Energy Disaggregation via Impulse Pairing and Bundling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing non-intrusive appliance load monitoring (NIALM) systems fail to provide near real-time energy usage data, leading to limited user empowerment in modifying energy consumption, and often require additional components or have low confidence in identifying specific appliances, neglecting user knowledge and non-electrical information.

Innovation Solution

A system for energy disaggregation using whole-house energy usage profiles, pairing and bundling impulses to identify appliance cycles, with a classification module and graphical user interface for user validation, enabling real-time data analysis and improved accuracy through generic and house-specific models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If prior art NIALM techniques are used to break down energy usage post-consumption, then energy itemization is achieved, but near real-time information for immediate user action is not provided

Engineering Contradiction:

Improvetime delay in energy usage informationVSAvoidconfidence level of appliance identification

Core Design Contradiction:

Loss of timeVSMeasurement precision

Solution Approach 1:

The patent segments the energy disaggregation process into distinct modules: impulse detection module, impulse pairing module, impulse bundling module, and classification module. This segmentation allows real-time processing of energy waveform data through specialized sub-functions, enabling near real-time appliance identification while maintaining measurement precision through dedicated processing for each stage.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-defining appliance templates and characteristics before actual energy disaggregation. The classification module uses pre-established knowledge bases of appliance signatures to immediately identify appliances as impulses are detected and paired, eliminating post-consumption analysis delays while maintaining high confidence through template matching.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If additional components or sub-metering devices are installed for appliance monitoring, then measurement precision is improved, but device complexity and installation requirements increase

Engineering Contradiction:

Improveappliance identification accuracyVSAvoidsystem component requirements

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements a universal energy disaggregation system that uses a single whole-house energy meter to perform multiple functions: detecting impulses, pairing transitions, bundling impulses, and classifying appliances. This multi-functional approach achieves precise appliance identification without requiring separate sub-metering devices for each appliance, reducing overall system complexity while maintaining measurement precision.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system enables self-service by utilizing existing user knowledge and appliance characteristics stored in databases. The classification module automatically matches detected impulse patterns against known appliance signatures without requiring additional sensors or user intervention, achieving accurate identification using only the standard energy meter already present in the system.

Inventive Principle:

Principle #25Self-service

3Productivity

If software analysis is performed on past data collected, then energy usage breakdown is achieved, but real-time data analysis for immediate user empowerment is not provided

Engineering Contradiction:

Improvespeed of energy data processingVSAvoidnon-electrical information and user knowledge

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

The patent implements feedback mechanisms where the classification module continuously compares detected impulse patterns against stored appliance templates and updates identification confidence in real-time. This feedback loop enables immediate user empowerment by providing real-time appliance identification results while incorporating user knowledge and appliance characteristics to refine accuracy, processing energy data as it is generated rather than analyzing past data.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS10460274B2Energy disaggregation techniques for whole-house energy consumption data

Publication Date: 2019.10.29 BIDGELY

AI summary

The present invention is directed to systems and methods for performing energy disaggregation of a whole-house energy usage waveform, based at least in part on the whole-house energy usage profile, training data, and predetermined generic models, including: a module for pairing impulses identified in the whole-house energy usage waveform to indicate an appliance cycle, pairing impulses with at least one up transition with at least one down transition; a module for bundling impulses that are representative of an appliance cycle; a classification module, which upon determination of a type of appliance associated with bundles, is configured to classify the bundles of transitions in accordance with bundles exhibited by similar appliances with similar characteristics; and utilizing such pairing module and module for bundling to perform energy disaggregation. Moreover, the present invention sets forth graphical user interfaces for the presentation of such data and the receipt of user-supplied validation and information.