A scalable wide area monitoring system using cellular neural networks

Synchrophasor systems make power grids more observable by collecting data from various locations, time-align and process them as a coherent data set. Better observability results in better control actions. A limiting factor to this approach is communication delays. Power system wide area communication delays range from several milliseconds to several seconds depending on the communication media and distance. One way to deal with this is to have an intelligent system which can predict state values for one or more time steps ahead of time. A novel four dimensional scalable multirate cellular neural network (CNN) architecture for use as wide area monitoring system (WAMS) is proposed. Recurrent neural network (RNN) is used as computational engine for each cell as RNNs have dynamic memory. By using information from phasor measurement units (PMUs) that are optimally located in a power system, each layer predicts a state variable for one or more time steps. Data from remote PMUs are replaced by the respective CNN cells´ time delayed predicted state values for next time step. This enables local controllers to take real-time control action with system wide information. A 12-bus test power system is used to develop and demonstrate the effectiveness of the proposed CNN framework for WAMS.