Power supply and demand simulation method and system based on panoramic time sequence construction strategy

Abstract

The invention relates to the technical field of electric power systems, in particular to an electric power supply and demand simulation method and system based on a panoramic time sequence construction strategy, and the method comprises the steps: obtaining annual electric power supply and demand related data of a plurality of dimensions of an electric power system, and determining a monthly optimal clustering number through a contour coefficient method based on annual hourly original time sequence data; obtaining each monthly clustering center based on the monthly optimal clustering number, coupling each monthly clustering center with the original time sequence data to obtain an annual panoramic time sequence, and constructing a medium and long term time sequence production simulation model based on the annual panoramic time sequence; and obtaining a power supply and demand time sequence simulation result according to the annual power supply and demand related data of each dimension in combination with a preset medium and long term time sequence production simulation model. According to the method, the annual panoramic time sequence is obtained through monthly adaptive clustering, the solving speed is increased, and efficient and accurate simulation of the power supply and demand time sequence is further facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method and system for simulating power supply and demand based on a panoramic time series construction strategy. Background Art

[0002] The higher penetration rate of renewable energy increases the imbalance between electricity supply and demand in the long-term time scale of the power system, so it is necessary to carry out power system operation planning. Among them, time-series production simulation is an important means of power system operation planning. It can measure the power balance at a long-term and hourly fine time scale to simulate the power balance process. However, medium- and long-term time-series production simulation contains a large number of integer variables and complex system constraints, which makes its solution time span long, the problem scale large and the calculation difficulty high, resulting in limited application scope. Therefore, efficient solution of production simulation model is the key to ensure the long-term reliable operation and system planning of power system.

[0003] In recent years, a large number of solution technologies for improving the computational efficiency of time series production simulation have been proposed, and have played an important role in practical applications. The existing method of selecting typical days is the most common, but the existing technology mainly focuses on time series clustering on the annual time scale when selecting typical representative time periods, and does not fully consider the data fluctuation characteristics of local time periods, which leads to low efficiency of power supply and demand time series simulation. Summary of the invention

[0004] In order to solve the technical problem of low efficiency of the above-mentioned existing power supply and demand time series simulation, the purpose of the present invention is to provide a power supply and demand simulation method and system based on a panoramic time series construction strategy. The technical solution adopted is as follows: An embodiment of the present invention provides a method for simulating power supply and demand based on a panoramic time series construction strategy, the method comprising the following steps: Obtaining annual power supply and demand related data of several dimensions of the power system; wherein the annual power supply and demand related data is load time series data, wind and solar time series data, traditional unit data, hydropower unit data, pumped storage unit data, battery energy storage system data or wind power photovoltaic unit data; Based on the original hourly time series data for the whole year, the silhouette coefficient method is used to determine the optimal number of monthly clusters, and based on the monthly optimal number of clusters, the k-means++ clustering method is used to obtain each monthly cluster center; wherein the original time series data includes load time series data and wind and solar time series data; Coupling each monthly cluster center with the original time series data to obtain an annual panoramic time series, and building a medium- and long-term time series production simulation model based on the annual panoramic time series; According to the annual electricity supply and demand related data of each dimension, and combined with the preset medium- and long-term time series production simulation model, the power supply and demand time series simulation results are obtained.

[0005] Furthermore, the method of determining the monthly optimal number of clusters based on the original hourly time series data for the whole year using the silhouette coefficient method includes: Label each data in the original hourly time series for the whole year with its month and day; Determine the number of natural clusters and the proportional coefficient for each month based on the annotated original time series; wherein the number of natural clusters is the number of test clusters that maximizes the silhouette coefficient; For any month, the product of the natural cluster number and the proportional coefficient of the month is calculated, the product is rounded down, and the rounded value plus the preset parameter is used as the monthly optimal cluster number of the month; Get the monthly optimal number of clusters for each month, and then obtain the set of monthly optimal number of clusters corresponding to the original time series.

