Load curve decomposition method and system based on curvature-averaged rational b-spline basis function

Abstract

The application discloses a load curve decomposition method and system based on curvature equalization rational B-spline basis functions, and the method comprises the following steps: calculating the curvature of a historical load sequence, generating a continuous curvature function, and determining a set of B-spline node sequences meeting the cumulative absolute curvature equalization condition according to the continuous curvature function, so that the node distribution is adaptive to the load fluctuation intensity; generating B-spline basis functions based on the node sequences, and constructing rational B-spline basis functions by optimizing the weights, so as to finely depict the continuous time fluctuation mode; and combining time period virtual variables to establish a fitting model, and decomposing the load curve into two parts, i.e., a 'time period characteristic load level' representing the reference electricity intensity in different time periods and a 'time characteristic load curve' representing the continuous change fluctuation mode. The method overcomes the defect that the traditional uniform spline has poor adaptability to non-uniform load forms, realizes adaptive and clear physical meaning decomposition, and provides a higher-quality data basis for load analysis and prediction.

Description

Technical Field

[0001] This invention belongs to the field of load curve decomposition technology, and particularly relates to a method and system for load curve decomposition based on curvature-partitioned rational B-spline basis functions. Background Technology

[0002] Load curve decomposition is commonly used in power system load forecasting, energy dispatch optimization, and electricity market analysis. Current mainstream load curve decomposition techniques include Fourier transform, wavelet transform, Empirical Mode Decomposition (EMD), Variational Mode Decomposition (VMD), and Singular Spectrum Analysis (SSA). The core of these key decomposition techniques lies in breaking down complex load sequences into components with clear physical meaning, such as trend terms, periodic terms, and random terms (or fluctuation terms, noise terms), providing support for subsequent data analysis. Although these techniques have played an important role in the power system field, they generally do not fully consider the differentiated impact of electricity time-period characteristics and are difficult to accurately characterize the actual electricity consumption behavior patterns of electricity users.

[0003] Therefore, there is an urgent need for a load curve decomposition method based on time-of-use pricing to extract the load level component characterizing time-period characteristics and the load curve component characterizing time evolution characteristics. Against the backdrop of deepening energy structure transformation and accelerated smart grid construction, this decomposition method will provide key technical support for refined operation and management of the power system (such as scientific time-period division and customized retail electricity pricing package design). Summary of the Invention

[0004] This invention provides a load curve decomposition method and system based on curvature-equal-partition rational B-spline basis functions, which is used to solve the technical problem that it is difficult to accurately characterize the electricity consumption behavior of power users.

[0005] In a first aspect, the present invention provides a method for decomposing load curves based on curvature-partitioned rational B-spline basis functions, comprising:

[0006] For a given historical load sequence at point T, calculate the curvature of each load point in the historical load sequence at point T, and obtain the continuous curvature function corresponding to the historical load sequence at point T through local linear interpolation;

[0007] Based on the continuous curvature function, a set of B-spline node sequences that satisfy the curvature equal division condition is determined, wherein the B-spline node sequence contains at least one curvature equal division spline node.

[0008] Based on at least one curvature-divided spline node and the selected spline order p, the p-order B-spline basis function is calculated using the B-spline recursive formula.

[0009] The objective function is to minimize the fitting error of the historical load curve, and the optimal weights are obtained by solving the objective function based on the particle swarm optimization algorithm.

[0010] Based on the optimal weights and the p-order B-spline basis functions, construct a curvature-equipartition rational B-spline basis function.

[0011] Divide the historical period into m time periods, and construct a dummy variable for each time period i. Where, when time t belongs to time period i =1, otherwise =0;

[0012] Using the curvature-divided rational B-spline basis functions and the dummy variables A fitting model is established, and the least squares method is used to solve the fitting model to obtain the estimated value of the control peak and the estimated value of the load level for each time period;

[0013] Based on the control peak estimate and the load level estimate for each time period, the historical load sequence at point T is decomposed into a time-specific load level component and a time-specific load curve component.

[0014] Secondly, the present invention provides a load curve decomposition system based on curvature-partitioned rational B-spline basis functions, comprising:

[0015] The interpolation module is configured to calculate the curvature of each load point in a given historical load sequence at point T, and obtain a continuous curvature function corresponding to the historical load sequence at point T through local linear interpolation.

