Daily load model forming method and device for reconfigurable distribution network, medium and equipment

Abstract

The invention discloses a daily load model forming method and device for a reconfigurable distribution network, a medium and equipment, and belongs to the technical field of new energy high-permeability distribution networks, and the method comprises the steps: obtaining historical load data, including instantaneous loads at different moments, in the reconfigurable distribution network; according to the historical load data, constructing an influence factor and a basic load cluster; taking the basic load clusters as load composition options of the daily load model, and introducing composition vectors to construct a discrete daily load model; and defining a linear fitting rule to serialize the discrete daily load model to obtain a daily load model. According to the method, the problems of many interference factors and complex construction in the modeling process of the reconfigurable distribution network daily load model are solved.

Description

Technical Field

[0001] The present invention relates to a method, device, medium and equipment for forming a daily load model for a reconfigurable distribution network, and belongs to the technical field of new energy high-penetration distribution networks. Background Art

[0002] Driven by the "dual carbon" goal, my country's new energy industry is booming at an unprecedented speed, showing the distinctive characteristics of "large scale" and "high quality". In recent years, the installed capacity of new energy such as wind power and photovoltaics has achieved rapid growth, and the penetration rate of these clean and renewable energy in the distribution network has continued to increase, bringing profound changes to the structure and operation of the power system. With the continuous increase in the proportion of new energy power generation, the complexity of the operation and regulation of the distribution system has increased significantly, and higher requirements have been put forward for the flexibility and stability of the power grid. In this context, it is increasingly important to explore the impact of random load access on the distribution network and distributed resources, and to study the reconfigurable distribution network power generation operation. In order to meet the needs of new energy development, existing technologies have developed a variety of load models, aiming to more accurately simulate and predict load changes in different scenarios, and provide strong support for the planning, operation and optimization of the power system. These models range from simple static models to complex dynamic models, which can adapt to the analysis of load characteristics in different time scales and spatial ranges.

[0003] Although the existing technology has made significant progress in the development and application of load models, it still faces many challenges in the energy optimization management of reconfigurable distribution networks. First, there are many types of load models and their structures are complex, which undoubtedly increases the difficulty of system analysis. Different load models may be based on different assumptions, mathematical expressions and data sources, resulting in greater uncertainty in model selection and parameter setting. Secondly, with the continuous increase in the penetration rate of renewable energy power generation in the distribution network, the randomness and volatility of the load have significantly increased, which has put forward higher requirements on the accuracy and adaptability of the load model. However, existing models often find it difficult to fully and accurately reflect these complex changes, resulting in errors and uncertainties in the energy optimization management of reconfigurable distribution networks. Summary of the invention

[0004] The purpose of the present invention is to provide a method, device, medium and equipment for constructing a daily load model for a reconfigurable distribution network. The method extracts basic load vectors based on historical load data and forms basic load clusters as candidates for discrete daily load model construction. The model construction process is simplified by constructing vectors, and the discrete daily load model is continuous using linear fitting rules, thereby solving the problems of many interference factors and complex construction in the modeling process of the daily load model of the reconfigurable distribution network.

[0005] In order to solve the above technical problems, the present invention is implemented by adopting the following technical solutions.

[0006] In a first aspect, the present invention provides a method for constructing a daily load model for a reconfigurable distribution network, comprising:

[0007] Obtain historical load data in the reconfigurable distribution network;

[0008] Based on the historical load data, construct influencing factors describing the impact of different external interference factors on the new energy high penetration distribution network, and then construct a basic load cluster;

[0009] The basic load cluster is used as the candidate load composition of the daily load model, and the composition vector is introduced to construct the discrete daily load model.

[0010] Define the linear fitting rule to make the discrete daily load model continuous and obtain the daily load model.

