Dynamic Price Prediction for Amazon Spot Instances

Variable pricing cloud resources are the most recent advancement in cloud computing business models. Cloud vendors like Amazon Web Services, a.k.a. Amazon AWS provide a new cloud instance type known as "Spot instance". The distinguishing feature of spot instance is its dynamic pricing. The price of spot instances varies dynamically with time based on demand and supply of cloud resources in the data centers across the globe. Customers place bids to obtain spot instances using an online auction platform. The auction platform determines the market clearance price, a.k.a. "Spot price" and the users whose bids are above the aforementioned price obtain the instances. Cloud vendors provide current and archived spot price data to assist their customers in bidding process. The major challenge for the customers in this new business model is to predict the spot price before placing their bids. In this paper, we have provided a novel algorithm for spot price prediction. We also have instantiated and demonstrated the proposed algorithm. The results show high accuracy of 9.4% Mean Absolute Percent Error (MAPE) for short term (one day ahead) and less 20% MAPE for long term (five days ahead) forecasting.

[1]  Nandini Mukherjee,et al.  A Novel Checkpointing Scheme for Amazon EC2 Spot Instances , 2013, 2013 13th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing.

[2]  Artur Andrzejak,et al.  Monetary Cost-Aware Checkpointing and Migration on Amazon Cloud Spot Instances , 2012, IEEE Transactions on Services Computing.

[3]  J. Contreras,et al.  Forecasting Next-Day Electricity Prices by Time Series Models , 2002, IEEE Power Engineering Review.

[4]  Miao Pan,et al.  Optimal Resource Rental Planning for Elastic Applications in Cloud Market , 2012, 2012 IEEE 26th International Parallel and Distributed Processing Symposium.

[5]  Rajkumar Buyya,et al.  Reliable Provisioning of Spot Instances for Compute-intensive Applications , 2011, 2012 IEEE 26th International Conference on Advanced Information Networking and Applications.

[6]  Danilo P. Mandic,et al.  A generalized normalized gradient descent algorithm , 2004, IEEE Signal Processing Letters.

[7]  V. Mendes,et al.  Short-term electricity prices forecasting in a competitive market: A neural network approach , 2007 .

[8]  Hsing Kenneth Cheng,et al.  Cloud Computing Spot Pricing Dynamics: Latency and Limits to Arbitrage , 2013 .

[9]  Thomas Erl,et al.  Service-Oriented Architecture: Concepts, Technology, and Design , 2005 .

[10]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[11]  Mark Lycett,et al.  Service-oriented architecture , 2003, 2003 Symposium on Applications and the Internet Workshops, 2003. Proceedings..

[12]  Bruce Nordman,et al.  Data Center Power Requirements: Measurements From Silicon Valley , 2003 .

[13]  Alexandar Angelus,et al.  Electricity Price Forecasting in Deregulated Markets , 2001 .

[14]  Fred L. Collopy,et al.  Error Measures for Generalizing About Forecasting Methods: Empirical Comparisons , 1992 .

[15]  Tom Gedeon,et al.  A fuzzy-neural approach to electricity load and spot-price forecasting in a deregulated electricity market , 2003, TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region.

[16]  Aaron Vegh.  MySQL Database Server , 2011 .

[17]  Thomas Hess,et al.  Software as a Service , 2008, Wirtschaftsinf..

[18]  Singh Ghuman,et al.  Cloud Computing-A Study of Infrastructure as a Service , 2015 .

[19]  Artur Andrzejak,et al.  Reducing Costs of Spot Instances via Checkpointing in the Amazon Elastic Compute Cloud , 2010, 2010 IEEE 3rd International Conference on Cloud Computing.

[20]  Ashwani Kumar,et al.  Electricity price forecasting in deregulated markets: A review and evaluation , 2009 .

[21]  Kai Song,et al.  Exploring the profit-reliability trade-off in Amazon's spot instance market: A better pricing mechanism , 2013, 2013 IEEE/ACM 21st International Symposium on Quality of Service (IWQoS).

[22]  Muli Ben-Yehuda,et al.  Deconstructing Amazon EC2 Spot Instance Pricing , 2011, CloudCom.

[23]  Christoph Meinel,et al.  Increasing Spot Instances Reliability Using Dynamic Scalability , 2012, 2012 IEEE Fifth International Conference on Cloud Computing.

[24]  Yang Song,et al.  Optimal bidding in spot instance market , 2012, 2012 Proceedings IEEE INFOCOM.

[25]  Michele Mazzucco,et al.  Achieving Performance and Availability Guarantees with Spot Instances , 2011, 2011 IEEE International Conference on High Performance Computing and Communications.

[26]  Dinkar Sitaram,et al.  Platform as a Service , 2012, CloudCom 2012.