Conference Paper

Wide area monitoring in power systems using cellular neural networks

Real-Time Power & Intell. Syst. Lab., Missouri Univ. of Sci. & Technol., Rolla, MO, USA
DOI: 10.1109/CIASG.2011.5953343 Conference: Computational Intelligence Applications In Smart Grid (CIASG), 2011 IEEE Symposium on
Source: IEEE Xplore

ABSTRACT The demand of power and the size and complexity of the power system is increasing. Wide area monitoring and control is an integral part in transitioning from the traditional power system to a Smart Grid. However, wide area monitoring becomes challenging as the size of the electric power grid, and consequently the number of components to be monitored, grows. Wide area monitor (WAM) designed using feed-forward and feedback neural network architectures do not scale up to handle the growing complexity of the Smart Grid. In this paper, cellular neural network (CNN) is presented as a way to provide scalability in the development of a WAM for Smart Grid. The CNN based WAM is compared with multilayer perceptrons (MLP) based WAM on two different power systems. The results show that the CNN has better or comparable performance with, and scales up much better than, MLP.

  • [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    Neural Networks (IJCNN), The 2012 International Joint Conference on; 01/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: The power systems of the future - smart grids - will see an increase in both renewable energy sources and load demand, thus increasing the need for fast dynamic reconfiguration of system parameters to handle energy and load dispatches. Power systems will need to be monitored continuously to maintain stability under normal and abnormal operating conditions and when facing disturbances. A combination of system state prediction, dynamic power flow, system optimization, and solution stability checking will allow for a more reliable, affordable, efficient and clean power grid. The optimization and control systems on a smart grid will require a computational systems thinking capability to handle the uncertainties and variability that exist in a smart grid environment. The concept of sense-making based on computational intelligence methods, including neural networks, fuzzy logic and swarm intelligence, as well as online measurements from a smart grid to provide 'situational' awareness in the context of stability, is introduced in this paper.
    Power and Energy Society General Meeting, 2011 IEEE; 01/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: The Static state estimation is widely used in power systems for real time monitoring and analysis. Standard methods, such as the weighted least squares (WLS) algorithm, require the computation of bus admittance and Jacobian matrices and the solution is found in an iterative process. This paper presents an alternative for the classic state estimation (SE) algorithms, which uses a multilayer perceptron for the state estimator. Results are presented for the IEEE 14 bus system.
    Neural Network Applications in Electrical Engineering (NEUREL), 2012 11th Symposium on; 01/2012


Available from