Heena T. Shaikh,
Kazi Kutubuddin Sayyad Liyakat,
- Assistant Professor, Department of Electronics and Telecommunication Engineering, Brahmdevdada Mane Institute of Technology, Solapur, Maharashtra, India
- 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 (iOS)—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 reconfigures 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 the average application latency by 23%, improves overall 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: Contextual perception engine, decision-making, intelligence, iOS, operating systems
[This article belongs to Journal of Operating Systems Development & Trends ]
References
- Cámara J, de Lemos R. Evaluation of resilience in self-adaptive systems using probabilistic model-checking. 2012 7th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS), Zurich, Switzerland. 2012. p. 53–62. doi:10.1109/SEAMS.2012.6224391.
- Joshi A, Segireddy A. Adaptive runtime security for Kubernetes using eBPF telemetry and machine learning. 2026 6th International Conference on Expert Clouds and Applications (ICOECA), Bengaluru, India. 2026; Bengaluru, India. p. 1663–1668. doi:10.1109/ICOECA68095.2026.11485567.
- Zhang Y, Kang Q, Yu WY, Gong H, Fu X, Han X, Zhong T, Ma C. Decision information meets large language models: the future of explainable operations research [preprint]. 2025. arXiv:2502.09994. doi:10.48550/arXiv.2502.09994.
- Dwork C, Roth A. The algorithmic foundations of differential privacy. Found Trends Theor Comput Sci. 2014;9(3–4):211–407. doi:10.1561/0400000042.
- Kephart JO, Chess DM. The vision of autonomic computing. Computer. 2003;36(1):41–50. doi:10.1109/MC.2003.1160055.
- Li X, Zhou T, Wang H, Lin M. Energy-efficient computation with DVFS using deep reinforcement learning for multi-task systems in edge computing. IEEE Trans Sustain Comput. 2025;10(6):1116–1127. doi:10.1109/TSUSC.2025.3593971.
- Li J, Jiang W, He Y, Yang Q, Gao A, Ha Y, Özcan E, Bai R, Cui T, Yu H. FiDRL: flexible invocation-based deep reinforcement learning for DVFS scheduling in embedded systems. IEEE Trans Comput. 2025;74(1):71–85. doi:10.1109/TC.2024.3465933.
- Zhong Z, Xu M, Rodriguez MA, Xu CZ, Buyya R. Machine learning-based orchestration of containers: a taxonomy and future directions. ACM Comput Surv. 2022;54(10s):1–35. doi:10.1145/3510415.
- Ye Z, Gao W, Hu Q, Sun P, Wang X, Luo Y, Zhang T, Wen Y. Deep learning workload scheduling in GPU datacenters: a survey. ACM Comput Surv. 2024;56(6):1–38. doi:10.1145/3638757.
- Shin DJ, Kim JJ. Deep reinforcement learning-based network routing technology for data recovery in exa-scale cloud distributed clustering systems. Appl Sci. 2021;11(18):8727. doi:10.3390/app11188727.
- Russell SJ, Norvig P. Artificial Intelligence: A Modern Approach. 4th global ed. Harlow (UK): Pearson Education Limited; 2022.
- Faruki P, Bhan R, Jain V, Bhatia S, El Madhoun N, Pamula R. A survey and evaluation of Android-based malware evasion techniques and detection frameworks. Information. 2023;14(7):374. doi:10.3390/info14070374.
- Liu X, Wang S, Ma Y, Zhang Y, Mei Q, Liu Y, Huang G. Operating systems for resource-adaptive intelligent software: challenges and opportunities. ACM Trans Internet Technol. 2021;21(2):27:1–27:19. doi:10.1145/3425866.
Journal of Operating Systems Development & Trends
| Volume | 13 | |
| Issue | 01 | |
| Received | 06/04/2026 | |
| Accepted | 07/04/2026 | |
| Published | 30/04/2026 | |
| Publication Time | 24 Days |