MOGATS: a multi-objective genetic algorithm-based task scheduling for heterogeneous embedded systems

Abstract

Multi-objective optimisation is an unavoidable requirement in different steps of embedded systems design, including task mapping and scheduling. In this paper, a new multi-objective genetic algorithm-based task mapping and scheduling (abbreviated as MOGATS) is presented for heterogeneous embedded system design. In MOGATS, the architecture of the hardware platform and the set of tasks in the form of a task graph are assumed to be given as the inputs. Task mapping and scheduling problems are modelled as a genetic algorithm-based optimisation approach. In summary, our task scheduling tool is the first multi-objective task scheduling in the design stage of embedded systems to help the designer to figure out which set of scheduling would provide their desired outcome. Additionally, in comparison to EGA-TS, the state-of-art task scheduling algorithm, in terms of speedup and SLR, we have gain 27.8 and 28.6 immediate improvements respectfully.