Power distribution network material supply chain node load analysis method and device based on multi-dimensional historical data, medium and product

Abstract

The invention discloses a power distribution network material supply chain node load analysis method and device based on multi-dimensional historical data, a medium and a product, and relates to the technical field of power distribution network material supply chain management.The method comprises the steps that spatial features and time features of supply chain node loads are extracted; constructing a dynamic effective capacity model of the node according to the physical attribute data; according to the business logic data and the time characteristics, constructing a multi-factor demand generation model, and performing node load demand prediction; according to the dynamic effective capacity model of the node and the node load demand prediction result, defining a composite load index, and quantifying the load state of the node to obtain a load quantification result; and constructing a power distribution network supply chain space-time network according to the spatial features and the load quantification result, and identifying key bottleneck nodes by using a node load pressure propagation algorithm. The potential bottleneck and risk point of the supply chain can be revealed, and data support is provided for network structure optimization and emergency strategy formulation.

Description

Technical Field

[0001] This application relates to the field of power distribution network material supply chain management technology, and in particular to a method, equipment, medium and product for load analysis of power distribution network material supply chain nodes based on multi-dimensional historical data. Background Technology

[0002] With the accelerated construction of new power systems and the continuous rapid expansion of distribution networks, the complexity of the power supply chain is constantly increasing. Building an efficient and resilient distribution network supply chain system has become a crucial foundation for supporting the construction of new power systems and ensuring reliable power supply for people's livelihoods. Simultaneously, with the deepening implementation of "dual-carbon" goals and the large-scale integration of new elements such as distributed energy and electric vehicles, the distribution network structure is becoming increasingly complex. Its planning, construction, operation, and maintenance place unprecedentedly higher demands on the timeliness, accuracy, and flexibility of material supply. Considering the development needs of new power systems and the inherent characteristics of distribution networks—wide geographical distribution and significant differences—deeply mining and utilizing massive, multi-dimensional historical operational data to conduct refined load analysis and forecasting of key nodes in the supply chain is currently the most promising path to improve the overall efficiency of the supply chain and support the high-quality development of the power grid. Therefore, developing efficient and accurate load analysis methods for distribution network supply chain nodes based on multi-dimensional historical data has become an important research topic.

[0003] Currently, the demand for distribution network materials exhibits complex characteristics, including a massive total volume, dispersed spatial distribution, severe cyclical fluctuations, and sensitivity to policy guidance. The distribution network material supply system faces the challenge of dynamic load imbalance. The current distribution network material supply chain suffers from core bottlenecks such as insufficient analysis of load transmission paths, imperfect modeling of time-delay response mechanisms, and inaccurate wide-area resource adaptation. Specifically, this manifests as the nonlinear propagation of node overload risk along the supply chain network, and the inability of traditional static scheduling strategies to adapt to multi-dimensional spatial heterogeneity. Against this backdrop, constructing an intelligent and efficient method for analyzing the node load of the distribution network material supply chain has become a key breakthrough for ensuring the safe operation of the new power system. Summary of the Invention

[0004] The purpose of this application is to provide a method, equipment, medium and product for load analysis of nodes in the power distribution network material supply chain based on multidimensional historical data. This method can reveal potential bottlenecks and risk points in the supply chain, provide data support for network structure optimization and emergency strategy formulation, and ultimately promote the intelligent upgrading of the power distribution network material supply chain and ensure the reliable and economical operation of the power grid.

