Intelligent data caching method based on cooperative sensing

Abstract

The invention relates to an intelligent data caching method based on cooperative sensing, and belongs to the technical field of wireless communication. The method comprises the following steps of: firstly, respectively updating global popularity and local popularity on a long time scale and a short time scale by analyzing historical request information and a hit state of a request, and then modeling equipment request file transmission delay in an industrial internet scene; and finally, a multi-agent reinforcement learning model based on an Actor-Critic framework is utilized to update the cache state at the micro base station, and bandwidth resources are adaptively allocated to maximize rate weighting and an objective function. According to the method, the time delay of acquiring the key data file by the equipment in the industrial internet can be obviously reduced, and the application performance is improved.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and relates to a data intelligent caching method based on cooperative perception. Background technique [0002] With the development of intelligent manufacturing demand, the use of artificial intelligence, edge computing, cloud-edge collaboration and other technologies to support traditional industrial production has become a hot issue in the international industry. Industrial Internet (Industrial Internet) will become a new type of infrastructure for the deep integration of a new generation of information and communication technology and industrial economy, and undertake the integration and connection of people, things and networks. In industrial manufacturing scenarios, equipment is extremely diverse, and it is difficult to undertake intelligent and comprehensive connections in the entire industrial Internet system only by using traditional cellular networks and fiber-optic wired...

AI Technical Summary

Problems solved by technology

[0004] In a large number of existing studies, there are certain studies on using a single SBS to analyze historical data for caching decisions, analyzing device mobility, and using long-term and short-term caches to track regional content popularity, but they all focus on At the level of mobile content, there are certain similar characteristics in different regions

On the other hand, content popularity tends to be different in the coverage areas of different SBSs, but since the distribution of industrial production of the same type is often concentrated together, there may be some similarities between adjacent SBSs

In addition, the amount of data requested for a region often affects the cache efficiency of a region, so how to efficiently cache popular files and transfer them to devices is still an unresolved problem

Images