New Tech Could Triple the Video Calls Your Cell Tower Handles

Prior research showed that QoE-aware resource sharing for real-time interactive video can support up to three times more simultaneous sessions at acceptable quality compared to rate-fair allocation — but the capabilities it requires (QoE-targeted encoding, runtime spatial complexity estimation, and rich application-network APIs) aren't available in commercial deployments yet. So researchers took an evolutionary approach and designed a prototype that delivers QoE-aware resource allocation using only capabilities that can be assembled in a lab today. They extend the utility-based allocation framework to the radio resource domain by introducing composite spatial complexity, which combines a session's video spatial complexity with its time-variant spectral efficiency into a single resource demand function. Because commercial real-time video streaming applications use rate-based congestion control and lack the capability to measure QoE, the prototype uses external tooling for QoE measurements, along with an incremental reallocation algorithm whose per-interval limits encode both the congestion control algorithm's speed constraint and the fact that spatial complexity estimates are reliable only near the current rate. The result combines external QoE measurements with congestion-signal-based rate steering and does not require modification to commercial applications. The authors also chart an evolution path from this prototype toward full QoE-aware resource sharing, mapping emerging standards (IETF SCONE, CAMARA, Media over QUIC) to the progressive capabilities they enable.