Power distribution network material supply guarantee management and control system

Abstract

The invention provides a power distribution network material supply guarantee management and control system, and relates to the technical field of power distribution network material management and control. Comprising a demand prediction module, an inventory management module, an evaluation module, an optimization module and a visualization module. The demand prediction module and the optimization module are both connected with the inventory management module and the evaluation module, and the visualization module is connected with the optimization module; the demand prediction module is used for predicting the demand quantity of various materials of the power distribution network, the inventory management module is used for monitoring inventory data to obtain monitoring data and generating an automatic replenishment plan according to the demand quantity of various materials, and the evaluation module is used for evaluating the flexibility and overlap ratio of various materials. The optimization module is used for optimizing the various materials of the power grid according to the flexibility and the overlap ratio of the various materials and the automatic replenishment plan to obtain an optimization result, and the visualization module is used for displaying the optimization result. According to the invention, the problems of low efficiency and insufficient accuracy of power distribution network material management in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of material management and control of distribution networks, and in particular to a material supply guarantee management and control system for distribution networks. Background Art

[0002] In the construction and operation of modern distribution networks, the accuracy and timeliness of material supply are crucial to ensuring the stability and efficient operation of the power system. However, the current material supply management model has some technical problems that need to be solved, mainly including:

[0003] Information asymmetry between supply and demand: The material demand of distribution network projects is changeable, especially in terms of demand forecasting and historical data integration, which often leads to a large deviation between actual supply and demand.

[0004] Inefficient inventory management: Traditional inventory management methods fail to effectively handle dynamically changing demand, which can easily lead to insufficient or excessive inventory, thus affecting project progress and cost control.

[0005] Lack of flexibility: The existing material supply chain lacks the ability to respond to sudden changes in demand, especially in the conversion and substitution between different material groups.

[0006] Lack of a comprehensive evaluation mechanism: There is a lack of scientific evaluation of the flexibility of various material groups and the overlap of suppliers, which limits the optimal allocation of material resources.

[0007] In summary, the existing distribution network material management is inefficient and lacks accuracy. Summary of the invention

[0008] In order to overcome the deficiencies of the prior art, an object of the present invention is to provide a distribution network material supply guarantee management and control system, which solves the problems of low efficiency and insufficient accuracy in distribution network material management in the prior art.

[0009] To achieve the above object, the present invention provides the following solutions:

[0010] A distribution network material supply guarantee management and control system, comprising:

[0011] Demand forecasting module, inventory management module, evaluation module, optimization module and visualization module;

[0012] The demand forecasting module is used to forecast the demand for various materials in the distribution network, the inventory management module is used to monitor the inventory data to obtain monitoring data and generate an automatic replenishment plan based on the demand for the various materials, the evaluation module is used to evaluate the flexibility and overlap of the various materials, the optimization module is used to optimize the various materials in the power grid based on the flexibility and overlap of the various materials and the automatic replenishment plan to obtain optimization results, and the visualization module is used to display the optimization results.

[0013] Preferably, the demand forecasting module comprises:

[0014] Data acquisition submodule and prediction submodule;

[0015] The data acquisition submodule is used to acquire historical procurement data, and the prediction submodule is used to build a prediction model based on the historical procurement data to predict the demand for various types of materials in the distribution network.

[0016] Preferably, the prediction submodule comprises:

[0017] Recognition unit, feature extraction unit, data preprocessing unit, optimization unit, model selection unit, model verification unit and model updating unit;

[0018] The identification unit is used to identify the influencing factors of the historical procurement data to obtain the influencing factors, the feature extraction unit is used to extract features of the influencing factors to obtain a feature data set, the data preprocessing unit is used to preprocess the feature data set to obtain a preprocessed data set, the optimization unit is used to optimize the preprocessed data set according to ASSO regression, remove redundant or inefficient influencing factors, and obtain optimized data, the model selection unit is used to construct an initial prediction model according to an adaptive time series model and the optimized data, the model verification unit verifies the results of the initial prediction model to obtain a verification result, and the model updating unit updates and optimizes the parameters of the initial prediction model according to the verification result to obtain a final prediction model.

