Energy-Aware Service Offloading for Semantic Communications in Wireless Networks

TL;DR

This work tackles energy-efficient semantic communication in heterogeneous wireless networks by jointly optimizing user-edge association, semantic extraction ratio, and local/edge CPU frequencies under QoS and delay constraints. It introduces an energy-minimization framework, relaxes a challenging MINLP to a convex geometric programming problem, and leverages a DL autoencoder/classifier to perform semantic tasks on MNIST data. The proposed sub-optimal solution outperforms baseline association strategies in total energy consumption, with transmission-energy effects dominating under various QoS/delay settings. Practically, this approach enables smarter offloading decisions for AI-enabled applications in 6G-era networks, balancing computation and communication costs while maintaining semantic accuracy.

Abstract

Today, wireless networks are becoming responsible for serving intelligent applications, such as extended reality and metaverse, holographic telepresence, autonomous transportation, and collaborative robots. Although current fifth-generation (5G) networks can provide high data rates in terms of Gigabytes/second, they cannot cope with the high demands of the aforementioned applications, especially in terms of the size of the high-quality live videos and images that need to be communicated in real-time. Therefore, with the help of artificial intelligence (AI)-based future sixth-generation (6G) networks, the semantic communication concept can provide the services demanded by these applications. Unlike Shannon's classical information theory, semantic communication urges the use of the semantics (meaningful contents) of the data in designing more efficient data communication schemes. Hence, in this paper, we model semantic communication as an energy minimization framework in heterogeneous wireless networks with respect to delay and quality-of-service constraints. Then, we propose a sub-optimal solution to the NP-hard combinatorial mixed-integer nonlinear programming problem (MINLP) by utilizing efficient techniques such as discrete optimization variables' relaxation. In addition, AI-based autoencoder and classifier are trained and deployed to perform semantic extraction, reconstruction, and classification services. Finally, we compare our proposed sub-optimal solution with different state-of-the-art methods, and the obtained results demonstrate its superiority.

Figures (6)

• Figure 1: System Model
• Figure 2: Classification accuracy of reconstructed images by trained autoencoders with variable output size $\theta$.
• Figure 3: Classification accuracy of reconstructed images by our autoencoder with $\theta = 0.5 (\times 28 \times 28)$ and variable semantic extraction ratio $\delta_{un}$.
• Figure 4: Average computation time of semantic extraction and selection $t_{un}^{comp_u}$ at the user side, and reconstruction and classification $t_{un}^{comp_e}$ at the edge side.
• Figure 5: Total system energy consumption with variable threshold $T^{max}$