Caching method and device based on content popularity

A popular and caching technology, applied in the field of computer communication, can solve problems that cannot be solved, and achieve the effect of eliminating repetitive traffic, strong practicability, and improving cache accuracy

Active Publication Date: 2019-12-03
THE PLA INFORMATION ENG UNIV
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the "value" in this method depends on the judgment of the popularity index T, and T in this article is a preset fixed value, so it cannot be an online solution

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
  • Caching method and device based on content popularity
  • Caching method and device based on content popularity
  • Caching method and device based on content popularity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Embodiment one, see figure 1 As shown, a caching device based on content popularity includes:

[0043] The content popularity learning module is used to obtain the historical popularity of the first k time slots of the content object by learning the first k time slots of the current time slot of the content object, wherein k is a natural number;

[0044] A content popularity prediction module is used to predict the popularity of content objects in future time slots by setting corresponding influence weights on the first k time slots according to historical popularity;

[0045] The cache decision module is used to convert the optimal cache of the content object in the router into a 0-1 knapsack model. In the 0-1 knapsack model: the reward factor is equivalent to the item value, and the cost factor is equivalent to the item weight , the cache capacity M of the router is equivalent to the capacity of the backpack;

[0046] The content object cache module is used to solve...

Embodiment 2

[0048] Embodiment two, see Figure 1~2 As shown, it is basically the same as Embodiment 1, the difference is that the content object cache module includes:

[0049] The input module is used to input content objects and predicted popularity;

[0050] A cache capacity initialization unit, configured to initialize the remaining cache capacity of the router;

[0051] a content object sorting unit, configured to sort the input content objects in non-ascending order according to the predicted popularity;

[0052] The content object cache unit is used to obtain the size of the content object according to the cost factor in the 0-1 knapsack model, compare the size of the content object with the remaining cache capacity of the router, and determine whether to cache the content object, and according to the judgment As a result, update the router's remaining cache traffic until all input content objects are traversed.

[0053] The input objects are sorted by the predicted content obje...

Embodiment 3

[0054] Embodiment three, see Figure 1~3 As shown, a caching method based on content popularity includes the following content:

[0055] Step 1. Divide time into multiple time slots, the multiple time slots are the first k time slots of the current time slot, and the length of the time slot is T; learn the content objects of the first k time slots, and obtain the first k content objects The historical popularity of the time slot, k is a natural number;

[0056] Step 2. Predict the popularity of the content object in the future time slot according to the historical popularity, and obtain the predicted popularity;

[0057] Step 3. According to the predicted popularity, the caching decision of the content object is modeled as a 0-1 knapsack model;

[0058] Step 4. Solve the 0-1 knapsack model through the popularity priority greedy cache algorithm, obtain the cache priority according to the solution result, and cache the content object according to the cache priority.

[0059] ...

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 present invention relates to a caching method and device based on content popularity. The method includes the following content: time is divided into multiple time slots, the multiple time slots are the first k time slots of the current time slot, and the length of the time slot is Be T; learn the content object of the previous k time slots, obtain the historical popularity of the previous k time slots of the content object, k is a natural number; predict the popularity of the content object in the future time slot according to the historical popularity, and obtain the predicted popularity; According to the predicted popularity, the caching decision of the content object is modeled as a 0‑1 knapsack model; the 0‑1 knapsack model is solved by the popularity priority greedy caching algorithm, and the cache priority is obtained according to the solution result, and according to the cache priority Cache content objects. The invention solves the problem of low cache accuracy and cache performance caused by not considering content popularity or setting content popularity in the prior art, greatly improves the cache accuracy and performance of the cache system, and has strong practicability.

Description

technical field [0001] The invention belongs to the technical field of computer communication, and in particular relates to a caching method and device based on content popularity. Background technique [0002] With the continuous increase of Internet users, personal devices, and video services, global IP traffic has shown "explosive" growth. According to the forecast of the network giant Cisco, by 2019, global IP traffic will reach 168EB per month, a significant increase compared to 59.9EB per month in 2014. The rapid growth of network traffic has made "Internet congestion" increasingly serious. In addition, the Internet adopts an independent service model based on end-to-end connections to provide network services for each user. In this model, access to hot content in the network generates a large number of repetitive links and traffic. These repetitive traffic willfully consume network resources, further exacerbating "Internet congestion", resulting in low network trans...

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 Patents(China)
IPC IPC(8): H04L12/747H04L29/08
CPCH04L45/742H04L67/568
Inventor 王鹏申涓刘贵财张校辉伊鹏马腾刘宗海
Owner THE PLA INFORMATION ENG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products