[0005] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a method for load analysis of distribution network material supply chain nodes based on multi-dimensional historical data, characterized by including: Acquire supply chain node data; the supply chain node data is multi-dimensional historical data of power distribution network material supply chain nodes; the multi-dimensional historical data includes: spatiotemporal distribution data, physical attribute data, and business logic data; Based on the supply chain node data, extract the spatial and temporal characteristics of the supply chain node load; Based on the physical attribute data, combined with environmental factors and material shelf-life decay factors, a dynamic effective capacity model for the nodes is constructed. Based on the business logic data and the time characteristics, a multi-factor demand generation model is constructed, and node load demand is predicted. Based on the dynamic effective capacity model of the nodes and the predicted load demand of the nodes, a composite load index is defined, and the load status of the nodes is quantified to obtain the load quantification result. Based on the spatial characteristics and the load quantization results, a spatiotemporal network of the power distribution network supply chain is constructed with inter-node transportation paths as edges. Based on the spatiotemporal network of the power distribution network supply chain, a node load pressure propagation algorithm is used to identify key bottleneck nodes.

[0006] Optionally, based on the supply chain node data, spatial and temporal characteristics of the supply chain node load are extracted, specifically including: Based on the supply chain node data, obtain the location and weight of demand points within the node's radiation range; By using geographic information systems and network analysis methods, and combining the location and weight of demand points within the node's radiation range, the service density index and traffic accessibility weight are calculated to obtain spatial characteristics. The load data in the supply chain node data is separated and split using the STL time series decomposition method to obtain time features.

[0007] Optionally, based on the physical attribute data, and in conjunction with environmental factors and material shelf-life decay factors, a dynamic effective capacity model for the node is constructed, specifically including: The theoretical maximum storage capacity of the node is calculated based on the physical attribute data and the physical attributes of the materials; the physical attributes of the materials include: volume, weight, and storage environment requirements; Based on the node's theoretical maximum storage capacity, and considering environmental factors and the material's shelf-life decay factor, a dynamic effective capacity model for the node is constructed. The mathematical formula is as follows: ; in, C eff ( t () represents the dynamic effective capacity; C max This is the theoretical maximum storage capacity; α ( t) represents the dynamic environmental factor, indicating the real-time impact of current environmental factors on storage capacity; β ( t) This is the material shelf-life decay factor, which represents the impact of the shortened shelf life of materials due to accelerated environmental degradation on capacity. f env This is the static environment adaptation factor, representing the degree to which the node's storage environment adapts to the requirements of material storage; V node This represents the total storage volume of the node; W node This represents the maximum load-bearing capacity of the node. v For unit material volume; w For the quality of materials in the unit; a T ( t ) represents the temperature influence factor; a H ( t ) represents the humidity influencing factor; a other ( t Other environmental factors; λ nominal The nominal degradation rate represents the expected degradation rate of a material under standard environmental conditions. λ (t) represents the real-time degradation rate, indicating the actual degradation rate under the current environmental conditions.

[0008] Optionally, the mathematical formula for the multi-factor demand generation model is: ; In the formula, D t For time points t The demand for materials at each node; α 0、 α 1. α 2 represents the trend coefficient. α 0 is the basic load constant. α 1 represents the linear growth coefficient. α 2 represents the acceleration / deceleration coefficient; m The maximum harmonic order; h Harmonic sequence number; β h , ϕ h For periodic component parameters; P The length of the main period; X f,t For the first f External influencing factors over time t The value of ; n is the number of external influencing factors; γ j External influencing factorsX j The elastic modulus; F t For power grid business logic coupling factor; λ The impact of sudden failures on demand; ε t This represents random noise.

[0009] Optionally, the mathematical formula for the composite load index is: ; In the formula, L i ( t ) represents the composite load index of node i; Q actual ( t () represents the actual amount of materials occupied at time t; C eff ( t ) represents the dynamic effective capacity of a node; T process ( t () represents the average processing time for inbound and outbound data at each node; T standard ( t () represents the standard inbound / outbound processing time for each node; R criticality ( t The key level weight of the node material is )

[0010] Optionally, the node load pressure propagation algorithm employs discrete-time step iteration, and the update formula for the node pressure value is: ; In the formula, p i ( t )and p i ( t +1) are nodes i In time t and t The pressure value is +1, where the pressure value is the ratio of the node's current load to its design load. o j ( t ), o k ( t These represent the overload portions of adjacent upstream and downstream nodes, respectively. D ( i ) is a node i The set of downstream adjacent nodes; U ( i ) is a node iThe set of upstream adjacent nodes; w ik Indicates from node i to downstream nodes k Path weights; w ji Indicates from the upstream node j To the node i Path weights; α This is the downstream propagation coefficient; β This represents the upstream propagation coefficient.

