CBR and neural networks based technique for predictive prefetching

Authors:
Sohail Sarwar;Zia Ul-Qayyum;Owais Ahmed Malik
Affiliations:
School of Electrical Engineering and Computer Sciences, National University of Sciences and Technology, Islamabad, Pakistan;University Institute of Information Technology, University of Arid Agriculture, Rawalpindi, Pakistan;School of Electrical Engineering and Computer Sciences, National University of Sciences and Technology, Islamabad, Pakistan
Venue:
MICAI'10 Proceedings of the 9th Mexican international conference on Artificial intelligence conference on Advances in soft computing: Part II
Year:
2010

Citing 6
Cited 0

Design and evaluation of a compiler algorithm for prefetching

ASPLOS V Proceedings of the fifth international conference on Architectural support for programming languages and operating systems
(invited paper) A new theoretical framework for information retrieval

Proceedings of the 9th annual international ACM SIGIR conference on Research and development in information retrieval
Constructing Suffix Trees On-Line in Linear Time

Proceedings of the IFIP 12th World Computer Congress on Algorithms, Software, Architecture - Information Processing '92, Volume 1 - Volume I
Techniques and Knowledge Used for Adaptation During Case-Based Problem Solving

IEA/AIE '98 Proceedings of the 11th International Conference on Industrial and Engineering Applications of Artificial In telligence and Expert Systems: Tasks and Methods in Applied Artificial Intelligence
Merging CBR and Neural Networks for SLA-Based Radio Resource Management for QoS Sensitive Cellular Networks

ISADS '07 Proceedings of the Eighth International Symposium on Autonomous Decentralized Systems
Layered Memory Architecture for High IO Intensive Information Services to Achieve Timeliness

HASE '08 Proceedings of the 2008 11th IEEE High Assurance Systems Engineering Symposium

Quantified Score

Hi-index	0.00

Visualization

Abstract

Cache prefetching in memory management greatly relies upon effectiveness of prediction mechanism to fully exploit available resources and for avoiding page faults. Plenty of techniques are available to devise strong prediction mechanism for prefetching but they either are situation specific (Locality of reference principle) or inadaptable (Markovian model) and costly. We have proposed a generic and adaptable technique benefiting from past experience by employing hybrid of Case Based Reasoning (CBR) and Neural Networks (NNs). Here we will be concerned with improving adaptation phase of CBR using NN and its impact on predictive accuracy for prefetching. The level of predictive accuracy attained (specifically in case adaptation of CBR) is ameliorated by handsome margin with declined cost than contemporary techniques as would be affirmed by results.