원문정보
초록
영어
In this paper, a BCC-DPSO scheduling algorithm is proposed to solve multi-objective optimization problem for task scheduling on Network-on-Chip (NoC). In our proposal, the relative advantage of the solution is evaluated by calculating its efficiency using BCC model in Data Envelopment Analysis (DEA), and the referred-time method is introduced to rank the BCC-efficient solution. Moreover, a sub-swarm strategy is adopted to reduce the high computational requirement introduced by the DEA. There are four sub-swarms, each of which optimizes one of four observed metrics, namely makespan, energy, link load and workload balance. Meanwhile, the speed vector updating formulation is modified to comply with the sub-swarm strategy. By conducting comparative simulations, the results show that our proposal produces more efficient schedule solution than other multi-objective Particle Swarm Optimization (PSO).
목차
1. Introduction
2. Problem Formulation
2.1. Task Model
2.2. NoC Structure
2.3. Metrics
3. The Proposed Algorithm
3.1. The Input-oriented BCC Model
3.2. Referred-time
3.3. Sub-swarm Strategy
3.4. The Algorithm Flow
4. Experiment and Discuss
4.1. Test Bed
4.2. Comparative Simulation
5. Conclusion and Future Study
Acknowledgements
References