AVAC: A Machine Learning based Adaptive RRAM Variability-Aware Controller for Edge Devices
This work addresses performance and energy efficiency issues for edge devices running dynamic applications, though it is incremental as it extends existing RRAM controllers with adaptive capabilities.
The paper tackles the problem of maintaining ideal performance in edge devices with static RRAM controllers by proposing AVAC, an adaptive controller that dynamically updates parameters using machine learning, resulting in up to 29% performance increase and 19% energy reduction compared to static controllers.
Recently, the Edge Computing paradigm has gained significant popularity both in industry and academia. Researchers now increasingly target to improve performance and reduce energy consumption of such devices. Some recent efforts focus on using emerging RRAM technologies for improving energy efficiency, thanks to their no leakage property and high integration density. As the complexity and dynamism of applications supported by such devices escalate, it has become difficult to maintain ideal performance by static RRAM controllers. Machine Learning provides a promising solution for this, and hence, this work focuses on extending such controllers to allow dynamic parameter updates. In this work we propose an Adaptive RRAM Variability-Aware Controller, AVAC, which periodically updates Wait Buffer and batch sizes using on-the-fly learning models and gradient ascent. AVAC allows Edge devices to adapt to different applications and their stages, to improve computation performance and reduce energy consumption. Simulations demonstrate that the proposed model can provide up to 29% increase in performance and 19% decrease in energy, compared to static controllers, using traces of real-life healthcare applications on a Raspberry-Pi based Edge deployment.