Using Energy-Aware Scheduling Weather Forecast Based Harvesting for Reconfigurable Hardware

Abstract

Energy is the most limited resource for sustainable systems, especially battery-based systems, such as Wireless Sensor Network (WSN) or Cyber-Physical System (CPS) nodes. Harvesting energy from a deployed environment is proved to be a feasible method to enable a sustainable operation. Meanwhile, field-programmable gate arrays (FPGAs), which are a reconfigurable fabric, are widely used in sustainable systems. Various applications can be configured into FPGA as required. The available energy varies during the harvesting process. Therefore, configuring FPGA to match the processing requirement within the varied energy is an important issue. As opposed to the traditional scheduling methods that solely focus on reducing computational energy, we adapted a weather forecast method in studying the history data to predict the future harvested data in this study. The predicted future harvested energy was then used in energy-based scheduling. Experiment results indicate that reconfigurable hardware can save up to 50 percent energy compared to software-based execution. Using the weather forecasted scheduling method can execute 35 percent more task compared to the past-predict-future method.