Smart Meter Anomaly Monitoring With Dynamic Shared Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Smart meters struggle to detect anomalies such as leaks or fraud efficiently without increasing complexity or data exchange volume, which is critical for battery-powered meters with long lifespans like water or gas meters.
Innovation Solution
A monitoring method where each meter acquires primary measurements and selects pertinent ones based on specific criteria, transmitting these to a remote processor device for centralized analysis and dynamic threshold adjustment, minimizing data exchange and maintaining meter simplicity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If meters perform comprehensive anomaly detection locally, then detection accuracy improves, but device complexity increases
Solution Approach 1:
The system divides anomaly detection functionality into two segments: meters perform local pre-processing and selection of pertinent measurements, while the remote processor performs comprehensive anomaly detection and threshold adjustment. This segmentation allows accurate detection without requiring full detection capability in each meter.
Solution Approach 2:
The remote processor acts as an intermediary that receives pertinent measurements from meters and performs the complex anomaly detection algorithms. This intermediary handles the computational complexity centrally while meters remain simple data collection points.
2Measurement precision
If meters transmit all primary measurements to the remote processor, then detection accuracy improves, but data exchange volume increases
Solution Approach 1:
The system extracts only the pertinent measurements from the complete set of primary measurements before transmission. Each meter applies selection criteria to identify and transmit only those measurements that are relevant for anomaly detection, filtering out redundant data.
Solution Approach 2:
Meters perform preliminary processing and selection of measurements before transmission. By pre-selecting pertinent measurements at the source, the system reduces the data volume that needs to be transmitted while ensuring that the most relevant information is available for anomaly detection.
3Adaptability or versatility
If detection threshold is adjusted dynamically in each meter, then detection adaptability improves, but device complexity increases
Solution Approach 1:
Instead of having each meter independently adjust detection thresholds, the system inverts the approach by having the remote processor determine and manage thresholds based on aggregate data from all meters. This centralizes the adaptability logic where it can benefit from all available information.
Solution Approach 2:
The remote processor serves multiple functions: collecting data from all meters, performing anomaly detection, dynamically adjusting thresholds, and managing the entire monitoring system. This multi-functionality consolidates complexity in a single device rather than distributing it across many meters.
4Measurement precision
If meters perform extensive data processing locally, then detection accuracy improves, but energy consumption increases
Solution Approach 1:
Meters perform only partial processing locally by selecting pertinent measurements rather than transmitting or processing all data. This partial action at the meter level is sufficient to reduce data volume while the remote processor performs the remaining processing needed for accurate anomaly detection.
Data Source
AI summary
A method of monitoring a set of meters that are connected to a common remote processor device, the method comprising both first steps performed in each meter for: acquiring primary measurements of a magnitude representative of the occurrence of an anomaly; selecting pertinent measurements from the primary measurements, the pertinent measurements satisfying a pertinence criterion; regularly transmitting the pertinent measurements to the remote processor device; and second steps performed in the remote processor device, for: comparing, for each meter, the pertinent measurements with a detection threshold common to all of the meters of the set of meters in order to attempt detecting an anomaly associated with said meter; and adjusting the detection threshold dynamically as a function of the percentage of meters detected as being associated with an anomaly.