A Hypothesis Testing Approach for Topology Error Detection in Power Grids

Wu, Wei Biao; Cheng, Min‐Yuan; Gou, Bei

doi:10.1109/jiot.2016.2539363

Cited by 11 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For bad data identification, HTI methods show significant advantages over methods based on normalized residuals, which may be strongly correlated [7]. HTI techniques also demonstrated potential for discerning error type, such as in topology error identification [42,43].…”

Section: Hypothesis Testingmentioning

confidence: 99%

Anomaly Detection in Power System State Estimation: Review and New Directions

Cooper,

Bretas,

Meyn

2023

Energies

View full text Add to dashboard Cite

Foundational and state-of-the-art anomaly-detection methods through power system state estimation are reviewed. Traditional components for bad data detection, such as chi-square testing, residual-based methods, and hypothesis testing, are discussed to explain the motivations for recent anomaly-detection methods given the increasing complexity of power grids, energy management systems, and cyber-threats. In particular, state estimation anomaly detection based on data-driven quickest-change detection and artificial intelligence are discussed, and directions for research are suggested with particular emphasis on considerations of the future smart grid.

show abstract

Section: Hypothesis Testingmentioning

confidence: 99%

Anomaly Detection in Power System State Estimation: Review and New Directions

Cooper,

Bretas,

Meyn

2023

Energies

View full text Add to dashboard Cite

show abstract

“…See [18], [19], [25] for a book-length history and [26] for an overview of the latest developments. Within anomaly detection, most statistical approaches have been tested, including hypothesis testing [9], dimension reduction [20], variants of filtering [13], and Gaussian processes [9]. In Computer Science, Complex Event Processing [54]- [56] and deep-learning methods [21]- [24] are popular.…”

Section: Related Workmentioning

confidence: 99%

“…Correspondingly, there is a long history of work on monitoring and event detection (also known as anomaly detection or outlier detection), going back at least to [18], [19] in the univariate case. Outside of traditional methods, such as dimension reduction [20] and Gaussian processes [9], deeplearning methods [21]- [24] have been widely used recently. We refer to [25], [26] for excellent surveys.…”

Section: Introductionmentioning

confidence: 99%

Low-Rank Methods in Event Detection With Subsampled Point-to-Subspace Proximity Tests

et al. 2022

View full text Add to dashboard Cite

Monitoring of streamed data to detect abnormal behaviour (variously known as event detection, anomaly detection, change detection, or outlier detection) underlies many applications, especially within the Internet of Things. There, one often collects data from a variety of sources, with asynchronous sampling, and missing data. In this setting, one can detect abnormal behavior using low-rank techniques. In particular, we assume that normal observations come from a low-rank subspace, prior to being corrupted by a uniformly distributed noise. Correspondingly, we aim to recover a representation of the subspace, and perform event detection by running point-to-subspace distance query for incoming data. We use a variant of low-rank factorisation, which considers interval uncertainty sets around "known entries", on a suitable flattening of the input data to obtain a low-rank model. On-line, we compute the distance of incoming data to the low-rank normal subspace and update the subspace to keep it consistent with the seasonal changes present. For the distance computation, we consider subsampling. We bound the one-sided error as a function of the number of coordinates employed. In our experimental evaluation, we test the proposed algorithm on induction-loop data from Dublin, Ireland.

show abstract

“…Instead of analyzing the matrix product, WM, which is a tedious task, the product, GM, is analyzed to identify the topology errors. Once measurement selection is over, matrices M 1 and M 2 can be calculated and thus matrix product, GM, can be calculated, according to (16). The algorithm is illustrated here by considering the IEEE 14-bus test system.…”

Section: Detection Of Critical Branch and Critical Pair Of Branchesmentioning

confidence: 99%

“…In [15], a Bayesian-based hypothesis testing procedure is developed and applied to topology error processing via normalized Lagrange multipliers. The research work in [16] has proposed a method based on hypothesis testing for topology error detection. This approach is based on residuals which are obtained by comparing the original measurement with the recovered power flows by solving the network tree.…”

Section: Introductionmentioning

confidence: 99%