An Overview on Intelligent Operating Systems (iOS)

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 13 | 01 | Page :
    By

    Heena T Shaikh,

  • Kazi Kutubuddin Sayyad Liyakat,

  1. Assistant Professor, Department of Electronics and Telecommunication Engineering, Brahmdevdada Mane Institute of Technology, Solapur, Maharashtra, India
  2. Professor and Head, Department of Electronics and Telecommunication Engineering, Brahmdevdada Mane Institute of Technology, Solapur, Maharashtra, India

Abstract

The rapid convergence of artificial intelligence techniques with core operating system services is ushering in a new class of platforms—Intelligent Operating Systems (Intelligent OS)—that can anticipate, adapt, and optimize on behalf of both applications and users. This paper surveys the architectural shifts required to embed learning, reasoning, and self healing capabilities into the kernel, scheduler, memory manager, and I/O subsystems. We present a prototype framework, NeuroKernel, that augments traditional OS primitives with three tightly coupled layers: (1) a Contextual Perception Engine that continuously harvests telemetry from hardware counters, user interaction patterns, and network conditions; (2) a Decision Making Fabric that applies lightweight reinforcement learning policies to translate perception into concrete system actions; and (3) an Adaptive Enforcement Module that safely re configures resources, migrates workloads, and patches vulnerabilities in real time. Through a series of controlled experiments on heterogeneous edge cloud testbeds, we demonstrate that NeuroKernel reduces average application latency by 23 %, improves energy efficiency by 18 %, and mitigates three out of five simulated fault scenarios without human intervention. Qualitative user studies also reveal higher perceived responsiveness and trust. Our findings suggest that intelligent OS design can close the feedback loop between workload dynamics and system provisioning, moving the operating system from a static resource allocator to an autonomous performance steward.

Keywords: Operating systems, intelligence, decision-making, iOS, Contextual Perception Engine

How to cite this article:
Heena T Shaikh, Kazi Kutubuddin Sayyad Liyakat. An Overview on Intelligent Operating Systems (iOS). Journal of Operating Systems Development & Trends. 2026; 13(01):-.
How to cite this URL:
Heena T Shaikh, Kazi Kutubuddin Sayyad Liyakat. An Overview on Intelligent Operating Systems (iOS). Journal of Operating Systems Development & Trends. 2026; 13(01):-. Available from: https://journals.stmjournals.com/joosdt/article=2026/view=242357


References

  1. Alur, R., et al. (2021). Probabilistic Model Checking for Real‑Time Adaptive Systems. IEEE Transactions on Dependable and Secure Computing, 18(3), 1312‑1325.
  2. Bauer, M., et al. (2021). eBPF‑based Telemetry for Machine Learning in the Kernel. Proceedings of the USENIX Annual Technical Conference, 45‑58.
  3. Chen, L., et al. (2024). Explainable Kernel Decisions with Large Language Models. ACM Symposium on Operating Systems Principles (SOSP), 112‑124.
  4. Dwork, C., & Roth, A. (2022). The Algorithmic Foundations of Differential Privacy. Cambridge University Press.
  5. Kephart, J. O., & Chess, D. M. (2003). The Vision of Autonomic Computing. Computer, 36(1), 41‑50.
  6. Kumar, S., et al. (2020). Flicker: Reinforcement Learning for DVFS on ARM Heterogeneous Platforms. Proceedings of the International Conference on Embedded Systems, 87‑99.
  7. Lee, H., et al. (2023). CoCoOS: Co‑Designed Compiler–OS Hints for Deadline‑Critical Scheduling. EuroSys, 28(2), 247‑260.
  8. Lin, Y., & Patel, R. (2023). Model Orchestration for Kernel‑Level Machine Learning. Journal of Systems Architecture, 115, 101922.
  9. Mao, H., et al. (2016). Neural Scheduling: Learning to Schedule CPU Tasks. ICLR Workshop on Machine Learning for Systems, 1‑10.
  10. Nguyen, T., et al. (2024). Reinforcement‑Learning‑Based Job Placement in ExaScale OS. SC ’24: International Conference for High Performance Computing, Networking, Storage and Analysis, 1‑12.
  11. Russell, S., & Norvig, P. (2020). Artificial Intelligence: A Modern Approach (4th ed.). Pearson.
  12. Silva, M., & Wang, J. (2024). Morpheus: Self‑Modifying Kernels via Program Synthesis. Operating Systems Review, 58(1), 33‑48.
  13. Zhang, Y., & Gupta, R. (2022). SageOS: A Learning‑Enabled Operating System. Proceedings of the 2022 ACM Symposium on Cloud Computing, 201‑215.
Ahead of Print Subscription Review Article
Volume 13
01
Received 06/04/2026
Accepted 07/04/2026
Published 30/04/2026
Publication Time 24 Days
46

Login


My IP

PlumX Metrics