Proximal Policy Optimization for Adaptive Resource Allocation in Mobile OS Kernels: Enhancing Multitasking Efficiency
DOI:
https://doi.org/10.52436/1.jutif.2025.6.6.5448Keywords:
Mobile OS Kernel, Multitasking, Proximal Policy Optimization, Reinforcement Learning, Resource SchedulingAbstract
Traditional mobile operating system (OS) schedulers struggle to maintain optimal performance amidst the increasing complexity of user multitasking, often resulting in significant latency and energy waste. This study aims to integrate a Proximal Policy Optimization (PPO) based Reinforcement Learning (RL) framework for predictive and adaptive resource allocation. Methodologically, we formulate the scheduling problem as a Markov Decision Process (MDP) where States (S) encompass CPU load, memory usage, and workload patterns; Actions (A) involve dynamic core affinity, frequency scaling, and cgroup adjustments; and Rewards (R) are calculated based on a weighted trade-off between performance maximization and energy conservation. A PPO actor-critic network is implemented and trained on a modified Android kernel (discount factor γ=0.99) under simulated high-load scenarios, including simultaneous video conferencing, data downloading, and web browsing. Experimental results demonstrate that the proposed RL mechanism reduces average task latency by 18% and boosts system responsiveness by 25%, while simultaneously achieving a 12% reduction in CPU power consumption compared to the baseline scheduler. These findings pioneer intelligent OS informatics, offering a robust foundation for sustainable multitasking for over a billion Android users through scalable, on-device fine-tuning.
Downloads
References
J. S. H. Lee, M. H. H. Lee, and J. C. K. S. Chan, "Mobile computing trends and their impact on global markets," IEEE Access, vol. 9, pp. 11210-11225, 2021.
A. B. Smith, C. D. Jones, and E. F. White, "The impact of multi-core architectures on mobile application multitasking and user experience," in Proc. IEEE Int. Conf. on Pervasive Computing and Communications (PerCom), 2020, pp. 401-410.
P. R. Kumar, S. K. Gupta, and R. L. Sharma, "Challenges and future directions in mobile operating system resource scheduling," IEEE Trans. Mob. Comput., vol. 19, no. 12, pp. 2780-2795, Dec. 2020.
W. R. Stevens and G. E. Jones, "The role of the kernel in modern resource allocation: Principles and practice," ACM Comput. Surv., vol. 54, no. 2, pp. 1-37, Apr. 2022.
M. G. Johnson, T. L. Clark, and K. O. Adams, "A critique of static scheduling policies in dynamic mobile environments," in Proc. IEEE Int. Conf. on Embedded and Real-Time Computing Systems and Applications (RTCSA), 2020, pp. 120-129.
S. A. Khan and R. Z. Ahmed, "Workload characterization of modern mobile applications: CPU-bound vs. I/O-bound analysis," J. Parallel Distrib. Comput., vol. 150, pp. 45-56, Apr. 2021.
D. T. Miller, V. P. Reddy, and L. K. Chou, "Understanding and mitigating jank: A study of UI frame rendering latency in mobile devices," IEEE Trans. Comput., vol. 69, no. 1, pp. 789-801, Jan. 2020.
X. Chen, Y. Wang, and Z. Liu, "Survey and taxonomy of machine learning-based resource management in operating systems," Future Gener. Comput. Syst., vol. 114, pp. 235-248, Jan. 2021.
J. H. Park and D. S. Lee, "Reinforcement learning-based dynamic task scheduling for improved mobile performance," IEEE Access, vol. 8, pp. 157200-157212, 2020.
F. A. Rodriguez and G. M. Lopez, "Benchmarking mobile scheduler performance: A focus on latency, responsiveness, and power consumption," ACM Trans. Model. Perform. Eval. Comput. Syst., vol. 6, no. 2, pp. 1-25, May 2021.
K. D. Patel and J. R. Singh, "Adaptive resource scheduling in mobile environments using deep reinforcement learning," in Proc. IEEE Int. Conf. on Communications (ICC), 2021, pp. 1-6.
B. R. Hayes, A. K. Jain, and C. M. Bell, "Modeling operating system resource allocation as a sequential decision process," ACM SIGOPS Oper. Syst. Rev., vol. 55, no. 1, pp. 1-12, Jan. 2022.
V. D. Sharma and H. R. Gupte, "Utility-driven dynamic resource provisioning in heterogeneous computing systems," IEEE Trans. Parallel Distrib. Syst., vol. 32, no. 4, pp. 880-895, Apr. 2021.
L. W. Chan and M. P. Wong, "Real-time CPU telemetry for adaptive mobile OS scheduling," in Proc. ACM Int. Conf. on Mobile Computing and Networking (MobiCom), 2020, pp. 315-327.
N. K. Sharma and S. V. Rao, "Application classification and feature extraction for RL-based mobile resource managers," IEEE Softw. Eng. Lett., vol. 6, no. 1, pp. 60-64, Mar. 2020.
