Churn-Aware Spectrum Admission in Low-Latency Mobile Networks

Abstract

Spectrum admission in low-latency mobile networks increasingly relies on fast control loops under time-varying traffic and radio conditions. A key challenge in such settings is reconfiguration churn: small score fluctuations near the admission boundary can repeatedly flip the marginal admitted request, even when the resulting utility gain is negligible. These boundary-level replacements are disproportionately expensive because admission and eviction trigger higher-layer control procedures, signaling exchanges, and coordination overhead. To address this problem, we propose TOA-S, a churn-aware admission primitive for latency-bounded mobile control. TOA-S targets cellular radio access network (RAN) deployments operating over licensed spectrum, where control loops of the ultra-reliable low-latency communication class at the near-real-time RAN Intelligent Controller must complete within sub-second decision windows. TOA-S preserves the greedy allocation structure for the responsive core of the admitted set and applies stabilization only at the admission boundary, in a single pass per decision epoch, without iterative optimization or learning. We show that TOA-S incurs only an $\varepsilon $ -bounded utility deviation, modifies at most one membership decision per epoch, and suppresses oscillatory replacements under persistent boundary near-tie conditions. Simulations on synthetic workloads with measurement-verified parameters show that TOA-S substantially reduces reconfiguration churn while maintaining spectrum utilization and latency-compatible execution.