Application of Least-Squares Support Vector Regression with PSO for CPU Performance Forecasting

Abstract:

The success of CPU performance prediction will make many benefits. This study adopts the least-squares support vector regression (LS-SVR) with particle swarm optimization (PSO) algorithm to improver accuracy of CPU performance prediction. LS-SVR with PSO, support vector regression (SVR) with PSO, general regression neural network (GRNN), radial basis neural network (RBNN), and linear regression are employed for CPU performance prediction. Empirical results indicate that the LS-SVR (Linear kernel) with PSO has better performance in terms of forecasting accuracy than the other methods. Therefore, the LS-SVR (Linear kernel) with PSO model can efficiently provide credible CPU performance estimated value.

• Periodical: Advanced Materials Research (Volume 630)
• Pages: 366-371
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.630.366
• Online since: December 2012
• Authors: Kuo Ping Lin
• Keywords: CPU Performance Prediction, Least-Squares Support Vector Regression, Particle Swarm Optimization (PSO)

References

[1] A. Asuncion, and D.J. Newman, UCI Machine Learning Repository, University of California, School of In formation and Computer Science, Irvine, CA, (Online) Available: (http: /archive. ics. uci. edu/beta/), (2007).

[2] A. De Gloria, F. Ancarani, F. Bellotti, M. Olivieri, Instruction level analytic prediction of parallel CPU architecture performance, International Conference on Intelligent Information Systems, The Bahamas, (1997).

DOI: 10.1109/iis.1997.645379

[3] J. Kennedy, The Particle Swarm: Social Adaptation of Knowledge, in Proc. IEEE Int. Conf. Evol. Comput., Indianapolis, IN, 1997, pp.303-308.

[4] D. Kibler, D.W. Aha, M.K. Albert, Instance-based prediction of real-valued attributes, Computational Intelligence 5 (1989) 1-57.

DOI: 10.1111/j.1467-8640.1989.tb00315.x

[5] X. Li, S. Ming, D. Lixing, Particle swarm optimization-based LS-SVM for building cooling load prediction, Journal of Computers 5 (2010) 614-621.

DOI: 10.4304/jcp.5.4.614-621

[6] X. Peng, Y. Wang, A normal least squares support vector machine (NLS-SVM) and its learning algorithm, Neurocomputing 72 (2009) 3734-3741.

DOI: 10.1016/j.neucom.2009.06.005

[7] R. Srinivasan, J. Cook, O. Lubeck, Ultra-Fast CPU performance prediction: Extending the Monte Carlo approach, in Proc. 18th International Symposium on Computer Architecture and High Performance Computing, Brazil, 2006, pp.107-116.

DOI: 10.1109/sbac-pad.2006.31

[8] J.A.K. Suykens, T. Van Gestel, J. De Brabanter, B. De Moor, J. Vandewalle, , Least Squares Support Vector Machines, World Scientific, Singapore, (2002).

DOI: 10.1142/5089

[9] J. Mercer, Function of Positive and Negative Type and Their Connection with the Theory of Integral Equations, Philosophical Transactions of the Royal Society A209 (1909) 415-446.