Autonomic Workflow Scheduler for Hybrid Cloud Resource Provisioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Managing and optimizing workflows on dynamically federated hybrid clouds is challenging due to the need to balance resource provisioning, scheduling, and quality of service while considering heterogeneous computing requirements and cost constraints.
Innovation Solution
An autonomic workflow framework that includes a workflow manager, an autonomic scheduler, and a resource manager, which provisions nodes across multiple clouds to achieve user objectives, such as time constraints, budget constraints, and privacy constraints, by utilizing a federated cloud infrastructure that integrates private and public clouds, grids, and data centers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If resources are dynamically provisioned across multiple clouds to meet user objectives, then workflow execution efficiency and quality of service are improved, but system complexity and management overhead increase
Solution Approach 1:
The patent introduces an autonomic scheduler as an intermediary component that manages resource provisioning across multiple clouds. The scheduler receives workflow descriptions with user objectives, automatically determines resource requirements, and provisions nodes without manual intervention. This mediator handles the complexity of multi-cloud coordination, allowing improved workflow execution efficiency while shielding users from system complexity.
Solution Approach 2:
The system implements self-service through autonomic computing principles where the scheduler automatically monitors workflow progress, detects resource bottlenecks, and dynamically provisions or deprovisions nodes based on real-time conditions. The system self-adjusts to meet user objectives without requiring manual reconfiguration, thereby improving productivity while managing complexity through automation.
2Adaptability or versatility
If heterogeneous cloud infrastructures are integrated into a federated cloud, then adaptability and resource versatility are improved, but system complexity and coordination difficulty increase
Solution Approach 1:
The patent creates a universal federated cloud platform that can accommodate heterogeneous cloud infrastructures (private clouds, public clouds, grids, data centers) through a common interface and standardized resource abstraction. The autonomic scheduler is designed to work with diverse node types and cloud providers, providing resource versatility while managing coordination complexity through unified management protocols.
Solution Approach 2:
The system manages heterogeneity by dynamically adjusting parameters such as resource provisioning levels, scheduling policies, and node configuration based on workflow requirements and cloud conditions. The autonomic scheduler modifies these parameters automatically to optimize performance across diverse infrastructures, enabling adaptability while reducing coordination difficulty through parameter-based control.
3Productivity
If autonomic scheduling is implemented to balance quality of service with costs, then resource optimization is improved, but computational overhead and processing time increase
Solution Approach 1:
The patent applies preliminary action by having users specify their objectives (time constraints, budget constraints, privacy constraints) in advance when submitting workflows. The autonomic scheduler uses these pre-defined criteria to make rapid scheduling decisions without requiring complex real-time analysis. This preliminary specification enables resource optimization while minimizing processing time during execution.
Solution Approach 2:
The system implements feedback mechanisms where the scheduler continuously monitors workflow progress, resource utilization, and cost metrics, then adjusts provisioning decisions accordingly. This closed-loop control enables automatic optimization of resource allocation based on actual performance and cost data, improving resource efficiency while maintaining responsive decision-making that limits additional processing time.
Data Source
AI summary
An autonomic workflow framework may include a federated cloud that includes a plurality of clouds, where each cloud in the federated cloud includes one or more nodes. An autonomic workflow framework may include a workflow manager configured to receive a workflow. The workflow may include a plurality of stages, and the workflow may be associated with a user objective. An autonomic workflow framework may include an autonomic scheduler in communication with the workflow manager. The autonomic scheduler may be configured to provision one or more of the one or more nodes to process the stages to achieve the user objective.