Content Popularity Prediction Towards Location-Aware Mobile Edge Caching

TL;DR

This paper introduces location-aware online algorithms for mobile edge caching that adaptively predict content popularity, improving hit rates by accounting for user demand variability and noise in predictions.

Contribution

It proposes two robust online algorithms for location-specific content caching, one based on ridge regression and another on $H_{}$ filtering, with proven asymptotic optimality and applicability to real data.

Findings

Algorithms achieve content hit rates comparable to hindsight optimal strategies.

Proposed methods are robust to different noise structures and demand variations.

Extensive experiments validate the effectiveness of the algorithms in real-world scenarios.

Abstract

Mobile edge caching enables content delivery within the radio access network, which effectively alleviates the backhaul burden and reduces response time. To fully exploit edge storage resources, the most popular contents should be identified and cached. Observing that user demands on certain contents vary greatly at different locations, this paper devises location-customized caching schemes to maximize the total content hit rate. Specifically, a linear model is used to estimate the future content hit rate. For the case where the model noise is zero-mean, a ridge regression based online algorithm with positive perturbation is proposed. Regret analysis indicates that the proposed algorithm asymptotically approaches the optimal caching strategy in the long run. When the noise structure is unknown, an $H_{\infty}$ filter based online algorithm is further proposed by taking a prescribed threshold as input, which guarantees prediction accuracy even under the worst-case noise process. Both online algorithms require no training phases, and hence are robust to the time-varying user demands. The underlying causes of estimation errors of both algorithms are numerically analyzed. Moreover, extensive experiments on real world dataset are conducted to validate the applicability of the proposed algorithms. It is demonstrated that those algorithms can be applied to scenarios with different noise features, and are able to make adaptive caching decisions, achieving content hit rate that is comparable to that via the hindsight optimal strategy.