Fuzzy-Controlled Voltage Scaling Based on Supply Current Tracking

We discuss an adaptive fuzzy logic controller to accurately and robustly predict and track supply current variations of digital processors. The proposed controller tracks supply current variations without updating any parameter during its runtime prediction. It can be used to adjust the supply voltage and clock frequency of digital processors based on workload variations when accounting for timing-constraints and other practical requirements. Additionally, we comprehensively examine the stability analysis of the closed-loop configuration containing the fuzzy controller and the digital processor model. We prove that the fuzzy controller guarantees the asymptotic stability of the closed-loop architecture. Several experiments are performed to exhibit effectiveness of the proposed fuzzy controller comparing to the other existing conventional prediction methods. The results show that the proposed controller outperforms the other existing methods.