Autoregressive Time Series Forecasting of Computational Demand

Details Autoregressive Time Series Forecasting of Computational Demand Autoregressive Time Series Forecasting of Computational Demand

2007-11-14

arxiv.org/abs/0711.2062v1

Computer Science

Distributed, Parallel, and Cluster Computing

Scientific paper

We study the predictive power of autoregressive moving average models when forecasting demand in two shared computational networks, PlanetLab and Tycoon. Demand in these networks is very volatile, and predictive techniques to plan usage in advance can improve the performance obtained drastically. Our key finding is that a random walk predictor performs best for one-step-ahead forecasts, whereas ARIMA(1,1,0) and adaptive exponential smoothing models perform better for two and three-step-ahead forecasts. A Monte Carlo bootstrap test is proposed to evaluate the continuous prediction performance of different models with arbitrary confidence and statistical significance levels. Although the prediction results differ between the Tycoon and PlanetLab networks, we observe very similar overall statistical properties, such as volatility dynamics.

Affiliated with

Also associated with

No associations

Rating

Autoregressive Time Series Forecasting of Computational Demand does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Autoregressive Time Series Forecasting of Computational Demand, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Autoregressive Time Series Forecasting of Computational Demand will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-529635