RL-Driven Semantic Compression Model Selection and Resource Allocation in Semantic Communication Systems

2025-06-23

AI Summary

In multi-user semantic communication systems, heterogeneous user computational/communication capabilities and requirements impede the joint optimization of semantic accuracy, latency, and energy consumption. To address this, we propose a Proximal Policy Optimization (PPO)-based framework for semantic compression model selection and joint resource allocation. Our approach innovatively introduces the Rate-Distortion Efficiency (RDE) metric to jointly quantify semantic reconstruction quality and communication efficiency. Under non-convex constraints, the framework enables dynamic, adaptive decision-making for co-optimizing multiple semantic models, bandwidth, and transmit power. Experimental results demonstrate that our method significantly outperforms multiple baseline strategies in overall system efficiency—achieving improvements in semantic fidelity, latency reduction, and energy savings—while exhibiting strong generalizability, scalability, and practical deployability.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Learning on the Edge & Model Compression
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Semantic communication (SemCom) is an emerging paradigm that leverages semantic-level understanding to improve communication efficiency, particularly in resource-constrained scenarios. However, existing SemCom systems often overlook diverse computational and communication capabilities and requirements among different users. Motivated by the need to adaptively balance semantic accuracy, latency, and energy consumption, this paper presents a reinforcement learning (RL)-driven framework for semantic compression model (SCM) selection and resource allocation in multi-user SemCom systems. To address the challenges of balancing image reconstruction quality and communication performance, a system-level optimization metric called Rate-Distortion Efficiency (RDE) has been defined. The framework considers multiple SCMs with varying complexity and resource requirements. A proximal policy optimization (PPO)-based RL approach is developed to dynamically select SCMs and allocate bandwidth and power under non-convex constraints. Simulations demonstrate that the proposed method outperforms several baseline strategies. This paper also discusses the generalization ability, computational complexity, scalability, and practical implications of the framework for real-world SemCom systems.

Problem

• Adaptively balance semantic accuracy, latency, and energy consumption
• Optimize image reconstruction quality and communication performance
• Dynamically select models and allocate bandwidth and power

Innovation

• RL-driven framework for SCM selection
• Defines Rate-Distortion Efficiency metric
• PPO-based dynamic resource allocation