] In the above embodiment, the target sample data corresponding to the target time period is first determined; secondly, for any time point, the time point sample data of any time point is obtained from the target sample data; then, at least part of the data in the time point sample data is subjected to a specified type of clustering operation suitable for at least part of the data, and a corresponding plurality of clustering results are obtained; finally, the initial declaration strategy at any time point is adjusted according to the inter-cluster differences corresponding to each clustering result in the plurality of clustering results, and a target declaration strategy at any time point is obtained. By performing multiple clustering on at least part of the data in the time point sample data, risks can be more fully identified, providing data-based decision support for the adjustment of the initial declaration strategy, so that power sales companies can achieve more accurate decisions in the dynamic and changing power market.

[0084] According to an embodiment of the present application, an embodiment of a method for adjusting an electricity trading declaration strategy is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0085] See also Figure 2 In this embodiment, a method for adjusting a power transaction declaration strategy is provided, the method comprising:

[0086] S110, determining target sample data corresponding to a target time period.

[0087] The target time period may be the time period required for power trading declaration, such as 1 day, or other time lengths, such as half a day, 6 hours, etc.

[0088] The target sample data is used to characterize the supply and demand situation of the electricity market in multiple time periods related to the target time period. The target time period can be divided into a time period of every 15 minutes, or it can be 30 minutes or 60 minutes, etc.

[0089] Specifically, the target sample data may include boundary condition data, namely load conditions, wind power output, photovoltaic output, and weather data closely related to supply and demand conditions. The boundary condition data can be obtained from the historical boundary condition data released by the trading center, and the weather data can be obtained from relevant databases.

[0090] S120 . For any time point, obtain time point sample data at any time point from the target sample data.

[0091] The time point sample data may be a set of sample data corresponding to each time point.

[0092] In this embodiment, the time point sample data is composed of similar sample data and historical sample data. Specifically, for any time point, the closest m data can be selected as similar sample data according to the bidding space of the target sample data (bidding space = load situation - wind power output - photovoltaic output) and the degree of proximity to the bidding space of the time point in the target time period. In addition, the data of the corresponding time point in the n time periods closest to the target time period can also be selected as historical sample data.

[0093] S130: Perform a first type of clustering operation based on the time point sample data to obtain a first clustering result at any time point.

[0094] The first type of clustering operation may be clustering with a set number of clusters.

[0095] Specifically, the first type of clustering operation can be to cluster the power supply and demand data in the time point sample data. The purpose of the clustering operation is to determine the changes in power supply and demand between clusters, as well as the differences in electricity prices. If the difference in electricity prices between clusters is large when the power supply and demand changes little, it means that under the current boundary conditions, some market players may have changed their quotation strategies, resulting in large price fluctuations. From the perspective that there may be two quotation strategies, robust and aggressive, in the power trading market, it is possible to consider clustering the time point sample data into two clusters. Accordingly, the first clustering result includes two clusters.

[0096] S140: Perform a second type of clustering operation based on the time point sample data to obtain a second clustering result at any time point.

[0097] The second type of clustering operation may be a clustering operation without setting the number of clusters, where the clustering algorithm is used to find clusters in the time point sample data. The second clustering result generally includes N clusters (N>2).

[0098] Specifically, we can consider not setting the number of clusters, but instead using a clustering algorithm to discover clusters in the time point sample data in order to further explore the details of market behavior. Clustering can utilize more data, such as all data, namely load conditions, wind power output, photovoltaic output and weather data.

[0099] S150, adjusting the initial declaration strategy at any time point according to the first inter-cluster difference situation corresponding to the first clustering result and the second inter-cluster difference situation corresponding to the second clustering result, to obtain the target declaration strategy at any time point.

[0100] The first inter-cluster difference situation may be the electricity price difference situation and the supply-demand difference situation between two clusters, and the second inter-cluster difference situation may be the electricity price difference situation and the supply-demand difference situation between any two clusters.

