Smart Meter Load Disaggregation via Central Pattern Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems, such as Smart Meters, provide real-time load information but lack the capability to easily disaggregate customer load and generation profiles to identify contributing appliances, requiring additional sensors and processing, which is inconvenient for customers and utilities.

Innovation Solution

A system and method that utilizes existing Smart Meters to analyze customer load and generation profiles by recognizing predetermined electrical patterns through feature extraction and pattern recognition, determining the devices contributing to these profiles without the need for additional software or processing at the customer premises, using a database of known load patterns to match against real-time data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If additional sensors are installed to sense load drawn by specific appliances, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
Improveload measurement precisionVSAvoidsensor installation complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts the disaggregation functionality from the customer premises equipment and relocates it to the central utility system. The Smart Meter continues to measure total load as before, but the complex pattern recognition and appliance identification algorithms are executed centrally at the utility, eliminating the need for additional sensors at customer sites while achieving detailed load breakdown.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The central utility system performs multiple functions: it maintains traditional billing and load monitoring while simultaneously executing advanced disaggregation analysis to identify individual appliances. This multi-functionality allows the existing Smart Meter infrastructure to support both aggregate monitoring and detailed appliance-level analysis without requiring separate dedicated systems.

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

2Loss of information

If additional processing is implemented at customer premises to disaggregate load profiles, then information completeness is improved, but ease of operation deteriorates

Engineering Contradiction:
Improveload breakdown informationVSAvoidcustomer configuration ease
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

Instead of having the customer premises system perform disaggregation analysis, the patent inverts the approach by having the central utility system perform the analysis on data transmitted from customer meters. This reversal eliminates the need for customers to configure additional software or processing equipment at their premises, while still providing complete load breakdown information through centralized computational resources.

Inventive Principle:
Principle #13The other way round (Inversion)

3Loss of information

If Smart Meters communicate detailed load profile data, then information completeness is improved, but loss of time in data transmission increases

Engineering Contradiction:
Improveload profile detailVSAvoiddata transmission time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent extracts only the essential aggregated load profile data from the detailed measurements for transmission to the central system. The Smart Meter continues to capture detailed appliance-level information locally, but only transmits summary statistics and key features to the utility, minimizing transmission time and bandwidth requirements while enabling centralized disaggregation analysis.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP2290328B1Utility management system
Publication Date: 2015.03.04 ACCENTURE GLOBAL SERVICES LTD
  • EP2290328B1 patent drawingFigure 1
  • EP2290328B1 patent drawingFigure 2
  • EP2290328B1 patent drawingFigure 3

AI summary

A system and method for analyzing a customer load and/or generation profile in order to disaggregate the customer load and/or generation profile is provided. The analysis of the customer load and/or customer generation profile may thereby determine the one or more devices that are operating and that contribute to the customer load and/or generation profile. In this way, the system and method may automatically analyze the customer load and/or generation profile in order to determine the one or more devices that contribute to the load and/or generation profile.