Outage Management System for Power Distribution Network

Abstract

Outage detection is the first and foremost step in the electric power distribution Outage Management System (OMS). Unplanned outage detection is very important for improving the distribution system reliability and accessibility. Traditionally, customers' trouble calls are the primary source of outage notification. However, customers report only one third of outages in the first hour of outages. The advanced metering infrastructure (AMI) can send outage notifications almost instantly to the utility and could also give restoration notification when power is restored. AMI data may be corrupted due to communication channel noise and there may also be unnecessary outage notifications due to the temporary outages. In this thesis, an algorithm is proposed to filter out the meter notifications due to corrupted data and temporary outages of duration less than one minute. An AMI data filter is modelled by probabilistic and fuzzy membership functions to remove the corrupted data. Integration of distribution supervisory control and data acquisition system (SCADA) with AMI for outage location finding is also proposed by fuzzy membership function based model. Proposed models have been tested on a radial distribution test feeder and results are analyzed.