Building Digital Twin Agent Processing for Scalable Timeseries Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing building management systems struggle to efficiently analyze and manage the vast amounts of data generated in smart building environments, leading to challenges in optimizing building operations and improving energy efficiency.

Innovation Solution

The implementation of an agent-entity based communication and control system, where agents are generated to communicate with entities in an entity database, allowing for data ingestion, entity creation, and operation of physical building entities based on timeseries data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If traditional building management systems are used to collect data from building equipment and sensors, then data collection capability is maintained, but data analysis efficiency deteriorates due to the exponential increase in data volume

Engineering Contradiction:
Improvedata volumeVSAvoiddata analysis efficiency
Core Design Contradiction:
Quantity of substanceVSProductivity

Solution Approach 1:

The patent segments the building management system into multiple intelligent agents, each responsible for specific building entities (equipment, spaces, systems). This segmentation allows distributed data processing where each agent independently analyzes data from its assigned entities, preventing the central system from being overwhelmed by exponential data growth while maintaining comprehensive data analysis capability across the entire building.

Inventive Principle:
Principle #1Segmentation

2Adaptability or versatility

If the number of buildings transitioning to smart building environment increases, then building automation coverage is improved, but data management complexity increases exponentially

Engineering Contradiction:
Improvesmart building coverageVSAvoiddata management complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a universal agent architecture where each agent can manage multiple types of building entities (equipment, spaces, systems) through standardized interfaces and protocols. This multi-functionality allows the same agent framework to handle diverse building types and equipment varieties, enabling scalable expansion to multiple buildings without proportionally increasing management complexity, as the universal agent design can be replicated and adapted across different building contexts.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Reliability

If centralized data analysis is used to manage building operations, then comprehensive control is achieved, but real-time processing capability deteriorates due to data volume

Engineering Contradiction:
Improvecontrol comprehensivenessVSAvoidreal-time processing speed
Core Design Contradiction:
ReliabilityVSSpeed

Solution Approach 1:

The patent divides the centralized control function into multiple distributed agents that operate autonomously on edge devices or local servers. Each agent processes data in real-time for its assigned building entities, eliminating the bottleneck of centralized processing. This segmentation maintains comprehensive control through coordinated agent interactions while achieving real-time processing speeds at the distributed level, as each agent handles only its specific data subset rather than the entire building's data volume.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS20250164950A1Building system with digital twin based agent processing
Publication Date: 2025.05.22 JOHNSON CONTROLS TECHNOLOGY CO
  • US20250164950A1 patent drawing
  • US20250164950A1 patent drawing
  • US20250164950A1 patent drawing

AI summary

A system can include one or more memory devices that can store instructions thereon. The instructions can, when executed by one or more processors, cause the one or more processors to receive timeseries data associated with a building, detect that a new building device has been added to the building, determine that a representation of the new building device is absent from a digital twin of the building, and execute a machine learning model to add the representation of the new building device to the digital twin of the building.