Power grid equipment supply chain coordinated scheduling method

Abstract

The invention discloses a power grid equipment supply chain coordinated scheduling method, and relates to the technical field of power grid equipment supply chain scheduling, and the method comprises the following steps: obtaining power grid equipment working nodes of a to-be-tested region, and obtaining transportation influence data and a transportation mode between every two nodes according to the power grid equipment working nodes; constructing a transportation weight model between the two nodes based on a machine learning algorithm according to the transportation influence data, and obtaining a transportation weight coefficient of each transportation mode between the two points; according to the transportation weight coefficient, based on a multimodal transportation method and a shortest path algorithm, performing data analysis to obtain an optimal transportation route; by establishing the transportation weight model and combining with the shortest path method, the problems that the comprehensive advantages of different transportation modes cannot be fully considered, the resource allocation is unreasonable, and the total transportation cost and time are increased are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of supply chain scheduling, and more specifically, to a method for coordinated scheduling of a power grid equipment supply chain. Background Art

[0002] The coordination and dispatching of the power grid equipment supply chain is a key link in the management of modern power systems, involving the entire process from raw material procurement, production and manufacturing to equipment delivery and maintenance. With the rapid development of renewable energy and the widespread application of smart grid technology, the demand for power grid equipment is becoming increasingly diversified and complex, and the traditional supply chain management model is facing challenges. Power grid equipment usually has high technical content and a long life cycle, and its production process requires close cooperation of multiple links. For example, the production of key facilities such as transformers and switchgear involves the collaboration of multiple suppliers and manufacturers. Therefore, how to optimize the coordination and dispatching of each link, improve resource utilization efficiency, and reduce costs has become a key task.

[0003] As market demand uncertainty increases, the power grid equipment supply chain needs to be flexible and adaptable. Natural disasters, policy changes, market fluctuations and other factors all affect the stability of the supply chain. Therefore, real-time data analysis and forecasting technology is particularly important. Use big data analysis, artificial intelligence and machine learning technologies to improve the accuracy of demand forecasts, thereby optimizing inventory management and production scheduling.

[0004] The above disclosed technical solutions have at least the following technical problems: Traditional methods usually only consider a single mode of transportation, fail to fully utilize the advantages of multimodal transportation, and rely too much on personnel experience and fail to fully consider the comprehensive advantages of different modes of transportation, resulting in unreasonable resource allocation and increased total transportation costs and time. In view of the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method for coordinated scheduling of a power grid equipment supply chain, by obtaining working nodes of power grid equipment in a test area, and obtaining transportation impact data and transportation modes between every two nodes according to the working nodes of the power grid equipment; constructing a transportation weight model between two nodes based on a machine learning algorithm according to the transportation impact data, and obtaining a transportation weight coefficient of each transportation mode between the two points; performing data analysis based on the transportation weight coefficient and a multimodal transport method and a shortest path algorithm to obtain an optimal transportation route, so as to solve the problem that traditional methods usually only consider a single transportation mode, fail to fully utilize the advantages of multimodal transport, and rely too much on personnel experience and fail to fully consider the comprehensive advantages of different transportation modes, resulting in unreasonable resource allocation and increased total transportation cost and time. To achieve the above object, the present invention provides the following technical solutions: A power grid equipment supply chain coordination and scheduling method includes obtaining working nodes of power grid equipment in a test area, obtaining transportation impact data and transportation modes between every two nodes based on the working nodes of the power grid equipment; constructing a transportation weight model between two nodes based on a machine learning algorithm according to the transportation impact data, and obtaining a transportation weight coefficient of each transportation mode between the two points; and performing data analysis based on the transportation weight coefficients based on a multimodal transport method and a shortest path algorithm to obtain an optimal transportation route.

[0006] In a preferred embodiment, the transportation impact data includes fluctuations in power grid equipment demand, and the specific steps for obtaining the fluctuations in power grid equipment demand are as follows: obtaining historical load data, power demand data and voltage fluctuations of the area to be tested, and performing data preprocessing on the historical load data, power demand data and voltage fluctuations to remove missing values ​​and outliers; capturing data trends based on a linear regression model, smoothing the historical load data, power demand data and voltage fluctuations, and drawing them into a linear graph; extracting characteristic data of the load data and power demand data in each time period based on a time series method according to the load data and power demand data; obtaining the valley and peak values ​​of the voltage in each time period according to the linear graph, thereby obtaining the fluctuation state of each time period; constructing a power grid equipment demand fluctuation model based on a machine learning algorithm according to the load data, power demand data and voltage fluctuations, and obtaining the power grid equipment demand fluctuation coefficient of the area to be tested.