[0011] Optionally, after identifying key bottleneck nodes based on the spatiotemporal network of the distribution network supply chain and using a node load pressure propagation algorithm, the method further includes: Based on the calculated node composite load index, a three-level early warning system of yellow, orange, and red is deployed. When a yellow warning is issued, the node is slightly overloaded, and a monitoring mechanism is activated to prevent bottlenecks. When an orange warning is issued, the node is moderately overloaded, and the load is close to the critical capacity, so dynamic allocation is activated. When a red warning is issued, the node is severely overloaded, and business diversion, forced expansion, and cross-regional collaborative support measures are implemented.

[0012] Secondly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the distribution network material supply chain node load analysis method based on multidimensional historical data as described above.

[0013] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the distribution network material supply chain node load analysis method based on multidimensional historical data as described above.

[0014] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method for load analysis of distribution network material supply chain nodes based on multidimensional historical data.

[0015] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a method, equipment, medium, and product for load analysis of distribution network material supply chain nodes based on multidimensional historical data. The method includes: acquiring supply chain node data; the supply chain node data is multidimensional historical data of distribution network material supply chain nodes; the multidimensional historical data includes: spatiotemporal distribution data, physical attribute data, and business logic data; extracting spatial and temporal characteristics of the supply chain node load based on the supply chain node data; constructing a dynamic effective capacity model of the nodes based on the physical attribute data, combined with environmental factors and material validity decay factors; constructing a multi-factor demand generation model based on the business logic data and the temporal characteristics, and predicting node load demand; defining a composite load index based on the node's dynamic effective capacity model and the node load demand prediction results, and quantifying the node's load status to obtain load quantification results; constructing a distribution network supply chain spatiotemporal network based on the spatial characteristics and the load quantification results, with inter-node transportation paths as edges; and identifying key bottleneck nodes using a node load pressure propagation algorithm based on the distribution network supply chain spatiotemporal network. This application collects and processes historical data of nodes in the distribution network material supply chain, extracts their characteristics, analyzes node load, obtains their dynamic capacity, and constructs a multi-factor demand generation model based on the node dynamic capacity to predict node load. Simultaneously, a composite load index is defined to quantify the load status of distribution network nodes in multiple dimensions. Finally, based on the above model and algorithm, a dynamic closed loop for distribution network material supply chain node decision-making and material allocation is formed, thereby revealing potential bottlenecks and risks in the supply chain. This provides data support for network structure optimization and emergency strategy formulation, ultimately promoting the intelligent upgrading of the distribution network material supply chain and ensuring the reliable and economical operation of the power grid. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is an application environment diagram of a load analysis method for distribution network material supply chain nodes based on multidimensional historical data, as described in one embodiment of this application.

[0018] Figure 2 This is a flowchart illustrating a method for analyzing the load of nodes in the power distribution network material supply chain based on multidimensional historical data, provided as an embodiment of this application.

[0019] Figure 3 This is a schematic diagram of the overall process of a load analysis method for distribution network material supply chain nodes based on multidimensional historical data, provided as an embodiment of this application.

[0020] Figure 4 This is a schematic diagram of the data processing flow of a load analysis method for distribution network material supply chain nodes based on multidimensional historical data, provided as an embodiment of this application.

