A content deployment and distribution method and system for mobile edge computing

Abstract

In order to alleviate the network pressure caused by the local traffic surge in the emergency communication scene, the embodiment of the present invention provides a mobile edge computing-oriented content deployment and distribution method and system, which realizes the adaptive content deployment strategy and launch in the dynamic and unknown network environment Joint optimization of power, the method includes: aiming at maximizing the long-term average content hit rate of the system, establishing a target optimization problem; constructing a weighted graph according to the physical domain and social domain information of cache nodes and request nodes, and according to the weighted The weight graph clusters the cache nodes to obtain clustered cache nodes; based on deep reinforcement learning, solves the target optimization problem, and determines the behavior selection strategy of the clustered cache nodes, so that users can directly obtain content request. The embodiment of the present invention adopts a deep reinforcement learning method to realize an adaptive storage strategy of cache nodes and collaborative optimization of transmission power when the popularity is unknown or changes dynamically.

Description

Technical field [0001] The present invention relates to the field of wireless distributed caching, and in particular, to the content deployment and distribution method and system of moving edge calculations. Background technique [0002] With the continuous spread of intelligent equipment, the new business has gradually emerged, and global mobile data traffic is exponentially growing. At the same time, the spectral resources below 6GHz are very scarce, and the current network is difficult to withstand heavy loads from high mobile data traffic, which in turn affects business service quality and user experience. On the one hand, Cisco's statistical data found that most of the mobile data traffic comes from video services; on the other hand, the emerging video service presents the characteristics of content reuse, that is, different users will repeat the same hot content. Based on the above background, wireless distributed cache technology is proposed and applied, so that the more p...

AI Technical Summary

Problems solved by technology

[0004] At present, many research works are based on the assumption that the content popularity distribution is known and will not change dynamically, and optimize the content deployment and distribution strategies in the system based on this assumption. However, the content popularity may change dynamically or in the actual system. Unknown, the existing technology does not have a content deployment and distribution strategy for the above situation

Images