Search

CN-122027566-A - Intelligent load balancing-based flow distribution method, device, equipment and storage medium

CN122027566ACN 122027566 ACN122027566 ACN 122027566ACN-122027566-A

Abstract

The application discloses a flow distribution method, a device, equipment and a storage medium based on intelligent load balancing, which relate to the technical field of network communication and comprise the steps of obtaining current flow characteristics based on current flow data and current service data; the method comprises the steps of obtaining a current flow characteristic, obtaining a flow prediction value in a preset time period in the future by taking the current flow characteristic as input of a flow prediction model, determining flow distribution proportion of main equipment and backup equipment based on the current flow data and the flow prediction value, and adjusting the flows of the main equipment and the backup equipment based on the flow distribution proportion. By introducing a flow prediction mechanism, the technical problem that the prior art cannot adapt to flow burst and load unbalance of main and standby equipment due to the fact that the flow distribution is carried out only by depending on static configuration or current load is solved. Compared with the prior art, the load balance degree and the overall resource utilization rate between the main equipment and the standby equipment are obviously improved.

Inventors

  • FENG WEI
  • YUAN FENG

Assignees

  • 深圳市丰润达科技有限公司

Dates

Publication Date
20260512
Application Date
20260312

Claims (10)

  1. 1. A traffic distribution method based on intelligent load balancing, the method comprising: obtaining current flow characteristics based on the current flow data and the current service data; taking the current flow characteristic as the input of a flow prediction model to obtain a flow prediction value in a future preset period; determining the flow distribution proportion of the main equipment and the backup equipment based on the current flow data and the flow prediction value; and adjusting the flow of the main equipment and the backup equipment based on the flow distribution proportion.
  2. 2. The method of claim 1, wherein the obtaining the current traffic characteristics based on the current traffic data and the current traffic data comprises: Collecting current flow data and current service data; obtaining the current service type duty ratio based on the current service data; and preprocessing the current flow data and the current service type duty ratio to obtain a current flow characteristic.
  3. 3. The method of claim 1, wherein the step of using the current flow characteristic as an input to a flow prediction model, before obtaining a flow prediction value within a predetermined period of time in the future, further comprises: acquiring historical flow data and historical service type data of different historical time periods; Obtaining a historical flow characteristic and a flow prediction target value based on the historical flow data and the historical service type data, wherein the historical flow characteristic comprises a flow rate, a CPU utilization rate, a memory occupancy rate, a service type duty ratio and the historical period; And taking the historical flow characteristics and the flow prediction target value as training samples of an initial prediction model to obtain a flow prediction model.
  4. 4. The method of claim 1, wherein the determining the traffic allocation ratio of the primary device and the backup device based on the current traffic data and the traffic prediction value comprises: based on the current flow data, the current utilization rates of the main equipment and the backup equipment are obtained; obtaining the residual load energy of the main equipment based on the preset performance threshold value, the rated energy and the current utilization rate of the main equipment; obtaining the residual load energy of the backup equipment based on the preset performance threshold value, rated energy and current utilization rate of the backup equipment; and determining a flow distribution proportion based on the main equipment residual load energy, the backup equipment residual load energy and the flow prediction value.
  5. 5. The method of claim 4, wherein the determining a traffic distribution ratio based on the primary device residual load energy, the backup device residual load energy, and the traffic prediction value comprises: obtaining a core service flow predicted value and a common service flow predicted value according to the flow predicted value; Determining a core service flow distribution proportion according to the core service flow prediction value, the main equipment residual load energy and the backup equipment residual load energy; determining a common service flow distribution proportion according to the common service flow prediction value, the main equipment residual load energy and the backup equipment residual load energy; and taking the core service flow distribution proportion and the common service flow distribution proportion as flow distribution proportions.
  6. 6. The method of claim 1, wherein adjusting traffic of the primary device and the backup device based on the traffic distribution ratio comprises: obtaining a utilization rate difference value based on the current utilization rates of the main equipment and the backup equipment; And when any one of the current utilization rate of the main equipment is larger than or equal to a preset utilization rate threshold value, the current utilization rate of the backup equipment is larger than or equal to a preset utilization rate threshold value and the utilization rate difference value is larger than or equal to a preset utilization rate difference threshold value is met, the flow rates of the main equipment and the backup equipment are adjusted based on the flow distribution proportion.
  7. 7. The method of claim 1, wherein after adjusting the traffic of the primary device and the backup device based on the traffic distribution ratio, further comprising: acquiring running state data and flow parameters of the main equipment and the backup equipment; based on the running state data and the flow parameters, obtaining load balance degree and service transmission quality indexes; and updating the flow prediction model based on the load balance degree and the service transmission quality index.
  8. 8. A traffic distribution device based on intelligent load balancing, the device comprising: the input module is used for obtaining the current flow characteristics based on the current flow data and the current service data; the prediction module is used for taking the current flow characteristic as the input of a flow prediction model to obtain a flow prediction value in a future preset period; the calculation module is used for determining the flow distribution proportion of the main equipment and the backup equipment based on the current flow data and the flow prediction value; And the distribution module is used for adjusting the flow of the main equipment and the backup equipment based on the flow distribution proportion.
  9. 9. A traffic distribution device based on intelligent load balancing, characterized in that the device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the traffic distribution method based on intelligent load balancing according to any of claims 1 to 7.
  10. 10. A storage medium, characterized in that the storage medium is a computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the steps of the intelligent load balancing based flow distribution method according to any one of claims 1 to 7.

