Virtualized Computing Environment Configuration Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Optimizing a cloud-computing environment is challenging due to the numerous configurable components and shared resources, where optimizing one component can negatively impact others, making simultaneous optimization of multiple components inefficient or inaccurate within a reasonable time frame.
Innovation Solution
A method involving a processor that selects candidate resource and environment configurations, provisions a virtual test environment, evaluates fitness characteristics, and iteratively revises configurations until an optimal configuration is identified, using a biological ecosystem model to simulate and optimize the cloud-computing environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If simultaneous optimization of multiple components is attempted, then optimization accuracy improves, but computation time becomes unreasonably long
Solution Approach 1:
The patent segments the optimization problem into hierarchical levels: individual component optimization, subsystem optimization, and full system optimization. This allows the system to tackle smaller optimization problems separately and combine results, reducing the computational burden of optimizing all components simultaneously while maintaining acceptable accuracy through iterative refinement.
Solution Approach 2:
The patent performs preliminary optimization of individual components and subsystems before conducting full system optimization. By pre-optimizing smaller units and storing their results, the system reduces the search space for subsequent full-system optimization, significantly cutting computation time while preserving optimization accuracy.
2Reliability
If parameters of multiple components are optimized together, then system-wide performance improves, but complexity of the optimization process increases
Solution Approach 1:
The optimization process is divided into manageable segments corresponding to different system levels (components, subsystems, full system). Each segment handles a specific scope of parameters, reducing the complexity of any single optimization task while achieving system-wide performance improvement through cumulative effects.
Solution Approach 2:
The patent introduces a hierarchical dimension to the optimization process, organizing parameters and components into multiple levels. This dimensional transformation converts a single complex high-dimensional optimization problem into multiple lower-dimensional problems that are easier to solve while collectively addressing system-wide performance.
3Measurement precision
If more candidate configurations are evaluated, then optimization accuracy improves, but computation resources are consumed excessively
Solution Approach 1:
The patent evaluates a partial set of candidate configurations at each hierarchical level rather than exhaustively evaluating all possible configurations. By selecting representative subsets and using iterative refinement, the system achieves satisfactory optimization accuracy while consuming reasonable computation resources.
Solution Approach 2:
The system performs preliminary evaluation and filtering of candidate configurations at lower hierarchical levels before proceeding to higher levels. This preliminary action eliminates obviously suboptimal configurations early, reducing the number of configurations that require full evaluation and thus conserving computation resources.
Data Source
AI summary
A method and associated systems for optimizing a computing platform. A processor joins sets of configurable parameters into groups that each identifies a configuration of the computing environment or of a component or subsystem of the computing environment. The processor generates a set of variations of each group, where each variation identifies a candidate configuration of the component, subsystem, or platform, and where each candidate configuration identifies a distinct set of values of the group of parameters associated with that component, subsystem, or platform. Each configuration of this first generation of configurations undergoes a massively parallel iterative procedure that generates a next generation of configurations by performing operations upon the first generation that are similar to those of a natural-selection process. The procedure repeats until successive generations converge, within resource constraints, to a fittest generation that represents an optimal or most nearly optimal configuration of the computing platform.