期刊名称：International Journal on Electrical Engineering and Informatics
印刷版ISSN：2085-6830
出版年度：2015
卷号：7
期号：2
DOI：10.15676/ijeei.2015.7.2.8
出版社：School of Electrical Engineering and Informatics
摘要：Wind power is the safest, cleanest resource and has emerged as the speediestgrowing renewable energy in terms of annual installed capacity. Before a wind-drivesystem is set up, thorough wind resource assessment (WRA) must be conducted. In thispaper, a methodology based on ground-station and topographical neural networkmodeled data is proposed to study the wind energy potential, in the monitored locationand areas not covered by directly measurement instrumentation at Kuching. A newtopographical feed forward neural network (T-FFNN) back propagation trained withLevenberg-Marquardt (LM), which consists of three layers was used to model the windspeed profile. The daily 10 m height, average hourly measured wind speed data for aperiod of ten years (2003-2012) for eight stations operated by Malaysia MeteorologicalDepartment (MMD) were used for the training, testing and validation. Thegeographical, meteorological and synthesized topographical parameters were used asinput data, whereas the monthly wind speeds as the objective function. The optimumtopology with maximum mean absolute percentage error of 6.4 % and correlation valueof 0.9946 between the reference measured and predicted was obtained. The predictedmonthly wind speed varied from 1.3-1.98 m/s with an average annual wind speed of1.62 m/s. The characteristics of ground -based station was analyzed and presented. Itwas found in all the areas examined that the wind power falls within a low powerdensity class (PD ≤ 100w/m2). Results from the micro-sizing showed an annual energyoutput (AEO) in the range of 4-12 MWh/year.
