Device Utilization Estimation via Iterative Range Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Calculating average device utilization in computing systems using queueing theory is computationally prohibitive for embedded processors due to the involvement of logarithmic and exponential functions, and the number of servers is often unknown or subject to change, making it difficult to estimate accurately.
Innovation Solution
A method that determines an initial numerical range based on the count of service channels, repeatedly updates boundary values until they differ by a pre-determined threshold, and estimates utilization efficiently by interpolating within this range, allowing for accurate estimation of device utilization without relying heavily on complex mathematical functions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If queueing theory with logarithmic and exponential functions is used to calculate average device utilization, then measurement precision is improved, but device complexity increases and computational efficiency decreases
Solution Approach 1:
The patent transforms the complex queueing theory calculation involving logarithmic and exponential functions into a simplified parameter-based estimation method. By changing the computational parameters from complex mathematical functions to simpler arithmetic operations on queue length, service rate, and arrival rate, the system achieves acceptable utilization measurement without embedded processor overload
Solution Approach 2:
The patent uses lightweight, computationally inexpensive estimation algorithms that can be executed rapidly on resource-constrained embedded processors. These simplified calculation methods act as 'cheap' computational alternatives to the expensive queueing theory formulas, providing sufficient accuracy for monitoring purposes without requiring powerful processing hardware
2Adaptability or versatility
If the number of servers is unknown or subject to change, then adaptability is improved, but measurement precision deteriorates
Solution Approach 1:
The patent implements feedback mechanisms where the monitoring system continuously observes queue lengths, service rates, and arrival rates, then adjusts utilization estimates in real-time. This feedback loop allows the system to adapt to changing server configurations dynamically, maintaining measurement precision even when the number of servers varies without prior knowledge
Solution Approach 2:
The patent employs dynamic estimation methods that adjust calculation parameters based on current system state rather than relying on fixed, pre-determined server counts. The utilization estimation adapts dynamically to changing conditions, allowing accurate measurement whether servers are known, unknown, or subject to change
3Measurement precision
If complex mathematical functions are used for accurate utilization calculation, then measurement precision is improved, but productivity decreases
Solution Approach 1:
The patent changes the computational parameters from complex mathematical functions to simple arithmetic operations. By estimating utilization through straightforward calculations on queue metrics rather than evaluating logarithmic and exponential functions, the system maintains acceptable measurement precision while dramatically improving calculation speed and monitoring productivity
Data Source
AI summary
Monitoring a level of utilization is provided. An initial numerical range based, at least in part, on a count of service channels of a device is determined. A candidate numerical range, defined by an upper value and a lower value, based, at least in part, on the initial numerical range, is determined. A level of utilization of a first measurement interval of the device is estimated by: repeatedly updating the lower value and the upper value based, at least in part, on the level of utilization, until the lower value and the upper value differ less than a pre-determined threshold; and determining an estimated level of utilization based, at least in part, on the lower value and the upper value. The estimated level of utilization is reported.