[0007] In a preferred embodiment, the transport impact data includes transport road conditions, and the specific steps for obtaining the transport road conditions are as follows: obtaining road condition evaluation index parameters for all transport modes on the transport route to be tested, the road condition evaluation index parameters including road conditions, traffic flow and weather conditions; setting scoring indicators according to the different degrees of impact of the road condition evaluation index parameters on all transport modes; obtaining the scores of various index parameters of all transport modes, and obtaining the comprehensive road condition scores of the transport routes of all transport modes based on the weighted average method; obtaining the preferred transport mode based on the comprehensive road condition score of each transport mode; obtaining the road condition evaluation index parameters in real time through GPS and a real-time traffic monitoring system, and continuously updating the comprehensive road condition score of the transport route.

[0008] In a preferred embodiment, the transportation weight model between the two nodes is constructed based on the machine learning algorithm according to the transportation impact data to obtain the transportation weight coefficient of each transportation mode between the two points, specifically: according to the power grid equipment demand fluctuation and the transportation road condition, the transportation weight model between the two nodes is constructed based on the machine learning algorithm; the transportation mode between the areas to be tested is obtained, the transportation road condition between the areas to be tested is obtained according to the transportation mode, and the transportation road conditions of different transportation modes are downgraded to obtain a priority sorting form; the power grid equipment demand fluctuation data of the area to be tested is obtained, and the power grid equipment demand fluctuation state is calculated based on the power grid equipment demand fluctuation formula; according to the power grid equipment demand fluctuation and the transportation road condition, the transportation weight coefficient between the areas to be tested is calculated based on the transportation weight model.

[0009] In a preferred embodiment, the data analysis is performed based on the multimodal transport method and the shortest path algorithm according to the transport weight coefficient to obtain the optimal transport route, specifically: obtaining the transportation network information between the areas to be tested, including the infrastructure of road, rail, water and air transport modes; evaluating the geographical location of the area to be tested, and determining the relative position and distance between the area to be tested and other areas; identifying places with large transportation volume and strong connectivity by analyzing traffic flow data, and obtaining major transportation hubs; determining the major transportation hubs between the areas to be tested, and collecting the transportation mode and distance data of each hub; for each transportation mode, calculating its proportion in the total transportation distance, and obtaining the transportation weight coefficient of each mode; using the weighted average method to combine the weights of each transportation mode to form a comprehensive transportation weight coefficient to reflect the efficiency of multimodal transport; applying the comprehensive transportation weight coefficient to the shortest path algorithm to identify the best combination of transportation modes and the optimal route to ensure the minimization of overall transportation efficiency and cost.

[0010] Technical effects and advantages of the power grid equipment supply chain coordination and scheduling method of the present invention: 1. The present invention constructs a demand fluctuation model for power grid equipment through in-depth analysis of historical load data, power demand data, and voltage fluctuations. Accurately predicting demand fluctuations can better plan the supply and transportation needs of power grid equipment and reduce the risk of equipment shortage or surplus. By evaluating the road conditions and impacts of different transportation modes, the transportation mode is prioritized based on the comprehensive road condition score, effectively reducing delays and costs during transportation and improving response speed.

[0011] 2. The present invention obtains road condition evaluation index parameters in real time, so that the transportation route can be dynamically adjusted according to the current traffic conditions. This flexibility enables the system to respond quickly to emergencies and ensure the continuity and reliability of transportation. Combining different modes of transportation, the transportation weight coefficient is integrated through the weighted average method, effectively utilizing the advantages of each mode of transportation, reducing the overall transportation cost, and improving the flexibility of the supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a structural schematic diagram of the coordinated scheduling method for the power grid equipment supply chain of the present invention. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0014] Embodiment 1, Figure 1 A method for coordinating and dispatching a power grid equipment supply chain according to the present invention is provided, comprising the following steps: S1, obtaining working nodes of power grid equipment in the area to be tested, and obtaining transportation impact data and transportation methods between every two nodes according to the working nodes of the power grid equipment.

[0015] In this embodiment, the step of obtaining working nodes of power grid equipment in the tested area and obtaining transportation impact data between every two nodes according to the working nodes of the power grid equipment includes: Fluctuations in demand for power grid equipment refer to the instability and changes in demand for power equipment in the power system over a certain period of time.