[0011] Furthermore, based on the historical load data, influencing factors and basic load clusters are constructed, including:

[0012] Constructing an impact factor based on the historical load data, with a value of 0.5 to 1.5, reflecting the impact of external interference factors on the load in the reconfigurable distribution network, wherein the external interference factors include climate, festivals and electricity prices;

[0013] Extracting instantaneous load magnitudes at different times of historical load data in the reconfigurable distribution network as basic load vector elements for forming a basic load vector, wherein each basic load vector element in the basic load vector is arranged in chronological order;

[0014] constructing a basic load vector according to the influencing factors and the basic load vector elements;

[0015] Based on the base load vector, a base load cluster is constructed.

[0016] Further, the basic load vector is expressed as:

[0017] P ele_i = α ele _ i ⋅ [ P ele _ i , 1 P ele _ i , 2 ⋯ P ele _ i , j − 1 P ele _ i , j ] ;

[0018] In the formula, Indicates A basic load vector, Indicates The influencing factor of the base load is Represents the total number of basic load vector elements. The total number of basic load vectors is 25, which is used to represent each moment of the 24 hours in a day. Indicates The first element in the base load vector, Indicates The second element in the base load vector, Indicates The j-1th element in the basic load vector, Indicates The first of the base load vectors elements.

[0019] Further, the basic load cluster is represented as:

[0020] P base = [ P ele_1 P ele_2 ⋯ P ele_i ⋯ P ele_s-1 P ele_s ] T ;

[0021] In the formula, represents the base load cluster, represents the first basic load vector, represents the second basic load vector, Indicates A basic load vector, Indicates A basic load vector, It is used to describe the total number of base load vectors in the base load cluster. , Indicates transpose.

[0022] Furthermore, the constituent vector is expressed as:

[0023] X load = [ x 1 x 2 ⋯ x i ⋯ x s − 1 x s ] T ;

[0024] In the formula, Indicates load The constituent vectors of represents the composition coefficient of the first basic load in the basic load cluster, represents the composition factor of the second basic load in the basic load cluster, Indicates the first The composition factor of the basic load is represents the composition coefficient of the s-1th basic load in the basic load cluster, It represents the composition coefficient of the sth basic load in the basic load cluster. When a composition coefficient is 0, it means that the basic load cluster corresponding to its subscript is not in the daily load model. When it is 1, it means that the basic load cluster is in the daily load model. Indicates transpose.

[0025] Furthermore, the discrete daily load model is expressed as:

[0026] { P load = ∑ i = 1 s x i ⋅ P ele_i = [ P sum _ 1 P sum _ 2 ⋯ P sum _ k ⋯ P sum _ j − 1 P sum _ j ] P sum _ k = ∑ i = 1 s x i ⋅ α ele _ i ⋅ P ele _ i , k ;

[0027] In the formula, Indicates load Discrete daily load model, Indicates the discrete daily load model The instantaneous load at time , For the The first elements.

[0028] Furthermore, the linear fitting rule is expressed as:

[0029] ;

[0030] In the formula, Indicates load Discrete daily load model, Indicates the discrete daily load model The instantaneous load at time , For the The first elements.

[0031] In a second aspect, the present invention provides a daily load model forming device for a reconfigurable distribution network, comprising:

[0032] A data acquisition module, used to acquire historical load data in the reconfigurable distribution network;

[0033] An element construction module, used to construct influencing factors and basic load clusters according to the historical load data;

[0034] A discrete daily load model construction module is used to take the basic load cluster as a candidate load composition of the daily load model and introduce a composition vector to construct a discrete daily load model;

[0035] The daily load model conversion module is used to define the linear fitting rules to make the discrete daily load model continuous to obtain the daily load model.

[0036] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for constructing a daily load model for a reconfigurable distribution network as described in the first aspect.

