Title: Learning predictors for flash memory endurance: a comparative study of alternative classification methods
Authors: Tom Arbuckle; Damien Hogan; Conor Ryan
Addresses: Computer Science and Information Systems, University of Limerick, Limerick, Ireland ' Computer Science and Information Systems, University of Limerick, Limerick, Ireland ' Computer Science and Information Systems, University of Limerick, Limerick, Ireland
Abstract: Flash memory's ability to be programmed multiple times is called its endurance. Beyond being able to give more accurate chip specifications, more precise knowledge of endurance would permit manufacturers to use flash chips more effectively. Rather than physical testing to determine chip endurance, which is impractical because it takes days and destroys an area of the chip under test, this research seeks to predict whether chips will meet chosen endurance criteria. Timing data relating to erasure and programming operations is gathered as the basis for modelling. The purpose of this paper is to determine which methods can be used on this data to accurately and efficiently predict endurance. Traditional statistical classification methods, support vector machines and genetic programming are compared. Cross-validating on common datasets, the classification methods are evaluated for applicability, accuracy and efficiency and their respective advantages and disadvantages are quantified.
Keywords: flash memory endurance; performance prediction; linear programming; support vector machines; SVMs; genetic programming; learning predictors; classification methods; timing data; erasure; programming; modelling.
International Journal of Computational Intelligence Studies, 2014 Vol.3 No.1, pp.18 - 39
Available online: 13 Jan 2014 *Full-text access for editors Access for subscribers Purchase this article Comment on this article