[0006] Furthermore, determining the number of natural clusters for each month based on the annotated original time series includes: Number of natural clusters in month m The calculation formula is: ; In the formula, It means to find the maximum function of the independent variable. represents the number of test clusters, represents the day of the mth month, d represents the dth day, represents the input data of the dth day of the mth month, that is, 24 hours of time series data, Indicates that the number of test clusters is Monthly input data The silhouette coefficient SC.

[0007] Furthermore, the step of obtaining the silhouette coefficient includes: For any day of input data, when the number of test clusters is Under the premise of , we first calculate the average distance between the input data of that day and other input data in its cluster, recorded as ; Then calculate the shortest average distance between the input data of that day and the input data in other clusters, recorded as ; Finally, the silhouette coefficient is determined based on the average distance and the shortest average distance corresponding to the input data of that day.

[0008] Furthermore, when the number of test clusters is Monthly input data The calculation formula of the silhouette coefficient SC is: .

[0009] Furthermore, the proportional coefficient of each month is determined based on the annotated original time series, including: Proportional coefficient for the mth month The calculation formula is: ; In the formula, Indicates the compactness of the mth month, Indicates the minimum compactness, M represents the set of month numbers; The compactness of the mth month The calculation formula is: ; In the formula, represents the number of natural clusters in the mth month, represents the data set belonging to the i-th cluster center in the m-th month, represents the number of input data in the data set belonging to the i-th cluster center in the m-th month, represents the input data of the dth day of the mth month, Represents the input data corresponding to the i-th cluster center, Represents the distance between two input data.

[0010] Furthermore, based on the monthly optimal cluster number, the k-means++ clustering method is used to obtain each monthly cluster center, including: For the monthly optimal number of clusters in any month, a data point is randomly selected from the monthly data set of that month as the cluster center to be determined; Calculate the distance between each pending cluster center and each data point in the monthly data set of that month, determine the next pending cluster center, and continue to determine and repeat the next pending cluster center until the optimal pending cluster center is selected as the monthly cluster center of that month.

[0011] Furthermore, coupling each monthly cluster center with the original time series data to obtain an annual panoramic time series includes: The set of cluster centers of each month is taken as the typical day set, and the daily data in the original time series data is replaced by the corresponding typical day, and the annual panoramic time series is obtained by splicing.

[0012] Furthermore, the medium- and long-term time-series production simulation model includes a traditional thermal power unit model, an energy storage device model, a pumped storage model, a wind power photovoltaic model, a run-of-river hydropower model and a network model.

[0013] Another embodiment of the present invention provides a power supply and demand simulation system based on a panoramic time series construction strategy, including: A data acquisition module is used to acquire annual power supply and demand related data of several dimensions of the power system; wherein the annual power supply and demand related data is load time series data, wind and solar time series data, traditional unit data, hydropower unit data, pumped storage unit data, battery energy storage system data or wind power photovoltaic unit data; A model building module is used to determine the monthly optimal number of clusters based on the original hourly time series data throughout the year by using the silhouette coefficient method, and based on the monthly optimal number of clusters, obtain each monthly cluster center by using the k-means++ clustering method; wherein the original time series data are load time series data and wind and solar time series data; Coupling each monthly cluster center with the original time series data to obtain an annual panoramic time series, and building a medium- and long-term time series production simulation model based on the annual panoramic time series; The time series simulation module is used to obtain the power supply and demand time series simulation results based on the annual power supply and demand related data of each dimension and in combination with the preset medium- and long-term time series production simulation model.

