This work is a review on previous research and studies on the solar disturbance activities and faults that occur on the electric power transmission line. Research has shown that low latitude regions could also be affected by solar disturbance events. The effects of these events on earth are considerable and may cause electric power transmission failure. Geomagnetically induced current is one of the ground impacts to the transmission line, which may cause fault or disturbance and consequently power system failure. Solar disturbance data from magnetometers and electric power transmission line fault data from a digital fault recorder are reviewed in this work. These data would be valuable in determining the characteristics and effects of solar disturbances on Malaysia’s electric power transmission lines.
This paper examines the prediction of the ionospheric F2 layer’s critical frequencies (foF2) using a backpropagation neural network model in conjunction with particle swarm optimization (BPNN–PSO) for various solar and geomagnetic activities. The critical frequency data were taken from an ionosonde located at Universiti Tun Hussein Onn Malaysia (UTHM) in Johor (1.86° N, 103.80° E). The models’ predictive ability for foF2 was investigated under various solar activity and geomagnetic storm circumstances. The developed graphical user interface (GUI) was used to forecast the critical frequency of the ionospheric F2 layer. The forecasted data was then assessed using mean absolute percentage error (MAPE) and root-mean-square error (RMSE). The model performs best during high solar activity, with an RMSE of 0.2003 MHz and a MAPE of 4.2263%. Meanwhile, the model also performs best in moderate storms, with an RMSE of 0.3255 MHz and a MAPE of 7.5888%.
The total electron content (TEC) of the ionospheric atmosphere is frequently used in studies on ionospheric physics and the effects of space weather. This paper focuses on a feasibility study of the Neural Network (NN) model for the TEC prediction in Peninsular Malaysia which is included in low latitude region. The selection data is based on available data from Universiti Kebangsaan Malaysia (UKM) station from the year 2011 until 2015 which was the ascending solar cycle period in cycle 24. A feedforward neural network with a back propagation algorithm was proposed as a prediction model. The NN parameters were selected based on the TEC influence’s factor which were the seasonal variation, diurnal variation, and solar activity. The TEC value predicted by the NN model was evaluated using the GPS-TEC and compared to IRI01-corr TEC models result. The result shows the proposed NN model give less root mean square error (RMSE) against the IRI01-corr TEC models with the average RMSE approximately 3.58 TECU and 14.72 TECU respectively. In addition, the best prediction falls during the solstice compared to the equinox.
27 December 2025 in Journal of Industrial Integration and Management
This paper considers the prediction of the critical frequencies of the ionospheric F2 layer, foF2, by using two models: a backpropagation neural network (BPNN) model and a BPNN combined with particle swarm optimization (BPNN–PSO) model for different states of solar activity: low, medium and high. Nine-year critical frequency data from an ionosonde installed at the Universiti Tun Hussein Onn Malaysia in Johor (1.86° N, 103.80° E) were used. The efficiency of the models in predicting foF2 under different states of solar activity was explored. The output of the models was evaluated using root-mean-square error (RMSE) and mean average percentage error (MAPE). The BPNN–PSO model provided a better result compared with the BPNN model during low, medium and high solar activity. The BPNN–PSO model had RMSE and MAPE equal to 0.50 MHz and 5.27%, respectively, during low solar activity and RMSE and MAPE of 0.32 MHz and 4.16%, respectively, during medium solar activity. In addition, the BPNN–PSO model had the lowest RMSE (0.24 MHz) and MAPE (2.45%) during high solar activity. Overall, the performance of the BPNN–PSO model was higher than that of the BPNN model during any state of solar activity.