Energy-Efficient Probabilistic Semantic Communication Over Visible Light Networks With Rate Splitting

2026-01-15

AI Summary

This work addresses energy efficiency optimization in semantic communication for resource-constrained visible light communication (VLC) systems by proposing a novel framework based on probabilistic graphical models, which uniquely integrates probabilistic semantic communication with VLC. Leveraging rate-splitting multiple access (RSMA), the framework enables joint transmission of knowledge base updates and semantic information, while simultaneously optimizing beamforming, DC bias, common rate allocation, and semantic compression ratio. The design explicitly accounts for the computational overhead induced by semantic compression alongside communication energy consumption. An efficient solution is developed using successive convex approximation (SCA) combined with the Dinkelbach algorithm. Simulation results demonstrate that the proposed scheme significantly enhances system energy efficiency and effectively balances computation and transmission costs.

Technology Category

• Machine Learning: Probabilistic Circuits and Graphical Models
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

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
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

Visible light communication (VLC) is emerging as a key technology for future wireless communication systems due to its unique physical-layer advantages over traditional radio-frequency (RF)-based systems. However, its integration with higher-layer techniques, such as semantic communication, remains underexplored. This paper investigates the energy efficiency maximization problem in a resource-constrained VLC-based probabilistic semantic communication (PSCom) system. In the considered model, light-emitting diode (LED) transmitters perform semantic compression to reduce data size, which incurs additional computation overhead. The compressed semantic information is transmitted to the users for semantic inference using a shared knowledge base that requires periodic updates to ensure synchronization. In the PSCom system, the knowledge base is represented by probabilistic graphs. To enable simultaneous transmission of both knowledge and information data, rate splitting multiple access (RSMA) is employed. The optimization problem focuses on maximizing energy efficiency by jointly optimizing transmit beamforming, direct current (DC) bias, common rate allocation, and semantic compression ratio, while accounting for both communication and computation costs. To solve this problem, an alternating optimization algorithm based on successive convex approximation (SCA) and Dinkelbach method is developed. Simulation results demonstrate the effectiveness of the proposed approach.

Problem

• Visible Light Communication
• Semantic Communication
• Energy Efficiency
• Rate Splitting
• Probabilistic Graph

Innovation

• Probabilistic Semantic Communication
• Visible Light Communication
• Rate Splitting Multiple Access
• Energy Efficiency Optimization
• Knowledge Base Synchronization