Multi-Channel Recovery for Distributed Quality Management of Synchrophasor Data

Abstract

This paper presents a distributed synchrophasor data management (DSDM) technique for wide-area monitoring systems. The proposed technique focuses on managing voltage/ current phasor data measured from a specific target bus by defining neighbor phasor measurement units (PMUs). An algorithm for searching the neighbor PMUs is developed by interpreting the power network topology as a tree of which a root is the target bus. By exploiting data of neighbor PMUs, a multi-channel structure to recover missing entries is constructed by parallel implementation of LSTM (Long-Short Term Memory) networks. A successive output decision process automatically decides whether to adjust the multi-channel outputs or not. The proposed DSDM can complement the existing centralized management techniques by well-preserving information on local dynamics. Especially, due to the multi-channel structure, DSDM has the capability to flexible and reliable responses to defective data in neighbor PMUs such as an unintended change in a network topology. The effectiveness of DSDM is verified by using the real-world synchrophasor data under different conditions of power systems including local events and unintended changes of network topology.