Spatio-Temporal Missing Data Imputation for Smart Power Grids
Sanmukh R. Kuppannagari, Yao Fu, Chung Ming Chueng, Viktor K. Prasanna
Abstract
Availability of high fidelity timeseries data is imperative for critical power grid operational tasks such as state estimation, DER scheduling, etc. However, the data obtained from the metering infrastructure is prone to disruptions due to communication outages leading to missing values. State-of-the-art smart power grid Missing Data Imputation (MDI) algorithms either operate on individual timeseries and are unable to capture spatial dependencies due to the power grid topology or they operate on the entire dataset, requiring complex models which lead to overfitting.
Topics & Concepts
Imputation (statistics)Missing dataComputer scienceOverfittingTime seriesSmart gridData miningFidelityData modelingMetering modeGridReal-time computingScheduling (production processes)Distributed computingArtificial intelligenceMachine learningDatabaseEngineeringTelecommunicationsOperations managementMathematicsMechanical engineeringElectrical engineeringGeometryArtificial neural networkAge of Information OptimizationTraffic Prediction and Management TechniquesHuman Mobility and Location-Based Analysis