Application of BFNN in power flow calculation in smart distribution grid

Authors:
Qiuye Sun;Yunxia Yu;Yanhong Luo;Xinrui Liu
Affiliations:
School of Information Science and Engineering, Northeastern University, Shenyang, Liaoning 110819, PR China;School of Information Science and Engineering, Northeastern University, Shenyang, Liaoning 110819, PR China;School of Information Science and Engineering, Northeastern University, Shenyang, Liaoning 110819, PR China;School of Information Science and Engineering, Northeastern University, Shenyang, Liaoning 110819, PR China
Venue:
Neurocomputing
Year:
2014

Citing 6
Cited 0

Numbering of Nodes in a Communication Network

WCECS '08 Proceedings of the Advances in Electrical and Electronics Engineering - IAENG Special Edition of the World Congress on Engineering and Computer Science 2008
Neural-network-based near-optimal control for a class of discrete-time affine nonlinear systems with control constraints

IEEE Transactions on Neural Networks
Modeling, identification, and control of a class of nonlinear systems

IEEE Transactions on Fuzzy Systems
Global Asymptotic Stability of Recurrent Neural Networks With Multiple Time-Varying Delays

IEEE Transactions on Neural Networks
Robust Stability Analysis for Interval Cohen–Grossberg Neural Networks With Unknown Time-Varying Delays

IEEE Transactions on Neural Networks
Neural Network-Based Multiple Robot Simultaneous Localization and Mapping

IEEE Transactions on Neural Networks - Part 2

Quantified Score

Hi-index	0.01

Visualization

Abstract

Power flow study is performed to ensure the whole electricity system operating safely, stably and reliably. A back/forward sweep neural network (BFNN) algorithm is put forward based on numbering all nodes using breadth first search plan. All neurons use the same excitation function. The BFNN has a clear structure with a high approximation speed and high precision. Each neuron acts as the threshold to its adjacent neuron in front. In BFNN method weights adjusting means voltage adjusting, hence, when the learning process according to BP algorithm ended, the desired voltages are acquired. And then the power flow can be derived. In this paper the convergence of BFNN has also been validated. The proposed BFNN algorithm is proved to have a better approximation effect than using conditional back/forward method by computing power flow in Tongliao 16-bus distribution system in Inner Mongolia.