Investigation of Q-learning applied to DVFS management of a System-on-Chip

  • Anca Molnos, Suzanne Lesecq, Julien Mottin, and Diego Puschini. Investigation of Q-learning applied to DVFS management of a System-on-Chip. In Proceedings of 4th IFAC International Conference on Intelligent Control and Automation Sciences, pages 278-284, Reims, France, 2016. doi:10.1016/j.ifacol.2016.07.126
    [BibTeX] [Abstract]

    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.

    @InProceedings{2016-06-MOLNOS,
    author = {Anca Molnos and Suzanne Lesecq and Julien Mottin and Diego Puschini},
    title = {{Investigation of Q-learning applied to DVFS management of a System-on-Chip}},
    booktitle = {{Proceedings of 4th IFAC International Conference on Intelligent Control and Automation Sciences}},
    date = {2016-06-01/2016-06-03},
    year = {2016},
    address = {Reims, France},
    pages = {278-284},
    doi = {10.1016/j.ifacol.2016.07.126},
    abstract = {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.}
    }

This entry was posted in Dissemination. Bookmark the permalink.

Comments are closed.