Adaptive Predictor Integration for System Performance Prediction

The integration of multiple predictors promises higher prediction accuracy than the accuracy that can be obtained with a single predictor. The challenge is how to select the best predictor at any given moment. Traditionally, multiple predictors are run in parallel and the one that generates the best result is selected for prediction. In this paper, we propose a novel approach for predictor integration based on the learning of historical predictions. It uses classification algorithms such as k-Nearest Neighbor (k-NN) based supervised learning to forecast the best predictor for the workload under study. Then only the forecasted best predictor is run for prediction. Our experimental results show that it achieved 20.18% higher best predictor forecasting accuracy than the cumulative MSB based predictor selection approach used in the popular network weather service system. In addition, it outperformed the observed most accurate single predictor in the pool for 44.23% of the performance traces.