[0101] Specifically, if the supply and demand difference between the two clusters in the first clustering result is not large, but the difference in electricity prices is large, it indicates that according to the first clustering result, under this boundary condition, the day-ahead price forecast may have a large risk. If the supply and demand difference between any two clusters in the second clustering result is not large, but there is a large difference in electricity prices between the two clusters, it indicates that according to the second clustering result, under this boundary condition, the day-ahead price forecast may have a large risk. Finally, the initial declaration strategy is adjusted based on the difference between the first cluster and the difference between the second cluster. Exemplarily, if there is no large risk in the difference between the first cluster and the difference between the second cluster, the initial declaration strategy can remain unchanged; if only one of the difference between the first cluster and the difference between the second cluster is a large risk, the initial declaration strategy can be adjusted by the first amplitude; if both the difference between the first cluster and the difference between the second cluster are large risks, the initial declaration strategy can be adjusted by the second amplitude; it can be understood that the higher the risk, the greater the adjustment of the initial declaration strategy, so the second amplitude is greater than the first amplitude.

[0102] In the above embodiment, the target sample data corresponding to the target time period is first determined; then, for any time point, the time point sample data of any time point is obtained from the target sample data; then, a first type of clustering operation is performed based on the time point sample data to obtain a first clustering result at any time point, and a second type of clustering operation is performed based on the time point sample data to obtain a second clustering result at any time point; finally, the initial declaration strategy at any time point is adjusted according to the difference between the first clusters corresponding to the first clustering result and the difference between the second clusters corresponding to the second clustering result, to obtain the target declaration strategy at any time point. By clustering the time point sample data, the risks therein are accurately assessed, and the initial declaration strategy is optimized according to the risk assessment results, so as to achieve more accurate decision-making in the dynamic and changing power market.

[0103] In some embodiments, performing a first type of clustering operation based on the time point sample data to obtain a first clustering result at any time point includes: performing a partitioning type clustering operation on a specified portion of the time point sample data to obtain the first clustering result.

[0104] The specified part of the data may be a boundary condition, namely, load conditions, wind power output, and photovoltaic output. The goal of the partitioning clustering operation is to partition the specified part of the time point sample data into a predetermined number of clusters.

[0105] Specifically, the K-Means clustering method can be used, a specified part of the data in the time point sample data is input, and the K value (i.e., the number of clusters) is set. Through this method, the load conditions, wind power output, and photovoltaic output in the time point sample data can be clustered into a predetermined number of clusters, such as two clusters.

[0106] In some embodiments, performing a second type of clustering operation based on the time point sample data to obtain a second clustering result at any time point includes: performing a density-based clustering operation on all data in the time point sample data to obtain a second clustering result.

[0107] Among them, all data can be boundary conditions and weather data, namely load conditions, wind power output, photovoltaic output and weather data. The purpose of density-based clustering operation is not to specify the number of clusters, but to find clusters in the time point sample data through clustering algorithm.

[0108] Specifically, the density-based clustering operation can be clustering using the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm. After setting the neighborhood radius parameter r, DBSCAN automatically clusters the time point sample data into N clusters and noise points. For example, a k-distance graph can be used to select a suitable neighborhood radius parameter r.

[0109] See also Figure 3 In some embodiments, the first clustering result includes a first clustering cluster and a second clustering cluster; the difference between the first clusters is determined by:

[0110] S410: Determine price difference related data and silhouette coefficient between the first cluster and the second cluster.

[0111] S420: Determine the difference between the first clusters according to the price difference related data and the silhouette coefficient.

[0112] Among them, the price difference related data can be the difference in Mean Absolute Price Difference (MAPD) ​​between the first cluster and the second cluster. When the price difference related data between the first cluster and the second cluster is less than the preset price difference threshold, it means that the price difference is stable. Conversely, when it is greater than the preset price difference threshold, it means that the price difference is unstable. The silhouette coefficient represents the degree of distinction of the boundary conditions between the first cluster and the second cluster. When the silhouette coefficient is greater than the preset silhouette coefficient threshold, it means that the boundary conditions between the first cluster and the second cluster are greatly different. Conversely, when the silhouette coefficient is less than the preset silhouette coefficient threshold, it means that the boundary conditions between the first cluster and the second cluster are less different. The difference between the first clusters includes the comparison results of the price difference related data between the first cluster and the second cluster with the preset price difference threshold, and the comparison results of the silhouette coefficients of the first cluster and the second cluster with the preset silhouette coefficient threshold.