[0016] The specific steps for obtaining the power grid equipment demand fluctuation are as follows: Obtaining historical load data, power demand data, and voltage fluctuations of the area to be tested, and performing data preprocessing on the historical load data, power demand data, and voltage fluctuations to remove missing values ​​and abnormal values ​​therein; Capturing the trend of data based on a linear regression model, smoothing the historical load data, power demand data and voltage fluctuations, and drawing them into a linear graph; Extracting characteristic data of the load data and the power demand data in each time period based on the load data and the power demand data based on a time series method; Obtaining the valley value and peak value of the voltage in each time period according to the linear graph, thereby obtaining the fluctuation state of each time period; According to the load data, power demand data and voltage fluctuation, a power grid equipment demand fluctuation model is constructed based on a machine learning algorithm to obtain a power grid equipment demand fluctuation coefficient of the area to be tested.

[0017] The specific calculation formula for the power grid equipment demand fluctuation is as follows:

[0018] In the formula, represents the fluctuation of the power grid equipment demand, is a proportionality coefficient used to adjust the unit and magnitude of the formula, is the power demand, is the load data, is the voltage fluctuation.

[0019] It should be noted that when D > P, the system is in a load growth state, and S is positive, indicating that power supply needs to be increased to meet the demand; when D < P, the system load is too high, and S is negative, indicating the risk of voltage instability. The smaller the absolute value of the stability coefficient S, the lower the stability of the system and the greater the fluctuation of the power grid equipment demand.

[0020] Transportation road conditions. Classifying transportation road conditions is an important step in optimizing logistics transportation and planning. Through reasonable classification of road conditions, it helps transportation managers better formulate transportation plans and estimate transportation time.

[0021] The specific steps to obtain the above-mentioned transportation road conditions are as follows: Obtain the road condition evaluation index parameters of all transportation modes on the transportation route to be measured. The road condition evaluation index parameters include road surface conditions, traffic flow, and weather conditions; Set scoring indicators according to the different degrees of influence of the above-mentioned road condition evaluation index parameters on all transportation modes; Obtain the scores of the index parameters of all transportation modes, and based on the weighted average method, obtain the comprehensive road condition score of the transportation routes of all transportation modes; Obtain the preferred transportation mode according to the comprehensive road condition score of each transportation mode; Obtain the road condition evaluation index parameters in real time through GPS and real-time traffic monitoring systems, and continuously update the comprehensive road condition score of the transportation route.

[0022] The specific calculation formula of the above-mentioned transportation road conditions is as follows:

[0023] In the formula, is the transportation road condition, n is the number of road condition evaluation index parameters, w is the weight of the road condition evaluation index parameters, represents the weight of the i-th road condition evaluation index parameter, is the score of the road condition evaluation index parameter, represents the score of the i-th road condition evaluation index parameter.

[0024] It should be noted that the sum of the weight coefficients of various road condition assessment index parameters is 1, and the weight ratio of the road condition assessment index parameters is adjusted according to the degree of influence of the road condition assessment index parameters on different modes of transportation; the evaluation score of each road condition assessment index parameter is between [0,5], so the final score result of the transportation road condition is between [0,5]. The higher the comprehensive road condition score, the better the transportation road condition. The best transportation mode is selected according to the transportation road condition scores of different transportation modes.

[0025] The scoring criteria for the various road condition evaluation index parameters are as follows: Road conditions: 1 point: severely damaged and impassable; 2 points: The damage is serious and you need to drive carefully; 3 points: Average, with some flaws; 4 points: good, smooth road surface; 5 points: Very good, newly paved road.

[0026] Traffic Flow: 1 point: severe congestion and slow driving; 2 points: relatively congested, with occasional stagnation; 3 points: average, moderate flow; 4 points: relatively smooth, with less traffic; 5 points: Unobstructed.

[0027] Weather conditions: 1 point: Extremely bad weather, heavy rain, snowstorm or hail, extremely low visibility, serious impact on travel, and potential safety hazards; 2 points: Bad weather, heavy rain or strong wind, poor visibility, which may cause the road surface to be slippery or flooded, so drive carefully; 3 points: normal weather, light rain or cloudy, moderate temperature, good visibility, occasional minor impacts, please be careful when traveling; 4 points: Good weather, sunny or cloudy, suitable temperature, good visibility, relatively smooth travel; 5 points: Very good weather, sunny, comfortable temperature, no wind, no precipitation, suitable for travel, excellent weather conditions.