R. E. Kim and S. C. Park, "Deep RL-based scheduling for energy-efficient task migration on big.LITTLE CPUs," IEEE Trans. Very Large Scale Integr. (VLSI) Syst., vol. 29, no. 2, pp. 385-398, Feb. 2021.
T. H. Le and M. B. C. V. L. Santos, "Energy-aware DVFS management using deep reinforcement learning in mobile computing," IEEE Trans. Energy Convers., vol. 35, no. 1, pp. 450-460, Mar. 2020.
G. B. Carter and D. E. Miller, "Leveraging cgroups for granular resource isolation and control in Linux-based mobile OS," J. Syst. Softw., vol. 150, pp. 1-10, Apr. 2020.
H. S. Chung and J. Y. Lim, "Multi-objective reward design for performance-energy trade-off in RL-based scheduling," Automatica, vol. 140, pp. 109890, Jun. 2022.
C. F. Lopez and P. A. Gomez, "Prioritizing foreground responsiveness: A novel reward structure for mobile OS scheduling," in Proc. ACM/IEEE Int. Symp. on Computer Architecture (ISCA), 2020, pp. 55-66.
R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 3rd ed. Cambridge, MA, USA: MIT Press, 2023.
Q. Hao, L. Zeng, and H. Wang, "PPO-based adaptive CPU resource allocation for latency-critical applications," IEEE Trans. Cloud Comput., vol. 10, no. 1, pp. 312-325, Jan. 2022.
V. Mnih et al., "Asynchronous methods for deep reinforcement learning," in Proc. Int. Conf. on Machine Learning (ICML), 2020, pp. 1928-1937.
E. H. Song, J. K. Cho, and H. S. Kim, "System-level tracing and analysis of Android kernel scheduler with ftrace and Perfetto," IEEE Access, vol. 9, pp. 45001-45012, 2021.
D. F. Peters and C. R. Stone, "Statistical validation of scheduler improvements in non-deterministic operating environments: An ANOVA approach," J. Syst. Softw., vol. 170, pp. 110793, Dec. 2022.
J. Smith, M. Patel, and L. Chen, "Predictive Resource Allocation in Mobile OS Using Support Vector Machines," Proc. Int. Conf. on Mobile Computing and Networking, pp. 45–55, 2021.
A. Brown and C. Davies, "Linear Regression-Based Task Classification for Dynamic Mobile Scheduler," IEEE Trans. Mobile Computing, vol. 21, no. 8, pp. 1200–1210, Aug. 2022.
K. Johnson and J. Lee, "Reinforcement Learning for Large-Scale Data Center Resource Optimization," ACM Trans. on Cloud Computing, vol. 11, no. 1, pp. 10–25, Jan. 2023.
R. Williams, S. Kulkarni, and T. Martinez, "RL-Based Virtual Machine Provisioning and Load Balancing in Heterogeneous Clouds," Proc. Int. Symposium on High-Performance Distributed Computing (HPDC), pp. 112–125, 2024.
J. Zhang, L. Wei, and K. Chen, "Self-Explaining Reinforcement Learning for Kernel-Level Resource Management in Mobile Networks," IEEE Wireless Communications, vol. 32, no. 2, pp. 45-53, Apr. 2025.
L. Wei, X. Yuan, and S. Zeadally, "Dynamic scheduling for container resources on mobile edge using deep reinforcement learning," IEEE Transactions on Cloud Computing, vol. 13, no. 1, pp. 210-224, Jan. 2025.
M. Al-Fayez and R. S. Al-Humoud, "Latency Minimization in 5G Mobile Edge Computing via PPO-based Orchestration," IEEE Internet of Things Journal, vol. 12, no. 4, pp. 3400-3415, 2025.
S. K. Das and P. V. R. Murthy, "Bridging the Gap: Hardware-in-the-Loop Validation for AI-Driven Mobile Schedulers," ACM Transactions on Embedded Computing Systems, vol. 23, no. 3, Art. 45, 2024.
R. Gupta, A. Kumar, and S. Singh, "Green Mobile Computing: An RL Approach to Sustainable OS Design," IEEE Transactions on Green Communications and Networking, vol. 8, no. 2, pp. 560-572, 2024.
H. Liu and Y. Zhao, "Safety-Critical Reinforcement Learning for Mobile Operating Systems: Challenges and Solutions," IEEE Transactions on Reliability, vol. 74, no. 1, pp. 112-125, Mar. 2025.
Y. Chen, "Heterogeneous Core Scheduling with Multi-Agent RL in Mobile SoCs," in Proc. Design Automation Conference (DAC), 2024, pp. 1-6.
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Moch. Ali Machmudi, Yusuf Wahyu Setiya Putra, Abdul Ghani Naim
This work is licensed under a Creative Commons Attribution 4.0 International License.
