The Evolution of Edge AI: A New Paradigm in Decentralized Cloud Computing

References

[1] Abate, G., Nencioni, G., & Seno, L. (2021). Security and privacy in federated learning: A survey. ACM Computing Surveys, 54(9), 1–36. https://

[2] Ali, S., Rehman, M. H., Khan, M. A., & Riaz, A. (2022). A comprehensive survey on real-time applications in edge computing. Journal of Network and Computer Applications, 204, 103399. https://

[3] Anagnostopoulos, C., Kolomvatsos, K., & Hadjiefthymiades, S. (2021). Privacy-preserving federated learning for edge intelligence: A survey. Future Generation Computer Systems, 123, 200 –220. https://

[4] Chen, Y., Wang, X., & Zhang, K. (2021). Decentralized machine learning: A review. ACM Transactions on Intelligent Systems and Technology, 12(5), 1 –35. https://

[5] Duan, Y., Li, C., Zheng, Z., & Yang, H. (2023). Blockchain-based decentralized federated learning: A survey. Information Fusion, 92, 74– 91. https://

[6] Gai, K., Qiu, M., Zhao, H., & Liu, M. (2021). Privacy-aware AI and machine learning: A survey and outlook. Future Generation Computer Systems, 117, 311 –325. https://

[7] Ghosh, U., Biswas, S., & Sengupta, S. (2022). TinyML: Machine learning on ultra-low-power embedded systems. ACM Computing Surveys, 55(6), 1–37. https://

[8] Guo, Y., Shi, W., & Zhao, H. (2022). Fog and edge computing: A review on challenges and research directions. IEEE Internet of Things Journal, 9(1), 4 –24. https://

[9] Jiang, Y., Yu, H., & Wang, Y. (2021). Swarm learning: Concept, technology, and applications. IEEE Access, 9, 41616 –41628. https://

[10] Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2021). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 38(3), 50 –60. https://

[11] Lu, Y., Huang, X., Dai, Y., Maharjan, S., & Zhang, Y. (2021). Blockchain and federated learning for privacy-preserved data sharing in industrial IoT. IEEE Transactions on Industrial Informatics, 17(6), 4119 –4127. https://

[12] Mahmoud, R., Yousuf, T., & Farag, A. (2023). Edge AI for autonomous systems: Opportunities and challenges. ACM Transactions on Embedded Computing Systems, 22(2), 1–22. https://

[13] Meng, W., Liu, Z., Zhou, Y., & Zhang, J. (2021). AI at the edge: A review on edge intelligence. ACM Computing Surveys, 54(12), 1–36. https://

[14] Minerva, R., Biru, A., & Rotondi, D. (2021). Towards edge intelligence: AI and edge computing convergence. Journal of Parallel and Distributed Computing, 152, 1 –12. https://

[15] Nguyen, D. C., Ding, M., Pathirana, P. N., & Seneviratne, A. (2022). Blockchain and AI- based solutions to combat COVID-19-like pandemics. IEEE Internet of Things Journal, 9(1), 603 –614. https://

[16] Park, S., Shin, J., & Lee, K. (2021). AI-powered IoT devices: A survey. ACM Transactions on Internet Technology, 21(4), 1 –27. https://

[17] Rausch, T., & Dustdar, S. (2021). Edge intelligence: The convergence of humans, things, and AI. IEEE Intelligent Systems, 36(3), 6–12. https://

[18] Ren, J., Yu, G., He, Y., & Lin, J. (2022). Privacy-preserving edge intelligence: Opportunities and challenges. IEEE Communications Magazine, 60(3), 24–30. https://

[19] Shrestha, A., & Mahmood, A. (2021). Review of deep learning algorithms and architectures. IEEE Access, 9, 120020 –120040. https://

[20] Singh, M., & Chatterjee, S. (2023). Decentralized computing and blockchain for smart environments: A review. Future Generation Computer Systems, 141, 1–17. https://

[21] Tan, Y., Zheng, Q., & Gao, Z. (2021). Security and efficiency in decentralized edge intelligence: A blockchain-based approach. Sensors, 21(4), 1083. https://

[22] Wang, J., Liu, Y., & Yang, J. (2022). Convergence of 6G, AI, and edge computing: Architecture, challenges, and opportunities. IEEE Network, 36(1), 58 –65. https://

[23] Xiao, Y., Zhang, N., Lou, W., & Hou, Y. T. (2021). A survey of distributed machine learning. ACM Computing Surveys, 54(5), 1– 35. https://

[24] Xu, X., Wu, Q., & Xu, L. D. (2023). Digital twins and edge intelligence: Industrial AI in smart manufacturing. IEEE Transactions on Industrial Informatics, 19(3), 2291–2300. https://

[25] Zhang, Q., Yang, L. T., Chen, Z., & Li, P. (2021). A survey on deep learning for big data. Information Fusion, 42, 146 –157. https://

@article{1708259,
      author = {Anant Mittal},
      title = {The Evolution of Edge AI: A New Paradigm in Decentralized Cloud Computing},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {8},
      number = {11},
      pages = {2185-2196},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1708259.pdf},
      abstract = {The fusion of edge computing and artificial intelligence (AI) has galvanized an emerging paradigm known as Edge AI, which transfers computational intelligence away from centralized cloud infrastructures and into decentralized edge nodes. These evolutionary changes address crucial limitations imposed on traditional cloud systems, such as high latent periods, bandwidth quotas, the concern of data privacy, and demands for real-time processing applications. Embedded simulated intelligence facilities in the edge devices then allow faster humane decisions, better human experience, and improved autonomy for various applications like smart cities, autonomous vehicles, industrial IoT, and healthcare systems. This paper discusses the technological evolution of Edge AI, analyzes the challenges of deploying intelligent systems in the edge, as well as the influence the technology has on the whole landscape of decentralized cloud computing. In presenting a picture of emerging architectures, hardware advancements, and algorithmic innovations, the ways in which Edge AI is transforming what is thought of as the computational model, as well as creating new standards for a more responsive, secure, and scalable digital future, is emphasized.},
      month = {May},
  }