[0014] The present invention has the following beneficial effects: The present invention provides a method and system for simulating power supply and demand based on a panoramic time series construction strategy. The method completes the power supply and demand time series simulation process through a pre-constructed medium- and long-term time series production simulation model and combines annual power supply and demand related data of different dimensions. It adaptively clusters the time series data on a monthly basis, which helps to improve the efficiency of power supply and demand time series simulation while taking into account the intraday and monthly fluctuations of wind and solar load data, that is, speeds up the solution. In the process of constructing the medium- and long-term time series production simulation model, based on the original hourly time series data throughout the year, the process fully considers the seasonal fluctuation characteristics between months on the time scale, and is not easy to lose its intraday fluctuation characteristics, ensuring the accuracy of the simulation; the monthly optimal cluster number is determined based on the silhouette coefficient method, and the monthly cluster center is obtained based on the monthly optimal cluster number and the k-means++ clustering method. This process can effectively avoid the problem of unstable clustering results caused by random selection of initial cluster centers. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1This is a flow chart of a method for simulating power supply and demand based on a panoramic time series construction strategy according to an embodiment of the present invention; Figure 2 is a flowchart of step S21 in an embodiment of the present invention; Figure 3 This is an example diagram of the silhouette coefficient under different test cluster numbers in January in an embodiment of the present invention; Figure 4 This is a schematic diagram of load clustering in January in an embodiment of the present invention; Figure 5 This is a schematic diagram of the clustering of wind power data in January in an embodiment of the present invention; Figure 6 This is a schematic diagram of photovoltaic data clustering in January in an embodiment of the present invention; Figure 7 This is a schematic diagram of the load clustering center in January in an embodiment of the present invention; Figure 8 Schematic diagram of the clustering center of wind power data in January in an embodiment of the present invention; Fig. 9 This is a schematic diagram of the photovoltaic data clustering center in January in an embodiment of the present invention; Fig.10 It is a schematic diagram of the structure of a medium- and long-term time series production simulation model in an embodiment of the present invention; Fig.11 This is an execution flow chart of an electric power supply and demand simulation system based on a panoramic time series construction strategy according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the technical solutions proposed by the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] In order to fully consider the seasonal fluctuation characteristics of load and renewable energy between months without losing their intra-day fluctuation characteristics, an annual panoramic time series construction method with adaptive clustering number is proposed. Specifically, an embodiment of the present invention provides a power supply and demand simulation method based on a panoramic time series construction strategy, such as Figure 1 As shown, the following steps are included: S1, obtain annual power supply and demand related data of several dimensions of the power system.

[0020] In this embodiment, the annual power supply and demand related data are load time series data, wind and solar time series data, traditional unit data, hydropower unit data, pumped storage unit data, battery energy storage system data or wind power photovoltaic unit data. Of course, the implementer can also use other dimensions of annual power supply and demand related data.

[0021] S2, based on the original hourly time series data throughout the year, uses the silhouette coefficient method to determine the optimal number of monthly clusters. Based on the optimal number of monthly clusters, the k-means++ clustering method is used to obtain the cluster center of each month.

[0022] Here, the full year in the full-year hourly raw time series data refers to data covering a whole year, that is, a complete cycle from the beginning of the year to the end of the year. Hourly means that the data is recorded hourly, usually to capture the power supply and demand situation every hour of every day, that is, 8736 hours of annual raw time series data. Raw time series data refers to data that has not been processed, processed or smoothed, and it maintains the original time sequence and value. For raw time series data, the raw time series data includes load time series data and wind and light time series data, that is, the full-year hourly raw time series data includes renewable energy output (wind power, photovoltaic) and load demand curve. Renewable energy output refers to the power output from renewable energy (such as wind power, solar energy, etc.). This part of the data records the fluctuations in power generation from these energy sources, while the load demand curve represents the changing trend of power demand and shows the changes in power load at different time points (such as every hour).

[0023] Since the existing selection methods for selecting typical representative time periods mainly focus on time series clustering on the annual time scale, they do not fully consider the seasonal electricity consumption fluctuation characteristics between months, and the selection of the number of clusters is relatively random, which leads to limited efficiency of time series generation simulation. Therefore, this embodiment is based on the original hourly time series data for the whole year, and uses the silhouette coefficient method to adaptively determine the optimal number of monthly clusters, and then determines each monthly cluster center as the typical representative data for subsequent medium- and long-term time series production simulation model construction.

[0024] The above step S2 can be implemented through steps S21 to S22 (not shown in the figure): S21, based on the original hourly time series data for the whole year, uses the silhouette coefficient method to determine the optimal number of clusters per month.

