Cloud Datacenter Service Placement via Decision Tables
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Service providers face challenges in determining suitable deployment and placement of services in cloud data centers due to the complexity of considering physical topology and conflicting service constraints, leading to inefficient resource use and potential dissatisfaction among customers.
Innovation Solution
A system that includes a container set manager, decision table manager, and placement engine to determine container sets, relative priority levels, and generate a placement plan based on application and data center placement models, enabling efficient deployment and resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If service providers manually determine deployment plans considering physical topology, then deployment accuracy improves, but time consumption and complexity increase significantly
Solution Approach 1:
The patent replaces manual mechanical deployment planning with an automated computational system. The placement engine uses algorithms to automatically analyze service requirements, evaluate data center topology, and generate deployment plans, substituting human manual processes with automated computing mechanisms that are both accurate and time-efficient.
Solution Approach 2:
The patent creates a virtual representation (model) of the data center topology and service requirements. By working with this digital model rather than physical infrastructure directly, the system can rapidly simulate and evaluate multiple deployment scenarios without physical constraints, enabling fast and accurate deployment planning.
2Reliability
If service providers consider conflicting service constraints in deployment, then deployment suitability improves, but decision complexity increases
Solution Approach 1:
The patent segments the deployment decision process into distinct components: service requirement analysis, constraint evaluation, topology mapping, and placement optimization. Each component handles specific aspects of the complex decision independently, making the overall system more manageable while maintaining comprehensive consideration of all constraints.
Solution Approach 2:
The patent introduces a decision table as an intermediary structure that mediates between service requirements and physical topology constraints. This decision table serves as a structured framework that organizes conflicting constraints and guides the placement engine through complex decision-making processes systematically.
3Adaptability or versatility
If deployment plans are extended to accommodate new constraints, then adaptability improves, but implementation difficulty increases
Solution Approach 1:
The patent implements a dynamic deployment planning system that can adapt to changing service requirements and constraints. The placement engine re-evaluates deployment plans when new constraints are introduced, automatically adjusting resource allocation and placement decisions to accommodate evolving requirements without manual reconfiguration.
Solution Approach 2:
The patent enables flexible adjustment of deployment parameters such as resource allocation, service placement locations, and constraint priorities. By allowing parameter changes within the deployment plan, the system can adapt to new constraints while maintaining the overall structure and logic of the original plan, simplifying the implementation process.
Data Source
AI summary
A container set manager may determine a plurality of container sets, each container set specifying a non-functional architectural concern associated with deployment of a service within at least one data center. A decision table manager may determine a decision table specifying relative priority levels of the container sets relative to one another with respect to the deployment. A placement engine may determine an instance of an application placement model (APM), based on the plurality of container sets and the decision table, determine an instance of a data center placement model (DPM) representing the at least one data center, and generate a placement plan for the deployment, based on the APM instance and the DPM instance.