[0021] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] This application relates to a method for load analysis of distribution network material supply chain nodes based on multidimensional historical data. The method includes: S1, collecting multidimensional historical data of distribution network material supply chain nodes and performing standardization processing; S2, extracting the spatial and temporal characteristics of supply chain node load based on the supply chain node data extracted in step S1; S3, constructing a static capacity model for supply chain nodes and introducing multi-factor dynamic adjustments to available capacity; S4, establishing a multi-factor demand generation model to predict node load demand coupled with distribution network business logic; S5, defining a composite load index to quantify the load status of distribution network nodes in multiple dimensions; S6, constructing a spatiotemporal network of the distribution network supply chain and running a node load pressure propagation algorithm; S7, identifying key bottleneck nodes based on the node load pressure propagation algorithm extracted in step S6 and generating dynamic allocation suggestions for distribution network materials; S8, deploying a three-level early warning system to reduce load in real time and adjust supply chain node business parameters. This application belongs to the field of intelligent management technology for power material supply chains, specifically involving a method for load analysis of distribution network material supply chain nodes that integrates spatiotemporal distribution, physical attributes, and business logic. Starting from the basic data of the power distribution network material supply chain, a model is established to understand the load status and transmission mechanism, and scientific evaluation thresholds are set. Then, by using priority reconstruction and dynamic balancing technology, and based on understanding the laws of business evolution, various scenarios are addressed in a targeted manner, which improves the load resilience and overall operating efficiency of key nodes in the power distribution network material supply chain in complex environments. This has high engineering application value.

[0024] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] The load analysis method for distribution network material supply chain nodes based on multi-dimensional historical data provided in this application can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on another server.

[0026] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0027] In one exemplary embodiment, such as Figure 2 As shown, a method for load analysis of distribution network material supply chain nodes based on multi-dimensional historical data is provided. This method is executed by computer equipment, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps A1 to A7. Wherein: A1. Obtain supply chain node data; the supply chain node data is multi-dimensional historical data of the power distribution network material supply chain nodes; the multi-dimensional historical data includes: spatiotemporal distribution data, physical attribute data, and business logic data.

[0028] In this embodiment, multi-dimensional historical data of power distribution network material supply chain nodes are collected and standardized. Historical data on the spatiotemporal distribution, physical attributes, and business logic of power distribution network material supply chain nodes are collected, and the data is cleaned, missing values ​​are filled, and spatiotemporal alignment is performed (such as locating work orders to the nearest node). The data is then uniformly converted into a structured time series format to complete the standardization process.

[0029] A2. Based on the supply chain node data, extract the spatial and temporal characteristics of the supply chain node load.

[0030] Based on the extracted supply chain node data, spatial and temporal characteristics of the supply chain node load are extracted. Spatial characteristics include the service density index (reflecting demand concentration) and transportation accessibility weight (reflecting delivery convenience) within the node's radiation range. These reflect the density of business demand and the ease with which goods can reach various points within the geographical area served by a supply chain node (such as a warehouse or distribution center). Temporal characteristics are obtained by decomposing historical load time series to extract seasonal fluctuation coefficients, trend terms, and sudden event markers, which can be used to predict future load changes. Specifically, the spatial characteristic extraction process utilizes GIS (Geographic Information System) and network analysis techniques, combining the location and weight of demand points within the node's radiation range to calculate the service density index and transportation accessibility weight. The temporal characteristic extraction process utilizes STL time series decomposition technology to separate and decompose the original load data into three additive components: a trend term (long-term direction), a seasonal component (periodic fluctuation, i.e., seasonal fluctuation coefficient), and a residual term. This provides crucial feature inputs for understanding the temporal dynamics of load, demand forecasting, and anomaly event identification.

[0031] A3. Based on the physical attribute data, combined with environmental factors and material shelf-life decay factors, construct a dynamic effective capacity model for the nodes.

[0032] In this embodiment, a static capacity model of supply chain nodes is constructed, and multiple factors are introduced to dynamically adjust the available capacity.