[0025] The above step S21 can be performed by Figure 2 The steps S211 to S214 shown implement: S211, label each data in the original hourly time series for the whole year with its month and date.

[0026] In this embodiment, each data in the original time series is labeled with its month and date in order to distinguish input data of the same day in different months, so as to facilitate the subsequent clustering processing of monthly input data.

[0027] S212, determining the number of natural clusters and the proportional coefficient for each month based on the annotated original time series.

[0028] Here, the number of natural clusters is the number of test clusters that maximizes the silhouette coefficient, and the proportionality coefficient is the ratio of the compactness of each month to the minimum compactness.

[0029] First, the number of natural clusters for each month is determined based on the labeled original time series.

[0030] As an example, the number of natural clusters in month m The calculation formula can be: ; In the formula, It means to find the maximum function of the independent variable. represents the number of test clusters, represents the day of the mth month, d represents the dth day, represents the input data of the dth day of the mth month, that is, 24 hours of time series data, Indicates that the number of test clusters is Monthly input data The silhouette coefficient SC.

[0031] In the calculation formula of the natural cluster number, the test cluster number is greater than or equal to 5, the input data of the mth month is clustered as clusters (sets), which can be recorded as The implementer can set the value range of the test cluster number according to the actual situation, without making any specific restrictions.

[0032] As a specific implementation, the step of obtaining the silhouette coefficient may include: For the input data on day d, when the number of test clusters is Under the premise of The cluster is , first calculate the input data for that day The average distance between it and other input data in its cluster is denoted as ; Then calculate the input data for that day The shortest average distance between the input data in other clusters is denoted as ; Finally, the silhouette coefficient is determined based on the average distance and the shortest average distance corresponding to the input data of that day. The specific formula is as follows: ; ; ; ; In the formula, Representation Cluster The number of data in Indicates the input data on day d (The cluster is ) and all other clusters except the cluster The average distance of all data in clusters other than , for example, to the second cluster The average distance is , It represents the jth input data in the i-th cluster of the m-th month, and min represents the minimum function.

[0033] Obviously, when the number of test clusters is Monthly input data The calculation formula of the silhouette coefficient SC can be expressed as: ; Secondly, the proportional coefficient for each month is determined based on the labeled original time series.

[0034] In this embodiment, the proportionality coefficient can be defined as the ratio of the compactness of each month to the minimum compactness, so the compactness of each month needs to be calculated. For a certain cluster, a greater compactness means a greater intra-cluster distance, that is, the data is more dispersed.

[0035] Proportional coefficient for the mth month The calculation formula can be: ; In the formula, Indicates the compactness of the mth month, Indicates the minimum compactness, and M represents the set of month numbers.

[0036] The compactness of the mth month The calculation formula can be: ; In the formula, represents the number of natural clusters in the mth month, represents the data set belonging to the i-th cluster center in the m-th month, represents the number of input data in the data set belonging to the i-th cluster center in the m-th month, represents the input data of the dth day of the mth month, Represents the input data corresponding to the i-th cluster center, Represents the distance between two input data.

[0037] S213, for any month, calculate the product of the number of natural clusters and the proportional coefficient of the month, round the product down, and add the rounded value plus the preset parameter as the monthly optimal number of clusters for the month.

[0038] As an example, the calculation formula for the monthly optimal number of clusters in the mth month can be: ; In the formula, represents the monthly optimal number of clusters in the mth month, Indicates rounding down. represents the proportional coefficient for the mth month, Represents the number of natural clusters in the mth month, and 1 represents the preset parameter.

[0039] S214, obtaining the monthly optimal clustering number for each month, and then obtaining a set of monthly optimal clustering numbers corresponding to the original time series.

[0040] In this embodiment, after obtaining the monthly optimal number of clusters for each month, the value range of m is 1 to 12, that is, , , N represents the set of monthly optimal clustering numbers, that is, the set of monthly optimal clustering numbers corresponding to the original time series is obtained. The example results of the monthly optimal clustering numbers are shown in Table 1: Table 1 S22, based on the monthly optimal number of clusters, use the k-means++ clustering method to obtain each monthly cluster center.

