SPEAR

Research

SPEAR Lab conducts cutting-edge research at the intersection of edge computing, next-generation network protocols, and Internet-wide measurements. We build practical systems and conduct measurements that shape the future of Internet infrastructure.

Our research spans five interconnected areas, each addressing critical challenges in modern computing and networking systems. We publish at top-tier venues and release open-source tools to enable reproducible research.

Join Our TeamView PublicationsContact Us
Featured InterviewBTW Media • 2025

Edge Computing, Satellites, and Internet Reality

Dr. Nitinder Mohan discusses how LEO satellites are transforming Internet connectivity and the future of distributed computing at the network edge.

Watch InterviewRead Article

Research Areas

Our research spans five interconnected areas, each addressing critical challenges in modern computing and networking systems.

Project Funding

Our research is supported by grants from leading funding agencies

View all funding
🇳🇱

6G Future Network Services Growth Fund

Organization: NWO Netherlands
Period: 2025-present
Role: Co-Principal Investigator

Research on next-generation 6G network services and edge computing architectures. Developing innovative solutions for future network infrastructure including intelligent edge orchestration, distributed AI workloads, and sustainable network design.

Learn More

Open Source & Tools

We release our research prototypes and datasets to enable reproducible research

View all tools & datasets
Oakestra Logo

Oakestra

Hierarchical Orchestration for the Edge-Cloud Continuum

A lightweight, hierarchical orchestration framework that enables efficient management of applications across distributed, heterogeneous edge infrastructures. Oakestra provides geographic-aware service placement, hybrid virtualization support, and seamless federation across multiple administrative domains.

Key Features

✓
Hierarchical multi-tier architecture
✓
Lightweight design for resource-constrained edge devices
✓
Hybrid virtualization (containers & VMs)
+3 more features

Status

Production ReadyActive DevelopmentGrowing Community
2DFS Logo

2DFS

On-Demand Container Partitioning for Distributed Machine Learning

A novel container image distribution system that enables on-demand, file-level container partitioning for distributed machine learning workloads. 2DFS dramatically reduces container startup times and bandwidth consumption by intelligently fetching only the required files when needed.

Key Features

✓
On-demand file-level fetching
✓
Optimized for ML workloads
✓
Significant startup time reduction
+3 more features

Status

Artifact BadgesResearch PrototypeML Optimized

Invited Talks & Panels

Recent presentations at standards bodies, academic seminars, and industry events

View all talks & panels
IETF 123

It's a bird? It's a plane? It's CDN!: Understanding Starlink CDN Performance

Internet Engineering Task Force (IETF) 123 - Measurement and Analysis for Protocols Research Group (MAPRG)
LEO SatellitesCDNPerformance Measurement+1 more
Video
RIPE 90

Frontiers of LEO Space Networks: Understanding the Intricacies of Starlink's Internet Access

RIPE 90 Meeting - RIPE Network Coordination Centre
LEO SatellitesStarlinkNetwork Architecture
Video
COMSNETS

Frontiers of LEO Space Networks: Understanding the Intricacies of Starlink's Internet Access

International Conference on Communication Systems & Networks (COMSNETS)
LEO SatellitesStarlinkNetwork Architecture