2007 · 14 citations · 29 references
ComputingData ScienceForecastingMachine LearningPredictive AnalyticsForecast EvaluationForecasting MethodsPredictive ModelingReal-time ForecastingTime Series ForecastingTime Series PredictionClassification AlgorithmsMachine Learning Forecasting ModelsNearest-neighbor ClassificationSupervised Classification Algorithms
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.
29
Xen and the art of virtualization
Paul Barham, Boris Dragovic, Keir Fraser et al. · ACM SIGOPS Operating Systems Review · 2003 · 5.9K citations
Live migration of virtual machines
Christopher J. Clark, Keir Fraser, Steven Hand et al. · 2005 · 2.6K citations
Lawrence Barker · Technometrics · 2002 · 2.5K citations