Electrical and Computer Engineering

Permanent URI for this collectionhttps://repository.mu.edu.et/handle/123456789/426

Browse

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • Item
    Forecasting-Based Operation and Maintenance Planning for Sustainable Urban Energy Supply
    (Mekelle University, 2025-07-29) Sa’ad Aden Yousuf
    This study presents a comprehensive analysis of energy load forecasting and operation and maintenance (O&M) planning for domestic, industrial, and commercial sectors within a rapidly growing urban utility network. Using historical energy consumption data from the past year, forecasts were generated for the years 2024, 2025, and 2026 using different regression techniques. The one with lower value of MAPE is selected to do the load forecast for the selected site. The analysis revealed a consistent upward trend in energy demand across all sectors, with notable seasonal variations that highlight peak consumption during the summer and winter months. These findings underscore the necessity for strategic infrastructure development and improved load management practices to ensure uninterrupted power supply and system reliability. The domestic sector showed the most dynamic growth, driven by increased electrification and lifestyle improvements. Industrial and commercial sectors also demonstrated steady rises in demand, linked to economic activity and service expansion. The monthly aggregate forecast identified critical peak-load periods, particularly in May, June, and December, suggesting the need for intensified operational readiness and real-time monitoring during these months. Conversely, months like April and October with lower forecasted loads were identified as ideal windows for conducting preventive maintenance. Based on the forecast results, an optimized O&M schedule was proposed, aligning maintenance activities with seasonal demand patterns to minimize disruptions and maximize resource efficiency. Recommendations include infrastructure upgrades, integration of smart technologies, targeted staff training, and enhanced demand-side management. The study concludes by emphasizing the importance of accurate forecasting and proactive maintenance planning in building a resilient and efficient energy distribution system. Future work will focus on incorporating machine learning algorithms, real-time data, and renewable energy integration to further refine the forecasting model and optimize utility operations.