A Survey on Lightweight Semantic Communication for Resource-Constrained Internet Things: Technologies, Applications, and Challenges

Siyin Dai

doi:10.54691/44dzht34

Authors

Siyin Dai Nanjing University of Posts and Telecommunications, Nanjing, 210023, Jiangsu, China

DOI:

https://doi.org/10.54691/44dzht34

Keywords:

Resource-constrained IoT; Semantic communication; Lightweight technologies.

Abstract

Terminal devices in the Resource-Constrained Internet of Things (RC-IoT) generally face multiple limitations in computing power, memory, bandwidth, and energy consumption, making it challenging to directly deploy semantic communication systems based on large-scale deep learning models. This paper presents a systematic survey on lightweight semantic communication research tailored for RC-IoT, establishing a unified classification and evaluation framework that encompasses three core technological categories: (1) Model compression (e.g., pruning, quantization, distillation); (2) Codec and lightweight architecture optimization (e.g., edge-side encoding, compressed sensing, distributed inference); (3) Dynamic resource allocation (e.g., event-triggered mechanisms, Value-of-Information (VoI) prioritization, deep reinforcement learning-based scheduling). A comparative analysis of representative approaches is conducted using metrics (BLEU, FID, mIoU, mAP, PSNR, bpp, latency, and energy consumption). Furthermore, adaptation strategies and engineering challenges are explored in three representative application scenarios: industrial IoT, healthcare, and smart homes. Finally, the study highlights current research gaps in robustness, privacy-performance trade-offs, cross-device semantic consistency, and standardization/reproducibility, while proposing future directions to facilitate the practical deployment of semantic communication in RC-IoT. This work aims to provide actionable insights for advancing semantic communication systems in resource-limited IoT environments.

Downloads

Download data is not yet available.

References

[1] X. Yu, D. Li, N. Zhang, and X. Shen, “A novel lightweight joint source-channel coding design in semantic communications,” IEEE Internet of Things J., vol. 12, no. 11, pp. 18447–18450, Jun. 2025.

[2] Y. Huang, B. Chen, J. Zhang, Q. Han, and S.-T. Xia, “Compressive sensing based asymmetric semantic image compression for resource-constrained IoT system,” in Proc. DAC, San Francisco, CA, USA, Jul. 2022, pp. 877–882.

[3] H. Xie and Z. Qin, “A lite distributed semantic communication system for internet of things,” IEEE J. Sel. Areas Commun., vol. 39, no. 1, pp. 142–153, Nov. 2021.

[4] B. Xie, Y. Wu, Y. Shi, D. W. K. Ng, and W. Zhang, "Communication-efficient framework for distributed image semantic wireless transmission," *IEEE Internet Things J.*, vol. 10, no. 24, pp. 22555–22567, 15 Dec. 2023.

[5] L. Yan, Z. Qin, R. Zhang, Y. Li, and G. Y. Li, "Resource allocation for text semantic communications," IEEE Wireless Commun. Lett., vol. 11, no. 7, pp. 1394-1398, July 2022

[6] E. Grassucci, G. Pignata, G. Cicchetti, and D. Comminiello, “Lightweight Diffusion Models for Resource-Constrained Semantic Communication,” IEEE Wireless Commun. Lett., to be published, DOI: 10.1109/LWC.2025.3578724.

[7] E. Abu-Helalah, J. Serra, and J. Perez-Romero, “On Splitting Lightweight Semantic Image Segmentation for Wireless Communications,” arXiv preprint arXiv:2507.14199v1, Jul. 2025.

[8] B. Chatterjee, N. Cao, A. Raychowdhury, and S. Sen, "Context-Aware Intelligence in Resource-Constrained IoT Nodes: Opportunities and Challenges," IEEE Des. Test, vol. 36, no. 2, pp. 7-40, Mar./Apr. 2019, doi: 10.1109/MDAT.2019.2899334.

[9] Y. Shao, Q. Cao, and D. Gündüz, "A theory of semantic communication," IEEE Trans. Mobile Comput., vol. 23, no. 12, pp. 12211–12234, Dec. 2024.

[10] J. Peng, H. Xing, Y. Li, L. Feng, L. Xu, and X. Lei, “Task-Oriented Multi-User Semantic Communication with Lightweight Semantic Encoder and Fast Training for Resource-Constrained Terminal Devices,” IEEE Wireless Commun. Lett., vol. 13, no. 9, pp. 2427–2431, Sep. 2024.

[11] H. Xie, Z. Qin, G. Y. Li, and B. H. Juang, "Deep Learning Enabled Semantic Communication Systems," IEEE Transactions on Signal Processing, vol. 69, pp. 2663–2675, 2021.

[12] C. Liu, Y. Zhou, Y. Chen, and S.-H. Yang, ‘‘Knowledge distillation based semantic communications for multiple users,’’ IEEE Trans. Wireless Commun., Dec. 2023.

[13] H. Xing, H. Ma, Z. Xiao, X. Wang, B. Zhao, S. Luo, L. Feng, and L. Xu, “On ECG signal classification: An NAS-empowered semantic communication system,” in Proc. IEEE 22nd Int. Conf. Trust, Secur. Privacy Comput. Commun., Exeter, U.K., 2023, pp. 470–476.

[14] G. Ma, H. Tong, N. Yang, and C. Yin, “Attention-based UNet enabled lightweight image semantic communication system over Internet of Things,” in Proc. IEEE Wireless Communications and Networking Conference (WCNC), 2024, pp. 1–6.

[15] L. Wang, W. Wu, F. Zhou, Z. Yang, Z. Qin, and Q. Wu, "Adaptive resource allocation for semantic communication networks," IEEE Transactions on Communications, vol. 72, no. 11, pp.6900-6916, 2024.

[16] F. Jiang, S. Tu, L. Dong, K. Wang, K. Yang, R. Liu, C. Pan, and J. Wang, “Lightweight vision model-based multi-user semantic communication systems,” arXiv preprint arXiv:2502.16424v1, Feb. 2025.

[17] M. Kountouris and N. Pappas, "Semantics-Empowered Communication for Networked Intelligent Systems,"arXiv preprint arXiv:2007.11579v3, Mar.2021

[18] K. Khatiwada, J. Hopper, J. Cheatham, A. Joshi, and S. Baidya, "Large Language Models in the IoT Ecosystem - A Survey on Security Challenges and Applications,"arXiv preprint arXiv:2502.17586v1, May. 2025.