[0033] Calculate the theoretical maximum storage capacity of the node based on the physical properties of the materials (volume, weight, storage environment requirements). C max Simultaneously, environmental factors (such as the effects of temperature and humidity on equipment storage) and material shelf-life decay factors are introduced to dynamically adjust the available capacity and define the dynamic effective capacity. C eff ( t In this context, supply chain nodes refer to warehouses, distribution centers, and other entities within the supply chain used for storing, distributing, and supplying materials to the power distribution network. The physical attributes of these materials (volume, weight, storage environment requirements) are used to calculate the storage capacity of the supply chain nodes (such as warehouses and distribution centers) in the power distribution network; simply put, it's how much material a node can store. When constructing the static capacity model of the supply chain nodes, environmental factors and subsequent variables are introduced to dynamically adjust the available capacity and derive the effective capacity. C eff ( t ).

[0034] The mathematical formula for the dynamic effective capacity model of a node is: ; in, C eff (t () represents the dynamic effective capacity; C max This is the theoretical maximum storage capacity; α ( t ) represents dynamic environmental factors, indicating the real-time impact of current environmental conditions (such as temperature and humidity) on storage capacity; β ( t) This is the material shelf-life decay factor, which represents the impact of the shortened shelf life of materials due to accelerated environmental degradation on capacity. f env This is the static environment adaptation factor, representing the degree to which the node's storage environment adapts to the requirements of material storage; V node m is the total storage volume of the node. 3 ; W node The maximum load-bearing capacity of the node is expressed in kg. v For unit material volume, m 3 ; w The unit of measurement for material weight is kg; a T ( t ) represents the temperature influence factor; a H ( t ) represents the humidity influencing factor; a other ( t Other environmental factors; λ nominal The nominal degradation rate represents the expected degradation rate of a material under standard environmental conditions, expressed in days. λ (t) represents the real-time degradation rate, indicating the actual degradation rate under the current environmental conditions, in days.

[0035] A4. Based on the business logic data and the time characteristics, a multi-factor demand generation model is constructed, and node load demand prediction is performed. This embodiment performs node load demand prediction coupled with the distribution network business logic.

[0036] The mathematical formula for the multi-factor demand generation model is: ; In the formula, ; In the formula, D t For time points t The demand for materials at each node; α 0、 α 1. α 2 represents the trend coefficient. α 0 is the basic load constant. α 1 represents the linear growth coefficient.α 2 represents the acceleration / deceleration coefficient; m The maximum harmonic order; h Harmonic sequence number; β h , ϕ h For periodic component parameters; P The length of the main period; X f,t For the first f External influencing factors over time t The value of ; n is the number of external influencing factors; γ j External influencing factors X j The elastic coefficient (sensitivity); F t For power grid business logic coupling factor; λ The impact of sudden failures on demand; ε t This is the random noise term (error adjustment amount).

[0037] A5. Based on the dynamic effective capacity model of the node and the node load demand prediction results, define the composite load index and quantify the load status of the node to obtain the load quantification results.

[0038] In this embodiment, a composite load index is defined. L i ( t ), and multidimensionally quantify the load status of distribution network nodes.

[0039] The mathematical formula for the composite load index is: ; In the formula, L i ( t ) represents the composite load index of node i; Q actual ( t () represents the actual amount of materials occupied at time t; C eff ( t ) represents the dynamic effective capacity of a node; T process ( t () represents the average processing time for inbound and outbound data at each node; T standard ( t () represents the standard inbound / outbound processing time for each node; R criticality ( t The key level weight of the node material is )

[0040] A6. Based on the spatial characteristics and the load quantification results, construct a spatiotemporal network of the power distribution network supply chain with the inter-node transportation paths as edges.

[0041] The supply chain spatiotemporal network uses warehouses and transit stations as points and transportation paths between nodes as edges. The algorithm simulates the chain effect of the load spreading upstream and downstream along the transportation path when a single node is overloaded.

