Disturbance-Learning Inertia Estimation Using Artificial Neural Networks for Power System Stability

Authors

• Sospeter Igaanja Gabriel, Mbeya University of Science and TechnologyFollow
• Francis Mwasilu, Department of Electrical Engineering, University of Dar es Salaam, P. O. Box 35091, Dar es Salaam, TanzaniaFollow
• PETER MAKOLO Dr., Department of Electrical Engineering, University of Dar es Salaam, P. O. Box 35091, Dar es Salaam, TanzaniaFollow

ORCID

ORCID:https://orcid.org/0009-0002-4006-5434

Abstract

ABSTRACT

Power systems are progressively shifting towards low inertia as a result of incorporating significant amounts of intermittent and converter-based renewable energy sources, such as wind and solar power, into the current power grid network. This integration poses considerable problems to inertia and frequency control within the network due to a reduction in the proportion of synchronous generators. Furthermore, rapid frequency deviations occur due to the disparity between supply and demand during contingencies, complicating the maintenance of frequency stability within the power system. The disturbance-learning inertia estimation method for power system stability is presented. The simulation analysis is performed using DigSilent PowerFactory on the IEEE 39 test bus system to validate the correctness of the proposed method. The extracted data were used for ANN training and validation in various scenarios of RES penetration in MATLAB. The model was trained, validated, and tested using 70%, 15%, and 15% of the frequency-extracted data following the disruption in the IEEE 39-bus system, respectively, and inertia estimation was performed.  The accuracy is very high, as the ANN estimated system inertia output values obtained are very close to the actual calculated system inertia, with the maximum averaged absolute percentage error of 2.88%. The accuracy of the estimated inertia values was evaluated using MAE, RMSE, and MAPE, and the results obtained are 0.078%,0.085%,1.899%, respectively. The suggested method provides precise and dependable inertia forecasting that aids the PSOs in making decisions for effective and stable management of the power network stability.

Recommended Citation

Gabriel, S. I., Mwasilu, F., & MAKOLO, P. (2026). Disturbance-Learning Inertia Estimation Using Artificial Neural Networks for Power System Stability. Tanzania Journal of Engineering and Technology (TJET), 45(2), 157-166. https://doi.org/10.65085/2619-8789.1085

Publisher Name

University of Dar es Salaam