[0113] It is understandable that when the silhouette coefficient between the first cluster and the second cluster is not large, but the price difference related data is large, it means that in the point-in-time sample data, although the boundary conditions are not much different, the price difference has experienced large fluctuations. Under this boundary condition, the day-ahead price forecast may be at great risk.

[0114] Specifically, firstly, the average absolute price difference between the first cluster and the second cluster is calculated, and the difference between the two is calculated, and then compared with the preset price difference threshold, and the comparison result is recorded; secondly, the silhouette coefficient of the first cluster and the second cluster is calculated, and compared with the preset silhouette coefficient threshold, and the comparison result is recorded; finally, according to the above two comparison results, the difference between the first clusters is obtained.

[0115] See also Figure 4 In some embodiments, the second clustering result includes a plurality of third clustering clusters; the difference between the second clusters is determined by:

[0116] S510: Determine price difference related data and silhouette coefficients between any two of the plurality of third clusters.

[0117] S520: Determine the difference between the second clusters according to the price difference correlation data and the silhouette coefficient between the two clusters.

[0118] Among them, the pairwise clusters can be any two clusters. The price difference related data can be the difference of the mean absolute price difference (MAPD) ​​between any pairwise clusters. When the price difference related data between the pairwise clusters is less than the preset price difference threshold, it means that the price difference is stable. Conversely, when it is greater than the preset price difference threshold, it means that the price difference is unstable. The silhouette coefficient represents the degree of distinction between the boundary conditions and weather data between the pairwise clusters. When the silhouette coefficient is greater than the preset silhouette coefficient threshold, it means that the boundary conditions and weather data between the pairwise clusters are greatly different. Conversely, when the silhouette coefficient is less than the preset silhouette coefficient threshold, it means that the boundary conditions between the pairwise clusters are less different. The second inter-cluster difference situation includes the comparison results of the price difference related data between the pairwise clusters and the preset price difference threshold, and the comparison results of the silhouette coefficient of any pairwise clusters with the preset silhouette coefficient threshold.

[0119] It is understandable that when the boundary conditions and weather data between any two clusters are slightly different, but the price difference related data is large, it means that in the sample data at a certain point in time, although the boundary conditions and weather data are not much different, the price difference has fluctuated greatly, and the day-ahead price forecast at that point in time may be at great risk.

[0120] Specifically, firstly, the average absolute price difference between any two clusters is calculated, and the difference between the two is calculated, and then compared with the preset price difference threshold, and the comparison result is recorded; secondly, the silhouette coefficient between any two clusters is calculated, and compared with the preset silhouette coefficient threshold, and the comparison result is recorded; finally, according to the above comparison results, the difference between the second clusters is obtained.

[0121] See also Figure 5 In some embodiments, the initial application strategy at any time point is adjusted according to the difference between the first clusters corresponding to the first clustering result and the difference between the second clusters corresponding to the second clustering result to obtain the target application strategy at any time point, including:

[0122] S610: Generate first risk characterization data at any time point according to the first inter-cluster difference.

[0123] S620: Generate second risk characterization data at any time point according to the difference between the second clusters.

[0124] S630. Adjust the initial declaration strategy based on the first risk characterization data and the second risk characterization data to obtain a target declaration strategy.

[0125] The target declaration strategy may be a declaration strategy obtained by adjusting the initial declaration strategy according to the first risk characterization data and the second risk characterization data. The first risk characterization data and the second risk characterization data are respectively used to describe whether there is a risk or a risk situation.

[0126] Specifically, if the difference between the first clusters is that the average absolute price difference between the first cluster and the second cluster is greater than the preset price difference threshold, and the silhouette coefficients of the two are less than the preset silhouette coefficient threshold, then the first risk characterization data can be "risky", otherwise it can be "no risk".

[0127] If the second inter-cluster difference situation is that the silhouette coefficients of any two clusters are less than the preset silhouette coefficient threshold, but there is one or more pairs of clusters whose average absolute price differences are greater than the preset price difference threshold, then the second risk characterization data can be "risky", otherwise it can be "no risk".

