Building Energy Disaggregation Using Weather-Adjusted Load Separation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing energy load measurement systems in large non-residential buildings struggle to disaggregate energy consumption effectively, as they provide only gross levels of energy use, making it difficult to identify causal factors and implement energy-saving measures without requiring expert knowledge.

Innovation Solution

A signal processing pipeline that separates raw energy load data into weather-dependent and weather-independent components, further processing the weather-independent component to determine a baseline and variable energy use, allowing for the identification of specific load components such as lighting, HVAC, and miscellaneous loads, using weather and occupancy data for improved analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If smart meters are deployed to measure energy consumption, then energy use data becomes available, but the data remains at gross level only, making it difficult to identify causal factors

Engineering Contradiction:

Improveenergy consumption measurementVSAvoidcausal factors of energy use

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The patent applies segmentation by decomposing the aggregated energy consumption signal into individual appliance-level components. The system segments the gross energy data into distinct load profiles representing different appliances, enabling identification of specific energy-consuming devices and their operational patterns without requiring additional physical sensors at each appliance.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent uses machine learning models as an intermediary between the gross energy measurements and the detailed appliance-level insights. These models act as a mediator that translates aggregated utility data into actionable granular information about individual appliance usage, bridging the gap between available data and needed information.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Ease of manufacture

If energy load sensor systems are passively attached to energy conduits, then installation is easy and utility billing is supported, but only single gross level energy consumption is provided

Engineering Contradiction:

Improveinstallation easeVSAvoiddetailed energy use breakdown

Core Design Contradiction:

Ease of manufactureVSLoss of information

Solution Approach 1:

The system maintains the simple passive installation approach while applying segmentation to the data processing side. The physical sensor remains a simple attachment to the energy conduit, but the computational system segments the aggregated measurements into appliance-specific consumption patterns, achieving data granularity without increasing installation complexity.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent replaces the need for complex physical measurement systems with a computational approach. Instead of installing multiple physical sensors throughout the building, the system uses machine learning algorithms to extract detailed appliance-level information from the single point measurement, substituting mechanical complexity with computational intelligence.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If disaggregation is performed on commercial buildings with multiple units and varying tenants, then energy analysis is needed, but the complexity of multiple appliances and systems makes analysis difficult

Engineering Contradiction:

Improveenergy disaggregation accuracyVSAvoidsystem analysis complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies universality by developing a multi-functional machine learning framework that handles diverse building types, tenant configurations, and appliance combinations through a single unified system. The disaggregation algorithm is designed to adapt to various building scenarios without requiring scenario-specific customization, reducing analysis complexity while maintaining accuracy across different commercial building configurations.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12444973B2Energy disaggregation methods and systems using weather data

Publication Date: 2025.10.14 ARBNCO LTD

AI summary

The system may have an energy load data interface to receive energy load data originating from energy use sensors for the building; a weather data interface to receive weather data for a location that includes the building; a weather adjustment pre-processor to process the energy load data and the weather data and to determine a weather-dependent energy use component of the energy load data and a weather-independent energy use component of the energy load data; a baseline adjustment pre-processor to process the weather-independent energy use component of the energy load data and determine a baseline energy use component of the energy load data, wherein the baseline adjustment pre-processor is configured to remove the baseline energy use component from the weather-independent energy use component to determine a variable energy use component of the energy load data; and an energy use disaggregator to process the variable energy use component of the energy load data and determine a plurality of time varying load components of the energy load data.