Smart Cloud Workload Balancer for Dynamic VM Topology Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional workload optimization methods in cloud computing systems rely on static planning, leading to unnecessary software license costs when all physical servers are licensed, and reduced performance when not enough licenses are purchased, resulting in inefficient resource utilization.
Innovation Solution
A dynamic workload optimization system using a smart cloud workload balancer that configures and reconfigures virtual machine topology based on business policies, software license costs, and power consumption, optimizing the distribution of workloads across physical servers to minimize total operational costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the cloud computing system acquires enough number of software licenses to fully utilize all physical servers at all time, then the cloud computing system can maintain high performance and full utilization, but the cloud computing system incurs unnecessary additional software license cost
Solution Approach 1:
The patent implements dynamic workload balancing that continuously monitors and adjusts virtual machine assignments across physical servers based on real-time utilization metrics. This allows the system to optimize software license usage by dynamically allocating workloads to the minimum necessary number of licensed servers while maintaining overall system performance, rather than statically licensing all servers at full capacity.
Solution Approach 2:
The system changes operational parameters by adjusting virtual machine placement and server activation states based on workload demands. By dynamically modifying which physical servers are active and how workloads are distributed, the system can reduce software license costs while maintaining productivity through efficient resource utilization.
2Quantity of substance
If the cloud computing system has too few number of software licenses to reduce extra cost, then the cloud computing system reduces software license cost, but the utilization of the physical servers degrades and performance is reduced
Solution Approach 1:
The dynamic workload balancing system continuously monitors server utilization and workload demands, adjusting virtual machine assignments in real-time. This enables the system to maintain high physical server utilization even with fewer software licenses by dynamically allocating available licensed capacity to handle peak workloads and consolidating resources during low-utilization periods.
Solution Approach 2:
The patent creates a multi-functional workload balancing system that can adapt to varying workload conditions. The same dynamic balancing mechanism serves multiple purposes: optimizing software license utilization, maintaining physical server productivity, and ensuring system performance across different operational scenarios, making the limited license pool more versatile and effective.
3Stability of the object's composition
If the cloud computing system uses static planning for workload distribution, then the system configuration is simple and stable, but the system cannot adapt to changing workload demands and incurs inefficiency
Solution Approach 1:
The patent implements a dynamic workload balancing system that continuously monitors system state and automatically adjusts virtual machine assignments across physical servers. This dynamic approach maintains stability through automated, policy-driven decisions while simultaneously improving productivity by adapting to changing workload demands, eliminating the need for manual reconfiguration.
Solution Approach 2:
The system incorporates feedback mechanisms that continuously monitor workload metrics, server utilization, and performance data. This feedback loop enables the dynamic workload balancer to make informed adjustments to virtual machine assignments, maintaining system stability through consistent monitoring while optimizing productivity based on real-time conditions.
Data Source
AI summary
A system and associated method for dynamically optimizing workload of a cloud computing system is disclosed. The cloud computing system comprises virtual machines, physical servers, a smart cloud workload balancer (SCWB), and an objects database (ODB) storing various parameters controlling operations and optimization behavior of the cloud computing system. The SCWB configures and runs the cloud computing system based on a VM topology. When the SCWB determines that the cloud computing system does not perform optimally based on a total cost of software cost for licensing all VMs and power cost of all running physical server, the SCWB calculates a new VM topology that minimizes the total cost and relocates VMs pursuant to the new VM topology.