[0041] In this embodiment, for the monthly optimal number of clusters in any month, a data point is randomly selected from the monthly data set of that month as a pending cluster center; the distance between each pending cluster center and each data point in the monthly data set of that month is calculated, and the greater the distance, the greater the probability of being selected, and the next pending cluster center is determined, and the next pending cluster center is continuously determined and repeated until the optimal pending cluster center is selected as the monthly cluster center of that month.

[0042] It is worth noting that obtaining the cluster center for each month can effectively avoid the problem of unstable clustering results caused by randomly selecting the initial cluster center.

[0043] Specifically, the steps for obtaining the cluster center of each month using the k-means++ algorithm include: The first step is to enter the month m=1, the monthly data set , the optimal number of clusters And the variable k=1 representing the current number of clusters.

[0044] The second step is to use the monthly data set Randomly select a sample as the initial cluster center .

[0045] The third step is to use the monthly data set Each sample The shortest distance to the existing cluster center. The calculation formula of the shortest distance can be: .

[0046] The fourth step is to calculate the probability of each sample being selected as the next cluster center. The probability calculation formula can be: , and then select the next cluster center according to the roulette method, k=k+1.

[0047] Step 5: Repeat steps 3 to 4 until the target cluster number k is equal to the monthly optimal cluster number obtained in step S21, that is, .

[0048] Step 6, m=m+1, jump to step 2 until m is greater than 12.

[0049] So far, this embodiment has obtained 12 months of monthly clustering clusters and monthly cluster centers .

[0050] S3, couple each monthly cluster center with the original time series data to obtain the annual panoramic time series, and build a medium- and long-term time series production simulation model based on the annual panoramic time series.

[0051] The above step S3 can be implemented by the following steps S31 to S32 (not shown): S31, couple each monthly cluster center with the original time series data to obtain the annual panoramic time series.

[0052] In this embodiment, the set formed by each monthly cluster center is taken as a typical day set, and the daily data in the original time series data is replaced by the corresponding typical day, and the annual panoramic time series is obtained by splicing.

[0053] Specifically, the input data for each month is clustered into several typical days. , these typical days contain the daily fluctuation characteristics of wind and solar load data, while maintaining the monthly fluctuation characteristics. In the medium- and long-term time series production simulation model, considering that the operation constraints such as unit ramp restrictions, start-stop constraints, and energy storage charge state require the coupling of adjacent days, the daily data in the original time series are replaced by the corresponding typical days, and the annual panoramic time series is obtained by splicing.

[0054] The expression of the original time series can be: ; ; In the expression of the original time series, the monthly clusters The cluster center is .

[0055] The expression of the annual panoramic time series can be: ; In the expression of the annual panoramic time series, i, j, and k are determined by the cluster to which the corresponding original sequence belongs.

[0056] Some examples of daily clusters are shown in Table 2: Table 2 In a specific embodiment, an example of the silhouette coefficient under different test cluster numbers in January is as follows: Figure 3 As shown in the figure, taking January as an example, the silhouette coefficients under different test cluster numbers are obtained, and the optimal cluster number is 6.

[0057] like Figures 4 to 6 As shown in the figure, taking January as an example, the clustering clusters of the three types of time series data, load, wind power, and photovoltaic, are displayed when the number of clusters is set to the optimal number of clusters 6.

[0058] like Figures 7 to 9 As shown in the figure, taking January as an example, the cluster centers of the three types of time series data, load, wind power, and photovoltaic, are displayed when the number of clusters is set to the optimal number of clusters 6.

[0059] S32, constructs a medium- and long-term temporal production simulation model based on the annual panoramic time series.

[0060] In this embodiment, the medium- and long-term time series production simulation model includes a traditional thermal power unit model, an energy storage device model, a pumped storage model, a wind power photovoltaic model, a run-of-river hydropower model, and a network model. Fig.10 , the schematic diagram of the medium and long-term time series production simulation model is as follows Fig.10 shown.

