Search
View Program
Advanced search
Return to Search Results
Print
Session Title
AI and Optimization Techniques in Forecasting and Security
Hierarchical Forecasting for Amazon EC2 demand
4:18 PM - 4:36 PM
Yiming Wang
,
Amazon
;
Ebrahin Nasrabadi
,
Amazon
.
Amazon’s Stores, Digital, and Other (SDO) is the largest user of AWS EC2 capacity. This poster introduces our in-house Hierarchical Bayesian and Hierarchical Reconciliation forecasting methods to forecast SDO EC2 demand. The demand forecasts are published at bi-monthly cadence, covering a rolling 2-year horizon, and at granularity of business group (Stores, Digital, Other), availability zone (e.g., us-east-1a), and instance type (e.g., c5.12xlarge) level. The forecasts can be used for AWS capacity planning to drive operational and financial decisions on global AWS data center infrastructure and space plan. To address the cold-start challenges in forecasting new instance generation and availability zones’s demand, we developed a novel Hierarchical Bayesian time series forecasting model. In back-testing, our model was proven to reduce the forecast error measured in Weighted Absolute Percentage Error (WAPE) to 18.6% from 30.0% using Meta’s open-source Prophet package for new AWS EC2 instances launched in 2023.
Print Abstract
More in this Session
4:00 PM - 4:18 PM
Convergence-Guaranteed Elastic Net Graphical Model Estimatio...
Dzung Phan
, IBM Research; Tsuyoshi Ide, IBM Research; Matt Menickelly, Argonne National Laboratory; Jayant Kalagn...
4:18 PM - 4:36 PM
Hierarchical Forecasting for Amazon EC2 demand
Yiming Wang
, Amazon; Ebrahin Nasrabadi, Amazon.
4:36 PM - 4:54 PM
Securing through evaluating: An autonomous cloud security as...
Yue Fang, School of Management, Xi'an Jiaotong University; YING GAO, School of Management, Xi'an Jiaotong University;
4:54 PM - 5:12 PM
A Deep Reinforcement Learning-Based Technique for Optimal Po...
Sepehr Soltani
, American Airlines; Ehsan Ghafourian, Iowa State University; Diego Martin, Universidad Politécnica...