Energy Management for Energy Harvesting Real Time System with Dynamic Voltage Scaling

Energy harvesting has recently emerged as a feasible option to increase the operating time of battery based real time embedded systems. In this paper, we propose a scheduling algorithm that offers lesser energy consumption for battery powered dynamic real time system modeled with aperiodic tasks and energy harvesting constraints. As the harvested energy is highly dependent on the environment thus, available power/energy of storage changes over the time. The proposed approach has to decide which speed or voltage level is to be to select leading to reduction in energy overhead as well as timing overhead due to the speed switching. We further, improve the quality of service to accept more number of aperiodic tasks and improve the system performance in terms of remaining energy. Theorem is being derived to show the effectiveness our approach having lesser energy consumption as compared to existing one. The simulation results and examples illustrate that our approach can effectively reduce the overall system energy consumption and improve the system performance in terms of remaining energy as well as reduce the rejection ratio of aperiodic tasks.