Forecasting in Online Caching
Exploration of the effects of forecaster methods on an online learning caching policy
G. Gareth Kit Kye Ler (TU Delft - Electrical Engineering, Mathematics and Computer Science)
F.A. Aslan – Mentor (TU Delft - Networked Systems)
George Iosifidis – Graduation committee member (TU Delft - Networked Systems)
Neil Yorke-Smith – Graduation committee member (TU Delft - Algorithmics)
N. Mhaisen – Graduation committee member (TU Delft - Networked Systems)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
This paper explores the effect of forecasting methods on the Optimistic Follow The Regularized Leader (OFTRL) caching policy. It has been theoretically proven that the performance of OFTRL improves with accurate forecasters. However, the forecasters were portrayed as black boxes. In this paper, we do not treat forecasters as a black box but rather use recommender systems and temporal convolutional networks (TCN) implementations as forecasters for OFTRL in the caching context. The said forecasters predict the next file requests directly from the request trace rather than monitoring popularity. Using request traces extracted from the well-known MovieLens dataset, it was found that incorporating a forecaster into an optimistic learning algorithm is not straightforward. In fact, it was found that simpler approaches such as one that predicts the most requested file, can outperform more complicated deep learning models in terms of regret even if they possess a lower accuracy.