[0061] The expression of the traditional thermal power unit model can be: In the expression of the traditional thermal power unit model, 01 variable indicating the start and stop status of the unit, 01 variable indicating the unit startup operation, A continuous variable representing the unit output level, A linear or quadratic function representing the unit's electricity generation cost, Indicates the climbing power during unit operation. Indicates the climbing power after the unit is started and stopped. Indicates the minimum technical output of the unit. Indicates the maximum output of the unit. represents the standby of the unit, t represents the time, T represents the total operating time, Indicates the minimum shutdown time of the unit. express The status of the unit at the moment, Refers to the constraint subjectto, Indicates the on / off operation of the unit at the i-th moment.

[0062] It should be noted that the traditional thermal power unit model requires the unit output to be within the maximum and minimum output range, satisfying the startup operation, minimum startup and shutdown time constraints and climbing constraints.

[0063] The expression of the energy storage device model can be: In the expression of the energy storage device model, represents the operating cost of the energy storage device, 01 variable indicating the energy storage operation status, is a continuous variable representing the output of energy storage, is a continuous variable representing the energy storage input, Indicates the charging efficiency, represents the power generation efficiency, represents the energy storage charge state at time t, t represents the energy storage charging and discharging time step, which is 1h.

[0064] It should be noted that the energy storage device model requires that the energy storage input and output output be within the maximum and minimum output range, and the state of charge SOC meets the specified requirements.

[0065] The expression of the pumped storage model can be: In the expression of the pumped storage model, represents the operating cost of the pumped storage unit, 01 variable indicating that pumped storage is operating in the pumping state, 01 variable indicating that pumped storage is operating in the power generation state, The 01 variable indicates that the pumped storage starts to enter the pumping state. The variable 01 indicates that the pumped storage starts to enter the power generation state. represents the pumped storage pumping power, represents the pumped storage power generation capacity, is a continuous variable representing the capacity of the upstream reservoir of the pumped storage, A continuous variable representing the capacity of the downstream reservoir of the pumped storage; represents the pumping efficiency of pumped storage, Represents the efficiency of pumped storage power generation.

[0066] The expression of wind power photovoltaic model can be: In the expression of wind power photovoltaic model, represents the operating cost of the photovoltaic unit, represents the operating cost of wind turbines, A continuous variable representing the actual photovoltaic output, is a continuous variable representing the amount of photovoltaic power curtailment, represents the photovoltaic installed capacity, Represents the photovoltaic output per unit curve; is a continuous variable representing the actual output of wind power, is a continuous variable representing the amount of wind power curtailment, represents the installed capacity of wind power, Represents the wind power output per unit curve.

[0067] The expression of the run-of-river hydropower model can be: In the expression of the run-of-river hydropower model, represents the operating cost of run-of-river hydropower, A continuous variable representing the actual output of run-of-river hydropower, is a continuous variable representing the amount of run-of-river hydropower curtailment, represents the installed capacity of run-of-river hydropower, Represents the per unit curve of run-of-river hydropower output.

[0068] The expression of the network model can be: In the expression of the network model, represents the load loss penalty cost, is a continuous variable representing the total power of the tie line in area n, is a continuous variable representing the total input power to region n, represents the load of area n, A continuous variable representing the load shedding in zone n.

[0069] It should be noted that the network model requires that the energy storage input and output output be within the maximum and minimum output range.

[0070] The objective function can be expressed as: It is worth mentioning that the medium- and long-term time-series production simulation model is constructed with the goal of optimal economic performance, which includes the lowest operating cost of each unit and the lowest penalty cost.

[0071] In a specific embodiment, the comparison results of the solution time of the medium- and long-term time series production simulation are shown in Table 3: Table 3 It can be seen from Table 3 that the medium- and long-term time series production simulation model constructed based on the annual panoramic time series has a much shorter solution time than the time series production simulation model based on the original time series, while ensuring the solution accuracy. This verifies the effectiveness of the method provided by the present invention.

