Data For \u201cContingency Analysis of Ethiopian Extra High Voltage Transmission Networks with Deep Neural Networks\u201d

Contingency analysis (CA) evaluates power system resilience during component outages by identifying overloads, voltage violations, and generator asynchronism, thereby supporting power grid security and emergency response strategies. For the Ethiopian Electric Power (EEP) network, an N-1 contingency analysis was conducted on Extra High Voltage (EHV) transmission lines using two Deep Feed Forward Neural Networks (DFFNNs) to predict bus voltage magnitudes and active power flows of branches on MATLAB\/MATPOWER platform. The Mean Square Error (MSE) training performance of the DFFNNs was 3.887\u00d710\u207b\u2075 and 7.32\u00d710\u207b\u00b3 with high regression values of 0.99234 and 0.99479. Predictions from the DFFNNs were used to employ a novel Hybrid Performance Index (PIhyb) that ranks contingencies according to their severity. Accordingly, failure of either circuit of the Dedessa\u2013Holeta 500 kV double-line sourced from the Great Ethiopian Renaissance Dam (GERD) was identified as the most severe contingency, with a PIhyb of 1.798, causing voltage instability at 19 buses and severe overloading of the Dedessa\u2013Nekemte 132 kV line.  Similarly, the next most critical contingencies were also linked to the GERD, yielding PIhyb values of 0.473 and 0.321, respectively. Corrective and preventive measures are recommended for the severe contingencies to effectively protect the system from cascading failures that lead to a total blackout.