Application of AdaSS Ensemble Approach for Prediction of Power Plant Generator Tension

摘要: The paper presents the application of ensemble approach in prediction tension a power plant generator. proposed Adaptive Splitting and Selection (AdaSS) algorithm performs fusion several elementary predictors is based on assumption that should take into account competence predictors. To full advantage complementarity predictors, evaluates their local specialization, creates set locally specialized System parameters are adjusted using evolutionary algorithms course learning process, which aims to minimize mean squared error prediction. Evaluation system carried an empirical data compared other classical methods. results show effectively returns more consistent accurate tension, thereby outperforming approaches.