Composable Core Matrix for Forecast-Based Storage Power Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data storage systems consume significant electrical power due to processor operations and cooling needs, and existing technologies fail to efficiently manage processor core allocations to balance performance and power consumption based on varying data access requirements.
Innovation Solution
Implement a storage system with dynamically adjustable processor cores allocated to pools based on time series forecasts and event-guided profiles, allowing for clock speed adjustments to match service levels and optimize power usage while maintaining performance compliance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If processor cores are allocated to pools with fixed clock speeds to maintain service level performance, then performance compliance is improved, but power consumption increases
Solution Approach 1:
The patent implements dynamic clock speed adjustment for processor cores based on time series forecasts of workload demand. Instead of fixed clock speeds, the system continuously adapts core configurations to match predicted service level requirements, reducing power consumption during low-demand periods while maintaining performance compliance during high-demand periods
Solution Approach 2:
The system changes the operational parameters of processor cores (clock speed, allocation to pools) based on forecasted workload characteristics. By adjusting these parameters dynamically rather than maintaining fixed settings, the system optimizes the balance between performance compliance and power consumption
2Use of energy by moving object
If processor cores are dynamically adjusted based on time series forecasts to reduce power consumption, then power efficiency is improved, but responsiveness to scheduled events deteriorates
Solution Approach 1:
The system performs preliminary actions by pre-configuring processor core allocations and clock speeds based on time series forecasts before scheduled events occur. This anticipatory adjustment allows the system to be pre-positioned for upcoming workload changes, maintaining both power efficiency and responsiveness when events actually occur
Solution Approach 2:
The system uses feedback from time series forecasting to continuously monitor and adjust processor core configurations. This closed-loop control ensures that the system responds appropriately to changing workload patterns while maintaining power efficiency, with the forecast mechanism providing early warning of scheduled events
3Adaptability or versatility
If processor cores are allocated to multiple pools with different clock speeds, then adaptability to varying service level demands is improved, but device complexity increases
Solution Approach 1:
The patent segments processor cores into multiple pools, with each pool assigned to specific service levels and configured with appropriate clock speeds. This segmentation allows different portions of the processor resource to be independently optimized for different performance requirements, improving adaptability while managing complexity through structured organization
Solution Approach 2:
The system creates a universal core allocation framework where processor pools can serve multiple service levels dynamically. The same physical cores can be allocated to different service level pools based on forecasted demand, providing multi-functionality that reduces the need for dedicated hardware for each service level
Data Source
AI summary
A storage system is configured with pools of processor cores. Each pool corresponds uniquely to one of the supported service levels of the storage system. In a dynamic time series forecast adjustment mode, processor cores within each pool run at a clock speed that is statically defined for the service level corresponding to the respective pool and core affiliations with pools are dynamically adjusted based on modelled data access latency. During a scheduled event, an event guided core matrix profile overrides the time series forecast adjusted core matrix profile. The event guided core matrix profile includes core clock speeds and pool affiliations, thereby enabling rapid reconfiguration.