Spot instances were introduced by Amazon EC2 in December 2009 to sell its spare capacity through auction based market mechanism. Despite its extremely low prices, cloud spot market has low utilization. Spot pricing being dynamic, spot instances are prone to out-of bid failure. Bidding complexity is another reason why users today still fear using spot instances. This work aims to present Regression Random Forests (RRFs) model to predict one-week-ahead and one-day-ahead spot prices. The prediction would assist cloud users to plan in advance when to acquire spot instances, estimate execution costs, and also assist them in bid decision making to minimize execution costs and out-of-bid failure probability. Simulations with 12 months real Amazon EC2 spot history traces to forecast future spot prices show the effectiveness of the proposed technique. Comparison of RRFs based spot price forecasts with existing non-parametric machine learning models reveal that RRFs based forecast accuracy outperforms other models. We measure predictive accuracy using MAPE, MCPE, OOB Error and speed. Evaluation results show that $MAPE < = 10\% \ $MAPE<=10% for 66 to 92 percent and $MCPE < = 15\% \ $MCPE<=15% for 35 to 81 percent of one-day-ahead predictions with prediction time less than one second. $MAPE < = 15\% \ $MAPE<=15% for 71 to 96 percent of one-week-ahead predictions.

中文翻译：

---

使用回归随机森林的 Amazon EC2 现货价格预测

Amazon EC2 于 2009 年 12 月引入了 Spot 实例，以通过基于拍卖的市场机制出售其备用容量。尽管价格极低，但云现货市场利用率低。Spot 定价是动态的，Spot 实例容易出价失败。出价复杂性是当今用户仍然害怕使用 Spot 实例的另一个原因。这项工作旨在提出回归随机森林（RRFs）模型来预测一周前和一天前的现货价格。预测将帮助云用户提前计划何时获取现货实例，估算执行成本，并帮助他们进行投标决策，以最大限度地降低执行成本和投标失败概率。使用 12 个月真实 Amazon EC2 现货历史跟踪来预测未来现货价格的模拟显示了所提议技术的有效性。基于 RRFs 的现货价格预测与现有非参数机器学习模型的比较表明，基于 RRFs 的预测准确性优于其他模型。我们使用 MAPE、MCPE、OOB 误差和速度来衡量预测准确性。评价结果表明$MAPE < = 10\% \ $米一种磷乙<=10% 66% 到 92% 和 $MCPE < = 15\% \ $米C磷乙<=15% 对于 35% 到 81% 的前一天预测，预测时间少于一秒。 $MAPE < = 15\% \ $米一种磷乙<=15% 71% 到 96% 的提前一周预测。