Neural network aided design for metering system of power system state estimation

This paper presents an artificial neural network (ANN) aided design approach for the determination of the measurement scheme to be employed for online power system state estimation (PSSE). According to predetermined values of both the state estimator performance objectives (accuracy, running time), the proposed technique provides decisions regarding to the adequate number of measurements, meter type and meter locations for the specific network configuration. An efficient modeling of the output layer of the proposed ANN is developed in this paper. The network is trained using offline prepared I/O data pairs and the backpropagation learning algorithm. Numerical experiments are conducted on a simple 6-bus system and simulation results are assessed