Random Forest Based Approach for Concept Drift Handling
This work addresses concept drift for applications in smart grid and wind power forecasting, presenting an incremental improvement over existing methods.
The paper tackles concept drift in smart grid analysis and wind power forecasting by proposing a Random Forest-based ensemble method with weighted majority voting and ensemble pruning. The method outperforms original Random Forest and state-of-the-art classifiers like AWE2 in empirical comparisons.
Concept drift has potential in smart grid analysis because the socio-economic behaviour of consumers is not governed by the laws of physics. Likewise there are also applications in wind power forecasting. In this paper we present decision tree ensemble classification method based on the Random Forest algorithm for concept drift. The weighted majority voting ensemble aggregation rule is employed based on the ideas of Accuracy Weighted Ensemble (AWE) method. Base learner weight in our case is computed for each sample evaluation using base learners accuracy and intrinsic proximity measure of Random Forest. Our algorithm exploits both temporal weighting of samples and ensemble pruning as a forgetting strategy. We present results of empirical comparison of our method with original random forest with incorporated "replace-the-looser" forgetting andother state-of-the-art concept-drfit classifiers like AWE2.