Comprehensive strategies for time-sensitive networks: path selection, scheduling, security, and virtual reality traffic insights

Abstract

Distributed real-time applications (RTAs) demand that their communication networks be robust and deterministic. Two properties identify the network's determinism, which are (1) the stability in terms of end-to-end latency and jitter and (2) the resilience to failures and security threats. To achieve determinism, the IEEE Time-Sensitive Networking (TSN) Task Group has amended the standards of IEEE 802.3 Ethernet to support the stringent timing requirements of RTAs. The primary purpose of this dissertation is to satisfy these two properties in the context of TSN and analyze the traffic characteristics of one popular RTA application, namely Virtual Reality (VR). To meet the stability property, we design an incremental performance-aware path selection and non-time-slotted scheduling framework that uses performance measurements to route TSN flows while load-balancing both TSN and best-effort traffic and diversifying the selected paths to avoid creating bottleneck links. Then, the framework uses non-time-slotted scheduling to find the appropriate transmission time to avoid queuing delays (or make them predictable) while enhancing bandwidth utilization compared to existing time-slotted scheduling solutions. The incremental nature of the framework, although increasing its flexibility by allowing RTAs to join the network while it is in operation, introduces security threats. We identify these threats, evaluate their impacts, and propose reactive defenses to detect and react to them upon their occurrences. To better understand future RTAs, we also analyzed the traffic characteristics of the ideal VR experience, where we used the information of the human vision capabilities to derive specific values for the required capacity, latency, and reliability for such an experience. To evaluate the accuracy of these estimated values, we derived corresponding values for Quest 2 using its provided specifications. Then, we conducted realistic VR experiences over an edge-enabled IEEE 802.11ax network to evaluate how far the calculated values were from the measured values. Results showed that the schedulability of better load-balanced TSN flows increases by up to 95.08\%. Compared with time-slotted scheduling, non-time-slotted scheduling increases the schedulability of TSN flows by fivefold in some cases. Moreover, non-time-slotted scheduling reduces the number of guard bands, enhancing link utilization by more than 60\%. Furthermore, the reactive defenses retained TSN's determinism by dropping less than 1\% of TSN flows in some scenarios. Finally, the measured traffic characteristics from the realistic VR experience over IEEE 802.11ax aligned with their corresponding calculated values.