Data Quality, Consistency, and Interpretation Management for Wind Farms by Using Neural Networks

Abstract

The intermittent nature of wind poses significant problems to generation companies that wish to keep a close watch on the performance of their wind mills. A regular data mining process on historical measures becomes mandatory to analyze the behavior of each turbine, especially during periods of normal operation - that is when working regularly but with a possible loss of generation. GDF SUEZ has developed an innovative approach in order to recompute generations during suspicious periods by the use of a natural clustering method coupled with Neural Networks (NN) built from a huge genetic algorithm. This process, part of what is called Data Quality, Consistency and Interpretation Management (DQCIM), will be roughly depicted and intensively illustrated.