| dc.description.abstract |
A distribution transformer serves as a critical interface between the distribution network and
low-voltage consumers, where unbalanced phase loading can adversely affect operational
performance. In the Shebe distribution network, significant phase current disparities have led
to elevated neutral currents, voltage deviations, and increased stress on transformer
components, highlighting the need for an effective load balancing strategy. This study proposes
an intelligent transformer load balancing and performance monitoring approach based on an
Adaptive Neuro-Fuzzy Inference System (ANFIS). The ANFIS model was developed using
historical and periodically recorded operational data, including phase voltages, phase currents,
and load profiles, collected in collaboration with the Ethiopian Electric Utility. Simulation
results obtained in MATLAB demonstrate that the proposed method achieves substantial
improvements in phase current symmetry and voltage regulation while drastically reducing
neutral current magnitude. Furthermore, performance evaluation metrics indicate notable
reductions in load power deviation and prediction errors, as evidenced by improved normalized
MAE and RMSE values. The results validate the robustness and effectiveness of the proposed
ANFIS-based approach in enhancing load balance and power quality on the low-voltage side of
distribution transformers. |
en_US |