Unlock instant, AI-driven research and patent intelligence for your innovation.

Load balancing method based on video request number prediction

A video request and load balancing technology, applied in digital transmission systems, data exchange networks, electrical components, etc., can solve the problems of becoming overloaded servers, failing to reach the update cycle, affecting the transmission video rate, etc., to ensure balanced deployment. Effect

Inactive Publication Date: 2018-10-09
XIDIAN UNIV +1
View PDF7 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Compared with the traditional load balancing algorithm, the periodic dynamic feedback load balancing strategy has absorbed the strengths of the traditional load balancing algorithm, but there are also some shortcomings: during the update period, if a streaming media server receives more video requests , it has become a heavy-loaded server at this time, but the update cycle has not yet been reached, and the load balancer has not yet started to collect the load of each streaming media server. At this time, the light-loaded server has become a heavy-loaded server, but it is still In light server queue
When the load balancer assigns the request task to the streaming media server, the server has reached the working bottleneck and basically does not have the ability to copy and forward the video stream, thus affecting the video transmission rate and reducing the service quality of the server

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Load balancing method based on video request number prediction
  • Load balancing method based on video request number prediction
  • Load balancing method based on video request number prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] See figure 1 , figure 1 It is a schematic flowchart of a load balancing method based on video request number prediction provided by an embodiment of the present invention.

[0042] A load balancing method based on video request number prediction, applied to a streaming media system including a streaming media server and a load balancer, comprising the following steps:

[0043] (a) predict the number of video requests in the next cycle according to the load prediction model established;

[0044] (b) calculating the load variation of the streaming media server in the next cycle according to the number of video requests in the next cycle;

[0045] (c) determining the load of the streaming media server in the next cycle according to the current load of the streaming media server and the load variation of the next cycle;

[0046] (d) Balancing the load of the streaming media server by the load balancer according to the load of the streaming media server in the next cycle....

Embodiment 2

[0055] see again figure 1 , on the basis of the foregoing embodiments, this embodiment focuses on a detailed description of a load balancing method based on prediction of the number of video requests.

[0056] (S10) Collect the current number of video requests, the maximum number of video requests, alarm messages, and abnormal behavior messages within a predetermined time period, and use the BP neural network algorithm to establish the load prediction model.

[0057] The load of the streaming media server is all brought by the number of video requests. When multiple video requests are sent to the streaming media server, the streaming media server requests the video from the camera, and then copies and forwards to the video requesting party. The streaming media Therefore, the server will generate a load, and the number of video requests in the next time period is related to the current number of video requests, the maximum number of video requests, whether the alarm point gener...

Embodiment 3

[0115] See Figure 4 , Figure 4 It is a schematic flowchart of another load balancing method based on video request number prediction provided by an embodiment of the present invention. On the basis of the foregoing embodiments, this embodiment introduces in detail a load balancing method based on prediction of the number of video requests.

[0116] (S30) The program starts.

[0117] (S31) The streaming media server calculates its own real-time load;

[0118] (S32) The BP neural network algorithm predicts the number of video requests in the next cycle.

[0119] (S33) monitoring load and predicting load changes, detecting whether the streaming media server is overloaded, if so, then the load balancer updates the queue, and detecting whether there is a video request again, if yes, it is allocated to the streaming media server, otherwise Continue to monitor load and predict load changes; if it is no to detect that the streaming media server is overloaded, then whether the de...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a load balancing method based on video request number prediction. The method is applied to a streaming media system comprising streaming media servers and a load balancer. Themethod comprises the following steps of (a), predicting the video request number in a next period according to an established load prediction model; (b), calculating load change quantity of the streaming media servers in the next period according to the video request number in the next period; (c), determining the load quantity of the streaming media servers in the next period according to the current load quantity of the streaming media servers and the load change quantity in the next period; and (d), balancing the load of the streaming media servers by the load balancer according to the load quantity of the streaming media servers in the next period. According to the embodiment of the invention, through prediction of the video request number in the next period, the load balancer can reasonably allocate the load of the streaming media servers which receive the video request number, so the quality of service of the streaming media servers is improved.

Description

technical field [0001] The invention belongs to the technical field of computer applications, and in particular relates to a load balancing method based on video request number prediction. Background technique [0002] Load balancing is based on the existing network structure, which provides a cheap, effective and transparent method to expand the bandwidth of network devices and servers, increase throughput, strengthen network data processing capabilities, and improve network flexibility and availability. [0003] Commonly used load balancing algorithms are as follows: (1) Polling algorithm: assign request tasks to each server in the cluster in sequence. Its advantage is that it is simple and easy to implement, and its disadvantage is that it does not consider the processing capacity between server nodes The difference, unable to make full use of node resources. (2) Weighted polling algorithm: Add a weight to each server to represent its processing capability. When assignin...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04L29/08H04L29/06H04L12/24
CPCH04L41/147H04L67/1004H04L67/1008H04L65/75
Inventor 沈玉龙翟开放徐真真雎悦陈博闻余正伟刘宇鹃
Owner XIDIAN UNIV