Latency, Security, and Resource Optimization in Serverless AI/ML: A Comparative Review of Healthcare and Edge-Cloud Solutions

  • Unique Paper ID: 198672
  • Volume: 12
  • Issue: 11
  • PageNo: 13285-13294
  • Abstract:
  • Serverless architectures greatly influence the devel- opment and deployment of AI/ML solutions. Nevertheless, there exist a number of issues including increased latency, resource unpredictability, and security tool deployment difficulties. I went through 15 recent papers (2021-2025) on FaaS, there are 3 main segments which we can observe – Pure cloud-native FaaS, FaaS on the edge and Fuzzy Edge (FaaS that has some cloud involvement as well). There is a lot of focus on improving resource usage with some strong numbers – 25% to 50% latency improvements when using reinforcement learning. Edge security is mostly hit or miss. Fuzzy HIPAA compliance is mostly theoretical and has very little practical value. After surveying the many approaches that have tackled these issues in other studies, a striking gap emerges: there is no unified framework for applying latency-tuning heuristics, for automatically enforcing compliance checks, and for migrating applications between edge and cloud platforms. Optimizations that affect performance on edge platforms tend to remain siloed and tackled on a case-by- case basis, as opposed to developing a more holistic perspective for tackling issues of latency, security, and flexibility all at once.

Copyright & License

Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{198672,
        author = {RATNADEEPIKA MOSA and SHREYA HANDE and AAYUSHI RAMANI and DOLLY YADAV and Dr. Asha Durafe},
        title = {Latency, Security, and Resource Optimization in Serverless AI/ML: A Comparative Review of Healthcare and Edge-Cloud Solutions},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {13285-13294},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198672},
        abstract = {Serverless architectures greatly influence the devel- opment and deployment of AI/ML solutions. Nevertheless, there exist a number of issues including increased latency, resource unpredictability, and security tool deployment difficulties. I went through 15 recent papers (2021-2025) on FaaS, there are 3 main segments which we can observe – Pure cloud-native FaaS, FaaS on the edge and Fuzzy Edge (FaaS that has some cloud involvement as well). There is a lot of focus on improving resource usage with some strong numbers – 25% to 50% latency improvements when using reinforcement learning. Edge security is mostly hit or miss. Fuzzy HIPAA compliance is mostly theoretical and has very little practical value. After surveying the many approaches that have tackled these issues in other studies, a striking gap emerges: there is no unified framework for applying latency-tuning heuristics, for automatically enforcing compliance checks, and for migrating applications between edge and cloud platforms. Optimizations that affect performance on edge platforms tend to remain siloed and tackled on a case-by- case basis, as opposed to developing a more holistic perspective for tackling issues of latency, security, and flexibility all at once.},
        keywords = {Serverless computing, function-as-a-service, ma- chine learning inference, edge computing, healthcare systems, resource optimization, systematic review},
        month = {April},
        }

Cite This Article

MOSA, R., & HANDE, S., & RAMANI, A., & YADAV, D., & Durafe, D. A. (2026). Latency, Security, and Resource Optimization in Serverless AI/ML: A Comparative Review of Healthcare and Edge-Cloud Solutions. International Journal of Innovative Research in Technology (IJIRT), 12(11), 13285–13294.

Related Articles