[0028] Furthermore, what are the advantages of analyzing the road conditions, traffic flow and weather conditions for the comprehensive assessment of transportation road conditions? Improve safety. Comprehensive assessment can monitor road conditions and weather changes in real time, promptly identify potential safety hazards such as water accumulation or ice, reduce the probability of traffic accidents, and ensure driving safety. Optimize route planning. By analyzing real-time traffic flow and road conditions, transportation companies can flexibly adjust routes and effectively avoid congested areas, thereby improving overall transportation efficiency and punctuality; Resource allocation efficiency: The comprehensive evaluation results can help transport companies to rationally allocate vehicles and personnel and optimize operation arrangements to reduce resource waste and improve the control and efficiency of operating costs; Enhance decision support, provide accurate and comprehensive road condition information, help managers obtain key information in a timely manner, so as to make more informed and effective decisions, and further improve the overall quality of transportation services; The system is highly adaptable, with real-time monitoring and feedback capabilities, and can quickly adapt to different weather and traffic changes, ensuring that transportation plans can be adjusted in a timely manner to maintain efficient operations.

[0029] S2, constructing a transportation weight model between two nodes based on the transportation impact data and a machine learning algorithm to obtain a transportation weight coefficient for each transportation mode between the two points.

[0030] In this embodiment, the transportation weight model between two nodes is constructed based on the transportation impact data based on the machine learning algorithm to obtain the transportation weight coefficient of each transportation mode between the two points, specifically: Constructing a transportation weight model between two nodes based on a machine learning algorithm according to the power grid equipment demand fluctuations and transportation road conditions; Obtain the transportation mode between the areas to be tested, obtain the transportation road conditions between the areas to be tested according to the transportation mode, and perform downgrading sorting on the transportation road conditions of different transportation modes to obtain a priority sorting form; Obtain the power grid equipment demand fluctuation data of the area to be tested, and calculate the power grid equipment demand fluctuation state based on the power grid equipment demand fluctuation formula; According to the fluctuation of the power grid equipment demand and the transportation road conditions, the transportation weight coefficients between the areas to be tested are obtained based on the transportation weight model calculation.

[0031] The specific calculation formula of the transportation weight model is as follows:

[0032] In the formula, is the transport weight, It's the transportation road conditions. It is the fluctuation in demand for power grid equipment.

[0033] It should be noted that the overall range of values ​​of the transport weight coefficient is not certain, because the mutual influence of different items will lead to the superposition of values.

[0034] S3, performing data analysis to obtain the optimal transportation route based on the transportation weight coefficient and the multimodal transportation method and the shortest path algorithm.

[0035] In this embodiment, the optimal transportation route is obtained by performing data analysis based on the transportation weight coefficient based on the multimodal transportation method and the shortest path algorithm, specifically: Obtaining information on the transportation network between the areas to be tested, including the infrastructure of road, rail, water and air transportation modes; Evaluate the geographical location of the area to be tested and determine the relative position and distance between the area to be tested and other areas; By analyzing traffic flow data, we can identify locations with large transportation volumes and strong connectivity, and obtain major transportation hubs; Identify the main transportation hubs between the areas to be tested and collect transportation mode and distance data for each hub; For each mode of transportation, calculate its proportion in the total transportation distance and obtain the transportation weight coefficient of each mode; The weights of each mode of transport are combined using the weighted average method to form a comprehensive transport weight coefficient, which reflects the efficiency of multimodal transport; The comprehensive transportation weight coefficient is applied to the shortest path algorithm to identify the best combination of transportation modes and the optimal route to ensure the overall transportation efficiency and cost minimization.

[0036] Further, the advantages of the multimodal transport method and the shortest path algorithm are analyzed: Multimodal transport allows the selection of the best combination of transport modes, such as road, rail, water and air, according to specific needs. Different goods and transportation conditions use the most appropriate mode, and by combining different modes of transport, minimize transportation time and costs; By choosing the most economical combination of transport modes, multimodal transport helps reduce overall logistics costs, especially in bulk cargo transportation. Reasonable combination of transport modes can effectively optimize resource use and reduce carbon emissions. Multimodal transport can effectively connect different transportation networks, improve inter-regional logistics efficiency, and promote economic development; The shortest path algorithm can quickly calculate the optimal transportation route under given conditions, ensuring that the time and cost of cargo transportation are minimized. Automated path calculation reduces the interference of human factors and makes transportation decisions more scientific and efficient.

[0037] The shortest path algorithm can handle complex transportation networks, consider different modes of transportation and transit hubs, and provide support for multimodal transport. Combined with real-time traffic flow and weather conditions, the shortest path algorithm can dynamically adjust transportation routes to further improve the flexibility and adaptability of transportation.