[0019] Preferably, the prediction model is expressed as:

[0020]

[0021] in, is the predicted demand, N is the window size of historical data, indicating the number of historical time steps we use, and w i is the weight of the i-th historical time point, reflecting the contribution of this time point to the current forecast, and f i (X t-i) is the characteristic function of the i-th historical time point, which is converted according to the past characteristic data X to generate the characteristics related to the predicted demand, M is the number of influencing factors, β j is the weight of the jth impact factor, g j (IF t-j ) is the function of the jth influencing factor, which is processed according to the historical influencing factor data IF, and A is the adjustment parameter.

[0022] Preferably, the evaluation module comprises:

[0023] flexibility evaluation submodule and overlap submodule;

[0024] The flexibility evaluation submodule is used to calculate the flexibility of the various materials, and the overlap submodule is used to calculate the overlap of the various materials.

[0025] Preferably, the calculation formula for the flexibility of each type of material is:

[0026]

[0027] Among them, S i is the set of suppliers that have actually supplied the i-th material in the material group in the past two years, and n is the number of materials in the material group.

[0028] Preferably, the calculation formula for the overlap of the various materials is:

[0029]

[0030] Among them, M ij is the supply overlap between the i-th material and the j-th material in the material group, M i {s1,s2,...s m} is the supplier list of the i-th material in the material group, M j {s1,s2,...s n} is the supplier list of the jth material in the material group.

[0031] Preferably, the inventory management module includes:

[0032] A monitoring submodule, and an alarm submodule and a plan generation submodule both connected to the monitoring submodule;

[0033] The monitoring submodule is used to track and locate the various types of materials based on RFID tag technology to obtain positioning information, the alarm submodule is used to issue an alarm based on the positioning information, and the plan generation submodule is used to generate an automatic replenishment plan based on the positioning information and the demand for the various types of materials.

[0034] The present invention discloses the following technical effects:

[0035] The present invention provides a distribution network material supply guarantee management and control system, comprising:

[0036] Demand forecasting module, inventory management module, evaluation module, optimization module and visualization module;

[0037] The demand forecasting module is used to forecast the demand for various materials in the distribution network, the inventory management module is used to monitor the inventory data to obtain monitoring data and generate an automatic replenishment plan based on the demand for various materials, the evaluation module is used to evaluate the flexibility and overlap of the various materials, the optimization module is used to optimize the various materials of the power grid based on the flexibility and overlap of the various materials and the automatic replenishment plan to obtain optimization results, and the visualization module is used to display the optimization results. The present invention uses historical data and market trend analysis technology through the demand forecasting module to predict the demand for various materials in real time and reduce the deviation between actual demand and prediction. This module can apply machine learning and statistical analysis models to achieve more accurate demand forecasts, prompting suppliers and decision makers to understand changes and trends in real time, and then respond quickly; the inventory management module can monitor real-time inventory data and generate an automatic replenishment plan based on predicted demand. This not only improves the accuracy of inventory use, but also reduces the deviation of human decision-making, ensures that inventory is maintained at the optimal level, and effectively avoids project delays and cost overruns caused by insufficient or excessive inventory; through the optimization module, the system can dynamically adjust the material configuration according to the flexibility and overlap of various materials, and realize rapid conversion and substitution between different material groups. When sudden changes in demand occur, the system can update the replenishment plan in real time, select the best suppliers and materials to meet new demands, and enhance the flexibility and adaptability of the overall supply chain; the evaluation module scientifically evaluates the flexibility of various materials (such as procurement timeliness, substitution adaptability, etc.) and the overlap of suppliers (for diversified supply of the same product). Through quantitative indicators, managers can clearly understand the potential for optimal allocation of material resources, thereby providing a basis for subsequent supply decisions and improving resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0039] Figure 1 A schematic diagram of the structure of a distribution network material supply guarantee management and control system provided in an embodiment of the present invention.

[0040] Description of reference numerals:

[0041] 1-Demand forecasting module, 2-Inventory management module, 3-Evaluation module, 4-Optimization module, 5-Visualization module. DETAILED DESCRIPTION

[0042] 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.

