Abstract: Grid computing was initially proposed to harness huge amounts computational resources. But the expected potential could not be fully exploited because the Grid applications are from a wide range of users each having own special requirements. In order to serve the needs, scheduling requirements of grid application first need to be understood. In this paper we will compare the performance aggressive, and conservative backfilling strategies based on average weighted response time(AWRT) and average slowdown of the jobs as the performance metrics.

• Publication Date: 17-Jun-2012
• DOI: 10.15224/978-981-07-2579-2-411
• Views: 0
• Downloads: 0

Abstract: We propose a robust non-fuzzy self-tuning scheme for fuzzy PI controllers (FPIC) for a class of systems. The output scaling factor (SF) of the proposed non-fuzzy self-tuning FPIC, termed as NF-STFPIC, is modified on-line based on the normalized change of error of the controlled variable. Performance of the proposed controller is evaluated for a pure integrating plus dead-time (IPD) and first-order integrating plus dead-time (FOIPD) processes with a wide variation in dead-time under both set-point change and load disturbance. Detailed performance comparison with conventional PI (both fuzzy and non-fuzzy) controllers as well as a self-tuning fuzzy PI controller (STFPIC) reported in the leading literature is provided with respect to a number of performance indices. Unlike STFPIC, which uses 49 expert's defined self-tuning fuzzy rules our NF-STFPIC uses a single deterministic rule. Experimental results justify the effectiveness of the proposed NF-STFPIC

• Publication Date: 17-Jun-2012
• DOI: 10.15224/978-981-07-2579-2-426
• Views: 0
• Downloads: 0