Hierarchical Compressor Control for Predictive Switching Schedules

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing compressor systems lack efficient control methods that consider future demand predictions and optimal switching times, leading to suboptimal operation and higher energy costs due to their reliance on current state-based control without predictive capabilities.

Innovation Solution

A hierarchical online compressor control model that splits the control problem into manageable scheduling and prediction tasks, utilizing a central controller to optimize compressor operations with a long-term horizon, incorporating a cloud-based long-term scheduling model and local short-term scheduling, with safety checks to ensure robustness and efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Use of energy by moving object

If a long-term horizon scheduling model is used to optimize compressor operations, then energy efficiency is improved, but computational complexity and time delay increase

Engineering Contradiction:

Improveenergy efficiencyVSAvoidcomputational complexity

Core Design Contradiction:

Use of energy by moving objectVSDevice complexity

Solution Approach 1:

The control system is divided into a hierarchical structure with a cloud-based long-term scheduling model and a local short-term control model. The long-term model handles strategic optimization with minimal computational burden, while the short-term model handles immediate operational adjustments. This segmentation allows energy optimization without requiring the entire system to perform complex computations in real-time.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The long-term scheduling model generates optimal schedules in advance based on predicted demand patterns, storing pre-computed optimization strategies in the cloud. This preliminary action allows the system to benefit from complex optimization calculations without performing them during critical real-time operation, thus reducing time delay while maintaining energy efficiency.

Inventive Principle:

Principle #10Preliminary action

2Speed

If real-time control based on current state is used, then responsiveness is improved, but energy optimization capability deteriorates

Engineering Contradiction:

ImproveresponsivenessVSAvoidenergy optimization

Core Design Contradiction:

SpeedVSUse of energy by moving object

Solution Approach 1:

The system adds a temporal dimension to control by implementing a hierarchical structure where the cloud-based long-term model operates on a strategic timescale for energy optimization, while the local short-term model operates on an tactical timescale for responsiveness. This dimensional separation allows both real-time responsiveness and long-term energy optimization to coexist without conflict.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

3Use of energy by moving object

If centralized control is implemented to optimize compressor operations, then energy efficiency is improved, but system complexity and cyber vulnerability increase

Engineering Contradiction:

Improveenergy efficiencyVSAvoidcyber threats

Core Design Contradiction:

Use of energy by moving objectVSObject-affected harmful factors

Solution Approach 1:

The control architecture is segmented into cloud-based and local components. The cloud handles long-term scheduling with minimal data exchange, while local units maintain autonomous short-term control capabilities. This segmentation reduces cyber vulnerability by limiting the attack surface and ensuring that compromise of one component does not endanger the entire system, while still achieving centralized energy optimization.

Inventive Principle:

Principle #1Segmentation

4Use of energy by moving object

If complex scheduling algorithms are used for long-term optimization, then energy efficiency is improved, but implementation time and computational resources increase

Engineering Contradiction:

Improveenergy efficiencyVSAvoidimplementation time

Core Design Contradiction:

Use of energy by moving objectVSLoss of time

Solution Approach 1:

Complex scheduling algorithms are executed in advance by the cloud-based long-term model to generate optimized schedules. These pre-computed schedules are then implemented by the local short-term model without requiring re-computation. This preliminary execution of complex algorithms eliminates implementation time delays during operational phases while maintaining energy efficiency benefits.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20260078749A1System and method for hierarchical compressor control

Publication Date: 2026.03.19 ATLAS COPCO AIRPOWER NV

AI summary

A method and system are provided at a local network level and a remote cloud level. The local network level includes compressors and a controller configured to create a short-term schedule having a short-term switching sequence for operation of the compressors, perform a validation assessment on the short-term schedule, and send the short-term schedule to a platform embedded with the main controller of the system. A prediction model, a long-term scheduling approach, and cloud storage that stores measurements from the compressors and executable instructions are provided at the remote cloud level. The long-term schedule is transferred to a safety check module at the local network level. Following validation, the embedded platform refines the long-term switching sequence and the safety check module allows the system to implement the long-term schedule, having the short-term schedule as a backup option.