Low Earth Orbit (LEO) satellite constellations utilize Inter-Satellite Links (ISLs) to ensure global network connectivity. While the 4-ISL grid is a common academic assumption, operational reports from industry leaders like Starlink reveal a shift toward hardware-constrained 3-ISL configurations to optimize the trade-off between networking performance and deployment costs. However, existing 3-ISL designs, such as the Honeycomb topology, remain predominantly traffic-agnostic, leading to severe path inflation under non-uniform global traffic demands. In this paper, we propose BiCayley, a traffic-aware optimization framework that constructs 3-ISL topologies using Bipartite Cayley graph. By leveraging the structural homogeneity and vertex transitivity of Walker-Delta constellations, BiCayley collapses the NP-hard adjacency matrix optimization problem into a low-dimensional search over global generator offsets. Guided by a global Gravity-model traffic matrix, we employ Parallel Simulated Annealing (PSA) to identify optimal offsets that minimize propagation delay and nodal processing delay. Evaluations on Starlink configurations demonstrate that BiCayley significantly outperforms the state-of-the-art Honeycomb topology and Grid topology. In asymmetric Shell, BiCayley reduces Average Shortest Path Length (ASPL) and Average Hop Count (AHC) by 80.0% and 63.4% compared to Honeycomb, and 46.0% and 42.8% compared to the Grid. In symmetric Shell, BiCayley achieves a 23.4% reduction in ASPL over Honeycomb, delivering performance within 4.5% of the Grid. Our results demonstrate that BiCayley provides a robust, zero-handover architecture that aligns logical connectivity with real-world terrestrial demands.
Dorado is a novel design that scales SmartNIC session tables entirely on inexpensive DDR modules and uses three new techniques that extract commodity DDR performance by restructuring session table layout, decomposing processing pipelines to reduce locking, and scheduling memory accesses to minimize stalls.
Heng Yu, Kai Ren, Jiajun Liang et al.· Conference on Applications,...· 0 citations
Network emulation has become an indispensable methodology for evaluating next-generation network architectures, offering a critical balance between experimental fidelity and operational scalability. However, its effectiveness is fundamentally constrained by inefficiencies in emulating large-scale networks, particularly during virtual network construction. This bottleneck arises from mandatory serialization of virtual link instantiation and operating system (OS) kernel-level notification overheads, which collectively degrade performance by orders of magnitude on 10K-node topologies. Departure from the current practice that employs a multi-machine framework for improvements, we propose SplitNN (Split Network and Namespace), a novel single-machine network emulation paradigm that breaks the serialization constraint through multi-VM (virtual machines) partitioning, and reduces notification overheads via namespace segmentation. Extensive evaluations show that SplitNN constructs 10K-node virtual networks within 1–5 minutes on a single machine, achieving a 98.5%–99.2% reduction in construction time compared to state-of-the-art emulators. While primarily a single-machine solution, SplitNN seamlessly integrates with multi-machine deployments, complementing them by enabling cumulative gains in both scalability and efficiency.
Kaifei Peng, Yan-Biao Li, Wenbin Li et al.· IEEE Transactions on Network...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