[0042] Steps A4, A5, and A6 form a progressive analysis process: demand forecasting drives load status assessment, and load status provides the basis for evaluating node load pressure. Specifically, A4's node load demand forecasting provides input data for A5 and A6; A5 compares and comprehensively calculates the load demand predicted by A4 with the node capacity established in A3 to obtain a multi-dimensional, comprehensive indicator (composite load index) to accurately quantify the load status of each node under forecasted demand; A6 uses the initial load status provided by A5 as the starting point for simulation, and further analyzes how local bottlenecks in the supply chain can trigger global problems, providing a comprehensive and dynamic basis for the decision-making in A7.

[0043] A7. Based on the spatiotemporal network of the power distribution network supply chain, key bottleneck nodes are identified using the node load pressure propagation algorithm.

[0044] The node load pressure propagation algorithm uses discrete time step iteration, and its core is the update formula for the node pressure value: ; In the formula, p i ( t )and p i ( t +1) are nodes i In time t and t +1 pressure value (the ratio of the node's current load to its design load); o j ( t ), o k ( t These represent the overload portions of adjacent upstream and downstream nodes, respectively. D ( i ) is a node i The set of downstream adjacent nodes; U ( i ) is a node i The set of upstream adjacent nodes; w ik Indicates from node i to downstream nodes k Path weights;w ji Indicates from the upstream node j To the node i Path weights; α This is the downstream propagation coefficient; β This represents the upstream propagation coefficient.

[0045] This allows us to obtain the overload portion of node i. o i ( t The formula is as follows: .

[0046] In this embodiment, a node load pressure propagation algorithm is used to identify key bottleneck nodes and generate dynamic allocation suggestions for distribution network materials.

[0047] Key bottleneck node identification is a dynamic analysis process based on the simulation of supply chain spatiotemporal network pressure propagation. Its core logic is to identify those nodes that have a nonlinear amplification effect on the efficiency of the global supply chain and whose own load status is close to or exceeds the safety threshold.

[0048] The bottleneck characteristics of nodes are considered from the following three aspects: identifying nodes that are depended on by multiple upstream nodes in the pressure propagation path and have high overflow pressure; calculating the sensitivity of node load index changes to the average latency of the entire network, with nodes showing high sensitivity considered bottlenecks; and calculating the proportion of cascading overloads of downstream nodes caused by a single node failure, with higher proportions indicating stronger bottleneck attributes. Simultaneously, bottlenecks are classified: bottleneck nodes that are chronically overloaded are identified as hard bottlenecks; bottleneck nodes with a surge in load index under specific business scenarios and high sensitivity are identified as soft bottlenecks; and bottleneck nodes with moderate normal load but high risk of cascading failures, easily leading to the paralysis of downstream nodes, are identified as latent bottlenecks. When generating dynamic allocation suggestions, based on the bottleneck identification results, targeted decoupling strategies are generated: physical expansion suggestions are given for hard bottlenecks; resource elastic scheduling strategies are adopted for soft bottlenecks; and topology optimization of the supply chain is performed for latent bottlenecks to reduce cascading risks.

[0049] This embodiment also includes: deploying a three-level early warning system to reduce load in real time and adjust business parameters of supply chain nodes.

[0050] Based on the node composite load index L i The value is yellow (0.75 ≥). L i ≥0.6), orange (0.9≥) L i ≥0.75), red ( L iThe three-level early warning system (≥0.9) immediately reduces load and adjusts business parameters of supply chain nodes. A yellow warning indicates a node is slightly overloaded, requiring the activation of monitoring mechanisms to prevent bottlenecks. An orange warning indicates a node is moderately overloaded, with the load approaching critical capacity and a significantly increased risk of response delays, requiring timely dynamic adjustments such as activating backup suppliers, optimizing routes, and temporary capacity increases. A red warning indicates a node is severely overloaded, requiring immediate implementation of measures such as business diversion, forced capacity expansion, and cross-regional collaborative support.

