Energy-Adaptive Imprecise-Computation Task Allocation And Scheduling For Energy Harvesting System

The rise of energy harvesting system enables embedded devices to run in harsh environment for a long time without changing the battery in the device frequently. The available energy of system comes from the transformation of some natural resources such as solar and wind. These natural resources have many uncertainty factors, therefore, the key issue of renewable generations such as solar and wind in energy harvesting system is the uncertainty of energy availability. The characteristic of imprecise computation that accepts an approximate result when energy is limited and executes more computations yielding better results if more energy is available, can be exploited to intelligently handle the uncertainty.In this paper, we first propose an energy-efficient task allocation scheme that adaptively assigns real-time imprecise-computation tasks to individual processors with consideration of the uncertainty in renewable energy resources, in order to make the most of energy supply and minimize system energy consumption. We then present a QoS-aware task scheduling scheme that determines the optional execution cycles of tasks under the constraint of energy budget, in order to maximize system QoS. The scheduling strategy consists of two steps. The first step is to determine the execution length of optional part of the task through the analysis of the energy characteristics of task before the actual scheduling. The second step is to dynamically adapt task execution to fluctuating harvested energy at runtime.Extensive simulations were performed to validate the effectiveness of our proposed schemes. Simulation results show that our schemes can reduce system energy consumption by up to 47.5% and improve system QoS by up to 65.7% as compared to benchmarking algorithms.