Implementation of Dynamic Voltage Frequency Scaling (DVFS) in Ubiquitous Processors Using AI / Machine Learning Techniques

Abstract

This thesis embodies the results of research carried out with an aim to achieve power optimization of a portable embedded system via Machine Learning (ML) model. Real Time embedded systems are highly complex due to interactions and interdependencies between various hardware/software units and policies of the processors with applications running on it. To deal with fluctuating workloads and subsequent tasks, smart adaptability of supply clock and voltage is required in order to optimize power without compromising on the performance. This is done using Dynamic Voltage and Frequency Scaling (DVFS) technique. An improved version of DVFS is proposed in this work which treats it as a recurrent problem with an aim to capture the intricate dependencies amongst various factors influencing the operation. This work has employed application independent- Radial Basis Neural Network to generate series of predicted frequencies for current workload of the processor, followed by sequence to sequence LSTM based encoder decoder model using Attention to decide if the frequency generated by the ML model is optimum from power conservation point of view. The proposed model predicts the workload and then compares the predicted frequency to the critical value or deadline of the current task pertaining to the application running. The experiments were conducted on a single core processor on which three benchmark applications were run, and promising prediction accuracy rates were obtained without incurring degradation of critical performance parameters.