An edge caching method, device and electronic device based on reinforcement learning

Abstract

An embodiment of the present invention provides an edge caching method, device, and electronic device based on reinforcement learning. The method includes: obtaining the number of requests for all content in multiple small cells within a preset time period and the content caching status of the current small cell ;Based on the number of requests for all content in multiple small cells, calculate the first content popularity and second content popularity corresponding to each content, and obtain the content popularity feature matrix; use the pre-trained cache built based on the reinforcement learning algorithm The policy model processes the content popularity characteristic matrix and the content caching situation of the current small cell to obtain the caching strategy of each content in the current small cell; based on the caching strategy of each content in the current small cell, the content in the current small cell for caching. By applying the embodiment of the present invention, the cache hit rate and the utilization rate of the cache space of the cache content of the small cell can be improved.

Description

technical field [0001] The present invention relates to the technical field of wireless communication, in particular to an edge caching method, device and electronic equipment based on reinforcement learning. Background technique [0002] With the rapid development of wireless communication technology, the demand for mobile data traffic has increased sharply, and dense small cell networks have emerged as the times require. In a dense small cell network, content distribution and sharing are included, such as video files, news, alerts, and so on. When a user needs to request content, the user sends a content request to the small cell base station, the base station forwards the content request to the core network, the core network sends the service data corresponding to the content request to the base station, and the base station then sends the service data corresponding to the content request to user. As the demand for services such as mobile video continues to increase, a ...

AI Technical Summary

Problems solved by technology

[0004] However, the existing method of caching content is realized based on the request probability of content within a preset time period of the small cell base station, and the content is cached based on the number of requests for content within the preset time period of the small cell base station, so that The content cached in the small cell base station is greatly affected by the preset time period set

Moreover, in practical applications, the content required by the user changes, so that the cached content corresponding to a higher probability of request within the preset time period is not necessarily the content required by the user, resulting in the cached content may not be the user's choice hit content with a high rate, resulting in a waste of cache space to a certain extent

Images