Resource Allocation for Green Probabilistic Semantic Communication with Rate Splitting

TL;DR

This work addresses energy-efficient design for a probabilistic semantic communication (PSC) system in a multiuser downlink setting using rate-splitting multiple access (RSMA). It introduces semantic compression ratio (SCR) to quantify the tradeoff between computation and communication overhead and jointly optimizes power, computation capacity, and SCR within an RSMA framework, with the objective of maximizing energy efficiency $EE$ defined as $EE=\frac{4RE(M+\sum_{i=1}^K k'_i)}{\sum_{i=0}^K (E_{cpi}+E_{cmi})+E_0}$, where $E_{cpi}=\xi l_{cp}(\Omega_i) f_i^2$ and $l_{cm}(\Omega)=2RE(2-\Omega)$, subject to semantic accuracy and latency constraints. The method combines a PSC-based multiuser semantic representation with a downlink RSMA transmission model, and uses training-based SCRs plus gradient-descent optimization to allocate power and compute resources. Key contributions include (i) extending PSC to multiuser RSMA, (ii) introducing SCR and its compression-round framework, and (iii) formulating and solving a joint computation-communication EE optimization under semantic constraints. Simulation results demonstrate notable EE gains over non-compression and imperfect-compression baselines, highlighting the practical potential for green semantic communication systems.

Abstract

In this paper, the energy efficient design for probabilistic semantic communication (PSC) system with rate splitting multiple access (RSMA) is investigated. Basic principles are first reviewed to show how the PSC system works to extract, compress and transmit the semantic information in a task-oriented transmission. Subsequently, the process of how multiuser semantic information can be represented, compressed and transmitted with RSMA is presented, during which the semantic compression ratio (SCR) is introduced to directly measure the computation overhead in a transmission task, and communication overhead is indirectly described as well. Hence, the problem of wireless resource allocation jointly considering the computation and communication consumption for the PSC system with RSMA is investigated. Both conventional wireless resource constraints and unique constraints on semantic communication are considered to maximize the energy efficiency (EE). Simulation results verify the effectiveness of the proposed scheme.

Figures (4)

• Figure 1: A schematic diagram of PSC model
• Figure 2: Multiuser semantic communication system based on PSC
• Figure 3: Mapping relations between $\Omega$ and $l_{cp}(\Omega)$/$l_{cm}(\Omega)$
• Figure 4: Energy efficiency vs. bandwidth of the BS