Investigation of Q-learning applied to DVFS management of a System-on-Chip
| Autor: | Suzanne Lesecq, Julien Mottin, Anca Molnos, Diego Puschini |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Engineering
business.industry 0211 other engineering and technologies Q-learning 02 engineering and technology Energy consumption Chip 020202 computer hardware & architecture Control and Systems Engineering Application domain Embedded system 0202 electrical engineering electronic engineering information engineering Overhead (computing) State space System on a chip business Throughput (business) 021106 design practice & management |
| Zdroj: | IFAC-PapersOnLine. 49:278-284 |
| ISSN: | 2405-8963 |
| Popis: | This paper presents a new Q-learning based strategy to manage Dynamic Voltage Frequency Scaling (DVFS) on a system on chip (SoC) such that the energy consumption is reduced. We address software applications with throughput constraints. The proposed Q-learning formulation has two main advantages: it has a reduced state space to limit the overhead and it embeds a new reward function tailored for throughput-constrained applications. The DVFS manager is evaluated on a test chip executing an HMAX object recognition application. We perform an experimental investigation of the main Q-learning parameters. The results suggest that the proposed method reduces the energy consumed with up to 44% at the cost of occasionally increasing the number of throughput violations, when compared to two state-of-the-art feedback controllers that address the same application domain. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|