[0072] So far, this embodiment has obtained a medium- and long-term time-series production simulation model.

[0073] S4, based on the annual electricity supply and demand related data of each dimension and combined with the preset medium- and long-term time series production simulation model, obtain the power supply and demand time series simulation results.

[0074] In this embodiment, the annual electricity supply and demand related data of all dimensions are input into the preset medium- and long-term time series production simulation model, which can complete the simulation of the electricity supply and demand time series and obtain the electricity supply and demand time series simulation results.

[0075] An embodiment of the present invention further provides a power supply and demand simulation system based on a panoramic time series construction strategy, the execution flow chart of the system is as follows: Fig.11 As shown, including: A data acquisition module is used to acquire annual power supply and demand related data of several dimensions of the power system; wherein the annual power supply and demand related data is load time series data, wind and solar time series data, traditional unit data, hydropower unit data, pumped storage unit data, battery energy storage system data or wind power photovoltaic unit data; A model building module is used to determine the monthly optimal number of clusters based on the original hourly time series data throughout the year by using the silhouette coefficient method, and based on the monthly optimal number of clusters, obtain each monthly cluster center by using the k-means++ clustering method; wherein the original time series data are load time series data and wind and solar time series data; Coupling each monthly cluster center with the original time series data to obtain an annual panoramic time series, and building a medium- and long-term time series production simulation model based on the annual panoramic time series; The time series simulation module is used to obtain the power supply and demand time series simulation results based on the annual power supply and demand related data of each dimension and in combination with the preset medium- and long-term time series production simulation model.

[0076] In summary, the present invention adaptively clusters the time series data on a monthly basis, which can take into account the intraday fluctuations and monthly fluctuations of wind and solar load data, speed up the solution speed, and help improve the efficiency of power supply and demand time series simulation. The optimal number of clusters per month is adaptively obtained through the improved silhouette coefficient method, and the monthly time series data is clustered using the k-means++ clustering method to obtain the clustering centers of each month, effectively avoiding the problem of unstable clustering results caused by random selection of initial centers, fully considering the data fluctuation characteristics of local time periods, and improving the efficiency of power supply and demand time series simulation. Finally, the typical days after clustering are coupled together according to the original time series to obtain the annual panoramic time series.

[0077] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A power supply and demand simulation method based on a panoramic time series construction strategy, characterized in that: The following steps are involved: Obtaining annual power supply and demand related data of several dimensions of the power system; wherein the annual power supply and demand related data is load time series data, wind and solar time series data, traditional unit data, hydropower unit data, pumped storage unit data, battery energy storage system data or wind power photovoltaic unit data; Based on the original hourly time series data for the whole year, the silhouette coefficient method is used to determine the optimal number of monthly clusters, and based on the monthly optimal number of clusters, the k-means++ clustering method is used to obtain each monthly cluster center; wherein the original time series data includes load time series data and wind and solar time series data; Coupling each monthly cluster center with the original time series data to obtain an annual panoramic time series, and building a medium- and long-term time series production simulation model based on the annual panoramic time series; According to the annual electricity supply and demand related data of each dimension, and combined with the preset medium- and long-term time series production simulation model, the power supply and demand time series simulation results are obtained.

2. The power supply and demand simulation method based on the panoramic time series construction strategy according to claim 1 is characterized in that: The method of determining the optimal number of monthly clusters based on the original hourly time series data for the whole year using the silhouette coefficient method includes: Label each data in the original hourly time series for the whole year with its month and day; Determine the number of natural clusters and the proportional coefficient for each month based on the annotated original time series; wherein the number of natural clusters is the number of test clusters that maximizes the silhouette coefficient; For any month, the product of the natural cluster number and the proportional coefficient of the month is calculated, the product is rounded down, and the rounded value plus the preset parameter is used as the monthly optimal cluster number of the month; Get the monthly optimal number of clusters for each month, and then obtain the set of monthly optimal number of clusters corresponding to the original time series.

