Fault-tolerant distributed and edge computing

How do distributed systems keep agreeing when machines crash, links fail, and some nodes are hostile?

Cyber-physical systems increasingly run on clusters at the edge rather than a single controller. That buys resilience only if the replicas can agree under adversarial conditions, at latencies a physical process can tolerate. The center works on the protocols and the systems that make that true.

What the group builds

Fault-tolerant consensus and state machine replication

Protocols that stay correct and fast when replicas crash or misbehave, with the latency budgets that control loops actually impose.

Blockchain and decentralized coordination

Where a shared, tamper-evident record is worth its cost, and where it is not.

Satellite and drone edge coordination

Coordination when connectivity is intermittent and nodes move, including satellite-edge and aerial platforms.

Digital twins from hybrid clouds

Delivering twin fidelity from a mix of on-premise and cloud resources without breaking real-time guarantees.

Other thrusts

Most projects cut across two or three of them.

Smart grid cybersecurity and resilience AI and agentic systems for cyber-physical control Next-generation optical and 6G transport Hardware security and high performance computing Connected transportation, health, and infrastructure Nuclear energy and security