Edge AI Deployment Challenges in Smart Home Devices
DOI:
https://doi.org/10.63345/sjaibt.v2.i3.205Keywords:
Smart Home Devices, Deployment Challenges, Privacy, Energy Efficiency, InteroperabilityAbstract
The integration of Edge Artificial Intelligence (Edge AI) into smart home devices represents a paradigm shift in the Internet of Things (IoT) ecosystem, enabling real-time decision-making, autonomous functionality, and personalized user experiences without relying exclusively on cloud infrastructure. While Edge AI promises advantages such as ultra-low latency, reduced network dependency, enhanced data privacy, energy efficiency, and resilience in offline environments, its deployment in smart homes is fraught with multifaceted challenges. These challenges encompass hardware limitations, constrained computational resources, high energy consumption, interoperability issues among heterogeneous devices, cybersecurity vulnerabilities, and socio-economic inequalities in adoption. Furthermore, ethical concerns surrounding data governance, transparency of AI-driven decisions, and long-term user trust continue to complicate large-scale deployment.
Downloads
References
• https://www.mdpi.com/IoT/IoT-05-00002/article_deploy/html/images/IoT-05-00002-g001.png
• Chen, Y., Xu, Z., & Wang, L. (2022). Federated learning for smart homes: Challenges, methods, and future directions. IEEE Internet of Things Journal, 9(5), 3761–3775. https://doi.org/10.1109/JIOT.2021.3104821
• Deng, S., Zhao, H., Fang, W., & Wu, Z. (2020). Edge intelligence: The confluence of edge computing and artificial intelligence. IEEE Internet of Things Journal, 7(8), 7457–7469. https://doi.org/10.1109/JIOT.2020.2979638
• Gubbi, J., Buyya, R., Marusic, S., & Palaniswami, M. (2013). Internet of Things (IoT): A vision, architectural elements, and future directions. Future Generation Computer Systems, 29(7), 1645–1660. https://doi.org/10.1016/j.future.2013.01.010
• Hao, M. C., Zhang, Y., & Wu, X. (2021). AI model compression for efficient edge deployment. ACM Computing Surveys, 54(7), 1–35. https://doi.org/10.1145/3469021
• He, Q., Chen, W., & Zhou, S. (2022). Security and privacy challenges in edge AI-enabled IoT environments. IEEE Transactions on Network and Service Management, 19(2), 1098–1112. https://doi.org/10.1109/TNSM.2021.3119823
• Kumar, A., & Singh, R. (2021). Edge AI accelerators for smart home automation: A survey of hardware architectures. Journal of Systems Architecture, 115, 102004. https://doi.org/10.1016/j.sysarc.2021.102004
• Li, Y., Qiu, J., & Zhao, F. (2022). Lightweight neural networks for on-device AI: Design, training, and deployment. Pattern Recognition, 124, 108497. https://doi.org/10.1016/j.patcog.2021.108497
• Liu, Y., Yang, C., & Jiang, S. (2019). Smart home security and privacy protection using edge AI. IEEE Access, 7, 185465–185479. https://doi.org/10.1109/ACCESS.2019.2960117
• Mahmoud, R., Yousuf, T., & Aloul, F. (2015). Internet of Things (IoT) security: Current status, challenges and prospective measures. Proceedings of the 10th International Conference for Internet Technology and Secured Transactions (ICITST), 336–341. IEEE.
• McMahan, H. B., Moore, E., Ramage, D., & Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), 1273–1282. PMLR.
• Rahman, M. A., Hossain, M. S., & Alrajeh, N. (2021). Secure and privacy-aware federated learning for smart home AI. IEEE Transactions on Industrial Informatics, 17(12), 8485–8493. https://doi.org/10.1109/TII.2021.3065132
• Sarker, I. H. (2021). Machine learning for intelligent edge computing: A survey. Internet of Things, 14, 100381. https://doi.org/10.1016/j.iot.2021.100381
• Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge computing: Vision and challenges. IEEE Internet of Things Journal, 3(5), 637–646. https://doi.org/10.1109/JIOT.2016.2579198
• Sun, Y., Ansari, N., & Yu, R. (2020). Edge AI-enabled smart homes: Architecture, challenges, and future directions. IEEE Wireless Communications, 27(4), 12–18. https://doi.org/10.1109/MWC.001.2000037
• Tang, J., Wang, Z., & Zhou, C. (2022). Resource allocation strategies for AI inference in edge-based smart homes. IEEE Transactions on Smart Grid, 13(1), 48–59. https://doi.org/10.1109/TSG.2021.3125471
• Wang, L., Xu, Z., & Chen, Y. (2021). Interoperability of AI-driven IoT devices in smart homes. Future Internet, 13(8), 206. https://doi.org/10.3390/fi13080206
• Xu, J., Guo, S., & Liang, X. (2019). Energy-efficient AI model deployment in edge environments: A survey. ACM Transactions on Internet Technology, 19(2), 1–27. https://doi.org/10.1145/3309704
• Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019). Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology, 10(2), 1–19. https://doi.org/10.1145/3298981
• Zhang, K., Zhu, Y., & Xu, X. (2023). Hybrid cloud-edge frameworks for smart home AI applications. Journal of Network and Computer Applications, 213, 103584. https://doi.org/10.1016/j.jnca.2023.103584
• Zhou, Z., Chen, X., & Zhang, E. (2021). Privacy-preserving edge intelligence for smart homes: A comprehensive survey. ACM Computing Surveys, 53(5), 1–36. https://doi.org/10.1145/3417987
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Scientific Journal of Artificial Intelligence and Blockchain Technologies
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The license allows re-users to share and adapt the work, as long as credit is given to the author and don't use it for commercial purposes.