[0016] The determination module is configured to determine a set of B-spline node sequences that satisfy the curvature equal division condition based on the continuous curvature function, wherein the B-spline node sequence contains at least one curvature equal division spline node.

[0017] The calculation module is configured to calculate the p-th order B-spline basis function using the B-spline recursive formula based on the at least one curvature equipartition spline node and the selected spline order p.

[0018] The solution module is configured to take minimizing the fitting error of the historical load curve as the objective function, and solve the objective function based on the particle swarm optimization algorithm to obtain the optimal weights;

[0019] The first construction module is configured to construct a curvature-equipartition rational B-spline basis function based on the optimal weights and the p-order B-spline basis function.

[0020] The second construction module is configured to divide the historical time period into m time periods and construct a dummy variable for each time period i. Where, when time t belongs to time period i =1, otherwise =0;

[0021] The fitting module is configured to utilize the curvature-divided rational B-spline basis functions and the dummy variables. A fitting model is established, and the least squares method is used to solve the fitting model to obtain the estimated value of the control peak and the estimated value of the load level for each time period;

[0022] The decomposition module is configured to decompose the historical load sequence at point T into a time-specific load level component and a time-specific load curve component based on the control vertex estimate and the load level estimate for each time period.

[0023] Thirdly, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the load curve decomposition method based on curvature-equal rational B-spline basis functions according to any embodiment of the present invention.

[0024] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the steps of the load curve decomposition method based on the curvature-equally-partitioned rational B-spline basis function according to any embodiment of the present invention.

[0025] This application presents a load curve decomposition method and system based on curvature-equal division rational B-spline basis functions. Through a curvature-equal division mechanism, the distribution of B-spline nodes adapts to the intensity of load fluctuations, densifying the nodes in areas of rapid change and sparser them in areas of smooth change, thus efficiently capturing details. Furthermore, through weight optimization, rational B-spline basis functions are constructed to precisely extract continuous-time variation patterns. Finally, the load curve is clearly decoupled into two parts: a time-based baseline with explicit physical meaning and a continuous-time fluctuation pattern. This method significantly improves fitting accuracy and model interpretability, providing higher-quality input for downstream tasks such as load forecasting and characteristic analysis. Attached Figure Description

[0026] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 A flowchart illustrating a method for decomposing a load curve based on a curvature-equal rational B-spline basis function, as provided in an embodiment of the present invention;

[0028] Figure 2 A structural block diagram of a load curve decomposition system based on curvature-partitioned rational B-spline basis functions is provided in an embodiment of the present invention.

[0029] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] Please see Figure 1 The diagram shows a flowchart of a load curve decomposition method based on curvature-equal-partition rational B-spline basis functions according to this application.

[0032] like Figure 1 As shown, the load curve decomposition method based on the curvature-equal rational B-spline basis function specifically includes the following steps:

[0033] Step S101: For a given historical load sequence at point T, calculate the curvature of each load point in the historical load sequence at point T, and obtain a continuous curvature function corresponding to the historical load sequence at point T through local linear interpolation.

[0034] In this step, the continuous curvature function is calculated. The expression is:

[0035] ,

[0036] ,

[0037] In the formula, and They are respectively The first and second derivatives, Let the load be at time t. The number of points on the historical load curve. For parameters, Let be the curvature at time t-1. Let t be the curvature at time t.

[0038] Step S102: Based on the continuous curvature function, determine a set of B-spline node sequences that satisfy the curvature equal division condition, wherein the B-spline node sequence contains at least one curvature equal division spline node.

[0039] In this step, the constraints for the uniform curvature spline nodes are as follows:

[0040] ,

[0041] In the formula, For the (i+1)th B-spline node, For the i-th B-spline node, For the initial B-spline nodes, For the first B-spline node, For the first One B-spline node, The number of B-spline basis functions. For the first One B-spline node, For the first One B-spline node, For the first One B-spline node, Let B be the order of the spline. Let be the curvature of u at the interpolated time point.

