Adaptive Caching in the YouTube Content Distribution Network: A Revealed Preference Game-Theoretic Learning Approach

Abstract

Cognitive systems are dynamical systems that adapt their behavior to achieve sophisticated outcomes in nonstationary environments. This paper considers two cognitive aspects regarding the problem of distributed caching with limited capacity in a content distribution network that serves YouTube users with multiple edge servers: first, the theory of revealed preference from microeconomics is used to estimate human utility maximization behavior. In particular, a nonparametric learning algorithm is provided to estimate the request probability of YouTube videos from past user behavior. Second, using these estimated request probabilities, the adaptive caching problem is formulated as a noncooperative repeated game in which servers autonomously decide, which videos to cache. The utility function tradesoff the placement cost for caching videos locally with the latency cost associated with delivering the video to the users from a neighboring server. The game is nonstationary as the preferences of users in each region evolve over time. We then propose an adaptive popularity-based video caching algorithm that has two timescales: The slow timescale corresponds to learning user preferences, whereas the fast timescale is a regret-matching algorithm that provides individual servers with caching prescriptions. It is shown that, if all servers follow simple regret minimization for caching, their global behavior is sophisticated—the network achieves a correlated equilibrium, which means that servers can coordinate their caching strategies in a distributed fashion as if there exists a centralized coordinating device that they all trust to follow. In the numerical examples, we use real data from YouTube to illustrate the results.