EcoPull: Sustainable IoT Image Retrieval Empowered by TinyML Models
Abstract: This paper introduces EcoPull, a sustainable Internet of Things (IoT) framework empowered by tiny machine learning (TinyML) models for fetching images from wireless visual sensor networks. Two types of learnable TinyML models are installed in the IoT devices: i) a behavior model and ii) an image compressor model. The first filters out irrelevant images for the current task, reducing unnecessary transmission and resource competition among the devices. The second allows IoT devices to communicate with the receiver via latent representations of images, reducing communication bandwidth usage. However, integrating learnable modules into IoT devices comes at the cost of increased energy consumption due to inference. The numerical results show that the proposed framework can save > 70% energy compared to the baseline while maintaining the quality of the retrieved images at the ES.
- K. Sheth et al., “A taxonomy of AI techniques for 6G communication networks,” Comput. Commun., vol. 161, pp. 279–303, 2020.
- E. C. Strinati et al., “6G networks: Beyond shannon towards semantic and goal-oriented communications,” Comput. Netw., vol. 190, p. 107930, 2021.
- J. Lin et al., “MCUNet: Tiny deep learning on IoT devices,” Advances Neural Inf. Proc. Syst., vol. 33, pp. 11 711–11 722, 2020.
- J. Shiraishi et al., “Tinyairnet: Tinyml model transmission for energy-efficient wireless iot image retrieval,” arXiv preprint arXiv:2311.04788, 2023.
- F. Mentzer et al., “High-fidelity generative image compression,” Adv. Neural Inf. Process. Syst., vol. 33, pp. 11 913–11 924, 2020.
- N. Körber et al., “Tiny generative image compression for bandwidth-constrained sensor applications,” in 2021 20th IEEE Int. Conf. Mach. Learn. Appl. (ICMLA). IEEE, 2021, pp. 564–569.
- K. Huang et al., “Semantic data sourcing for 6G edge intelligence,” IEEE Commun. Mag., vol. 61, no. 12, pp. 70–76, 2023.
- A. Ramesh et al., “Hierarchical text-conditional image generation with clip latents,” arXiv preprint arXiv:2204.06125, vol. 1, no. 2, p. 3, 2022.
- M. Thorsager et al., “Generative network layer for communication systems with artificial intelligence,” IEEE Netw. Lett., 2024.
- X. Huang et al., “Federated learning-empowered AI-generated content in wireless networks,” IEEE Netw., 2024.
- J. Wen et al., “From generative AI to generative internet of things: Fundamentals, framework, and outlooks,” arXiv preprint arXiv:2310.18382, 2023.
- H. Du et al., “Generative AI-aided joint training-free secure semantic communications via multi-modal prompts,” in ICASSP 2024-2024 IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP). IEEE, 2024, pp. 12 896–12 900.
- S. Barbarossa et al., “Semantic communications based on adaptive generative models and information bottleneck,” IEEE Commun. Mag., vol. 61, no. 11, pp. 36–41, 2023.
- B. Moons et al., “Minimum energy quantized neural networks,” in Proc. 2017 51st Asilomar Conf. Signals, Syst., Comput. IEEE, 2017, pp. 1921–1925.
- M. Heusel et al., “GANs trained by a two time-scale update rule converge to a local Nash equilibrium,” Adv. neural inf. process. syst., vol. 30, 2017.
- F. Vázquez-Gallego et al., “Modeling and analysis of reservation frame slotted-aloha in wireless machine-to-machine area networks for data collection,” Sensors, vol. 15, no. 2, pp. 3911–3931, 2015.
- K. Xu et al., “EtinyNet: extremely tiny network for TinyML,” in Proc. AAAI conf. artif. intell., vol. 36, no. 4, 2022, pp. 4628–4636.
- T.-Y. Lin et al., “Microsoft COCO: Common objects in context,” in Comput. Vision–ECCV 2014: 13th Eur. Conf., Zurich, Switzerland, Sep. 6-12, 2014, Proc., Part V 13. Springer, 2014, pp. 740–755.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.