Problem
Research questions and friction points this paper is trying to address.
user scheduling
resource allocation
MU-MIMO-OFDMA
wireless networks
throughput optimization
MAxLM: Multi-Agent Language Model-Based Scheduling and Resource Allocation in MU-MIMO-OFDMA-Enabled Wireless Networks
🤖 AI Summary
This work addresses the joint optimization of user selection and resource allocation in uplink scheduling for MU-MIMO-OFDMA wireless local area networks. It proposes a novel scheduling approach based on a multi-agent framework, which uniquely integrates a pre-trained small-scale language model (xLM) into wireless resource management. By enabling collaborative, data-driven decision-making among multiple agents, the method facilitates autonomous scheduling without explicit rule-based programming. The effectiveness of the proposed scheme is validated on the AI-enhanced WiSER platform under diverse configurations of station (STA) counts and antenna setups. Experimental results demonstrate that the approach consistently outperforms existing benchmark schemes, achieving substantial gains in uplink throughput and establishing a new paradigm for intelligent wireless access.
📝 Abstract
Wireless networks support multi-user (MU) communication with multiple-input multiple-output (MIMO) and orthogonal frequency-division multiple access (OFDMA) technologies. In the joint MU-MIMO-OFDMA-enabled transmission mode, network throughput can be significantly increased by effectively utilizing the multi-channel resources to schedule numerous wireless users/stations (STAs) simultaneously. In this paper, we study ways to optimize the user scheduling and resource allocation (SRA) for the UL scheduled access (UL-SA) of a joint MU-MIMO-OFDMA-enabled wireless local area network (WLAN). In particular, we propose a multi-agent (MA) framework that utilizes an openly available pretrained small/medium-sized Language Model (xLM) to perform SRA for the UL-SA. To facilitate autonomous SRA using our proposed technique, we introduce the AI-assisted Wireless Systems Engineering and Research (WiSER) platform. We evaluate the performance of MAxLM-optimized SRA for network scenarios with a varying number of STAs and antenna settings on the WLAN Access Point. Numerical results confirm that our proposed technique achieves higher UL-SA throughput than the benchmark techniques.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multi-Agent Language Model
MU-MIMO-OFDMA
Resource Allocation
Wireless Scheduling
AI-assisted Networking
🔎 Similar Papers
No similar papers found.
