Modifying Wind Speed Data of Manual Observation Sequence to Automatic Observation Sequence Using a PSO-Based Neural Network

Abstract:

Recently, manual observation sequence has been gradually replaced by automatic observation sequence. The difference between manual observation sequence and automatic observation sequence is somewhat inevitable. This challenges the the homogeneity and the continuity of historical weather data, and influences atmospheric researches and applications. Therefore, based on the understanding of the influence caused by the two observation sequences, how to modify the data sequence of manual observation to automatic observation sequence has become a problem. In this paper, a model, which is a neural network based on the particle swarm optimization technique (PSONN), is established to modify the wind speed data sequence from manual observation to automatic observation. The proposed model achieves 15.6% in mean absolute percentage error (MAPE) compared to manual observation data sequence. For wind speed, it could be a promising candidate for modifying manual observing data sequence to automatic observing data sequence.

• Periodical: Advanced Materials Research (Volume 187)
• Pages: 688-692
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.187.688
• Online since: February 2011
• Authors: Xia Xiao, Hong Chao Zuo, Wen Yu Zhang, Ju Jie Wang
• Keywords: Homogeneity, Modified Model, Observation Sequence, PSONN, Wind Speed

References

[1] Wendland W M , Armstrong W. Comparison of maximum-minimum resistance and liquid-in-glass thermometer records. J At mos Ocean Tech , 1993 (10) : 233-237.

DOI: 10.1175/1520-0426(1993)010<0233:comral>2.0.co;2

[2] Quayle G, Easterling D R , Karl T R , et al. Effects of recent thermometer changes in the cooperative station network. B ull A mer Meteor Soc , 1991 (72) : 1718-1723.

DOI: 10.1175/1520-0477(1991)072<1718:eortci>2.0.co;2

[3] Guttman R N B , Baker C B. Exploratory analysis of the difference between temperature observations recorded by ASOS and conventional methods. B ull A mer Meteor Soc , 1996 (77) : 2865-2873.

DOI: 10.1175/1520-0477(1996)077<2865:eaotdb>2.0.co;2

[4] Wang, Y. H. (2009). Nonlinear neural network forecasting model for stock index option price: Hybrid GJR-GARCH approach. Expert Systems with Applications, 36, 564-570.

DOI: 10.1016/j.eswa.2007.09.056

[5] Kennedy J. Eberhart R. Particle swarm optimization. In: Proceedings of the IEEE international conference on neural networks, (1995).

[6] Bashir ZA. EI-Hawary ME. Applying wavelets to short-term load forecasting using PSO-based neural networks, IEEE Trans Power Syst, 2009 (24): 7-20.

DOI: 10.1109/tpwrs.2008.2008606

[7] K. W. Cha. Application of a PSO-based neural networks in analysis of outcomes of construction claims. Automation in construction 2007(16): 642-646.

DOI: 10.1016/j.autcon.2006.11.008

[8] J. Kennedy, R. Eberhart, Y. Shi. Swarm Intelligence, Morgan Kaufmann Publishers, San Francisco, (2001).

[9] M. Clerc, J. Kennedy. The particle swarm-explosion, stability, and Convergence in a multidimensional complex space. IEEE Transactions on Evolutionary Computation, 2002 (6): 58-73.

DOI: 10.1109/4235.985692

[10] K. W. Chau, Particle swarm optimization training algorithm ofr ANNs in stage prediction of shing Mun River, Journal of Hydrology 329, 2006: 363-367.

DOI: 10.1016/j.jhydrol.2006.02.025