MEC Deep Learning Based Caching System and Method for Self-Driving Car in Multi-access Edge Computing

摘要

Disclosed is a caching system. The caching system includes: an object to which content is provided; and a multi-access edge computing (MEC) server configured to determine caching content based on a probability that the content is requested from the object in an allocated area and a first predicted value including a predicted rating of the content, and download and cache the determined caching content from a content provider, wherein the object includes a recommendation module for identifying and recommending recommended content among the caching content by applying a k-means algorithm and a binary classification to the first predicted value and a second predicted value which is a predicted value for user′s characteristics of the object, and a deep learning-based caching module configured to query available MEC servers on a moving path of the object, select an optimal MEC server for downloading the recommended content from the available MEC servers, and download and cache the recommended content from the optimal MEC server.