[0042] In this embodiment, the mathematical model is endowed with the ability to adapt to load patterns through the "curvature equalization" mechanism (steps S101-S102). Traditional uniform node splines cannot match the uneven fluctuations of load curves. This invention introduces curvature (a second-order geometric feature of load changes) as a guide. By calculating discrete curvature and interpolating to obtain a continuous curvature function, the B-spline node sequence is determined according to constraints. This constraint requires that the "bending complexity" (cumulative absolute curvature) of the load curve carried by each node interval is equal. The direct technical effect is that in areas with drastic load fluctuations and large curvature values ​​(such as the transition period during power consumption mode switching), the algorithm automatically configures denser nodes to provide higher degrees of freedom to capture details; while in areas with gentle loads and small curvature values, the nodes are relatively sparse, avoiding resource waste and overfitting. Essentially, this allows the structure of the mathematical model to actively "fit" the physical characteristics of the data, ensuring from the source that the basis functions have the optimal approximation potential and descriptive efficiency for the complex spatiotemporal changes of the load curve.

[0043] Step S103: Based on the at least one curvature-divided spline node and the selected spline order p, calculate the p-order B-spline basis function using the B-spline recursive formula.

[0044] In this step, the expression for calculating the p-th order B-spline basis function is:

[0045] ,

[0046] In the formula, For the (i+j-1)th B-spline node, For the i-th B-spline node, Let i be the (j-1)th order B-spline basis function. For the (i+j)th B-spline node, Let be the (i+1)th (j-1)th order B-spline basis function.

[0047] Step S104: Minimize the fitting error of the historical load curve as the objective function, and solve the objective function based on the particle swarm optimization algorithm to obtain the optimal weight.

[0048] In this step, the expression for the objective function is:

[0049] ,

[0050] In the formula, Let be the weights of the i-th B-spline basis function. Let i be the control vertex of the i-th B-spline curve. The number of points on the historical load curve. The number of B-spline basis functions. Let j be the p-th B-spline basis function. Let j be the weights of the basis functions of the j-th B-spline. Let t be the load.

[0051] Step S105: Based on the optimal weights and the p-order B-spline basis functions, construct the curvature-equal rational B-spline basis functions.

[0052] In this step, the curvature is uniformly divided rational B-spline basis functions The expression is:

[0053]

[0054] In the formula, Let be the optimal weights for the i-th rational B-spline basis function. Let i be the p-th order B-spline basis function. Let be the optimal weights for the j-th rational B-spline basis function. Let j be the p-th B-spline basis function. The number of B-spline basis functions.

[0055] In this embodiment, refined extraction of the continuous-time characteristics of the load is achieved through "weight optimization" and "rationalization" construction (steps S103-S105). After obtaining nodes that match the curvature, standard p-order B-spline basis functions are generated using the B-spline recursive formula. However, the shape of the standard B-spline is fixed. To address this, the present invention introduces a set of adjustable weights and optimizes the objective function using a particle swarm optimization algorithm, thereby constructing a curvature-equal rational B-spline basis function. The key to this step is that the weight optimization process allows the shape of the basis function combination to further "learn" and conform to the pure continuous-time fluctuation patterns in historical load data, excluding time-period effects.

[0056] Step S106: Divide the historical period into m time periods, and construct a dummy variable for each time period i. Where, when time t belongs to time period i =1, otherwise =0.

[0057] Step S107: Utilize the curvature-divided rational B-spline basis functions and the dummy variables. A fitting model is established, and the least squares method is used to solve the fitting model to obtain the control peak estimate and the load level estimate for each time period.

[0058] In this step, the expression for the fitted model is:

[0059] ,

[0060] In the formula, For the i-th control vertex, For time period i, the load level Number of time periods Let i be a dummy variable for time period i. Let t be the load.

[0061] Step S108: Based on the control peak estimate and the load level estimate for each time period, the historical load sequence at point T is decomposed into a time-period characteristic load level part and a time-characteristic load curve part.

[0062] In this step, the expression for the time-period characteristic load level is:

[0063] ,

[0064] In the formula, Let time t represent the load level characteristic of the time period. For the load level estimation of time period i, Let i be the value of the dummy variable at time t. Number of time periods This represents the number of points on the historical load curve.

