Sushma Sunkollu Nagaraj

Adaptive Cloud Resource Allocation using Deep Reinforcement Learning

Allocating cloud resources — deciding which physical machine should host each arriving task, virtual machine, or container — is a combinatorial, online, multi-resource problem that classical bin-packing heuristics (first-fit, best-fit) solve only crudely: they ignore workload str...

Reinforcement Learning for Auto-Scaling and Cost Optimization in Multi-Cloud

Auto-scaling decides how much capacity to provision for a workload and — in a multi-cloud setting — where to place it across providers, regions, and pricing models. Traditional threshold and forecast-based autoscalers react with fixed rules and tend to over-provision, wasting mon...