Appliance-Level Energy Disaggregation for TOU Load Shifting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Household users lack visibility into their energy consumption and its real-time impact on time-of-use (TOU) energy pricing, making it difficult to make informed decisions about appliance usage and energy efficiency.

Innovation Solution

A method and device that receive and process entire energy profile data to generate disaggregated appliance-level data, apply behavior shift analysis based on TOU pricing and historical usage patterns, and predict potential energy savings, enabling users to optimize energy usage by shifting consumption to off-peak times.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If NILM is used to break down electricity usage without sub-metering devices, then device complexity and installation cost are reduced, but measurement precision of individual appliance consumption is degraded

Engineering Contradiction:

Improvecomplexity of energy monitoring systemVSAvoidprecision of individual appliance energy consumption measurement

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent segments the aggregate energy consumption signal into individual appliance-level signals through signal processing techniques. The system divides the whole-house load profile into component signals representing different appliances by analyzing unique signatures and patterns in the aggregated data, enabling appliance-specific monitoring without physical segmentation or sub-metering devices.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary processing layer that acts between the aggregate energy meter and the user interface. This intermediary system uses signal processing algorithms to extract and identify individual appliance consumption patterns from the aggregated signal, serving as a mediator that translates coarse aggregate data into fine-grained appliance-level information without requiring direct measurement of each appliance.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of information

If users are provided with detailed appliance-level energy consumption information, then user awareness and energy efficiency improve, but information processing complexity increases

Engineering Contradiction:

Improvevisibility of energy consumption informationVSAvoidcomplexity of data processing system

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The patent implements feedback mechanisms that provide users with actionable insights about their energy consumption patterns. The system analyzes disaggregated appliance-level data and feeds back recommendations to users about when and how to modify their energy usage behavior, creating a closed-loop system that continuously improves energy efficiency based on observed patterns and TOU pricing structures.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent enables the system to automatically perform complex data processing, appliance identification, and behavior analysis without requiring user intervention. The NILM system self-servicefully segments signals, identifies appliances, and generates insights, reducing the burden on users while maintaining high information quality and minimizing perceived system complexity.

Inventive Principle:

Principle #25Self-service

3Loss of energy

If energy consumption is shifted from peak to off-peak times, then energy cost and peak demand are reduced, but user convenience may be degraded

Engineering Contradiction:

Improveenergy cost and peak demandVSAvoiduser convenience

Core Design Contradiction:

Loss of energyVSEase of operation

Solution Approach 1:

The patent uses preliminary action by pre-cooling or pre-heating spaces, pre-charging batteries, or pre-preparing appliances before peak pricing periods begin. The system analyzes predicted peak times and TOU pricing structures to advance energy-intensive tasks to off-peak periods, reducing peak demand while maintaining user comfort and convenience through proactive scheduling.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements dynamic scheduling that adapts to user preferences, weather conditions, and real-time pricing signals. The system dynamically adjusts energy consumption timing based on changing conditions, allowing flexible load shifting that responds to user needs while optimizing cost savings and demand reduction, rather than using fixed rigid schedules.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11435772B2Systems and methods for optimizing energy usage using energy disaggregation data and time of use information

Publication Date: 2022.09.06 BIDGELY

AI summary

The present invention is generally directed to systems and methods for optimizing energy usage in a household. For example, methods for optimizing energy usage in a household may include steps of: receiving, using an energy optimization device, entire energy profile data associated with the household; obtaining, using the energy optimization device, time of use (TOU) energy pricing structure; processing, the entire energy profile data to generate disaggregated appliance level data related to one or more appliances used in the household; retrieving historical patterns of energy usage of the household during both peak and non-peak time periods; applying a behavior shift analysis on the disaggregated data based at least in part on the TOU energy pricing structure, disaggregated data, and historical patterns of the energy usage; and predicting potential energy savings based at least in part on the behavior shift analysis.