CN-121981425-A - Emergency guarantee demand load balancing method and system based on homogeneous group division

CN121981425ACN 121981425 ACN121981425 ACN 121981425ACN-121981425-A

Abstract

The application discloses an emergency guarantee demand load balancing method and system based on homogeneous group division, and relates to emergency guarantee and data processing technology, wherein the emergency guarantee demand load balancing method comprises the steps of screening material key characteristics of a supplier and normalizing the key characteristics to obtain load capacity characteristics of the supplier; dividing homogeneous supplier groups according to the obtained load capacity characteristics of the suppliers through a K-means clustering algorithm, carrying out double-layer load assessment in the groups according to the divided homogeneous supplier groups so as to realize omnibearing balancing of the supplier load, and completing comprehensive load balancing according to the information entropy of the demand load in the groups and the demand load balancing coefficient between the groups. According to the application, a quantification calculation method of the inter-group balance coefficient is constructed through the division of homogeneous groups, and the entropy values in the groups are combined to form a comprehensive balance evaluation rule of 'group internal entropy value and inter-group coefficient', so that the balance scheduling of the supply side bearing material demands is realized.

Inventors

LI JUN
LI RUI
GAO CHUNMEI
CHEN ZHENGXIONG

Assignees

中国电子科技集团公司第三十研究所

Dates

Publication Date: 20260505
Application Date: 20251210

Claims (8)

1. An emergency guarantee demand load balancing method based on homogeneous group division is characterized by comprising the following steps: Screening the material key characteristics of the supplier, and normalizing the key characteristics to obtain the load capacity characteristics of the supplier; dividing a homogeneous provider group according to the obtained load capacity characteristics of the provider by a K-means clustering algorithm; according to the divided homogeneous provider groups, double-layer load evaluation between groups is carried out, wherein local load difference of the provider is captured through information entropy in the groups, global load-capacity matching degree is regulated and controlled through balance coefficients between the groups, and therefore omnibearing balance of the load of the provider is achieved; and according to the intra-group demand load information entropy and the inter-group demand load balancing coefficient, completing the comprehensive load balancing.
2. The homogeneous population partitioning-based emergency security demand load balancing method of claim 1, wherein screening the supply key features and normalizing the key features comprises: Constructing original load capacity feature matrixes of the same type of suppliers, wherein each type of supplier has different original load capacity feature matrixes, and the original load capacity feature matrixes are as follows: Wherein, the Is the first First of the supply units Original values of the features; And (3) normalizing the original load capacity moment array, and normalizing by adopting Z-score to form a supply side load capacity characteristic matrix after normalization.
3. The emergency guarantee demand load balancing method based on homogeneous group division according to claim 2, wherein dividing the homogeneous group of suppliers according to the obtained load capacity characteristics of the suppliers by a K-means clustering algorithm comprises: determining the optimal clustering quantity K value; And selecting an initial center according to the determined optimal cluster number K, and selecting the initial center according to the selected initial center.
4. The emergency guarantee demand load balancing method based on homogeneous group partitioning as claimed in claim 3, wherein determining the optimal cluster number K value comprises: Initially setting a value range of the clustering quantity, and executing K-means clustering based on each clustering quantity; Based on the supplier load capacity feature matrix, calculating the square sum WSS in the group corresponding to each cluster number, wherein the smaller the WSS is, the more similar the supplier load capacity features in the group are; Constructing a WSS-cluster number relation curve, and determining the optimal cluster number by an inflection point detection method 。
5. The homogeneous population partitioning-based emergency security demand load balancing method of claim 4, wherein performing initial center selection comprises: selecting an initial center by adopting a K-means++ initialization method; based on the supplier load capacity feature matrix, calculating Euclidean distance between each supplier and each clustering center so as to classify the suppliers into the class with the nearest distance; repeating the center selection-attribution judgment, and calculating the distance between the new cluster center and the old cluster center until the distance between the new cluster center and the old cluster center is smaller than a preset threshold value.
6. The homogeneous population division-based emergency guarantee demand load balancing method of claim 4, wherein performing intra-population-to-inter-population double-layer load assessment based on the divided homogeneous provider population comprises: According to each homogeneous guarantee group, calculating the information entropy of the loads of all suppliers in the group so as to measure the load balance in the group, wherein the information entropy in the group is as follows: Wherein: Is the first The demand load information entropy of each guarantee group; Is the first A supply unit number of individual groups; Is the first The first group of individuals Load duty cycles of the individual supply units; Based on externally input material demand information and an original load capacity feature matrix, the inter-group load balancing coefficient is as follows: Wherein, the The demand load balance coefficient among groups is obtained; Is the first The total demand number borne by the individual guarantee groups; the total required number for all the guarantee groups; Is the first The total load capacity of the group is guaranteed; the total service capacity of all the guarantee groups.
7. The emergency guarantee demand load balancing method based on homogeneous group division according to claim 6, wherein completing load comprehensive balancing according to the demand load information entropy in the group and the demand load balancing coefficient among groups comprises: if all groups ≥ , Is the equalization threshold value in the preset group body, and ≥ , If the balance threshold value among the preset groups is set, the overall balance of the supply unit load is judged, and adjustment is not needed; if there is a population < Representing unbalanced demand load in a group, coping with supply units with excessive demand load in the group, and transferring partial demand to supply parties with excessive demand load in the same group; If it is < And the method represents unbalanced demand load among groups, adjusts the demand distribution proportion among groups, and inclines the demand to the groups with high service capacity and low load ratio.
8. An emergency guarantee demand load balancing evaluation system based on homogeneous population partitioning, comprising a processor and a memory, the memory having stored thereon a computer program which, when executed by the processor, implements the steps of the emergency guarantee demand load balancing method based on homogeneous population partitioning as claimed in any one of claims 1 to 7.

