Cloud VM Scheduling via Lag Time Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In cloud computing, satisfying service-level agreements (SLAs) is challenging due to lag times in delivering virtual resources, which can lead to compromised quality of service and increased costs from inefficient resource provisioning.
Innovation Solution
A method and system for scheduling virtual machines in a cloud computing infrastructure that involves collecting and analyzing lag time data to estimate the time needed to acquire new resources, allowing for more predictable and efficient management of resources by determining whether to start a new virtual machine based on the estimated lag time, thus ensuring compliance with SLAs and improving resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If virtual machines are provisioned on-demand in cloud computing infrastructure, then computing resources become available to meet service requests, but lag times occur in the delivery of virtual resources causing SLA violations
Solution Approach 1:
The patent applies preliminary action by proactively provisioning virtual machines before they are actually needed. The system monitors workload patterns and predicts future resource requirements, then pre-creates virtual machines in advance. This eliminates the lag time between service requests and resource availability, ensuring SLA compliance while maintaining on-demand provisioning benefits.
2Loss of time
If virtual machines are pre-provisioned to eliminate lag times, then service delivery speed improves, but resource utilization efficiency decreases due to idle resources
Solution Approach 1:
The patent implements dynamics by making the virtual machine provisioning system adaptive and responsive to changing workload conditions. The system continuously monitors actual workload demands and dynamically adjusts the number of pre-provisioned virtual machines. When demand is high, more VMs are pre-created; when demand is low, pre-provisioning is reduced. This dynamic approach eliminates lag times while optimizing resource utilization efficiency.
3Reliability
If more virtual machines are provisioned to meet peak demand, then service-level agreement compliance improves, but infrastructure costs increase due to inefficient resource provisioning
Solution Approach 1:
The patent applies feedback by implementing a closed-loop control system that continuously monitors workload patterns, predicts future demands, and adjusts virtual machine provisioning accordingly. The system uses historical data and real-time metrics to forecast resource requirements, then provisions VMs in advance of predicted peaks. This feedback mechanism ensures SLA compliance during high-demand periods while avoiding over-provisioning during low-demand periods, thus optimizing resource quantity.
Data Source
AI summary
A method of scheduling one or more virtual machines in a cloud computing infrastructure may include identifying, by a computing device, lag time data that has been collected over a period of time and that corresponds to one or more virtual machines in a cloud computing infrastructure, computing, by the computing device, a cumulative description of the identified lag time data, identifying a target performance level, determining, by the computing device, an estimated lag time that corresponds to the target performance level, and determining, by the computing device, whether to start a new virtual machine based, at least in part, on the estimated lag time.