[0128] The initial declaration strategy at any point in time can be adjusted according to the first risk characterization data and the second risk characterization data to obtain the target declaration strategy at that point in time. Generally, the higher the risk value at a certain point in time, the greater the adjustment of the initial declaration strategy. Exemplarily, at time A, the first risk characterization data and the second risk characterization data are both "risk-free", and the target declaration strategy can be the same as the initial declaration strategy. At time B, the first risk characterization data is "risky", and the second risk characterization data is "risk-free", and the target declaration strategy can be a 5% reduction in the initial declaration strategy. At time C, the first risk characterization data and the second risk characterization data are both "risky", and the target declaration strategy can be a 10% reduction in the initial declaration strategy.

[0129] See also Figure 6 In some embodiments, the first risk characterization data and the second risk characterization data are respectively represented in the form of risk labels, and the initial declaration strategy includes an initial risk coefficient; the initial declaration strategy is adjusted based on the first risk characterization data and the second risk characterization data to obtain a target declaration strategy, including:

[0130] S710: Determine the number of risk tags.

[0131] S720. Adjust the initial gap between the initial risk coefficient and the reference coefficient according to the number of risk labels to obtain an adjusted gap.

[0132] S730. The difference between the initial risk coefficient and the adjusted gap is used as the target risk coefficient.

[0133] The initial risk coefficient may be a preset risk value set according to relevant risk characterization data when formulating the initial declaration strategy. The target declaration strategy includes a target risk coefficient. The target risk coefficient is the initial risk coefficient adjusted according to the number of risk tags at the corresponding time point. The reference coefficient may be 1.

[0134] Specifically, when the first risk characterization data and the second risk characterization data at any point in time are both "risk-free", the number of risk labels at that point in time is 0; when the first risk characterization data and the second risk characterization data at any point in time, one is "risk-free" and the other is "risky", the number of risk labels at that point in time is 1; when the first risk characterization data and the second risk characterization data at any point in time are both "risky", the number of risk labels at that point in time is 2.

[0135] In this implementation, if the number of risk labels at any time point is 0, the initial risk coefficient is not modified; if the number of risk labels at any time point is 1, the initial risk coefficient is reduced by 1 / 3 of the difference between it and the reference coefficient to obtain the target risk coefficient, that is, the target risk coefficient = initial risk coefficient - (initial risk coefficient - reference coefficient) / 3; if the number of risk labels at any time point is 1, the initial risk coefficient is reduced by 1 / 2 of the difference between it and the reference coefficient to obtain the target risk coefficient, that is, the target risk coefficient = initial risk coefficient - (initial risk coefficient - reference coefficient) / 2. For example, please refer to Table 5.

[0136] Table 5 Example of initial declaration strategy adjustment based on the number of risk labels

[0137] Time 00:15 00:30 … 07:00 … 09:00 09:15 … Predicted power consumption 10000 9000 … 50000 … 60000 60000 … Initial risk factor 1.1 1.1 … 1 … 0.9 0.95 … Number of risk labels 1 2 … 2 … 1 2 … Target risk factor 1.067 1.05 … 1 … 0.933 0.975 … Declared electricity 10670 9450 … 50000 … 55980 58500 …

[0138] See also Figure 7 In some embodiments, determining target sample data corresponding to a target time period includes:

[0139] S810. Obtain historical sample data for the first specified number of days before the target time period.

[0140] S820: Determine a bidding space, and determine similar sample data of the target time period according to the bidding space.

[0141] S830. Construct target sample data based on historical sample data and similar sample data.

[0142] The first designated number of days may be one week, two weeks, 10 days, etc. The bidding space may be the difference between the load situation and the output of new energy, that is, bidding space = load situation - wind power output - photovoltaic output. Sometimes the amount of electricity input or output of the interconnection line is large, and the bidding space may also be = load situation - wind power output - photovoltaic output - interconnection line forecast.

[0143] Specifically, since the recent electricity supply and demand and weather conditions will have an impact on electricity prices, when constructing the target sample data, it is necessary to include the historical sample data of the first specified days before the target time period. In addition, when constructing the target sample data, similar sample data similar to the target time period is selected based on the bidding space difference. The smaller the bidding space difference, the higher the similarity. Exemplarily, 50 similar sample data are selected at each time point from the data of the previous year of the target time period, that is, for any time point of the target time period, 50 with the smallest bidding space difference are selected from the data of the corresponding time point of the previous year as similar sample data. It can be understood that for any time point, the similar sample data and the historical sample data of the first specified days constitute the sample data at that time point, and the time point sample data of all time points of the target time period constitute the target sample data of the target time period.