3. The power supply and demand simulation method based on the panoramic time series construction strategy according to claim 2 is characterized in that: The method of determining the number of natural clusters for each month based on the labeled original time series includes: Number of natural clusters in month m The calculation formula is: ; In the formula, It means to find the maximum function of the independent variable. represents the number of test clusters, represents the day of the mth month, d represents the dth day, represents the input data of the dth day of the mth month, that is, 24 hours of time series data, Indicates that the number of test clusters is Monthly input data The silhouette coefficient SC.

4. The power supply and demand simulation method based on the panoramic time series construction strategy according to claim 3 is characterized in that: The step of obtaining the silhouette coefficient comprises: For any day of input data, when the number of test clusters is Under the premise of , we first calculate the average distance between the input data of that day and other input data in its cluster, recorded as ; Then calculate the shortest average distance between the input data of that day and the input data in other clusters, recorded as ; Finally, the silhouette coefficient is determined based on the average distance and the shortest average distance corresponding to the input data of that day.

5. The power supply and demand simulation method based on the panoramic time series construction strategy according to claim 4 is characterized in that: When the number of test clusters is Monthly input data The calculation formula of the silhouette coefficient SC is: 。 6. The power supply and demand simulation method based on the panoramic time series construction strategy according to claim 2 is characterized in that: Determine the proportion coefficient for each month based on the labeled original time series, including: Proportional coefficient for the mth month The calculation formula is: ; In the formula, Indicates the compactness of the mth month, Indicates the minimum compactness, M represents the set of month numbers; The compactness of the mth month The calculation formula is: ； In the formula, represents the number of natural clusters in the mth month, represents the data set belonging to the i-th cluster center in the m-th month, represents the number of input data in the data set belonging to the i-th cluster center in the m-th month, represents the input data of the dth day of the mth month, Represents the input data corresponding to the i-th cluster center, Represents the distance between two input data.

7. The method for simulating power supply and demand based on a panoramic time series construction strategy according to claim 1, characterized in that: The method of obtaining each monthly cluster center based on the monthly optimal cluster number by using the k-means++ clustering method includes: For the monthly optimal number of clusters in any month, a data point is randomly selected from the monthly data set of that month as the cluster center to be determined; Calculate the distance between each pending cluster center and each data point in the monthly data set of that month, determine the next pending cluster center, and continue to determine and repeat the next pending cluster center until the optimal pending cluster center is selected as the monthly cluster center of that month.

8. The method for simulating power supply and demand based on a panoramic time series construction strategy according to claim 1, characterized in that: The coupling of each monthly cluster center with the original time series data to obtain an annual panoramic time series includes: The set of cluster centers of each month is taken as the typical day set, and the daily data in the original time series data is replaced by the corresponding typical day, and the annual panoramic time series is obtained by splicing.

9. The method for simulating power supply and demand based on a panoramic time series construction strategy according to claim 1, characterized in that: The medium- and long-term time-series production simulation model includes a traditional thermal power unit model, an energy storage device model, a pumped storage model, a wind power photovoltaic model, a run-of-river hydropower model and a network model.

10. A power supply and demand simulation system based on a panoramic time series construction strategy, characterized in that: include: A data acquisition module is used to acquire annual power supply and demand related data of several dimensions of the power system; wherein the annual power supply and demand related data is load time series data, wind and solar time series data, traditional unit data, hydropower unit data, pumped storage unit data, battery energy storage system data or wind power photovoltaic unit data; A model building module is used to determine the monthly optimal number of clusters based on the original hourly time series data throughout the year by using the silhouette coefficient method, and based on the monthly optimal number of clusters, obtain each monthly cluster center by using the k-means++ clustering method; wherein the original time series data are load time series data and wind and solar time series data; Coupling each monthly cluster center with the original time series data to obtain an annual panoramic time series, and building a medium- and long-term time series production simulation model based on the annual panoramic time series; The time series simulation module is used to obtain the power supply and demand time series simulation results based on the annual power supply and demand related data of each dimension and in combination with the preset medium- and long-term time series production simulation model.

Images