[0037] In a fourth aspect, the present invention provides a computer device, comprising:

[0038] A memory for storing instructions;

[0039] The processor is used to execute the instructions so that the device performs operations to implement the method for constructing a daily load model for a reconfigurable distribution network as described in the first aspect.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] 1. The present invention uses historical load data in the reconfigurable distribution network to construct influencing factors and basic load clusters, which can accurately reflect the inherent laws and main influencing factors of load changes. At the same time, the basic load cluster is used as a candidate for the load composition of the daily load model, and the composition vector is introduced, which can also flexibly construct a variety of discrete daily load models to meet the application requirements under different scenarios and needs. The present invention also makes the discrete daily load model continuous by defining a linear fitting rule, which not only improves the continuity and smoothness of the daily load model, but also enhances the prediction ability and rationality of the daily load model in the instantaneous load size change, and solves the problems of many interference factors and complex construction in the modeling process of the daily load model of the reconfigurable distribution network;

[0042] 2. The present invention also takes into account the impact of external interference factors such as climate, festivals and electricity prices on the new energy high penetration distribution network by constructing influencing factors, so that the constructed daily load model can more accurately reflect the actual load changes. At the same time, the influencing factors and basic load clusters are constructed using historical load data, which provides rich data support for the daily load model, further improves the accuracy and adaptability of the daily load model, and enables the daily load to better adapt to applications in different scenarios and needs;

[0043] 3. The present invention introduces a composition vector and uses the basic load cluster as a candidate for the load composition of the daily load model, so as to flexibly construct a diversified discrete daily load model, thereby improving the flexibility of the daily load model and making the daily load model have good scalability, and can be adjusted and optimized accordingly with the changes in the distribution network structure and load characteristics;

[0044] 4. The present invention makes the discrete daily load model continuous by defining a linear fitting rule, thereby obtaining a smooth daily load curve, which not only improves the prediction ability of the daily load model on the instantaneous load size change, but also makes the daily load model more practical and operable in energy management and optimized scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of a process of a method for constructing a daily load model for a reconfigurable distribution network provided by an embodiment of the present invention;

[0046] Figure 2 Shown is a schematic diagram of a basic load vector data acquisition curve provided by an embodiment of the present invention;

[0047] Figure 3 The figure shows the overall structure schematic diagram of the daily load model provided by the embodiment of the present invention;

[0048] Figure 4Shown is a schematic diagram of an example of the daily load model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0050] The term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the related objects are in an "or" relationship.

[0051] Example 1

[0052] like Figure 1 As shown, this embodiment introduces a method for constructing a daily load model for a reconfigurable distribution network, including:

[0053] Step 1: Obtain historical load data in the reconfigurable distribution network.

[0054] The present invention collects historical load data at various time points in the distribution network over a period of time in the past. The historical load data covers the instantaneous load at different times, can comprehensively reflect the changing characteristics of the load over time, ensure the accuracy and reliability of the construction of the daily load model, and also help to capture the details of the load changes, providing strong support for load forecasting and distribution network management.

[0055] Step 2: Construct influencing factors and basic load clusters based on the historical load data.

[0056] Among them, the impact factor is used to describe the impact of different external interference factors on the new energy high penetration distribution network.

[0057] The present invention analyzes historical load data, identifies key factors that affect load changes, such as climate, festivals, electricity prices, etc., and constructs influencing factors. At the same time, clustering algorithms and other methods can be used to divide historical load data into multiple basic load clusters, each cluster represents a typical load change pattern, and the influencing factors can quantify the impact of external factors on load changes and improve the interpretability of the daily load model. At the same time, the construction of basic load clusters also simplifies the complexity of the daily load model and improves the generalization ability of the daily load model.

[0058] Step 3: Take the basic load cluster as the candidate load composition of the daily load model, and introduce the composition vector to build a discrete daily load model.

[0059] The present invention uses the basic load cluster as the basic element for constructing the daily load model, and constructs a diversified daily load model by selecting different basic load clusters and their combinations. The present invention also introduces a composition vector, and realizes flexible configuration of the daily load model by adjusting the element value of the vector, that is, the composition coefficient of the basic load cluster. The flexibility and configurability of the daily load model are improved, and it can adapt to the load change requirements in different scenarios. At the same time, by adjusting the composition vector, a daily load model that meets specific requirements can also be quickly generated.

