,Dynamic task scheduling modeling in unstructured heterogeneous multiprocessor systems

• 作 者: Hamid TABATABAEE Mohammad Reza AKBARZADEH-T Naser PARIZ
• 机 构: Department of Computer Engineering,Islamic Azad University,Center of Excellence on Soft Computing an
• 出 处: Journal of Zhejiang University-Science C(Computers & Electro
• 发表日期: 2014年06期
• 关键词: Dynamic task scheduling Fuzzy logic Genetic algorithms Unstructured environment

An algorithm is proposed for scheduling dependent tasks in time-varying heterogeneous multiprocessor systems, in which computational power and links between processors are allowed to change over time. Link contention is considered in the multiprocessor scheduling problem. A linear switching-state space-modeling paradigm is introduced to enable theoretical analysis from a system engineering perspective. Theoretical analysis of this model shows its robustness against changes in processing power and link failure. The proposed algorithm uses a fuzzy decision-making procedure to handle changes in the multiprocessor system. The efficiency of the proposed algorithm is illustrated by several random experiments and comparison against a recent benchmark approach. The results show up to 18% average improvement in makespan, especially for larger scale systems.

An algorithm is proposed for scheduling dependent tasks in time-varying heterogeneous multiprocessor systems, in which computational power and links between processors are allowed to change over time. A linear switching-state space-modeling paradigm Theoretical analysis of this model shows its robustness against changes in processing power and link failure. The proposed algorithm to handle changes in the multiprocessor system. The efficiency of the proposed algorithm is illustrated by several random experiments and comparison against a recent benchmark. The results show up to 18% average improvement in makespan, especially for larger scale systems.