Resource Allocation for Semantic Aware Relay Networks using Multi-Agent Reinforcement Learning

The variety and volume of real-time video streaming services make network resources like power, frequency, and time critical to the user experience. Semantic communication, by transmitting only meaningful data, significantly reduces the load on the network, leading to faster transmission times and reduced latency-both crucial for enhancing user experience. In this paper, we develop a context-aware resource allocation framework for a semantic-aware regenerative AI-based Unmanned Aerial Vehicle (UAV) setup that accommodates both conventional and semantic communication users. Specifically, we define a semantic feature pooling mechanism, upon which a novel Quality of Experience (QoE) model is proposed. For dynamic network environments, we formulate a long-term resource allocation problem by maximizing the expected rewards. Each UAV is modeled as a learning agent, with each resource allocation solution corresponding to an action taken by the UAVs. We then develop a Multi-Agent Reinforcement Learning (MARL) framework in which each agent discovers its optimal strategy based on local observations. More specifically, we propose an agent-independent method where all agents execute a decision algorithm independently while sharing a common structure based on Q-learning. The proposed framework also facilitates intelligent traffic steering by dynamically adjusting resource distribution based on real-time context. Finally, simulation results demonstrate the effectiveness and superiority of the proposed method in terms of overall QoE.