Classifying Algorithm Based on a Fuzzy Neural network for the control of a Network Attached Optical Jukebox

Abstract

A new analytical method for improving the performance of a network attached optical jukebox is presented by means of artificial neural networks. Through analyzing operation (request) process in this system, the mathematics model and algorithm are built for this storage system, and then a classified method based on artificial neural networks for this system is proposed. Simulation results testified the feasibility and validity of the proposed method that it could overcome the drawbacks of the frequent I/O operation and provide an effective way for using the Network Attached Optical Jukebox.

References

[1] HeN. Studies on the Applications of Network Attached Jukebox in Mass Storage System, 2004, Beijing, Tsinghua University

[2] LiuX., LuT. J., JiaH. B.. The Sixth International Conference on Web-Age Information Management, 2005, Hangzhou China, Springer-Verlag

[3] LiuX., LuT. J., JiaH. B.. International Symposium on Communications and Information Technologies 2005, 2005, Bei Jing, China, IEEE

[4] HuseyinS.. Storage Network Performance Analysis, 2002, New York, Wiley Publishing Inc.

[5] LeonardK.. Queueing Systems, Volume I: Theory, 1975, New York, Wiley

[6] LeonardK.. Queueing Systems, Volume II: Computer Applications, 1975, New York, Wiley

[7] LiX., TsoS. K., WangJ.. IEEE Transactions on Systems, Man and Cybernetics-Part C: Applications and Reviews, 2000, 31: 352-352

[8] Hayashi Y. and Buckley J. J.,Int. J. Approx. Reas.,10 (1994).

[9] Liu, G. Y., Fang, Y. H., and Zheng, X. F.,Tuning Neuro-fuzzy Function Approximator by Tabu Search. International Symposium on Neural Networks, Dalian China, 2004, 276.

[10] YaoC. C., KuoY.. Proceeding of Fuzzy-IEEE/IFES 95. Yokohama, 1995, 3: 1503-1503

[11] ChaoC. T., ChenY. J., TengC. C.. IEEE Transaction on SMC, 1996, 26: 344-344