[0144] See also Figure 8 In this embodiment, a power transaction declaration strategy adjustment device 900 is also provided. The power transaction declaration strategy adjustment device 900 includes:

[0145] The target sample data determination module 910 is used to determine the target sample data corresponding to the target time period; wherein the target sample data is used to characterize the supply and demand of the power market in multiple time periods related to the target time period, and the target time period is divided into multiple time points;

[0146] The time point sample data acquisition module 920 is used to acquire the time point sample data of any time point from the target sample data;

[0147] A first clustering module 930, configured to perform a first type of clustering operation based on the time point sample data to obtain a first clustering result at any time point;

[0148] A second clustering module 940 is used to perform a second type of clustering operation based on the time point sample data to obtain a second clustering result at any time point;

[0149] The strategy adjustment module 950 is used to adjust the initial declaration strategy at any time point according to the first inter-cluster difference situation corresponding to the first clustering result and the second inter-cluster difference situation corresponding to the second clustering result to obtain the target declaration strategy at any time point.

[0150] In some implementations, the first clustering module 930 further includes:

[0151] The partitioning clustering unit is used to perform a partitioning clustering operation on a specified portion of the time point sample data to obtain a first clustering result.

[0152] In some implementations, the second clustering module 940 further includes:

[0153] The density-based clustering unit is used to perform a density-based clustering operation on all data in the time point sample data to obtain a second clustering result.

[0154] In some implementations, the first clustering result includes a first clustering cluster and a second clustering cluster; the strategy adjustment module 950 further includes:

[0155] A price difference profile determination unit, used to determine price difference related data and a profile coefficient between the first cluster and the second cluster;

[0156] The inter-cluster difference determination unit is used to determine the first inter-cluster difference situation according to the price difference related data and the silhouette coefficient.

[0157] In some implementations, the second clustering result includes a plurality of third clustering clusters; the strategy adjustment module 950 further includes:

[0158] A price difference profile determination unit, used to determine price difference related data and profile coefficients between any two of the plurality of third clusters;

[0159] The inter-cluster difference determination unit is used to determine the second inter-cluster difference situation according to the price difference related data and the silhouette coefficient between the two clustering clusters.

[0160] In some implementations, the policy adjustment module 950 further includes:

[0161] A risk data generating unit, configured to generate first risk characterization data at any time point according to the difference between the first clusters; and to generate second risk characterization data at any time point according to the difference between the second clusters;

[0162] A strategy adjustment unit is used to adjust the initial declaration strategy based on the first risk characterization data and the second risk characterization data to obtain a target declaration strategy.

[0163] In some embodiments, the first risk characterization data and the second risk characterization data are respectively represented in the form of risk labels, and the initial declaration strategy includes an initial risk coefficient; the strategy adjustment module 950 further includes:

[0164] A label quantity determination unit, used to determine the quantity of risk labels;

[0165] a gap adjustment unit, used for adjusting the initial gap between the initial risk coefficient and the reference coefficient according to the number of risk labels to obtain an adjusted gap;

[0166] The risk factor determination unit is used to use the difference between the initial risk factor and the adjusted gap as the target risk factor; wherein the target declaration strategy includes the target risk factor.

[0167] In some implementations, the target sample data determination module 910 further includes:

[0168] A historical sample data acquisition unit, used to acquire the historical sample data of the first specified number of days before the target time period;

[0169] A similar sample data determination unit, used to determine a bidding space, and determine similar sample data of a target time period according to the bidding space;

[0170] The target sample data determination unit is used to construct the target sample data according to the historical sample data and the similar sample data.

[0171] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0172] The adjustment device for the power trading declaration strategy in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0173] See also Fig. 9 , Fig. 9 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application, such as Fig. 9 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig. 9 A processor 10 is taken as an example.

[0174] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0175] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0176] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0177] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0178] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Fig. 9 The example of connecting through bus is taken in the following.

[0179] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0180] The embodiment of the present application also provides a computer-readable storage medium. The above method according to the embodiment of the present application can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0181] The embodiment of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method of any embodiment of the present application.

