Contingency Analysis of Ethiopian Extra High Voltage Transmission Networks With Deep Neural Networks

Contingency analysis (CA) is a vital technique of assessing power system resilience during outages by detecting overloads, voltage issues, and generator faults, strengthening grid security and emergency response planning. For the Ethiopian Electric Power (EEP) network, an N‑1 contingency analysis was conducted on Extra High Voltage (EHV) transmission lines. A dual‑depth Deep Feed Forward Neural Network (DFFNN) was employed on MATLAB/MATPOWER platform to predict bus voltage magnitudes and active power flows across branches. The DFFNN achieved strong training performance, with Mean Square Error (MSE) values of 3.887 x 10-5and 7.32 x10-3, alongside high regression values of 0.99234 and 0.99479, confirming its predictive accuracy. These predictions were used to implement a novel Hybrid Performance Index (PIhyb), which ranks contingencies according to severity. Results revealed that failure of either circuit of the Dedessa–Holeta 500 kV double-line, sourced from the Great Ethiopian Renaissance Dam (GERD), was the most severe contingency. This event produced a PIhybof 1.798, causing voltage instability at 19 buses and severe overloading of the Dedessa–Nekemte 132 kV line. Subsequent critical contingencies were also linked to GERD, with PIhybvalues of 0.473 and 0.321. Corrective and preventive measures are recommended to mitigate these risks, ensuring protection against cascading failures that could ultimately lead to a total blackout.