Edge cache system and method based on content popularity prediction

Abstract

The invention discloses an edge caching system and method based on content popularity prediction, comprising the following steps: (1) according to user history request information, offline training of each user's preference model in the node coverage area; (2) when When the request arrives, if the requested content is not in the cache, predict the content popularity online according to the user preference model; (3) compare the predicted value of the content popularity with the minimum value of the cache content popularity, and make a corresponding cache decision; (4) ) to update the content popularity value at the current moment, and evaluate the user preference model to determine whether to start offline user preference model learning. The present invention enables edge nodes to predict content popularity online and track changes in content popularity in real time, and make corresponding caching decisions based on the predicted content popularity, thereby ensuring that edge nodes continue to cache hot content and obtain an asymptotically ideal caching method cache hit rate.

Description

technical field [0001] The invention relates to an edge cache system and method based on content popularity prediction, and belongs to the technical field of edge cache in mobile communication. Background technique [0002] With the continuous and rapid increase of various smart devices and advanced mobile application services, wireless networks are under unprecedented data transmission pressure in recent years. The ever-increasing amount of data transmission puts enormous pressure on the backhaul links with limited capacity, especially during the peak hours of business transmission. Edge caching technology can effectively reduce the backhaul load by placing the most popular content on the node closer to the requesting user, and has received extensive attention from the industry and academia in recent years. Due to the limited storage space of nodes and content popularity changes with time and space, edge caching technology faces various challenges, such as, in order to mak...

AI Technical Summary

Problems solved by technology

[0003] Traditional caching strategies such as first-in-first-out caching strategy, least recently used caching strategy, least recently used caching strategy, and variants of these algorithms have been widely used in wired networks, however, due to the coverage and storage space of edge nodes in wireless networks Limited, the above traditional caching strategies cannot directly predict content popularity in advance, these traditional caching strategies may suffer severe performance degradation in wireless networks, therefore, these traditional caching strategies are no longer suitable for wireless networks

The current research work is turning to the popularity-based edge caching strategy, but the prediction of content popularity is complex and cannot track the changes of popularity in real time, and the cache performance is limited.

Images