Content caching method based on deep learning

Abstract

The invention discloses a content caching method based on deep learning. The method comprises the following steps: (1) collecting user request information of edge nodes to construct a time request sequence; (2) calculating content popularity according to the request sequence data; (3) carrying out maximum and minimum normalization processing; (4) converting a time sequence prediction problem into a supervised learning problem; (5) offline training a popularity prediction model based on the time convolutional network; (6) calling a popularity prediction model to predict popularity, performing weighted summation on predicted popularity data and historical popularity data based on index average, and calculating a content value; and (7) performing cache decision by using the LRU. Popularity distribution of the corresponding content can be predicted only according to the characteristic of the content request sequence, meanwhile, balance can be achieved between long-term memory and short-term sudden memory in combination with historical content popularity information, and good effects can be achieved on the aspects of prediction accuracy and cache hit rate improvement.

Description

technical field [0001] The invention relates to the technical field of edge caching in mobile communications, in particular to a content caching method based on deep learning. Background technique [0002] With the continuous and rapid popularization of various smart devices and advanced mobile application services, wireless networks have been under unprecedented data traffic pressure in recent years. Ever-increasing mobile data traffic puts enormous pressure on backhaul links with limited capacity, especially during traffic peaks. The content caching technology at the edge can effectively save the time and resources required to request and transmit content from the upper-level content server or original content server by placing the most popular content at the end user or the base station closer to the requesting user, and can reduce data flow. However, due to the limited cache capacity of nodes and the change of content popularity with time and space, content caching tec...

AI Technical Summary

Problems solved by technology

However, in the above methods, the model popularity prediction is not accurate enough, and the cache decision is too dependent on the predicted popularity ranking. Its parameters can only be updated regularly on a rough time scale, and cannot cope with and adapt to emergencies (such as the emergence of new hot content) In other cases, it is easy to cause problems such as low cache hit rate, increased network delay, and low utilization of cache space.

Images