StarryNet: Empowering Researchers to Evaluate Futuristic Integrated Space and Terrestrial
summary
StarryNet claims a practical, data-driven digital twin that emulates mega-constellations with 300 to 4000 satellites, uses real public orbit data plus model calibration, and runs a container-based emulation (Docker + Open vSwitch + tc) across R740 servers to auto-update handovers and link states; setup takes minutes, per-node CPU/memory overhead is measured, end-to-end latency matches live measurements more closely than simulators, and it supports 3U cubesat hardware-in-the-loop with CPU coremark profiles for Raspberry Pi/Jetson.
AI-written summary · about
chapters (6)
- 0:00Introduction to ISTN
- 2:52Experimental challenges
- 6:05Starrynet design
- 9:06Performance evaluation
- 12:31Case studies and results
- 15:32Conclusion and outlook
related talks
16mEmulating Space Computing Networks with RHONE
16mNeST: A Python based Network Emulator for Education and Research
21mMirrorNet: High-fidelity and Scalable Network Emulation for Software-defined WAN
17mCyberStar: Simple, Elastic and Cost-Effective Network Functions Management in...
48mRethinking Connectivity
16mLEOCraft: Towards Designing Performant LEO Networks
15mICARUS: Attacking low Earth orbit satellite networks
46mSelf-Programming Networks: Network Clock Synchronization, Event Playback and Real-time Action