A Novel Adaptive Fuzzy Logic Controller (A-FLC) to Reduce Retransmission and Service Roundtrip Time for Logical TCP Channels over the Internet

The novel Adaptive Fuzzy Logic Controller (A-FLC) proposed in this paper is created from the extant FLC model by adding the capability that allows it to auto-tune the range-thresholds of its “don’t care” fuzzy regions. The aim is to “squeeze” the range-threshold to achieve two purposes: a) to make the controller more responsive, and b) to reduce overshoot/undershoot to yield a less oscillatory control process. The range-threshold reduction process works with two parameters: “gradient threshold” and “given percentage”. The former decides when to begin the reduction process and the latter decides by how much. The preliminary results with the Java-based A-FLC prototype over the Internet indicate that the auto-tuning capability in the novel controller indeed makes the buffer overflow management more responsive, less oscillatory, and more accurate than the FLC predecessor.

[1]  Jean-Chrysostome Bolot,et al.  Performance Engineering of the World Wide Web: Application to Dimensioning and Cache Design , 1996, Comput. Networks.

[2]  Ibrahim Matta,et al.  On the origin of power laws in Internet topologies , 2000, CCRV.

[3]  Deborah Estrin,et al.  Recommendations on Queue Management and Congestion Avoidance in the Internet , 1998, RFC.

[4]  Allan K. Y. Wong,et al.  Genetic Algorithm and PID Control Together for Dynamic Anticipative Marginal Buffer Management: An Effective Approach to Enhance Dependability and Performance for Distributed Mobile Object-Based Real-Time Computing over the Internet , 2002, J. Parallel Distributed Comput..

[5]  Donald F. Towsley,et al.  Modeling TCP throughput: a simple model and its empirical validation , 1998, SIGCOMM '98.

[6]  Tharam S. Dillon,et al.  M/sup 3/RT: an Internet end-to-end performance measurement approach for real-time applications with mobile agents , 2002, Proceedings International Symposium on Parallel Architectures, Algorithms and Networks. I-SPAN'02.

[7]  Tharam S. Dillon,et al.  M2RT: A tool developed for predicting the mean message response time of communication channels in sizeable networks exemplified by the Internet , 2001, Comput. Networks.

[8]  Azer Bestavros,et al.  Self-similarity in World Wide Web traffic: evidence and possible causes , 1997, TNET.

[9]  Philip S. Yu,et al.  Caching on the World Wide Web , 1999, IEEE Trans. Knowl. Data Eng..

[10]  Wwk Lin,et al.  A novel fuzzy logic controller (FLC) for improving internet-based real-time application timeliness by eliminating user-level buffer overflow , 2003 .

[11]  Sally Floyd,et al.  Wide area traffic: the failure of Poisson modeling , 1995, TNET.

[12]  Tharam S. Dillon,et al.  An adaptive buffer management algorithm for enhancing dependability and performance in mobile-object-based real-time computing , 2001, Fourth IEEE International Symposium on Object-Oriented Real-Time Distributed Computing. ISORC 2001.