Power Metadata Allocation for Storage Tenant Billing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional charge-back mechanisms in cloud computing do not accurately capture power utilization, making it difficult for service providers to allocate and bill customers for energy costs, which is becoming a significant expense in data centers.
Innovation Solution
A method to determine and allocate power consumption in a computer storage system by obtaining metadata related to power consumption and storage configuration, allowing for precise attribution of power usage to applications and tenants based on data storage and access, enabling accurate charge-back mechanisms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional charge-back mechanisms are used in cloud computing, then implementation is simple, but power utilization cannot be accurately captured
Solution Approach 1:
The patent introduces power metadata as an intermediary element that mediates between the storage system and the charge-back mechanism. This metadata captures power consumption information without requiring direct integration between billing systems and power monitoring infrastructure, thus improving measurement precision while avoiding excessive complexity in the charge-back mechanism itself.
Solution Approach 2:
The patent segments power consumption measurement into discrete power metadata units that can be independently tracked, stored, and allocated. By breaking down power utilization into measurable segments associated with specific storage operations and data blocks, the system achieves accurate power capture without requiring a completely complex monolithic billing system.
2Measurement precision
If power consumption is accurately tracked and allocated to tenants, then billing accuracy improves, but system complexity increases
Solution Approach 1:
The patent performs preliminary actions by collecting and storing power metadata in advance of billing operations. Power consumption data is captured, aggregated, and organized into metadata structures before the actual charge-back process occurs, enabling accurate tenant attribution without adding complexity to the real-time billing system.
Solution Approach 2:
The patent creates copies of power consumption information in the form of power metadata that can be distributed and referenced by multiple systems without requiring complex real-time synchronization. This metadata copy mechanism allows accurate power tracking while keeping the allocation system relatively simple by working with static, pre-computed data representations.
3Loss of energy
If virtual machines are moved to optimize energy efficiency, then energy costs decrease, but system operational complexity increases
Solution Approach 1:
The patent implements feedback mechanisms where power metadata and consumption patterns are continuously monitored and fed back to the virtualization management system. This feedback enables automated, policy-driven decisions about VM placement and migration, reducing energy costs while managing operational complexity through intelligent automation rather than manual processes.
Solution Approach 2:
The patent enables dynamic parameter changes in VM placement decisions based on power consumption metrics. By adjusting VM location parameters according to power metadata and energy cost parameters, the system optimizes energy efficiency while the underlying virtualization infrastructure handles the complexity of coordinated migrations and service continuity.
Data Source
AI summary
Example embodiments of the present invention provide a method, an apparatus, and a computer program product for determining power consumption of a computer storage system attributable to an application. The method includes obtaining metadata relating to power consumption of a computer storage system and obtaining metadata relating to storage configuration of the computer storage system. Storage utilization of the computer system attributable to an application is then determined and a transformation is performed according to the metadata relating to power consumption of the computer storage system, the metadata relating to storage configuration of the computer storage system, and the storage utilization of the computer storage system attributable to the application.