Federated Learning Meets Random Access: Energy-Efficient Uplink Resource Allocation

TL;DR

This paper proposes energy-efficient uplink resource allocation strategies for wireless networks supporting federated learning and random access, optimizing energy use while meeting latency and throughput constraints.

Contribution

It introduces close-to-optimal solutions for joint resource allocation in systems with federated learning and random access, demonstrating significant energy savings.

Findings

ALOHA achieves up to 48% lower energy consumption with FL traffic.

Slotted-ALOHA is more efficient when RA traffic dominates, reducing energy use by 6%.

Proposed solutions effectively balance energy efficiency with system constraints.

Abstract

Artificial intelligence-generated traffic is changing the shape of wireless networks. Specifically, as the amount of data generated to train machine learning models is massive, network resources must be carefully allocated to continue supporting standard applications. In this paper, we tackle the problem of allocating radio resources for two sets of concurrent devices communicating in uplink with a gateway over the same bandwidth. A set of devices performs federated learning (FL), and accesses the medium in FDMA, uploading periodically large models. The other set is throughput-oriented and accesses the medium via random access (RA), either with ALOHA or slotted-ALOHA protocols. We derive close-to-optimal solutions to the non-convex problem of minimizing the system energy consumption subject to FL latency and RA throughput constraints. Our solutions show that ALOHA can sustain high FL efficiency, yielding up to 48% lower consumption when the system is dominated by FL traffic. On the other hand, slotted-ALOHA becomes more efficient when RA traffic dominates, yielding 6% lower consumption.