Published January 25, 2019 | Version v1
Journal article

Feedforward Neural Networks for Caching

Description

We propose a caching policy that uses a feedforward neural network (FNN) to predict content popularity. Our scheme outperforms popular eviction policies like LRU or ARC, but also a new policy relying on the more complex recurrent neural networks. At the same time, replacing the FNN predictor with a naive linear estimator does not degrade caching performance significantly, questioning then the role of neural networks for these applications.

Abstract

International audience

Additional details

Identifiers

URL
https://hal.inria.fr/hal-02411461
URN
urn:oai:HAL:hal-02411461v1