[0051] Overall, such as Figure 3 and Figure 4 As shown, this embodiment proposes a load analysis method for distribution network material supply chain nodes based on multidimensional historical data. It collects and processes historical data of distribution network material supply chain nodes, extracts their features, analyzes node load to obtain their dynamic capacity, and constructs a multi-factor demand generation model based on the node dynamic capacity to predict node load. Simultaneously, a composite load index is defined to quantify the load status of distribution network nodes in multiple dimensions. Finally, a dynamic closed loop for distribution network material supply chain node decision-making and material allocation is formed based on the above model and algorithm.

[0052] This embodiment proposes a load analysis method for distribution network material supply chain nodes based on multi-dimensional historical data. This method not only enables precise pre-positioning and dynamic optimization of inventory, improving the timeliness and reliability of material supply and ensuring the safe and stable operation of the power grid, but also reveals potential bottlenecks and risks in the supply chain. It provides data support for network structure optimization and emergency strategy formulation, ultimately promoting the intelligent upgrading of the distribution network material supply chain and ensuring the reliable and economical operation of the power grid. This embodiment extracts spatiotemporal features from standardized historical data, constructs a dynamically corrected capacity model and a multi-factor demand forecasting model, quantifies node status using a composite load index, and runs a pressure propagation algorithm in the spatiotemporal network to identify bottleneck nodes. Finally, it generates material allocation suggestions and deploys a three-level early warning system to achieve dynamic optimization. This improves the intelligence level of the distribution network material supply chain to a certain extent.

[0053] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 5As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for load analysis of power distribution network material supply chain nodes based on multi-dimensional historical data.

[0054] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0055] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0056] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0057] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0058] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0059] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0060] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0061] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0062] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for load analysis of distribution network material supply chain nodes based on multidimensional historical data, characterized in that, include: Acquire supply chain node data; The supply chain node data refers to the multi-dimensional historical data of the distribution network material supply chain nodes. The multidimensional historical data includes: spatiotemporal distribution data, physical attribute data, and business logic data; Based on the supply chain node data, extract the spatial and temporal characteristics of the supply chain node load; Based on the physical attribute data, combined with environmental factors and material shelf-life decay factors, a dynamic effective capacity model for the nodes is constructed. Based on the business logic data and the time characteristics, a multi-factor demand generation model is constructed, and node load demand is predicted. Based on the dynamic effective capacity model of the nodes and the predicted load demand of the nodes, a composite load index is defined, and the load status of the nodes is quantified to obtain the load quantification result. Based on the spatial characteristics and the load quantization results, a spatiotemporal network of the power distribution network supply chain is constructed with inter-node transportation paths as edges. Based on the spatiotemporal network of the power distribution network supply chain, a node load pressure propagation algorithm is used to identify key bottleneck nodes.

2. The method for load analysis of distribution network material supply chain nodes based on multi-dimensional historical data according to claim 1, characterized in that, Based on the supply chain node data, the spatial and temporal characteristics of the supply chain node load are extracted, specifically including: Based on the supply chain node data, obtain the location and weight of demand points within the node's radiation range; By using geographic information systems and network analysis methods, and combining the location and weight of demand points within the node's radiation range, the service density index and traffic accessibility weight are calculated to obtain spatial characteristics. The load data in the supply chain node data is separated and split using the STL time series decomposition method to obtain time features.

