Performance Improvement of Linux CPU Scheduler Using Policy Gradient Reinforcement Learning for Android Smartphones

Abstract

The Energy Aware Scheduler (EAS) was developed and applied to the Linux kernel of recent Android smartphones in order to exploit the ARM big.LITTLE processing architecture efficiently. EAS organizes CPU hardware information into Energy Model which are used to improve CPU scheduling performance. In particular, it reduces power consumption and improves process scheduling performance. However, EAS has limitations in improving CPU scheduling performance, because the Energy Model configures the CPU hardware information to fixed values, which does not reflect the characteristics of running tasks, such as the workload changes and the transition between running state and sleep state. To solve this problem, this paper introduces the Learning Energy Aware Scheduler (Learning EAS). The Learning EAS adjusts the TARGET_LOAD used to set the CPU frequency and the sched_migration_cost used as the task migration criteria according to the characteristics of the running task through the policy gradient reinforcement learning. In LG G8 ThinQ, Learning EAS improved power consumption by 2.3%-5.7%, hackbench results for process scheduling performance by 2.8%-25.5%, applications entry time by 4.4%-6.1%, and applications entry time under high CPU workload by 9.6%-12.5%, respectively compared with EAS. This paper also showed that the Learning EAS is scalable by applying the Learning EAS to highend and low-end chipset platforms of Qualcomm.Inc and MediaTek.Inc and improving power consumption by 2.8%-7.8%, application entry time by 2.2%-7.2%, respectively compared with EAS. Finally, this paper showed that the performance of CPU scheduling is improved gradually by the repetition of reinforcement learning. INDEX TERMS ARM big.LITTLE processing architecture, energy aware scheduler, process scheduler, CPU frequency governor, reinforcement learning, policy gradient, neural network, power consumption.

A Survey of Performance Optimization for Mobile Applications

“…Tseng et al [214] adapted the allocation of CPU resources to applications based on their delay-sensitivity. Further approaches adjust the frequency and voltage of devices (Dynamic Voltage and Frequency Scaling) [212], [213], CPU frequency [218] or the number of cores [216]. Muhuri et al [217] considered linguistic feedback from users to adapt CPU frequency accordingly.…”

“…Hecht et al [51] improved memory as well as user interface performance by correcting code smells. The approach of Han et al [218] on CPU scheduling could not only reduce energy consumption but also application launch time. Hsiu et al [215] reduced application response time by scheduling computing resources for energy reduction.…”

STUN: Reinforcement-Learning-Based Optimization of Kernel Scheduler Parameters for Static Workload Performance

“…In addition, studies have being addressed to improve the performance of Android scheduler. In [10], Learning EAS, a policy gradient reinforcement learning method for the Android smartphone scheduler EAS, was proposed. Learning EAS is applied on the characteristics of the running task, and adjusts the TARGET_LOAD and sched_migration_cost to improve the scheduler performance.…”