Artificial neural network approach to spatial estimation of wind velocity data

In any regional wind energy assessment, equal wind velocity or energy lines provide a common basis for meaningful interpretations that furnish essential information for proper design purposes. In order to achieve regional variation descriptions, there are methods of optimum interpolation with classical weighting functions or variogram methods in Kriging methodology. Generally, the weighting functions are logically and geometrically deduced in a deterministic manner, and hence, they are imaginary first approximations for regional variability assessments, such as wind velocity. Geometrical weighting functions are necessary for regional estimation of the regional variable at a location with no measurement, which is referred to as the pivot station from the measurements of a set of surrounding stations. In this paper, weighting factors of surrounding stations necessary for the prediction of a pivot station are presented by an artificial neural network (ANN) technique. The wind speed prediction results are compared with measured values at a pivot station. Daily wind velocity measurements in the Marmara region from 1993 to 1997 are considered for application of the ANN methodology. The model is more appropriate for winter period daily wind velocities, which are significant for energy generation in the study area. Trigonometric point cumulative semivariogram (TPCSV) approach results are compared with the ANN estimations for the same set of data by considering the correlation coefficient (R). Under and over estimation problems in objective analysis can be avoided by the ANN approach.

[1]  Zekai Sen,et al.  Wind Energy Directional Spatial Correlation Functions and Application for Prediction , 2000 .

[2]  J. Guiot,et al.  Spatial Objective Analysis With Applications in Atmospheric Sciences , 1988 .

[3]  Z. Şen,et al.  Regional assessment of wind power in western Turkey by the cumulative semivariogram method , 1997 .

[4]  Zekai Şen,et al.  Terrain topography classification for wind energy generation , 1999 .

[5]  S. Barnes,et al.  A Technique for Maximizing Details in Numerical Weather Map Analysis , 1964 .

[6]  G. Matheron.  Principles of geostatistics , 1963 .

[7]  James A. Anderson,et al.  Cognitive and psychological computation with neural models , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  D. Lalas,et al.  An analysis of wind power potential in Greece , 1983 .

[9]  W. R. Hargraves,et al.  Nationwide assessment of potential output from wind-powered generators , 1976 .

[10]  Neil J. Cherry.  Wind energy resource survey methodology , 1980 .

[11]  Z. Şen,et al.  Wind power potential in Turkey and Akhisar case study , 2002 .

[12]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[13]  R. Reyment,et al.  Statistics and Data Analysis in Geology. , 1988 .

[14]  H. J. Thiébaux,et al.  Spatial objective analysis : with applications in atmospheric science , 1987 .

[15]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[16]  Y. Sasaki,et al.  An ObJective Analysis Based on the Variational Method , 1958 .

[17]  Z. Şen,et al.  On the regional wind energy potential of Turkey , 2000 .

[18]  D. O. Hebb,et al.  The organization of behavior , 1988 .

[19]  Zekâi Sen,et al.  Cumulative semivariogram models of regionalized variables , 1989 .

[20]  Z. Şen,et al.  First-order Markov chain approach to wind speed modelling , 2001 .

[21]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[22]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[23]  Z. Şen,et al.  Regional wind energy evaluation in some parts of Turkey , 1998 .

[24]  G. P. Cressman.  AN OPERATIONAL OBJECTIVE ANALYSIS SYSTEM , 1959 .