Sim-to-Real Transfer in Multi-agent Reinforcement Networking for Federated Edge Computing
This work addresses the challenge of efficient prototyping and deployment for federated edge computing networks, though it appears incremental as it builds on existing frameworks with new extensions.
The paper tackles the problem of bridging the simulation-to-reality gap in multi-hop federated learning systems by introducing FedEdge simulator, which uses trace-based channel modeling and dynamic link scheduling to achieve high fidelity, as demonstrated in initial experiments showing superior sim-to-real transfer performance.
Federated Learning (FL) over wireless multi-hop edge computing networks, i.e., multi-hop FL, is a cost-effective distributed on-device deep learning paradigm. This paper presents FedEdge simulator, a high-fidelity Linux-based simulator, which enables fast prototyping, sim-to-real code, and knowledge transfer for multi-hop FL systems. FedEdge simulator is built on top of the hardware-oriented FedEdge experimental framework with a new extension of the realistic physical layer emulator. This emulator exploits trace-based channel modeling and dynamic link scheduling to minimize the reality gap between the simulator and the physical testbed. Our initial experiments demonstrate the high fidelity of the FedEdge simulator and its superior performance on sim-to-real knowledge transfer in reinforcement learning-optimized multi-hop FL.