Research Article
Anomaly Detection in Smart Metering Infrastructure with the Use of Time Series Analysis
Table 4
DR [%] and FP [%] for anomalies/attacks performed on the AMI network with Scenario
3.
| Feature | Holt | Winters | Brown | Description | DR [%] | FP [%] | DR [%] | FP [%] | DR [%] | FP [%] |
| NF1 | 86.40 | 8.60 | 84.10 | 10.30 | 80.70 | 12.60 | — | NF2 | 88.40 | 8.40 | 85.20 | 9.80 | 83.10 | 11.70 | Significant impact on NF2 in Scenario 3 | NF3 | 90.50 | 6.40 | 87.20 | 8.80 | 85.60 | 10.90 | Significant impact on NF3 in Scenario 3 | NF4 | 82.30 | 11.50 | 79.50 | 12.40 | 76.40 | 12.80 | — | NF5 | 86.20 | 12.40 | 83.40 | 12.50 | 80.80 | 12.80 | — |
|
|