[0038] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0039] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0040] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0041] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0042] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0043] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A coordinated dispatching method for a power grid equipment supply chain, characterized in that: include: Obtaining working nodes of power grid equipment in the area to be tested, and obtaining transportation impact data between every two nodes according to the working nodes of the power grid equipment; Constructing a transportation weight model between two nodes based on the transportation impact data and a machine learning algorithm to obtain a transportation weight coefficient for each transportation mode between the two points; According to the transport weight coefficient, based on the multimodal transport method and the shortest path algorithm, data analysis is performed to obtain the optimal transport route.

2. The power grid equipment supply chain coordination and scheduling method according to claim 1 is characterized in that: The transportation impact data includes power grid equipment demand fluctuations, and the specific steps for obtaining the power grid equipment demand fluctuations are as follows: Acquire historical load data, power demand data, and voltage fluctuations of the area to be tested, and perform data preprocessing on the historical load data, power demand data, and voltage fluctuations to remove missing values ​​and abnormal values ​​therein; Capturing the trends of load data, power demand data and voltage fluctuations based on a linear regression model, smoothing the historical load data, power demand data and voltage fluctuations, and drawing them into a linear graph; Extracting characteristic data of the load data and the power demand data in each time period based on the load data and the power demand data based on a time series method; Performing data analysis according to the linear graph to obtain the valley value and peak value of the voltage in each time period, thereby obtaining the fluctuation state of each time period; According to the load data, power demand data and voltage fluctuation, a power grid equipment demand fluctuation model is constructed based on a machine learning algorithm to obtain a power grid equipment demand fluctuation coefficient of the area to be tested.

3. The power grid equipment supply chain coordination and scheduling method according to claim 2 is characterized in that: The transport impact data includes transport road conditions, and the specific steps for obtaining the transport road conditions are as follows: Obtaining road condition evaluation index parameters for all transportation modes of the transportation route to be tested, wherein the road condition evaluation index parameters include road conditions, traffic flow and weather conditions; Setting scoring indicators based on the different degrees of impact of the road condition assessment indicator parameters on all modes of transportation; Obtain the scores of various indicator parameters of all transportation modes, and obtain the comprehensive road condition scores of the transportation routes of all transportation modes based on the weighted average method; The preferred mode of transportation is obtained based on the comprehensive road condition score of each mode of transportation; Through GPS and real-time traffic monitoring systems, road condition assessment index parameters are obtained in real time, and the comprehensive road condition scores of transportation routes are continuously updated.

4. The method for coordinating and dispatching a power grid equipment supply chain according to claim 3, characterized in that: The optimal transportation route is obtained by performing data analysis based on the transportation weight coefficient, based on the multimodal transportation method and the shortest path algorithm, specifically: Obtaining information on the transportation network between the areas to be tested, including the infrastructure of road, rail, water and air transportation modes; Evaluate the geographical location of the area to be tested and determine the relative position and distance between the area to be tested and other areas; By analyzing traffic flow data, we can identify locations with large transportation volumes and strong connectivity, and obtain major transportation hubs; Identify the main transportation hubs between the areas to be tested and collect transportation mode and distance data for each hub; For each mode of transportation, calculate its proportion in the total transportation distance and obtain the transportation weight coefficient of each mode; The weights of each mode of transport are combined using the weighted average method to form a comprehensive transport weight coefficient, which reflects the efficiency of multimodal transport; The comprehensive transportation weight coefficient is applied to the shortest path algorithm to identify the best combination of transportation modes and the optimal route to ensure the overall transportation efficiency and cost minimization.

5. The method for coordinating and dispatching a power grid equipment supply chain according to claim 4, characterized in that: The specific calculation formula for the power grid equipment demand fluctuation is as follows: In the formula, Indicates that the demand for power grid equipment fluctuates, is the scaling factor, which is used to adjust the units and magnitude of the formula, is the power demand, is the load data, It's voltage fluctuation.

6. The method for coordinating and dispatching a power grid equipment supply chain according to claim 5, characterized in that: The specific calculation formula for the transportation road conditions is as follows: In the formula, is the transportation road condition, n is the number of road condition evaluation index parameters, w is the weight of the road condition evaluation index parameter, represents the weight of the i-th road condition evaluation index parameter, is the score of the road condition evaluation index parameter, Represents the score of the i-th road condition evaluation index parameter.

7. The method for coordinating and dispatching a power grid equipment supply chain according to claim 6, characterized in that: The specific calculation formula of the transportation weight model is as follows: In the formula, is the transport weight, It's the transportation road conditions. The demand for power grid equipment fluctuates.

Images