Handling bad or missing smart meter data through advanced data imputation

Abstract

Smart meters and other the modern distribution measurement devices provide new and more data, but usually they are subject to longer delays and lower reliability than transmission system SCADA. Accurate and robust use of the modern distribution system measurements will be a cornerstone of the future advanced distribution management systems. This paper presents a novel and computationally efficient data processing method for imputing bad and missing load power measurements to create full power consumption data sets. The imputed data periods have a continuous profile with respect to the adjacent available measurements, which is a highly desirable feature for time-series (power flow) analyses. The method is shown to be superior in accuracy to a utility best practice approach. Our simulations use actual AMI data collected from 128 smart meters on the Georgia Tech campus.