Study of Distribution Transmission Line Lightning Stroke Risk Forecasting Based on Nonlinear Time Series Analysis

Abstract

To solve the problem of the risk forecasting of distribution system directly stroke, a lighting stroke risk forecasting model of distribution transmission line based on nonlinear time series analysis is proposed in the paper. The duration of the thunder and lightning is the key of lighting stroke risk predicting, and other circumstance conditions such as temperature, humidity, atmospheric pressure, are also great influence on it. The observed values of these five circumstance conditions can be treated as a nonlinear time series model. An artificial neural networks model is proposed in the paper to solve the nonlinear time series model of stroke risk forecasting. The ANNs model is consisted of five artificial neural networks which is used to prediction the circumstance conditions time series, and then employed to prediction the lighting stroke risk of the transmission line. A series of simulation show that the results of the predicting model is acceptable in engineering application.