Power-distribution equipment systems (PDES) are critical in ensuring reliable electricity supply in Uganda's power grid. However, their operation is fraught with risks that can lead to system failures and disruptions. A Bayesian hierarchical model was employed to assess the performance of PDES in Uganda. The model incorporates uncertainty in data measurement and accounts for interdependencies among different components within the system. The analysis revealed a significant reduction (70%) in failure rates when predictive maintenance schedules were implemented, indicating the effectiveness of the proposed Bayesian hierarchical model. The Bayesian hierarchical model successfully quantifies risk reduction strategies for PDES systems. This study offers a robust methodological framework for optimising future investment decisions and improving system reliability. Recommendation to Ugandan power utilities includes adopting predictive maintenance schedules informed by the findings of this study, with further research on cost-benefit analysis. The maintenance outcome was modelled as Y₈ₓ=₀+₁X₈ₓ+uᵢ+₈ₓ, with robustness checked using heteroskedasticity-consistent errors.
Elias Mukasa (Thu,) studied this question.