[0065] The expression for the time-characteristic load curve is as follows:

[0066] ,

[0067] In the formula, Let t represent the load with time-dependent characteristics. Let t be the load.

[0068] In summary, the method presented in this application employs a "curvature equalization" mechanism to adapt the distribution of B-spline nodes to the intensity of load fluctuations, densifying the nodes in areas of rapid change and sparser them in areas of gradual change, thereby efficiently capturing details. Furthermore, it constructs rational B-spline basis functions through "weight optimization" to precisely extract continuous-time variation patterns. Finally, it clearly decouples the load curve into two parts: a time-based baseline level with definite physical meaning and a continuous-time fluctuation pattern. This method significantly improves fitting accuracy and model interpretability, providing higher-quality input for downstream tasks such as load forecasting and characteristic analysis.

[0069] Please see Figure 2 The diagram shows a structural block diagram of a load curve decomposition system based on the curvature-equal-partition rational B-spline basis function of this application.

[0070] like Figure 2 As shown, the load curve decomposition system 200 includes an interpolation module 210, a determination module 220, a calculation module 230, a solution module 240, a first construction module 250, a second construction module 260, a fitting module 270, and a decomposition module 280.

[0071] The interpolation module 210 is configured to calculate the curvature of each load point in the given historical load sequence at point T, and obtain a continuous curvature function corresponding to the historical load sequence at point T through local linear interpolation.

[0072] The determining module 220 is configured to determine a set of B-spline node sequences that satisfy the curvature equal division condition based on the continuous curvature function, wherein the B-spline node sequence contains at least one curvature equal division spline node.

[0073] The calculation module 230 is configured to calculate the p-th order B-spline basis function based on the at least one curvature-divided spline node and the selected spline order p using the B-spline recursive formula.

[0074] The solver module 240 is configured to take minimizing the fitting error of the historical load curve as the objective function, and solve the objective function based on the particle swarm optimization algorithm to obtain the optimal weights;

[0075] The first construction module 250 is configured to construct a curvature-equipartition rational B-spline basis function based on the optimal weights and the p-order B-spline basis function.

[0076] The second construction module 260 is configured to divide the historical time period into m time periods and construct a virtual variable for each time period i. Where, when time t belongs to time period i =1, otherwise =0;

[0077] Fitting module 270 is configured to utilize the curvature-divided rational B-spline basis functions and the dummy variables. A fitting model is established, and the least squares method is used to solve the fitting model to obtain the estimated value of the control peak and the estimated value of the load level for each time period;

[0078] The decomposition module 280 is configured to decompose the historical load sequence at point T into a time-specific load level part and a time-specific load curve part based on the control vertex estimate and the load level estimate for each time period.

[0079] It should be understood that Figure 2 The modules and references described in the document Figure 1 The steps described in the text correspond to those in the method described above. Therefore, the operations, features, and corresponding technical effects described above also apply to the method described in the text. Figure 2 The various modules in the document will not be described in detail here.

[0080] In other embodiments, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the load curve decomposition method based on the curvature-equal rational B-spline basis function in any of the above method embodiments.

[0081] In one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, which are configured as follows:

[0082] For a given historical load sequence at point T, calculate the curvature of each load point in the historical load sequence at point T, and obtain the continuous curvature function corresponding to the historical load sequence at point T through local linear interpolation;

[0083] Based on the continuous curvature function, a set of B-spline node sequences that satisfy the curvature equal division condition is determined, wherein the B-spline node sequence contains at least one curvature equal division spline node.

[0084] Based on at least one curvature-divided spline node and the selected spline order p, the p-order B-spline basis function is calculated using the B-spline recursive formula.

[0085] The objective function is to minimize the fitting error of the historical load curve, and the optimal weights are obtained by solving the objective function based on the particle swarm optimization algorithm.

[0086] Based on the optimal weights and the p-order B-spline basis functions, construct a curvature-equipartition rational B-spline basis function.

