A statistical approach to risk mitigation in computational markets

We study stochastic models to mitigate the risk of poor Quality-of-Service (QoS) in computational markets. Consumers who purchase services expect both price and performance guarantees. They need to predict future demand to budget for sustained performance despite price fluctuations. Conversely, providers need to estimate demand to price future usage. The skewed and bursty nature of demand in large-scale computer networks challenges the common statistical assumptions of symmetry, independence, and stationarity. This discrepancy leads to underestimation of investment risk. We confirm this non-normal distribution behavior in our study of demand in computational markets. The high agility of a dynamic resource market requires flexible, efficient, and adaptable predictions. Computational needs are typically expressed using performance levels, hence we estimate worst-case bounds of price distributions to mitigate the risk of missing execution deadlines. To meet these needs, we use moving time windows of statistics to approximate price percentile functions. We use snapshots of summary statistics to calculate prediction intervals and estimate model uncertainty. Our approach is model-agnostic, distribution-free both in prices and prediction errors, and does not require extensive sampling nor manual parameter tuning. Our simulations and experiments show that a Chebyshev inequality model generates accurate predictions with minimal sample data requirements. We also show that this approach mitigates the risk of dropped service level performance when selecting hosts to run a bag-of-task Grid application simulation in a live computational market cluster