Workload Attribute Matrix for Multi-Platform Cloud Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current platform-as-a-service (PaaS) cloud systems lack automated support for managing service levels and budget aspects, relying on administrators to identify resource shortages or excesses and manage cloud resource provisioning, which is inefficient and limited in optimizing workload placement across multiple platforms.
Innovation Solution
A computer-implemented method and program product that estimates attributes of running workloads on multiple platforms by mapping workloads to platforms, optimizing placements to minimize completion time and cost, considering service levels, budgets, resources, and platform constraints, and automatically updating these mappings in response to changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If administrators manually manage cloud resource provisioning and workload placement, then service level and budget compliance can be monitored, but the system lacks automation and scalability in optimizing workload placement across multiple platforms
Solution Approach 1:
The system enables self-service automation where the workload placement optimization is performed automatically without requiring administrator intervention. The system autonomously monitors platform attributes, estimates workload performance attributes, and determines optimal placements across multiple platforms, freeing administrators from manual management tasks while maintaining service level and budget compliance
Solution Approach 2:
The system provides a universal platform that handles multiple functions simultaneously: monitoring service levels, tracking budget compliance, estimating workload attributes across different platforms, and optimizing workload placement. This multi-functional approach consolidates what would otherwise require separate manual processes into a single automated system
2Adaptability or versatility
If more platforms are added to the system to improve scalability and flexibility, then workload placement options increase, but the complexity of tracking and managing platform attributes increases
Solution Approach 1:
The system introduces an intermediary layer that automatically collects, standardizes, and manages platform attributes from multiple cloud providers. This intermediary mechanism handles the complexity of tracking diverse platform characteristics while presenting a unified view for workload placement decisions, enabling flexibility across multiple platforms without proportionally increasing management complexity
Solution Approach 2:
The system dynamically adjusts and monitors platform attributes as parameters that influence workload placement decisions. By treating platform characteristics as可变 parameters that can be estimated and optimized, the system adapts to changes in platform capabilities and conditions, maintaining flexibility while managing complexity through parameter-based control
3Productivity
If workload attributes are estimated and stored in a matrix for optimization, then automated decision-making is enabled, but the system requires continuous updates in response to triggering events
Solution Approach 1:
The system implements periodic updates of the workload attribute matrix triggered by specific events rather than continuous monitoring. When triggering events occur (such as changes in platform attributes or workload characteristics), the system automatically updates the relevant matrix entries, balancing the need for current information with efficient resource utilization and minimizing unnecessary processing time
Data Source
AI summary
A computer-implemented method and a computer program product for estimating attributes of running workloads on platforms in a system of multiple platforms as a service. A computer receives definitions of respective workloads and respective platforms that are eligible to run a set of the respective workloads. The computer maps the respective workloads and the respective platforms to attributes of running the respective workloads on the respective platforms. The computer estimates the attributes and storing the attributes in a matrix. The computer updates the attribute in the matrix, in response to a triggering event for modifying the matrix.