Digital Twin Capacity Forecasting for Power, Space, and Cooling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems, such as telecommunications networks, face challenges in assessing and managing power, space, and cooling capacity due to non-standardized outputs from subsystems, leading to inefficient resource utilization and excessive greenhouse gas emissions, particularly due to outdated drawings and lack of accurate capacity predictions.
Innovation Solution
A system that converts non-standard outputs into standardized units to determine and predict capacity, using a digital twin simulation to forecast future needs and optimize resource allocation, thereby reducing energy consumption and emissions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If engineers rely on outdated drawings to understand system capacity, then the system design information is available, but the capacity assessment becomes inaccurate and unreliable
Solution Approach 1:
The system performs preliminary actions by continuously collecting operational data from subsystems and updating the digital twin model in advance, so that current and accurate capacity information is available before engineers need to make decisions, eliminating reliance on outdated drawings
Solution Approach 2:
A digital twin (virtual copy) of the physical system is created and maintained with real-time data from subsystems. This copy provides accurate, up-to-date capacity information without requiring engineers to consult outdated physical drawings, thus resolving the contradiction between information availability and assessment accuracy
2Adaptability or versatility
If subsystems operate without standardized output representation, then each subsystem maintains operational independence, but the overall system capacity cannot be cohesively assessed
Solution Approach 1:
The digital twin model serves as a universal platform that can represent and integrate data from diverse subsystems with different output formats. By converting various subsystem outputs into standardized representations within the digital twin, the system maintains subsystem independence while enabling cohesive overall capacity assessment
3Productivity
If the system lacks accurate capacity understanding, then resource allocation decisions cannot be optimized, but resources continue to be consumed at excessive levels
Solution Approach 1:
The system continuously collects operational data from subsystems, updates the digital twin model, and uses this feedback to provide accurate capacity information. This enables optimized resource allocation decisions that reduce energy consumption while maintaining system performance, directly addressing the contradiction between productivity and energy loss
Data Source
AI summary
Described herein is a capacity system that predicts capacity needs of a system. The capacity system captures outputs from meters coupled to subsystems within the system, where the outputs are not expressed in standard power units. For each subsystem, the capacity system determines values for a set of conversion factors related to the subsystem. The conversion factors describe the design and operation of the subsystem. The capacity system converts the outputs to standard power units based on the set of conversion factors and simulates behavior of the subsystems based on trends shown by the converted outputs. The capacity system forecasts an expected capacity of the system over a time period and uses the forecast to predict a date during the time period when the subsystem will experience a reduction in capacity.