• Samindar Jalandar Vibhute
• Prof S. S. Redekar

Spot instances were introduced by Amazon EC2 in Dec 2009 to sell its spare capability through auction primarily based market mechanism. Despite its extraordinarily low costs, cloud commodity exchange has low utilization. Spot evaluation being dynamic, spot Instances square measure susceptible to out-of bid failure. Bidding complexness is another excuse why users nowadays still worry victimization spot instances. This work aims to gift Regression Random Forests (RRFs) model to predict one-week-ahead and one-day-ahead spot prices. The prediction would assist cloud users to arrange earlier once to accumulate spot instances, estimate execution prices, and additionally assist them in bid deciding to reduce execution prices and out-of-bid failure likelihood. Simulations with twelve Months real Amazon EC2 spot history traces to forecast future spot costs show the effectiveness of the projected technique. Comparison of RRFs most primarily based terms forecasts with existing non-parametric machine learning models reveal that RRFs based.

Deep Neural Network , Amazon EC2

"Amazon EC2 Price Prediction Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 4, page no.i86-i90, April-2022, Available :http://www.jetir.org/papers/JETIR2204809.pdf

"Amazon EC2 Price Prediction Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 4, page no. ppi86-i90, April-2022, Available at : http://www.jetir.org/papers/JETIR2204809.pdf