Reactive Power Optimization Control of Power Grid utilizing the Improved RBF Artificial Neural Network

Authors

  • Bin Xiao State Grid Hunan Electric Power Co., Ltd

Abstract

To optimize the management of the power grid and safeguard its operations, a design is presented under improved RBF artificial neural network (ANN) prediction of power grid reactive power optimization (PO) control to improve the traditional RBF ANN. The established genetic algorithm (GA), combined with the improved RBF artificial neural network (NN), uses the disorderly global optimization ability of GA to optimize the weights of RBF NN and narrow the search scope. The optimal solution is obtained by the accurate solution of RBF NN. On this basis, the improved RBF ANN is adopted to improve the power grid reactive power (RO) balance, forecast the grid voltage and power load values, and establish the objective function of minimum loss of transformer. The power load prediction is carried out in stages. The influence of average load, average temperature, rest day characteristic value and other data on load is considered. The load value, at the same time of the day before the prediction, is taken as the input, and the load value at the time to be tested on the day is taken as the output for prediction, for real-time monitoring and control. It shows that the improved RBF ANN can optimize the hidden layer neuron nodes, simplify the NN structure, improve the level of reactive PO, and reduce loss and save energy. Therefore, the method of improving RBF ANN can realize the nonlinear optimization problem of reactive PO of power grid and improve the quality and economic benefits of a power supply network.

Keywords: Reactive PO; ANN; Load forecasting; RBF; Substation

Cite As

B. Xiao, "Reactive Power Optimization Control of Power Grid utilizing the Improved RBF Artificial Neural Network",
Engineering Intelligent Systems, vol. 27 no. 4, pp. 193-200, 2019.







Downloads

Published

2019-12-01

Issue

Vol. 27 No. 4 (2019): International Journal of Engineering Intelligent Systems

Section

General Submission

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.