Edge Service Placement
Reinforcement-learning methods for latency-constrained service placement in edge-computing networks.
Research code and experiments for latency-constrained service placement in edge-computing infrastructures, developed in collaboration with Orange Gardens and CMAP in an industrial 6G research context.
The problem combines network-flow constraints, latency constraints, and computational-resource allocation. The reinforcement-learning approach aims to accelerate decision-making compared with exact integer-linear-programming formulations.
Area: edge computing, service placement, network/resource optimization.