Meter Anomaly Detection via Usage Data Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Utility companies face significant challenges in detecting meter anomalies such as meter-no-reading, meter-by-pass, and meter-silting, which result in revenue loss and inefficiencies, as existing methods are costly and inefficient, requiring manual inspection of each meter.

Innovation Solution

A data analysis method that collects and processes meter reading data to identify anomalous usage patterns, assigning anomaly scores and ranking meters based on these patterns, using time series techniques and expert knowledge without additional equipment or sensors, focusing on historical data for billing purposes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual inspection of each meter is performed to detect anomalies, then detection accuracy is improved, but cost and time consumption increase significantly

Engineering Contradiction:

Improveanomaly detection accuracyVSAvoidinspection time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the large-scale meter inspection problem into smaller analytical units by analyzing meter readings in groups or individually through automated data processing, allowing efficient handling of numerous meters without manual intervention for each one

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent replaces the mechanical manual inspection process with an automated computer-based system that collects, processes, and analyzes meter reading data algorithmically, eliminating the need for physical meter-by-meter examination while maintaining detection accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If manual inspection of each meter is performed to detect anomalies, then detection accuracy is improved, but cost increases significantly

Engineering Contradiction:

Improveanomaly detection accuracyVSAvoidinspection cost

Core Design Contradiction:

Measurement precisionVSLoss of energy

Solution Approach 1:

The patent replaces expensive manual inspection operations with automated computational analysis of existing meter reading data, significantly reducing labor costs and resource consumption while maintaining the ability to detect anomalies accurately

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent uses copies of meter reading data that already exist in the system for billing purposes, analyzing these data copies to detect anomalies without requiring additional physical inspection resources or generating extra operational costs

Inventive Principle:

Principle #26Copying

3Reliability

If additional equipment or sensors are installed to detect meter anomalies, then detection capability is improved, but device complexity and installation cost increase

Engineering Contradiction:

Improveanomaly detection capabilityVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent uses existing meter reading data copies that are already collected for billing purposes, analyzing these data copies to detect anomalies without requiring additional sensors, meters, or hardware equipment

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent enables the existing metering system to serve dual purposes: continuing its primary function of measuring consumption for billing while simultaneously providing data for anomaly detection, eliminating the need for separate detection equipment

Inventive Principle:

Principle #25Self-service

4Reliability

If comprehensive meter inspection is performed to detect all anomaly types, then detection coverage is improved, but productivity decreases due to resource constraints

Engineering Contradiction:

Improveanomaly detection coverageVSAvoidinspection efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent replaces resource-intensive manual inspection with automated computational analysis that can process numerous meter readings simultaneously and continuously, dramatically improving inspection efficiency while maintaining comprehensive anomaly detection coverage

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent enables continuous analysis of meter reading data as it is collected, allowing the system to detect anomalies in real-time or near-real-time without interrupting normal meter operations, thereby maintaining high productivity while ensuring comprehensive detection

Inventive Principle:

Principle #20Continuity of useful action

Data Source

PatentUS10088335B2Anomaly detection using usage data for metering system

Publication Date: 2018.10.02 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A method, system and computer program product for detecting anomalies in a metering system. In one embodiment, data representing usage of a defined commodity are collected from meters, and the data collected over a given time period are analyzed to identify any of the meters showing at least one defined type of anomalous usage pattern. For each of the meters showing an anomalous usage patterns, an anomaly score is determined for the usage pattern shown, and the anomaly scores are used to rank the meters. In one embodiment, the collected data are analyzed to identify any of the meters showing one or more of a group of types of anomalous patterns including meter-no-reading, meter-by-pass, and meter-silting patterns. Embodiments of the invention utilize time series techniques and data analysis on meter reading data. Further, embodiments of the invention require no additional installation of equipment or sensors.