Abstract
Although the kriged Kalman filter (KKF) has well-documented merits for prediction of spatial-temporal processes, its performance degrades in the presence of outliers due to anomalous events, or measurement equipment failures. This paper proposes a robust KKF model that explicitly accounts for presence of measurement outliers. Exploiting outlier sparsity, a novel l1-regularized estimator that jointly predicts the spatial-temporal process at unmonitored locations, while identifying measurement outliers is put forth. Numerical tests are conducted on a synthetic Internet protocol (IP) network, and real transformer load data. Test results corroborate the effectiveness of the novel estimator in joint spatial prediction and outlier identification.
Original language | American English |
---|---|
Pages | 1525-1529 |
Number of pages | 5 |
DOIs | |
State | Published - 2015 |
Event | 2015 49th Asilomar Conference on Signals, Systems and Computers - Pacific Grove, California Duration: 8 Nov 2015 → 11 Nov 2015 |
Conference
Conference | 2015 49th Asilomar Conference on Signals, Systems and Computers |
---|---|
City | Pacific Grove, California |
Period | 8/11/15 → 11/11/15 |
NREL Publication Number
- NREL/CP-5D00-65511
Keywords
- IP path delay monitoring
- Kalman filter
- kriging
- power consumption monitoring
- robust estimation
- sparsity