Description

Emergency guarantee demand load balancing method and system based on homogeneous group division Technical Field The application relates to the technical field of emergency guarantee and data processing, in particular to an emergency guarantee demand load balancing method and system based on homogeneous group division. Background In the fields of emergency guarantee and the like, proper supply units are often required to be selected according to material demands. After the supply units are selected, the demand load balance degree of the supply units can be measured by a method for calculating the overall entropy value of the material load proportion of the supply units. However, the method ignores the characteristic difference of the supply units, does not consider key characteristics such as service capacity, coverage area, historical load and the like of the supply units, and is difficult to accurately and reasonably evaluate the global balance degree of the demand load of the supply units, so that the local supply units are overloaded in demand or idle in material. Disclosure of Invention The embodiment of the application provides an emergency guarantee demand load balancing method and system based on homogeneous group division, which are used for constructing a quantitative calculation method of balance coefficients among groups and realizing balanced scheduling of material demands borne by suppliers. The embodiment of the application provides an emergency guarantee demand load balancing method based on homogeneous group division, which comprises the following steps: Screening the material key characteristics of the supplier, and normalizing the key characteristics to obtain the load capacity characteristics of the supplier; dividing a homogeneous provider group according to the obtained load capacity characteristics of the provider by a K-means clustering algorithm; according to the divided homogeneous provider groups, double-layer load evaluation between groups is carried out, wherein local load difference of the provider is captured through information entropy in the groups, global load-capacity matching degree is regulated and controlled through balance coefficients between the groups, and therefore omnibearing balance of the load of the provider is achieved; and according to the intra-group demand load information entropy and the inter-group demand load balancing coefficient, completing the comprehensive load balancing. The embodiment of the application provides an emergency guarantee demand load balancing evaluation system based on homogeneous group division, which comprises a processor and a memory, wherein a computer program is stored in the memory, and the computer program realizes the steps of the emergency guarantee demand load balancing method based on homogeneous group division when being executed by the processor. According to the embodiment of the application, a quantification calculation method of the inter-group balance coefficient is constructed through the division of homogeneous groups, and the entropy values in the groups are combined to form a comprehensive balance evaluation rule of 'group internal entropy value + inter-group coefficient', so that the balance scheduling of the supply side bearing material demands is realized. The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent. Drawings Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings: Fig. 1 is a basic flow diagram of an emergency guarantee demand load balancing method based on homogeneous group division according to an embodiment of the present application. Detailed Description Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. The embodiment of the application provides an emergency guarantee demand load balancing method based on homogeneous group division, which provides a method for representing the load capacity of a su