Learning to Cache: Federated Caching in a Cellular Network With Correlated Demands

• Published in: IEEE transactions on communications Vol. 70; no. 3; pp. 1653 - 1665
• Main Authors: Tharakan, Krishnendu S., Bharath, B. N., Garg, Navneet, Bhatia, Vimal, Ratnarajah, Tharmalingam
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.03.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Base stations; Caching; Cellular communication; Cellular networks; Distance learning; Distributed content caching; Distributed databases; Heuristic algorithms; Machine learning; Minimization; non-stationary demands; online learning; Optimization; Radio equipment; regret minimization; Service introduction; Wireless networks
• ISSN: 0090-6778; 1558-0857
• DOI: 10.1109/TCOMM.2021.3132048

In this paper, the problem of distributed content caching in a small-cell Base Stations (sBSs) wireless network that maximizes the cache hit performance is considered. Most of the existing works consider static demands, however, here, data at each sBS is considered to be correlated across time and sBSs. Federated learning (FL) based caching strategy is proposed which is assumed to be a weighted combination of past caching strategies of the sBS as well as the neighbouring sBSs. A high probability generalization guarantees on the performance of the proposed federated caching strategy is derived. The theoretical guarantee provides following insights on obtaining the caching strategy: (i) run regret minimization at each sBS to obtain a sequence of caching strategies across time, and (ii) maximize an estimate of the bound to obtain a set of weights for the caching strategy which depends on the discrepancy. Theoretical guarantee on the performance of the least recently frequently used (LRFU) caching strategy is derived. Further, FL based heuristic caching algorithm is also proposed. Finally, it is shown through simulations using Movie Lens dataset that the proposed algorithm significantly outperforms the recent online learning algorithms.