An Approach for Erosion and Power Loss Prediction of Wind Turbines Using Big Data Analytics

Abstract

Due to the huge costs associated with wind energy development, this makes wind farms maintenance and production reliability are of high necessity to ensure sustainability. The continuous evolution of turbines industry has a serious impact on the operation and maintenance costs. Thus, monitoring wind turbines performance and early deterioration prediction are highly required. During the operational life of turbines, some components are persistently exposed to extreme environmental influences that result in their edge erosion. Sensors can be deployed in wind farms to detect such factors, where vast quantities of incomplete, heterogeneous and multi-sourced data are rapidly generated. Hence, wind-related data have been considered as big data that necessitate the intervention of big data analytics for accurate data analysis, which become severely hard to process using traditional approaches. In this paper, we propose the Wind Turbine Erosion Predictor (WTEP) System that uses big data analytics to handle the data volume, variety, and veracity and estimate the turbines erosion rate, in addition to the total power loss. WTEP proposes an optimized flexible multiple regression technique. Experiments show that WTEP achieves high erosion rate prediction accuracy with fast processing time. Thus, it effectively evaluates the accompanied percentage of power loss for wind turbines.