[0060] Step 4: Define the linear fitting rule to make the discrete daily load model continuous and obtain the daily load model.

[0061] The present invention defines a linear fitting rule for a discrete daily load model, connects discrete points into a smooth curve, and transforms the discrete daily load model into a continuous daily load model through a linear interpolation or fitting method, thereby improving the continuity and smoothness of the daily load model, so that the daily load model can better reflect the continuous process of load changes over time. At the same time, the continuous daily load model provides a more convenient mathematical tool and analysis means for subsequent load forecasting, energy management, and optimal scheduling.

[0062] Example 2

[0063] This embodiment introduces specific implementation steps of a method for constructing a daily load model for a reconfigurable distribution network, including:

[0064] Step 1: Obtain historical load data in the reconfigurable distribution network, including instantaneous loads at different times.

[0065] Step 2: Construct influencing factors and basic load clusters based on the historical load data.

[0066] Among them, the impact factor is used to describe the impact of different external interference factors on the new energy high penetration distribution network.

[0067] In some embodiments, constructing an impact factor and a basic load cluster based on the historical load data includes:

[0068] Step 2.1: Based on the historical load data, construct an impact factor to describe the impact of different external interference factors on the new energy high penetration distribution network. The value is 0.5~1.5, reflecting the impact of external interference factors on the load in the reconfigurable distribution network. The external interference factors include climate, festivals and electricity prices.

[0069] Step 2.2: Extract the instantaneous load size of the historical load data at different times in the reconfigurable distribution network as the basic load vector element to form the basic load vector. Each basic load vector element in the basic load vector is arranged in chronological order, such as Figure 2 shown.

[0070] Step 2.3: Construct a basic load vector according to the influencing factors and the basic load vector elements.

[0071] In this embodiment, the basic load vector is expressed as:

[0072] P ele_i = α ele _ i ⋅ [ P ele _ i , 1 P ele _ i , 2 ⋯ P ele _ i , j − 1 P ele _ i , j ] ;

[0073] In the formula, Indicates A basic load vector, Indicates The influencing factor of the base load is Represents the total number of basic load vector elements. The total number of basic load vectors is 25, which is used to represent each moment of the 24 hours in a day. Indicates The first element in the base load vector, Indicates The second element in the base load vector, Indicates The j-1th element in the basic load vector, Indicates The first of the base load vectors elements.

[0074] Step 2.4: Construct a basic load cluster based on the basic load vector.

[0075] In this embodiment, the basic load cluster is represented as:

[0076] P base = [ P ele_1 P ele_2 ⋯ P ele_i ⋯ P ele_s-1 P ele_s ] T ;

[0077] In the formula, represents the base load cluster, represents the first basic load vector, represents the second basic load vector, Indicates A basic load vector, Indicates A basic load vector, It is used to describe the total number of base load vectors in the base load cluster. , Indicates transpose.

[0078] Step 3: Take the basic load cluster as the candidate load composition of the daily load model, and introduce the composition vector to build a discrete daily load model.

[0079] In this embodiment, the constituent vector is expressed as:

[0080] X load = [ x 1 x 2 ⋯ x i ⋯ x s − 1 x s ] T ;

[0081] In the formula, Indicates load The constituent vectors of represents the composition coefficient of the first basic load in the basic load cluster, represents the composition factor of the second basic load in the basic load cluster, Indicates the first The composition factor of the basic load is represents the composition coefficient of the s-1th basic load in the basic load cluster, It represents the composition coefficient of the sth basic load in the basic load cluster. When a composition coefficient is 0, it means that the basic load cluster corresponding to its subscript is not in the daily load model. When it is 1, it means that the basic load cluster is in the daily load model. Indicates transpose.