[0043] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0044] like Figure 1 As shown, the present invention provides a distribution network material supply guarantee management and control system, comprising:

[0045] Demand forecasting module, inventory management module, evaluation module, optimization module and visualization module;

[0046] The demand forecasting module and the optimization module are both connected to the inventory management module and the evaluation module, and the visualization module is connected to the optimization module;

[0047] The demand forecasting module is used to forecast the demand for various materials in the distribution network, the inventory management module is used to monitor the inventory data to obtain monitoring data and generate an automatic replenishment plan based on the demand for the various materials, the evaluation module is used to evaluate the flexibility and overlap of the various materials, the optimization module is used to optimize the various materials in the power grid based on the flexibility and overlap of the various materials and the automatic replenishment plan to obtain optimization results, and the visualization module is used to display the optimization results.

[0048] Furthermore, the demand forecasting module includes:

[0049] Data acquisition submodule and prediction submodule;

[0050] The data acquisition submodule is used to acquire historical procurement data, and the prediction submodule is used to build a prediction model based on the historical procurement data to predict the demand for various types of materials in the distribution network.

[0051] Furthermore, the prediction submodule includes:

[0052] Recognition unit, feature extraction unit, data preprocessing unit, optimization unit, model selection unit, model verification unit and model updating unit;

[0053] The identification unit is used to identify the influencing factors of the historical procurement data to obtain the influencing factors, the feature extraction unit is used to extract features of the influencing factors to obtain a feature data set, the data preprocessing unit is used to preprocess the feature data set to obtain a preprocessed data set, the optimization unit is used to optimize the preprocessed data set according to ASSO regression, remove redundant or inefficient influencing factors, and obtain optimized data, the model selection unit is used to construct an initial prediction model according to an adaptive time series model and the optimized data, the model verification unit verifies the results of the initial prediction model to obtain a verification result, and the model updating unit updates and optimizes the parameters of the initial prediction model according to the verification result to obtain a final prediction model.

[0054] Specifically, relevant data is extracted from historical procurement records, including procurement time, material type, procurement quantity, supplier information, market price fluctuations, etc., and statistical methods such as correlation analysis and factor analysis are used to analyze the collected data to identify factors that significantly affect procurement results (such as seasonal factors, market demand fluctuations, supplier delivery timeliness, etc.). According to the significance level of the influencing factors (p-value threshold, etc.), high-impact factors are screened out, their names and corresponding numerical ranges are recorded, and a preliminary list of influencing factors is formed.

[0055] Extract features from identified influencing factors: construct new features based on the identified influencing factors. For example, you can calculate the average, standard deviation, volatility and other statistical features of a factor in a specific time period; use principal component analysis (PCA) or other dimensionality reduction techniques to reduce feature dimensions while retaining important information to reduce the complexity of subsequent model training; organize the extracted feature results into feature data sets for subsequent processing.

[0056] Data preprocessing process: Check whether there are missing values ​​in the feature data set, and use interpolation (such as mean and median filling) or deletion of incomplete samples to process; scale the eigenvalues ​​proportionally to ensure that different eigenvalues ​​are on the same dimension to improve the convergence speed and stability of the model; use the z-score or IQR method to identify and process outliers to reduce the impact of noise on model training; generate a preprocessed data set: after the above processing, a cleaned preprocessed data set is obtained, ready for model training.

[0057] Specifically, the influencing factors are obtained: for planning, procurement, and contract professionals, the influencing factors are extracted from five aspects: distribution network investment scale, investment structure, external economic environment, historical agreement execution, and material group characteristics. Table 1 is a table of influencing factors for distribution network agreement inventory demand forecasting, as shown below:

[0058] Table 1 Distribution network protocol inventory demand forecast influencing factors

[0059]

[0060]

[0061] Influencing factor tracing: As an important factor in the prediction model, it is necessary to find a way to obtain the influencing factor. Combined with the material professional management ERP, ECP and other systems, analyze the data sources of each influencing factor one by one. For data that cannot be obtained internally, such as provincial GDP, inflation coefficient, etc., manually obtain it through the official website of the external network. Table 2 is the traceability table of the distribution network agreement inventory demand prediction modeling, and Table 2 is as follows:

[0062] Table 2 Distribution network protocol inventory demand forecast modeling traceability table

[0063]

[0064]

[0065] Optimize influencing factors. The more influencing factors there are, the more complex and less effective the model will be. Therefore, it is necessary to further optimize the traceable influencing factors and screen out the most relevant factors. Use multiple linear regression to select influencing factor features, select the optimal influencing factors through R-square test and t-value test, and exclude irrelevant or multicollinear factors to improve the accuracy and efficiency of the final model. Or perform feature selection and optimization on the preprocessed data set based on ASSO regression: bring the preprocessed data set into the ASSO regression model, and identify redundant or inefficient influencing factors through regression analysis; eliminate redundant factors: based on the results of ASSO regression, remove features that contribute little to the prediction results, and retain features that have the greatest impact on model performance; optimize data generation: generate an optimized feature data set that integrates significant influencing factors, laying the foundation for the training of subsequent prediction models.

