2017 IEEE International Conference on Edge Computing (EDGE) (2017)
Honolulu, Hawaii, United States
June 25, 2017 to June 30, 2017
Abstract-In this paper, we study forecasting through time series decomposition to predict Amazon Elastic Compute Cloud (EC2) Spot prices. To achieve this, we first decompose the Spot price history into time series components; each component, which can exhibit deterministic or non-deterministic qualities, is then separately forecast using different standard forecasting techniques and look back periods; and finally, the individual forecasts are aggregated to form the Spot price forecast. We compare our approach with several standard forecasting methods, namely Na¨ıve, Seasonal Na¨ıve, ARIMA, ETS, STL, and TBATS. From experimental results we make two observations: (i) none of the evaluated forecasting techniques yields consistently good results across all Spot markets, even though Seasonal Na¨ıve can be considered the most robust when applied to markets with strong seasonal components, and (ii) our proposed technique performs comparably with, and in some cases, outperforms, the state-of-the-art forecasting techniques. The latter observation suggests that time series decompositionbased forecasting with hybrid look-backs warrants further investigation.
Time series analysis, Forecasting, Estimation, Market research, Biological system modeling, Standards, Predictive models
M. B. Chhetri, M. Lumpe, Q. B. Vo and R. Kowalczyk, "On Forecasting Amazon EC2 Spot Prices Using Time-Series Decomposition with Hybrid Look-Backs," 2017 IEEE International Conference on Edge Computing (EDGE), Honolulu, Hawaii, United States, 2017, pp. 158-165.