Unified Cloud Resource Metering for Actual Usage Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing users often rent maximum computing resources based on theoretical maximum workloads, leading to inefficiencies and waste due to infrequent surges in usage, with providers charging based on rented resources rather than actual consumption.
Innovation Solution
A system and method to measure physical computing resources, normalize them to a common unit, and sum the normalized measurements to represent total usage as a single value, enabling accurate monitoring and optimization of resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If users rent maximum computing resources based on theoretical maximum workloads, then system performance reliability is improved, but resource waste increases
Solution Approach 1:
The patent implements dynamic resource allocation by continuously monitoring actual resource usage metrics (CPU utilization, memory consumption, storage I/O, network bandwidth) and adjusting the normalized resource allocation accordingly. This replaces static maximum allocation with adaptive allocation that responds to changing workload demands, ensuring reliability during surges while minimizing waste during low-utilization periods
Solution Approach 2:
The patent transforms disparate resource parameters (CPU cycles, memory bytes, storage I/O operations, network packets) into a unified normalized resource metric through mathematical conversion factors. This parameter transformation enables aggregation of heterogeneous resources into a single measurable quantity that can be dynamically adjusted based on actual usage patterns, resolving the contradiction between maintaining sufficient capacity and avoiding over-provisioning
2Stability of the object's composition
If cloud providers charge based on rented resources rather than actual consumption, then revenue stability is improved, but user cost efficiency deteriorates
Solution Approach 1:
The patent implements a feedback mechanism that continuously measures actual resource consumption across multiple metrics (CPU, memory, storage, network) and uses this information to adjust billing calculations. The system provides users with detailed usage reports and enables dynamic pricing adjustments based on actual consumption patterns, creating a feedback loop that aligns costs with actual value delivered while maintaining predictable billing structures
Solution Approach 2:
The patent creates a universal billing framework that handles multiple types of computing resources (CPU, memory, storage, network) through a single normalized resource metric and unified pricing model. This multi-functional approach allows providers to charge accurately for diverse resource types while maintaining revenue stability, eliminating the need for separate pricing strategies for each resource type
3Measurement precision
If disparate computing resources are measured separately, then measurement precision for individual resources is improved, but overall resource optimization deteriorates
Solution Approach 1:
The patent merges measurements of disparate computing resources (CPU cycles, memory bytes, storage I/O operations, network packets) into a single normalized resource metric through mathematical conversion factors. This combining approach preserves the precision of individual resource measurements while enabling aggregate analysis and optimization across the entire resource portfolio, allowing providers to identify overall utilization patterns and optimize total resource allocation
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A method for quantifying resource usage may include measuring a quantity of a plurality of physical computing resources being used over a period of time. The method may also include normalizing each measured quantity of each physical computing resource being used. The method may also include summing the normalized measured quantities of the physical computing resources being used to generate a single usage value representative of the physical computing resources being used over the period of time.