Energy-performance management in battery powered reconfigurable processors for standalone IoT systems

Reconfigurable processors are gaining more attention in battery powered portable platforms like IoTs. As the FPGA based reconfigurable processors are power hungry and the energy source is limited in battery powered system, energy management is vital for such systems. This paper addresses an energy-performance management method in battery powered reconfigurable processors for standalone IoT systems. It considers battery characteristics and nonlinearities to select the best set of task types with respect to energy-performance management policies while satisfying area and energy consumption constraints in different situations. The proposed method decides based on battery level and rate of discharge to adopt two different strategies: (1) energy-performance trade-off, (2) energy minimization. The proposed method benefits from three tools to reduce the power consumption: (1) reducing the total number of performed reconfiguration during the battery life, (2) using battery-ware scheduling, (3) reducing occupied resources. The results show that the energy-performance management system extends battery lifetime by 34% in energy minimizing scenario. Moreover, it boosts the average performance by 31% while extending the battery lifetime by 25% in the complete discharging scenario. In the situation that the battery is charging, the energy-performance management system has achieved an increment of 74% in performance compared to (3).