A fast-growing worldwide interest is directed toward green energies. Due to the huge costs of wind farms establishment, the location for wind farms should be carefully determined to achieve the optimum return of investment. Consequently, researches have been conducted to investigate land suitability prior to wind plants development. The generated data from the sensors detecting a potential land can be very huge, fast in generation, heterogeneous, and incomplete, which become seriously difficult to process using traditional approaches. In this paper, we propose Trio-V Wind Analyzer (WA) that handles data volume, variety, and veracity to identify the most suitable location for wind energy development in any study area using a modified version of multicriteria evaluation (MCE). It utilizes principal component analysis (PCA) and our proposed Double-Reduction Optimum Apriori (DROA) to analyze most of the environmental, physical, and economical criteria. In addition, Trio-V WA recommends the suitable turbines and proposes the adequate turbines’ layout distribution, predicting the expected power generated based on the recommended turbine’s specifications using a regression technique. Thus, Trio-V WA provides an integral system of land evaluation for potential investment in wind farms. Experiments indicate 80% and 95% average accuracy for land suitability degree and power prediction, respectively, with efficient performance.
Trio-V Wind Analyzer: A Generic Integral System for Wind Farm Suitability Design and Power Prediction Using Big Data Analytics
Contributed by the Advanced Energy Systems Division of ASME for publication in the JOURNAL OF ENERGY RESOURCES TECHNOLOGY. Manuscript received August 8, 2017; final manuscript received October 2, 2017; published online November 9, 2017. Assoc. Editor: Ryo Amano.
- Views Icon Views
- Share Icon Share
- Search Site
Fawzy, D., Moussa, S., and Badr, N. (November 9, 2017). "Trio-V Wind Analyzer: A Generic Integral System for Wind Farm Suitability Design and Power Prediction Using Big Data Analytics." ASME. J. Energy Resour. Technol. May 2018; 140(5): 051202. https://doi.org/10.1115/1.4038119
Download citation file: