Mixed-Timescale Precoding and Cache Control in Cached MIMO Interference Network

TL;DR

This paper introduces a mixed-timescale optimization framework for cache-enabled MIMO interference networks, leveraging opportunistic CoMP and adaptive cache control to reduce transmit power while satisfying media streaming rate requirements.

Contribution

It proposes a novel joint stochastic optimization approach for MIMO precoding and cache control that enhances interference mitigation without needing media popularity knowledge.

Findings

Significant power reduction compared to baselines

Effective interference mitigation via cache-induced CoMP

Robust low-complexity solution with convergence guarantees

Abstract

Consider media streaming in MIMO interference networks whereby multiple base stations (BS) simultaneously deliver media to their associated users using fixed data rates. The performance is fundamentally limited by the cross-link interference. We propose a cache-induced opportunistic cooperative MIMO (CoMP) for interference mitigation. By caching a portion of the media files, the BSs opportunistically employ CoMP to transform the cross-link interference into spatial multiplexing gain. We study a mixed-timescale optimization of MIMO precoding and cache control to minimize the transmit power under the rate constraint. The cache control is to create more CoMP opportunities and is adaptive to the long-term popularity of the media files. The precoding is to guarantee the rate requirement and is adaptive to the channel state information and cache state at the BSs. The joint stochastic optimization problem is decomposed into a short-term precoding and a long-term cache control problem. We propose a precoding algorithm which converges to a stationary point of the short-term problem. Based on this, we exploit the hidden convexity of the long-term problem and propose a low complexity and robust solution using stochastic subgradient. The solution has significant gains over various baselines and does not require explicit knowledge of the media popularity.