Background
The future computing infrastructure of cities may not be fixed. Public transport vehicles, autonomous cars and drones are increasingly being viewed as mobile computing platforms capable of providing services wherever demand arises.
These mobile edge platforms offer the possibility of bringing computational resources directly to users, supporting applications such as augmented reality, autonomous vehicles, environmental monitoring and emergency response.
Research Challenge
As AI applications become increasingly latency-sensitive and computationally demanding, traditional fixed cloud and edge infrastructures may struggle to provide responsive services in highly dynamic urban environments. Emerging technologies such as connected buses, trains, autonomous vehicles and drones offer the opportunity to transform mobile platforms into distributed computing resources that move throughout the city alongside users and data sources.
A key challenge is determining how AI services should be deployed, migrated and coordinated across computing resources that are themselves constantly moving. Service placement decisions must adapt to changing mobility patterns, fluctuating demand, intermittent connectivity and highly dynamic network topologies, while maintaining reliable Quality of Service (QoS).
This project investigates how AI services can be dynamically distributed across mobile edge platforms to optimise performance, resource utilisation and service availability. The research will explore challenges such as mobility-aware service placement, predictive workload migration, resource allocation, autonomous decision-making and coordination between fixed and mobile edge infrastructure.
Example application domains include autonomous vehicle ecosystems, drone-based emergency response, augmented reality services for smart tourism, mobile environmental monitoring, intelligent public transportation systems, and temporary AI infrastructure deployed during large public events or disaster scenarios. The work will involve designing and evaluating intelligent deployment strategies through simulation and experimentation.
Topics
Mobile Edge Computing; Autonomous systems; Drone computing platforms; Reinforcement learning; Service migration; Smart transportation systems
Impact
The project investigates a vision of future cities in which computing infrastructure moves alongside citizens, providing intelligent services exactly where and when they are needed.