NG-Scope

Accurate and highly-granular channel capacity telemetry of the cellular last hop is crucial for the effective operation of transport layer protocols and cutting edge applications, such as video on demand and video telephony. This paper presents the design, implementation, and experimental performance evaluation of NG-Scope, the first such telemetry tool able to fuse physical-layer channel occupancy readings from the cellular control channel with higher-layer packet arrival statistics and make accurate capacity estimates. NG-Scope handles the latest cellular innovations, such as when multiple base stations aggregate their signals together to serve mobile users. End-to-end experiments in a commercial cellular network demonstrate that wireless capacity varies significantly with channel quality, mobility, competing traffic within each cell, and the number of aggregated cells. Our experiments demonstrate significantly improved cell load estimation accuracy, missing the detection of less than 1% of data capacity overall, a reduction of 82% compared to OWL [10], the state-of-the-art in cellular monitoring. Further experiments show that MobileInsight-based [28] CLAW [43] has a root-mean-squared capacity error of 30.5 Mbit/s, which is 3.3× larger than NG-Scope (9.2 Mbit/s).