3. The method for load analysis of distribution network material supply chain nodes based on multidimensional historical data according to claim 1, characterized in that, Based on the physical attribute data, combined with environmental factors and material shelf-life decay factors, a dynamic effective capacity model for the nodes is constructed, specifically including: The theoretical maximum storage capacity of the node is calculated based on the physical attribute data and the physical attributes of the materials; the physical attributes of the materials include: volume, weight, and storage environment requirements; Based on the node's theoretical maximum storage capacity, and considering environmental factors and the material's shelf-life decay factor, a dynamic effective capacity model for the node is constructed. The mathematical formula is as follows: ； in, C eff ( t () represents the dynamic effective capacity; C max This is the theoretical maximum storage capacity; α ( t ) represents the dynamic environmental factor, indicating the real-time impact of current environmental factors on storage capacity; β ( t) This is the material shelf-life decay factor, which represents the impact of the shortened shelf life of materials due to accelerated environmental degradation on capacity. f env This is the static environment adaptation factor, representing the degree to which the node's storage environment adapts to the requirements of material storage; V node This represents the total storage volume of the node; W node This represents the maximum load-bearing capacity of the node. v For unit material volume; w For the quality of materials in the unit; a T ( t ) represents the temperature influence factor; a H ( t ) represents the humidity influencing factor; a other ( t Other environmental factors; λ nominal The nominal degradation rate represents the expected degradation rate of a material under standard environmental conditions. λ (t) represents the real-time degradation rate, indicating the actual degradation rate under the current environmental conditions.

4. The method for load analysis of distribution network material supply chain nodes based on multi-dimensional historical data according to claim 1, characterized in that, The mathematical formula for the multi-factor demand generation model is: ； In the formula, D t For time points t The demand for materials at each node; α 0、 α 1. α 2 represents the trend coefficient. α 0 is the basic load constant. α 1 represents the linear growth coefficient. α 2 represents the acceleration / deceleration coefficient; m The maximum harmonic order; h Harmonic sequence number; β h , ϕ h For periodic component parameters; P The length of the main period; X f,t For the first f External influencing factors over time t The value of ; n is the number of external influencing factors; γ j External influencing factors X j The elastic modulus; F t For power grid business logic coupling factor; λ The impact of sudden failures on demand; ε t This represents random noise.

5. The method for load analysis of distribution network material supply chain nodes based on multi-dimensional historical data according to claim 1, characterized in that, The mathematical formula for the composite load index is: ； In the formula, L i ( t ) represents the composite load index of node i; Q actual ( t () represents the actual amount of materials occupied at time t; C eff ( t ) represents the dynamic effective capacity of a node; T process ( t () represents the average processing time for inbound and outbound data at each node; T standard ( t () represents the standard inbound / outbound processing time for each node; R criticality ( t The key level weight of the node material is ) 6. The method for load analysis of distribution network material supply chain nodes based on multi-dimensional historical data according to claim 1, characterized in that, The node load pressure propagation algorithm uses discrete time step iteration, and the update formula for the node pressure value is: ； In the formula, p i ( t )and p i ( t +1) are nodes i In time t and t The pressure value is +1, where the pressure value is the ratio of the node's current load to its design load. o j ( t ), o k ( t These represent the overload portions of adjacent upstream and downstream nodes, respectively. D ( i ) is a node i The set of downstream adjacent nodes; U ( i ) is a node i The set of upstream adjacent nodes; w ik Indicates from node i to downstream nodes k Path weights; w ji Indicates from the upstream node j To the node i Path weights; α This is the downstream propagation coefficient; β This represents the upstream propagation coefficient.

7. The method for load analysis of distribution network material supply chain nodes based on multidimensional historical data according to claim 1, characterized in that, After identifying key bottleneck nodes based on the spatiotemporal network of the distribution network supply chain and using a node load pressure propagation algorithm, the process further includes: Based on the calculated node composite load index, a three-level early warning system of yellow, orange, and red is deployed. When a yellow warning is issued, the node is slightly overloaded, and a monitoring mechanism is activated to prevent bottlenecks. When an orange warning is issued, the node is moderately overloaded, and the load is close to the critical capacity, so dynamic allocation is activated. When a red warning is issued, the node is severely overloaded, and business diversion, forced expansion, and cross-regional collaborative support measures are implemented.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes the computer program to implement the distribution network material supply chain node load analysis method based on multidimensional historical data as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the method for load analysis of power distribution network material supply chain nodes based on multidimensional historical data as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the method for load analysis of power distribution network material supply chain nodes based on multidimensional historical data as described in any one of claims 1-7.

Images