[0066] Furthermore, the prediction model is expressed as:

[0067]

[0068] in, is the predicted demand, N is the window size of historical data, indicating the number of historical time steps we use, and w iis the weight of the i-th historical time point, reflecting the contribution of this time point to the current forecast, and f i (X t-i ) is the characteristic function of the i-th historical time point, which is converted according to the past characteristic data X to generate the characteristics related to the predicted demand, M is the number of influencing factors, β j is the weight of the jth impact factor, g j (IF t-j ) is the function of the jth influencing factor, which is processed according to the historical influencing factor data IF, and A is the adjustment parameter.

[0069] Furthermore, the evaluation module includes:

[0070] Flexibility evaluation submodule and overlap submodule;

[0071] The flexibility evaluation submodule is used to calculate the flexibility of the various materials, and the overlap submodule is used to calculate the overlap of the various materials.

[0072] Furthermore, the calculation formula for the flexibility of each type of material is:

[0073]

[0074] Among them, S i is the set of suppliers that have actually supplied the i-th material in the material group in the past two years, and n is the number of materials in the material group.

[0075] 7. A distribution network material supply guarantee management and control system according to claim 5, characterized in that the calculation formula for the overlap of the various types of materials is:

[0076]

[0077] Among them, M ij is the supply overlap between the i-th material and the j-th material in the material group, M i {s1,s2,...s m} is the supplier list of the i-th material in the material group, M j {s1,s2,...s n} is the supplier list of the jth material in the material group.

[0078] Specifically, in terms of material group flexibility assessment, a material group internal mapping rationality assessment model is constructed from the perspective of ensuring material supply flexibility, and an optimization plan is output. Optimization is performed based on the flexibility and material overlap formulas. The closer the flexibility D value is to 1, the higher the compatibility and flexibility of the material group during matching execution, and the more it can ensure the continuous consumption of the agreement.

[0079] Furthermore, the inventory management module includes:

[0080] A monitoring submodule, and an alarm submodule and a plan generation submodule both connected to the monitoring submodule;

[0081] The monitoring submodule is used to track and locate the various types of materials based on RFID tag technology to obtain positioning information, the alarm submodule is used to issue an alarm based on the positioning information, and the plan generation submodule is used to generate an automatic replenishment plan based on the positioning information and the demand for the various types of materials.

[0082] Specifically, RFID tags are installed for various materials to ensure that each item has unique identification information. Signal reception: RFID readers are used to regularly scan RFID tags in the surrounding environment to obtain the location information of materials. Data processing: The acquired location information and related material status (such as inventory quantity, material type) are transmitted to the central system for processing. Positioning information generation: Based on the read RFID data, detailed material location information is generated and updated to the monitoring database in real time for query and analysis at any time.

[0083] Alarm condition setting: preset alarm conditions and thresholds, such as inventory below safety level, abnormal material movement, expired items, unauthorized items entering or leaving, etc.

[0084] Real-time monitoring: Continuously monitor the positioning information transmitted by the monitoring submodule. Once the set alarm condition is triggered, immediately enter the alarm trigger process. Alarm information generation: Generate detailed alarm information, including trigger conditions, material types, locations and timestamps, etc. Alarm sending: Immediately send alarms to relevant personnel through preset communication methods (such as SMS, email, mobile app push, etc.) to ensure timely response.

[0085] Demand analysis: By collecting historical purchasing data, sales data and inventory turnover, analyze the demand for each material and its changing trend to generate demand forecasts. Current inventory comparison: Compare the current inventory status with the predicted demand to determine the list of materials that need to be replenished. Replenishment strategy formulation: According to the company's inventory management strategy (such as safety inventory, replenishment cycle, supplier delivery time, etc.), formulate a specific replenishment plan, including quantity, supplier, expected arrival time, etc. Replenishment plan generation and output: Generate an automated replenishment plan and output it as a document that can be reviewed and executed (such as a spreadsheet or system record), and can be selectively pushed to the relevant person in charge or the procurement team for approval.

