Fuzzy scheduling strategy for generalized switched server systems and its robustness over system heterogeneity
✍ Scribed by Xingxuan Wang; Da-Zhong Zheng
- Publisher
- John Wiley and Sons
- Year
- 2009
- Tongue
- English
- Weight
- 450 KB
- Volume
- 24
- Category
- Article
- ISSN
- 0884-8173
No coin nor oath required. For personal study only.
✦ Synopsis
Generalized switched server system, a discretely controlled continuous-time system, in which N tanks are used to represent N parallel entities, respectively, can be employed to address a class of load-balancing problems. A tank-pair model is a system that consists of two tanks and a single input single output controller, which regulates the inflows of the two tanks to acquire the two uniform levels under the specified inflow constraints. According to a quantized observation of the N tank levels, some discrete events are generated, and based on certain event feedback strategy, switching the location of the tank-pair can control all the N tanks in a time-sharing manner to acquire the N levels uniformity. Different from some existing scheduling strategies, this study proposes a fuzzy scheduling strategy (FSS) for such generalized switched server systems. Special measures are taken to reduce the N -inputs two-outputs fuzzy inference to a two-inputs one-output one, which greatly facilitates fuzzy scheduler design. Simulation results show that the proposed FSS strategy outperforms over the three existing scheduling strategies as a whole, and they also show that the proposed FSS strategy demonstrates high robustness over system heterogeneity.