[0087] Divide the historical period into m time periods, and construct a dummy variable for each time period i. Where, when time t belongs to time period i =1, otherwise =0;

[0088] Using the curvature-divided rational B-spline basis functions and the dummy variables A fitting model is established, and the least squares method is used to solve the fitting model to obtain the estimated value of the control peak and the estimated value of the load level for each time period;

[0089] Based on the control peak estimate and the load level estimate for each time period, the historical load sequence at point T is decomposed into a time-specific load level component and a time-specific load curve component.

[0090] Computer-readable storage media may include a stored program area and a stored data area, wherein the stored program area may store an operating system and an application program required for at least one function; the stored data area may store data created based on the use of a load curve decomposition system based on equipartition rational B-spline basis functions, etc. Furthermore, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include memory remotely located relative to a processor, which can be connected via a network to the load curve decomposition system based on equipartition rational B-spline basis functions. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0091] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention, such as... Figure 3 As shown, the device includes a processor 310 and a memory 320. The electronic device may also include an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 can be connected via a bus or other means. Figure 3Taking a bus connection as an example, memory 320 is the computer-readable storage medium described above. Processor 310 executes various server functions and data processing by running non-volatile software programs, instructions, and modules stored in memory 320, thereby implementing the load curve decomposition method based on the equipartition rational B-spline basis function described in the above method embodiment. Input device 330 can receive input digital or character information and generate key signal inputs related to user settings and function control of the load curve decomposition system based on the equipartition rational B-spline basis function. Output device 340 may include a display screen or other display device.

[0092] The aforementioned electronic device can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0093] In one implementation, the above-described electronic device is applied to a load curve decomposition system based on curvature-equal-partition rational B-spline basis functions, for a client, and includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0094] For a given historical load sequence at point T, calculate the curvature of each load point in the historical load sequence at point T, and obtain the continuous curvature function corresponding to the historical load sequence at point T through local linear interpolation;

[0095] Based on the continuous curvature function, a set of B-spline node sequences that satisfy the curvature equal division condition is determined, wherein the B-spline node sequence contains at least one curvature equal division spline node.

[0096] Based on at least one curvature-divided spline node and the selected spline order p, the p-order B-spline basis function is calculated using the B-spline recursive formula.

[0097] The objective function is to minimize the fitting error of the historical load curve, and the optimal weights are obtained by solving the objective function based on the particle swarm optimization algorithm.

[0098] Based on the optimal weights and the p-order B-spline basis functions, construct a curvature-equipartition rational B-spline basis function.

[0099] Divide the historical period into m time periods, and construct a dummy variable for each time period i. Where, when time t belongs to time period i =1, otherwise =0;

[0100] Using the curvature-divided rational B-spline basis functions and the dummy variables A fitting model is established, and the least squares method is used to solve the fitting model to obtain the estimated value of the control peak and the estimated value of the load level for each time period;

[0101] Based on the control peak estimate and the load level estimate for each time period, the historical load sequence at point T is decomposed into a time-specific load level component and a time-specific load curve component.

[0102] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for decomposing load curves based on curvature-equal-partition rational B-spline basis functions, characterized in that, include: For a given historical load sequence at point T, calculate the curvature of each load point in the historical load sequence at point T, and obtain the continuous curvature function corresponding to the historical load sequence at point T through local linear interpolation; Based on the continuous curvature function, a set of B-spline node sequences that satisfy the curvature equal division condition is determined, wherein the B-spline node sequence contains at least one curvature equal division spline node. Based on at least one curvature-divided spline node and the selected spline order p, the p-order B-spline basis function is calculated using the B-spline recursive formula. The objective function is to minimize the fitting error of the historical load curve, and the optimal weights are obtained by solving the objective function based on the particle swarm optimization algorithm. Based on the optimal weights and the p-order B-spline basis functions, construct a curvature-equipartition rational B-spline basis function. Divide the historical period into m time periods, and construct a dummy variable for each time period i. Where, when time t belongs to time period i =1, otherwise =0; Using the curvature-divided rational B-spline basis functions and the dummy variables A fitting model is established, and the least squares method is used to solve the fitting model to obtain the estimated value of the control peak and the estimated value of the load level for each time period; Based on the control peak estimate and the load level estimate for each time period, the historical load sequence at point T is decomposed into a time-specific load level component and a time-specific load curve component.

