Correlation Clustering Imputation for Diagnosing Attacks and Faults with Missing Power Grid Data
IEEE Transactions on Smart Grid
correlation connected clusters, cyber-attack discrimination, fault diagnosis, imputation, Missing data, power grids
While the quality of the synchronized measurements is of paramount importance for real-time monitoring and protection of the power grids, collected measurements often contain missing values. This paper proposes a scheme for diagnosing attacks and faults in the presence of missing measurements in power grid data. The proposed scheme contains four modules for clustering, missing data imputation, decision-making, and optimization. This paper develops a novel technique for missing data imputation based on the correlation-connected clusters that consider local correlation among the measurements in estimating missing data, handle high-dimensional data, and tolerate high missing ratios. The optimization module ties the imputation process to diagnostic performance. The proposed novel imputation technique is compared with other state-of-the-art techniques within the diagnostic scheme. The achieved results show that the proposed technique significantly outperforms other competitors.
Razavi-Far, Roozbeh; Farajzadeh-Zanjani, Maryam; Saif, Mehrdad; and Chakrabarti, Shiladitya. (2020). Correlation Clustering Imputation for Diagnosing Attacks and Faults with Missing Power Grid Data. IEEE Transactions on Smart Grid, 11 (2), 1453-1464.