Chilled Water System Predictive Modeling for Set Point Optimization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current cooling systems, particularly chilled water systems in data centers, lack the ability to model and predict how varying equipment set points affect performance parameters such as total gallons per minute, temperature differential, and supply chilled water temperature, and how changes in one component's set points impact other components in the system.

Innovation Solution

A comprehensive system and method that includes modules for calculating and optimizing the performance of various components of a chilled water system, allowing for predictive modeling and optimization of set points to achieve cost-effective and efficient operation by considering user-defined inputs and ambient conditions, using data sheets and flowcharts to analyze and adjust equipment staging and set points.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of energy

If comprehensive predictive modeling of cooling system components is implemented, then energy efficiency and cost savings are improved, but system complexity and computational requirements increase

Engineering Contradiction:
Improveenergy efficiencyVSAvoidsystem complexity
Core Design Contradiction:
Loss of energyVSDevice complexity

Solution Approach 1:

The cooling system is divided into discrete components (chillers, cooling towers, pumps, heat exchangers) with individual performance models. Each component has its own set of performance curves and parameters that can be independently analyzed and optimized, allowing comprehensive system modeling without overwhelming complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Performance data and curves for all system components are collected and stored in advance in a database. This preliminary data gathering enables the predictive modeling system to quickly evaluate different operating scenarios without requiring real-time complex calculations, reducing computational burden during operation.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If detailed performance curves and parameters for all components are collected and analyzed, then prediction accuracy is improved, but data collection and processing time increase

Engineering Contradiction:
Improveprediction accuracyVSAvoiddata collection time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

All necessary performance data, curves, and parameters for system components are collected and stored in a database during the design and commissioning phase. This preliminary data collection eliminates the need for extensive real-time data gathering when predictions are needed, significantly reducing processing time while maintaining high accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

Instead of collecting actual performance data in real-time, the system uses manufacturer-provided performance curves and characteristic data as copies of actual component behavior. These representative curves capture essential performance characteristics without requiring extensive field measurements.

Inventive Principle:
Principle #26Copying

3Productivity

If the system optimizes set points for multiple components simultaneously, then overall system performance is improved, but computational complexity and processing requirements increase

Engineering Contradiction:
Improvesystem performanceVSAvoidcomputational complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The optimization process addresses each system component separately using individual performance models and set of performance curves. By segmenting the optimization into discrete component-level analyses, the system can evaluate different set points for chillers, cooling towers, and pumps independently, then integrate results to determine overall system optimization without requiring complex simultaneous multi-variable calculations.

Inventive Principle:
Principle #1Segmentation

4Measurement precision

If real-time feedback from actual equipment performance is used, then model accuracy is improved, but system responsiveness and processing speed may be reduced

Engineering Contradiction:
Improvemodel accuracyVSAvoidprocessing speed
Core Design Contradiction:
Measurement precisionVSSpeed

Solution Approach 1:

The system incorporates feedback mechanisms where actual performance data from operating equipment is used to update and refine the predictive models. This feedback loop allows the system to learn from real-world performance and improve accuracy over time while maintaining the ability to provide timely predictions through the use of pre-established performance curves.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP2787296B1Method for energy analysis and predictive modeling of components of a cooling system
Publication Date: 2020.07.29 VERTIV CORP
  • EP2787296B1 patent drawingFigure 1
  • EP2787296B1 patent drawingFigure 2
  • EP2787296B1 patent drawingFigure 3

AI summary

A method is disclosed for analyzing performance of a chilled water (CW) system having a plurality of CW components. The method may consider a collection of at least one of allowable operating points, allowable operating ranges or allowable operating conditions, for each one of the CW components. A user set or system measured ambient wet bulb (WB) temperature may be considered for an environment in which at least a subplurality of the CW components are located. Equivalent loop conditions may be calculated for each of the CW components covering a load being thermally managed by the CW system. For each one of the calculated equivalent loop conditions, a processor may generate information for balancing the CW components to meet load requirements, and then analyze and select a balance condition that yields the user preferable optimization.