- 期刊
Performance Analysis of Hybrid Polling Schemes with Multiple Classes of Self-Similar and Long-Range Dependent Traffic Input
並列摘要
Queuing delay have significant impact on the performance of network applications. To meet distinct delay requirements of multi-classend-user traffic,various queuing and scheduling schemeshave been proposed. These schemes are analogous to a polling mechanism in which multiple traffic queues are concurrently handled by a single scheduler. However, researchers were unable to analyze this synergy between the conventional queuingcum- scheduling and polling models. Moreover, research on analyzing polling models assumed traditional Poisson traffic distribution which is unable to capture self-similar and long-range dependent (LRD) characteristics and hence yield misleading results. Furthermore, published work related to self-similar traffic modeling is mainly based on conventional queuing-cum-scheduling which are simple approximations.The objective of this work is to analyze different combinations of conventional queuing and polling models. In this paper, we exploit the synergy between traditional queuing-cum-scheduling and polling models. We analyze different combinations of queuing and polling mechanisms with realistic traffic distributions i.e., selfsimilar and LRD. An analytical framework for G/M/1 queuing system is developedwhich contemplatesmultiple classes of self-similar and LRDtraffic as input.We formulate the Markov chain for G/M/1 queuing system and extract closed-form expressions of queuing delay for corresponding traffic classes. We analyzea combination of limited service polling model with non-pre-emptive priority queuing. Different combinations of polling models (i.e., exhaustive, gated and limited service) are also analyzed. We validate the performance of the proposed analytical framework through simulations. Simulation results suggest that synergy of polling and schedulingdangle promising results.
延伸閱讀
- 李俊德（2016）。A Hybrid Approach with Constraint Programming and Mathematical Programming Models for the Driver Scheduling and Rostering Problems of Mass Rapid Transit Systems〔博士論文，國立交通大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0030-0803201714333561
- Lei, P. L. (2012). Effects of Individual Differences on Search Behaviors, Strategies and Performance in Various Types of Multimedia Search Engines [doctoral dissertation, National Chiao Tung University]. Airiti Library. https://doi.org/10.6842/NCTU.2012.00084
- 蔡志偉、唐麗英（2008）。Optimization of Multiple Responses from Designed Experiments by Using Data Envelopment Analysis and the Group Method of Data Handling。品質學報，15(4)，259-269。https://www.airitilibrary.com/Article/Detail?DocID=10220690-200808-15-4-259-269-a
- 楊雅涵（2019）。On Using Reinforcement Learning to Select Modulation/Coding Schemes for Non-Orthogonal Multiple Access in Multi-User Multiple-Input Multiple-Output Systems with Limited Feedback〔碩士論文，國立臺灣大學〕。華藝線上圖書館。https://doi.org/10.6342/NTU201900453
- Akay, M., Aci, Ç., & Abu, F. (2015). PREDICTING THE PERFORMANCE MEASURES OF A 2-DIMENSIONAL MESSAGE PASSING MULTIPROCESSOR ARCHITECTURE BY USING MACHINE LEARNING METHODS. Neural Network World, 25(3), 241-265. https://doi.org/10.14311/NNW.2015.25.013