[0182] Although the embodiments of the present application are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

[0183] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0184] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0185] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0186] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0187] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0188] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0189] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0190] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0191] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

[0192] Although the embodiments of the present application have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for adjusting a power transaction declaration strategy, characterized in that: The method comprises: Determine target sample data corresponding to a target time period; wherein the target sample data is used to characterize the supply and demand situation of the power market in multiple time periods related to the target time period, and the target time period is divided into multiple time points; For any time point, obtaining the time point sample data of the any time point from the target sample data; Performing a first type of clustering operation based on the time point sample data to obtain a first clustering result at any time point; Performing a second type of clustering operation based on the time point sample data to obtain a second clustering result at any time point; The initial declaration strategy at any time point is adjusted according to the first inter-cluster difference situation corresponding to the first clustering result and the second inter-cluster difference situation corresponding to the second clustering result to obtain the target declaration strategy at any time point.

2. The method according to claim 1, characterized in that The performing a first type of clustering operation based on the time point sample data to obtain a first clustering result at any time point includes: A partitioning clustering operation is performed on a specified portion of the time point sample data to obtain the first clustering result.

3. The method according to claim 1, characterized in that The performing a second type of clustering operation based on the time point sample data to obtain a second clustering result at any time point includes: A density-based clustering operation is performed on all data in the time point sample data to obtain the second clustering result.

4. The method according to claim 1, characterized in that The first clustering result includes a first clustering cluster and a second clustering cluster; the difference between the first clusters is determined by: Determining price difference correlation data and silhouette coefficient between the first cluster and the second cluster; The first inter-cluster difference is determined according to the price difference related data and the silhouette coefficient.

5. The method according to claim 1, characterized in that The second clustering result includes a plurality of third clustering clusters; and the difference between the second clusters is determined by: Determine price difference correlation data and silhouette coefficients between any two of the plurality of third clusters; The difference between the second clusters is determined according to the price difference related data and the silhouette coefficient between the two clusters.

6. The method according to claim 1, characterized in that The step of adjusting the initial declaration strategy at any time point according to the first inter-cluster difference situation corresponding to the first clustering result and the second inter-cluster difference situation corresponding to the second clustering result to obtain the target declaration strategy at any time point includes: Generate the first risk characterization data at any time point according to the first inter-cluster differences; Generate the second risk characterization data at any time point according to the difference between the second clusters; The initial declaration strategy is adjusted based on the first risk characterization data and the second risk characterization data to obtain the target declaration strategy.

7. The method according to claim 6, characterized in that The first risk characterization data and the second risk characterization data are respectively represented in the form of risk labels, and the initial declaration strategy includes an initial risk coefficient; The adjusting the initial declaration strategy based on the first risk characterization data and the second risk characterization data to obtain the target declaration strategy includes: Determine the number of risk tags; Adjusting the initial gap between the initial risk coefficient and the reference coefficient according to the number of the risk labels to obtain an adjusted gap; The difference between the initial risk coefficient and the adjusted gap is used as the target risk coefficient; wherein the target declaration strategy includes the target risk coefficient.

8. The method according to any one of claims 1 to 7, characterized in that: The target sample data corresponding to the target time period is determined, including: Obtain historical sample data for the first specified number of days before the target time period; Determine a bidding space, and determine similar sample data of the target time period according to the bidding space; The target sample data is constructed according to the historical sample data and the similar sample data.

9. A device for adjusting power transaction declaration strategy, characterized in that: The device comprises: A target sample data determination module is used to determine the target sample data corresponding to the target time period; wherein the target sample data is used to characterize the supply and demand situation of the power market in multiple time periods related to the target time period, and the target time period is divided into multiple time points; A time point sample data acquisition module, used for acquiring the time point sample data of any time point from the target sample data; A first clustering module, used for performing a first type of clustering operation based on the time point sample data to obtain a first clustering result at any time point; A second clustering module, used for performing a second type of clustering operation based on the time point sample data to obtain a second clustering result at any time point; A strategy adjustment module is used to adjust the initial declaration strategy at any time point according to the first inter-cluster difference situation corresponding to the first clustering result and the second inter-cluster difference situation corresponding to the second clustering result to obtain the target declaration strategy at any time point.

10. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 8 by executing the computer instructions.

Images