2. The method for decomposing load curves based on curvature-equal-partition rational B-spline basis functions according to claim 1, characterized in that, Calculate the continuous curvature function The expression is: ， ， In the formula, and They are respectively The first and second derivatives, Let the load be at time t. The number of points on the historical load curve. For parameters, Let be the curvature at time t-1. Let be the curvature at time t.

3. The method for decomposing load curves based on curvature-equal-partition rational B-spline basis functions according to claim 1, characterized in that, in, The constraints for the nodes of the uniformly parted curvature spline are: ， In the formula, For the (i+1)th B-spline node, For the i-th B-spline node, For the initial B-spline nodes, For the first B-spline node, For the first One B-spline node, The number of B-spline basis functions. For the first One B-spline node, For the first One B-spline node, For the first One B-spline node, Let B be the order of the spline. Let be the curvature of u at the interpolated time point.

4. The method for decomposing load curves based on curvature-equal-partition rational B-spline basis functions according to claim 1, characterized in that, The expression for calculating the p-th order B-spline basis functions is: ， In the formula, For the (i+j-1)th B-spline node, For the i-th B-spline node, Let i be the (j-1)th order B-spline basis function. For the (i+j)th B-spline node, Let be the (i+1)th (j-1)th order B-spline basis function.

5. The method for decomposing load curves based on curvature-equal-partition rational B-spline basis functions according to claim 1, characterized in that, The expression for the objective function is: ， In the formula, Let be the weights of the i-th B-spline basis function. Let i be the control vertex of the i-th B-spline curve. The number of points on the historical load curve. The number of B-spline basis functions. Let j be the p-th B-spline basis function. Let j be the weights of the basis functions of the j-th B-spline. Let t be the load.

6. The method for decomposing load curves based on curvature-equal-partition rational B-spline basis functions according to claim 1, characterized in that, The curvature equal-part rational B-spline basis function The expression is: ， In the formula, Let be the optimal weights for the i-th rational B-spline basis function. Let i be the p-th order B-spline basis function. Let be the optimal weights for the j-th rational B-spline basis function. Let j be the p-th B-spline basis function. The number of B-spline basis functions.

7. The method for decomposing load curves based on curvature-equal-partition rational B-spline basis functions according to claim 5, characterized in that, The expression for the fitted model is: ， In the formula, For time period Load level, Number of time periods for Time-period dummy variable load.

8. The method for decomposing load curves based on curvature-equal-partition rational B-spline basis functions according to claim 7, characterized in that, The expression for the time-period characteristic load level part is: ， In the formula, Let time t represent the load level characteristic of the time period. For the load level estimation in time period i, This represents the number of points on the historical load curve. The expression for the time-characteristic load curve is as follows: ， In the formula, Let t represent the time-dependent load.

9. A load curve decomposition system based on curvature-partition rational B-spline basis functions, characterized in that, include: The interpolation module is configured to calculate the curvature of each load point in a given historical load sequence at point T, and obtain a continuous curvature function corresponding to the historical load sequence at point T through local linear interpolation. The determination module is configured to determine a set of B-spline node sequences that satisfy the curvature equal division condition based on the continuous curvature function, wherein the B-spline node sequence contains at least one curvature equal division spline node. The calculation module is configured to calculate the p-th order B-spline basis function using the B-spline recursive formula based on the at least one curvature equipartition spline node and the selected spline order p. The solution module is configured to take minimizing the fitting error of the historical load curve as the objective function, and solve the objective function based on the particle swarm optimization algorithm to obtain the optimal weights; The first construction module is configured to construct a curvature-equipartition rational B-spline basis function based on the optimal weights and the p-order B-spline basis function. The second construction module is configured to divide the historical time period into m time periods and construct a dummy variable for each time period i. Where, when time t belongs to time period i =1, otherwise =0; The fitting module is configured to utilize the curvature-divided rational B-spline basis functions and the dummy variables. A fitting model is established, and the least squares method is used to solve the fitting model to obtain the estimated value of the control peak and the estimated value of the load level for each time period; The decomposition module is configured to decompose the historical load sequence at point T into a time-specific load level component and a time-specific load curve component based on the control vertex estimate and the load level estimate for each time period.

Images