Forecasting of wind velocity: An improved SVM algorithm combined with simulated annealing

Abstract

Accurate forecasting of wind velocity can improve the economic dispatch and safe operation of the power system. Support vector machine (SVM) has been proved to be an efficient approach for forecasting. According to the analysis with support vector machine method, the drawback of determining the parameters only by experts’ experience should be improved. After a detailed description of the methodology of SVM and simulated annealing, an improved algorithm was proposed for the automatic optimization of parameters using SVM method. An example has proved that the proposed method can efficiently select the parameters of the SVM method. And by optimizing the parameters, the forecasting accuracy of the max wind velocity increases by 34.45%, which indicates that the new SASVM model improves the forecasting accuracy.

Keywords

wind velocity / forecasting / improved algorithm / simulated annealing / support vector machine

References

[1] ZhaoP., WangJ.-f., XiaJ.-rong.. Performance evaluation and accuracy enhancement of a day-ahead wind power forecasting system in China [J]. Renewable Energy, 2011, 43: 234-241

[2] YangX.-y., XiaoY., ChenS.-yong.. Wind velocity and generated power forecasting in wind farm [J]. Proceedings of the CSEE, 2005, 25(11): 1-5

[3] LiG., ShiJ., ZhouJ.-yi.. Bayesian adaptive combination of short-term wind speed forecasts from neural network models [J]. Renewable Energy, 2011, 36(1): 352-359

[4] WangX.-l., WangM.-wei.. Short-term wind velocity forecasting based on wavelet decomposition and least square support vector machine [J]. Power System Technology, 2010, 34(1): 179-184

[5] SunC.-s., WangY.-n., LiX.-ran.. A vector autoregression model of hourly wind velocity and its applications in hourly wind velocity forecasting [J]. Proceedings of the CSEE, 2008, 28(14): 112-117

[6] WangX.-l., LiHui.. Effective wind velocity forecasting inannual prediction of output power for wind farm [J]. Proceedings of the CSEE, 2010, 30(8): 117-122

[7] NfaouiH., BuretJ., SayighA. A. M.. Stochastic simulation of hourly average wind speed sequences in Tangiers (Morocco) [J]. Solar Energy, 1996, 56(3): 301-314

[8] TrafalisB. T., AdriantoI., RichmanM. B.. Active learning with support vector machines for tornado prediction [J]. Lecture Notes in Computer Science, 2007, 4487: 1130-1137

[9] OsowskiS., GarantyK.. Forecasting of the daily meteorological pollution using wavelets and support vector machine [J]. Engineering Applications of Artificial Intelligence, 2007, 20: 745-755

[10] NiuD.-x., GuZ.-h., XingM., WangH.-ping.. Study on forecasting approach to short-term load of SVM based on data mining [J]. Proceedings of the CSEE, 2006, 26(18): 6-12

[11] PaiP.-f., HongW.-chiang.. Forecasting regional electric load based on recurrent support vector machines with genetic algorithms [J]. Electric Power Systems Research, 2005, 74(3): 417-425

[12] HongW.-chiang.. Electric load forecasting by support vector model [J]. Applied Mathematical Modeling, 2009, 33(5): 2444-2454

[13] LiY.-c., FangT.-j., YuE.-keng.. Study of support vector machines for short-term load forecasting [J]. Proceedings of the CSEE, 2003, 23(6): 55-59

[14] XieH., WeiJ.-p., LiuH.-li.. Parameter selection and optimization method of SVM model for short-term load forecasting [J]. Proceedings of the CSEE, 2006, 26(22): 17-22

[15] SreelakshmiK., KumarP. R.. Performance evaluation of short term wind speed prediction techniques [J]. International Journal of Computer Science and Network Security, 2008, 8: 162-169

[16] BelousovA., VerzakovS. A., VonfreseJ.. A flexible classification approach with optimal generalization performance: support vector machines [J]. Chemometrics and Intelligent Laboratory Systems, 2002, 64: 15-25

[17] ThissenaU., BrakelaR., WeijerbA. P., MelssenaW. J., BuydensL. M. C.. Using support vector machines for time series prediction [J]. Chemometrics and Intelligent Laboratory Systems, 2003, 69: 35-49

[18] JiaZ.-y., MaJ.-w., WangF.-j., LiuWei.. Hybrid of simulated annealing and SVM for hydraulic valve characteristics prediction [J]. Expert Systems with Applications, 2011, 38(7): 8030-8036

[19] SunW., ZhangJie.. Short time load forecasting based on simulated annealing and genetic algorithm improved SVM [C]. Proceedings of the 27th Chinese Control Conference, 2008KunmingIEEE81-85

[20] LuN., ZhouJ.-z., HeY.-yao.. Simulated annealing theory based particle swarm optimization for support vector machine model in short-term load forecasting [C]. International Conference on Information Engineering and Computer Science (ICIECS 2009), 2009WuhanIEEE1-4