[0082] In this embodiment, the discrete daily load model is expressed as:

[0083] { P load = ∑ i = 1 s x i ⋅ P ele_i = [ P sum _ 1 P sum _ 2 ⋯ P sum _ k ⋯ P sum _ j − 1 P sum _ j ] P sum _ k = ∑ i = 1 s x i ⋅ α ele _ i ⋅ P ele _ i , k ;

[0084] In the formula, Indicates load Discrete daily load model, Indicates the discrete daily load model The instantaneous load at time , For the The first elements.

[0085] Step 4: Define the linear fitting rule to make the discrete daily load model continuous and obtain the daily load model.

[0086] In this embodiment, the linear fitting rule is expressed as:

[0087] ;

[0088] In the formula, Indicates load Discrete daily load model, Indicates the discrete daily load model The instantaneous load at time , For the The first elements.

[0089] The overall structure of the daily load model is as follows: Figure 3 As shown, this embodiment takes four basic loads as an example and illustrates the daily load model under two construction vectors, such as Figure 4 shown.

[0090] Example 3

[0091] Based on the same inventive concept as Example 1, this example introduces a *** device, including:

[0092] A data acquisition module, used to acquire historical load data in the reconfigurable distribution network;

[0093] An element construction module, used to construct influencing factors and basic load clusters according to the historical load data;

[0094] A discrete daily load model construction module is used to take the basic load cluster as a candidate load composition of the daily load model and introduce a composition vector to construct a discrete daily load model;

[0095] The daily load model conversion module is used to define the linear fitting rules to make the discrete daily load model continuous to obtain the daily load model.

[0096] The specific functional implementation of each of the above modules can be found in the relevant contents of the method in Example 1 or 2 and will not be elaborated here.

[0097] Example 4

[0098] Based on the same inventive concept as other embodiments, this embodiment introduces a computer-readable storage medium on which computer instructions are stored. When the computer instructions are executed by a processor, the steps of the method in the above-mentioned embodiment 1 or 2 are implemented.

[0099] Example 5

[0100] Based on the same inventive concept as other embodiments, this embodiment introduces a computer program product, including computer instructions, which implement the steps of the method in the above-mentioned embodiment 1 or 2 when executed by a processor.

[0101] In summary, the present invention uses historical load data in the reconfigurable distribution network to construct influencing factors and basic load clusters, which can accurately reflect the inherent laws and main influencing factors of load changes. At the same time, the basic load cluster is used as a candidate for the load composition of the daily load model, and the composition vector is introduced, which can also flexibly construct a variety of discrete daily load models to meet the application requirements under different scenarios and needs. The present invention also makes the discrete daily load model continuous by defining a linear fitting rule, which not only improves the continuity and smoothness of the daily load model, but also enhances the prediction ability and rationality of the daily load model in terms of instantaneous load size changes, and solves the problems of many interference factors and complex construction in the modeling process of the daily load model of the reconfigurable distribution network;

[0102] The present invention also takes into account the impact of external interference factors such as climate, festivals and electricity prices on the new energy high penetration distribution network by constructing influencing factors, so that the constructed daily load model can more accurately reflect the actual load changes. At the same time, the influencing factors and basic load clusters are constructed using historical load data, which provides rich data support for the daily load model, further improves the accuracy and adaptability of the daily load model, and enables the daily load to better adapt to applications in different scenarios and needs;

[0103] The present invention introduces a composition vector and uses the basic load cluster as a candidate for the load composition of the daily load model, so as to flexibly construct a diversified discrete daily load model, thereby improving the flexibility of the daily load model and making the daily load model have good scalability, and can be adjusted and optimized accordingly with the changes in the distribution network structure and load characteristics;

[0104] The present invention makes the discrete daily load model continuous by defining a linear fitting rule, thereby obtaining a smooth daily load curve, which not only improves the prediction ability of the daily load model on the instantaneous load size change, but also makes the daily load model more practical and operable in energy management and optimized scheduling.

[0105] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0106] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 produce 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.

[0107] 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.

[0108] 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 The steps for the functions specified in one or more boxes.

