Distributed Resource Management Across Data Regions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cloud computing solutions face challenges in dynamically adjusting physical resources to meet varying user demand and infrastructure changes, leading to delayed responses in scaling, reduced service quality, and increased costs due to inefficient monitoring of virtual machine instance resource utilization.
Innovation Solution
A system and method for dynamically managing computing resources across multiple data regions using monitoring modules that communicate operational information and generate optimization proposals to adjust resource allocation based on predefined constraints, ensuring continuous operation and optimal pricing through a distributed consensus protocol and shared database.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If monitoring is performed at the VM instance level to track resource utilization, then measurement precision of resource usage is improved, but response speed in scaling computing resources deteriorates due to the delayed detection of resource violations
Solution Approach 1:
The system segments the monitoring function by introducing regional leader nodes in each data region that independently monitor operational parameters and detect constraint violations. This segmentation allows parallel monitoring across multiple regions simultaneously, improving both measurement precision and response speed by distributing the monitoring workload rather than relying on centralized VM-level monitoring
Solution Approach 2:
The system performs preliminary actions by proactively detecting when operational parameters are approaching constraint violation thresholds and triggering optimization proposals before actual violations occur. This preliminary detection and response mechanism prevents service quality degradation by scaling resources in advance, rather than reacting after violations have already impacted service levels
2Reliability
If centralized monitoring of each VM instance is implemented to ensure service quality, then reliability of service delivery is improved, but device complexity of the monitoring and management system increases
Solution Approach 1:
The monitoring system is segmented into distributed regional leader nodes, each responsible for a specific data region. This segmentation reduces the complexity of any single monitoring component while maintaining comprehensive service quality oversight across all regions through the coordinated action of multiple independent monitoring entities
Solution Approach 2:
Regional leader nodes act as intermediaries between the infrastructure layer and the optimization layer. These intermediaries aggregate operational information from multiple sources, perform local analysis, and coordinate with other regions, thereby simplifying the overall system architecture by introducing structured intermediary components that manage complexity
3Adaptability or versatility
If dynamic resource allocation is implemented to meet varying user demand, then adaptability of the cloud platform is improved, but loss of time in coordinating resource changes across multiple data regions increases
Solution Approach 1:
The resource allocation system is segmented into autonomous regional units with their own leader nodes that can independently evaluate optimization proposals and coordinate changes within their regions. This segmentation enables parallel processing of resource allocation decisions across multiple regions, dramatically reducing the total coordination time while maintaining platform-wide adaptability
Solution Approach 2:
Optimization proposals are prepared and evaluated in advance with predefined constraints and target values. When demand changes are detected, the system quickly activates pre-configured optimization proposals rather than computing new allocation strategies from scratch, reducing the time loss in coordinating resource changes while maintaining high adaptability
Data Source
AI summary
The present invention describes a system and a method for dynamically optimising the computing resources allocated to a client application in different data regions of one or more service providers. A number of monitoring modules are provided in each data regions, which are configured to collect operational information from each data region, which is communicated to the other data regions. As such, all data regions are aware of the operational environment of the other data regions.