Description

Intelligent load balancing-based flow distribution method, device, equipment and storage medium Technical Field The present application relates to the field of network communication monitoring technologies, and in particular, to a traffic distribution method, device, equipment and storage medium based on intelligent load balancing. Background With the rapid development of cloud computing, large data, high-definition video streaming and other services, the traffic scale required to be carried by core equipment of an enterprise network and a data center increases exponentially, and the traffic presents remarkable burstiness and unpredictability in time distribution. The method has the advantages that extremely high requirements are put on the resource utilization rate and processing capacity of network core equipment (such as routers and switches), and the network equipment is required to dynamically and uniformly distribute processing tasks according to real-time flow changes so as to avoid single-point overload and ensure the service quality and high availability of the whole network. Currently, a virtual routing redundancy protocol and its improved scheme are widely used for implementing primary-backup redundancy and traffic sharing between devices. However, the prior art mainly adopts two static modes, namely a traditional main-standby mode of 'full main equipment bearing and zero backup equipment bearing', which leads to long-term idle of backup resources, and an improved fixed proportion sharing mode, such as presetting a main equipment bearing seven-component flow and a backup equipment bearing three-component flow. The static configuration schemes are completely dependent on manual presetting, cannot sense real-time fluctuation and sudden change of network traffic, often lead to overload of the main equipment due to the sudden traffic in practical application, cause increase of forwarding delay and even packet loss, and lead to serious resource waste and uneven load due to the fact that the backup equipment is in a light-load state. Therefore, the technical scheme of effectively balancing the loads of the main equipment and the standby equipment becomes the technical problem to be solved currently urgently by breaking through the limitation of the existing static load distribution mode and realizing the technical scheme of sensing the flow change in real time and dynamically adjusting the flow ratio among the equipment. The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present application and is not intended to represent an admission that the foregoing is prior art. Disclosure of Invention The application mainly aims to provide a flow distribution method, a device, equipment and a storage medium based on intelligent load balancing, which aim to solve the technical problem of how to dynamically adjust the flow ratio between the equipment. In order to achieve the above object, the present application provides a traffic distribution method based on intelligent load balancing, the method comprising: obtaining current flow characteristics based on the current flow data and the current service data; taking the current flow characteristic as the input of a flow prediction model to obtain a flow prediction value in a future preset period; determining the flow distribution proportion of the main equipment and the backup equipment based on the current flow data and the flow prediction value; and adjusting the flow of the main equipment and the backup equipment based on the flow distribution proportion. In an embodiment, the obtaining the current traffic characteristic based on the current traffic data and the current service data includes: Collecting current flow data and current service data; obtaining the current service type duty ratio based on the current service data; and preprocessing the current flow data and the current service type duty ratio to obtain a current flow characteristic. In an embodiment, before the current flow characteristic is used as an input of a flow prediction model to obtain a flow prediction value in a preset time period in the future, the method further includes: acquiring historical flow data and historical service type data of different historical time periods; Obtaining a historical flow characteristic and a flow prediction target value based on the historical flow data and the historical service type data, wherein the historical flow characteristic comprises a flow rate, a CPU utilization rate, a memory occupancy rate, a service type duty ratio and the historical period; And taking the historical flow characteristics and the flow prediction target value as training samples of an initial prediction model to obtain a flow prediction model. In an embodiment, the determining the traffic allocation proportion of the primary device and the backup device based on the current traffic data and the traffic prediction value i