[0109] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A method for constructing a daily load model for a reconfigurable distribution network, characterized in that: include: Obtain historical load data in the reconfigurable distribution network; Based on the historical load data, construct influencing factors describing the impact of different external interference factors on the new energy high penetration distribution network, and then construct a basic load cluster; The basic load cluster is used as the candidate load composition of the daily load model, and the composition vector is introduced to construct the discrete daily load model. Define the linear fitting rule to make the discrete daily load model continuous and obtain the daily load model.

2. The method for constructing a daily load model for a reconfigurable distribution network according to claim 1, characterized in that: According to the historical load data, the influencing factors and basic load clusters are constructed, including: Constructing an impact factor based on the historical load data, with a value of 0.5 to 1.5, reflecting the impact of external interference factors on the load in the reconfigurable distribution network, wherein the external interference factors include climate, festivals and electricity prices; Extracting instantaneous load magnitudes at different times of historical load data in the reconfigurable distribution network as basic load vector elements for forming a basic load vector, wherein each basic load vector element in the basic load vector is arranged in chronological order; constructing a basic load vector according to the influencing factors and the basic load vector elements; Based on the base load vector, a base load cluster is constructed.

3. The method for constructing a daily load model for a reconfigurable distribution network according to claim 2, characterized in that: The basic load vector is expressed as: ； In the formula, Indicates A basic load vector, Indicates The influencing factor of the base load is Represents the total number of basic load vector elements. The total number of basic load vectors is 25, which is used to represent each moment of the 24 hours in a day. Indicates The first element in the base load vector, Indicates The second element in the base load vector, Indicates The j-1th element in the basic load vector, Indicates The first of the base load vectors elements.

4. The method for constructing a daily load model for a reconfigurable distribution network according to claim 3, characterized in that: The base load cluster is represented as: ； In the formula, represents the base load cluster, represents the first basic load vector, represents the second basic load vector, Indicates A basic load vector, Indicates A basic load vector, It is used to describe the total number of base load vectors in the base load cluster. , Indicates transpose.

5. The method for constructing a daily load model for a reconfigurable distribution network according to claim 4, characterized in that: The constituent vector is expressed as: ； In the formula, Indicates load The constituent vectors of represents the composition coefficient of the first basic load in the basic load cluster, represents the composition coefficient of the second basic load in the basic load cluster, Indicates the first The composition factor of the basic load is represents the composition coefficient of the s-1th basic load in the basic load cluster, It represents the composition coefficient of the sth basic load in the basic load cluster. When a composition coefficient is 0, it means that the basic load cluster corresponding to its subscript is not in the daily load model. When it is 1, it means that the basic load cluster is in the daily load model. Indicates transpose.

6. The method for constructing a daily load model for a reconfigurable distribution network according to claim 5, characterized in that: The discrete daily load model is expressed as: ； In the formula, Indicates load Discrete daily load model, Indicates the discrete daily load model The instantaneous load at time , For the The first elements.

7. The method for constructing a daily load model for a reconfigurable distribution network according to claim 6, characterized in that: The linear fitting rule is expressed as: ； In the formula, express The instantaneous power of the daily load model composed of time, Represents any time of the day, a continuous independent variable, in units of ; Considering the boundary conditions, k is taken as .

8. A daily load model forming device for a reconfigurable distribution network, characterized in that: include: A data acquisition module, used to acquire historical load data in the reconfigurable distribution network; An element construction module, used to construct influencing factors and basic load clusters according to the historical load data; A discrete daily load model construction module is used to take the basic load cluster as a candidate load composition of the daily load model and introduce a composition vector to construct a discrete daily load model; The daily load model conversion module is used to define the linear fitting rules to make the discrete daily load model continuous to obtain the daily load model.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for constructing a daily load model for a reconfigurable distribution network as described in any one of claims 1 to 7 is implemented.

10. A computer device, characterized in that: include: A memory for storing instructions; A processor is used to execute the instructions so that the device performs operations to implement the method for constructing a daily load model for a reconfigurable distribution network as described in any one of claims 1 to 7.

Images