[0086] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0087] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A distribution network material supply guarantee management and control system, characterized in that: include: Demand forecasting module, inventory management module, evaluation module, optimization module and visualization module; The demand forecasting module and the optimization module are both connected to the inventory management module and the evaluation module, and the visualization module is connected to the optimization module; The demand forecasting module is used to forecast the demand for various materials in the distribution network, the inventory management module is used to monitor the inventory data to obtain monitoring data and generate an automatic replenishment plan based on the demand for the various materials, the evaluation module is used to evaluate the flexibility and overlap of the various materials, the optimization module is used to optimize the various materials in the power grid based on the flexibility and overlap of the various materials and the automatic replenishment plan to obtain optimization results, and the visualization module is used to display the optimization results.

2. A distribution network material supply guarantee management and control system according to claim 1, characterized in that: The demand forecasting module comprises: Data acquisition submodule and prediction submodule; The data acquisition submodule is used to acquire historical procurement data, and the prediction submodule is used to build a prediction model based on the historical procurement data to predict the demand for various types of materials in the distribution network.

3. A distribution network material supply guarantee management and control system according to claim 2, characterized in that: The prediction submodule includes: Recognition unit, feature extraction unit, data preprocessing unit, optimization unit, model selection unit, model verification unit and model updating unit; The identification unit is used to identify the influencing factors of the historical procurement data to obtain the influencing factors, the feature extraction unit is used to extract features of the influencing factors to obtain a feature data set, the data preprocessing unit is used to preprocess the feature data set to obtain a preprocessed data set, the optimization unit is used to optimize the preprocessed data set according to ASSO regression, remove redundant or inefficient influencing factors, and obtain optimized data, the model selection unit is used to construct an initial prediction model according to an adaptive time series model and the optimized data, the model verification unit verifies the results of the initial prediction model to obtain a verification result, and the model updating unit updates and optimizes the parameters of the initial prediction model according to the verification result to obtain a final prediction model.

4. A distribution network material supply guarantee management and control system according to claim 3, characterized in that: The expression of the prediction model is: in, is the predicted demand, N is the window size of historical data, indicating the number of historical time steps we use, and w i is the weight of the i-th historical time point, reflecting the contribution of this time point to the current forecast, and f i (X t-i ) is the characteristic function of the i-th historical time point, which is converted according to the past characteristic data X to generate the characteristics related to the predicted demand, M is the number of influencing factors, β j is the weight of the jth impact factor, g j (IF t-j ) is the function of the jth influencing factor, which is processed according to the historical influencing factor data IF, and A is the adjustment parameter.

5. A distribution network material supply guarantee management and control system according to claim 1, characterized in that: The evaluation module includes: Flexibility evaluation submodule and overlap submodule; The flexibility evaluation submodule is used to calculate the flexibility of the various materials, and the overlap submodule is used to calculate the overlap of the various materials.

6. A distribution network material supply guarantee management and control system according to claim 5, characterized in that: The calculation formula for the flexibility of each type of material is: Among them, S i is the set of suppliers that have actually supplied the i-th material in the material group in the past two years, and n is the number of materials in the material group.

7. A distribution network material supply guarantee management and control system according to claim 5, characterized in that: The calculation formula for the overlap of the various materials is: Among them, M ij is the supply overlap between the i-th material and the j-th material in the material group, M i {s1,s2,...s m } is the supplier list of the i-th material in the material group, M j {s1,s2,...s n } is the supplier list of the jth material in the material group.

8. A distribution network material supply guarantee management and control system according to claim 1, characterized in that: The inventory management module includes: A monitoring submodule, and an alarm submodule and a plan generation submodule both connected to the monitoring submodule; The monitoring submodule is used to track and locate the various types of materials based on RFID tag technology to obtain positioning information, the alarm submodule is used to issue an alarm based on the positioning information, and the plan generation submodule is used to generate an automatic replenishment plan based on the positioning information and the demand for the various types of materials.

Images