The transition toward more sustainable and reliable energy systems requires advanced approaches for understanding, forecasting, and optimizing electricity generation and consumption. In this context, this doctoral research focuses on the application of machine learning methods to support energy planning and management, with a particular emphasis on electricity demand forecasting and hydropower system modeling.
The study is grounded in the Albanian energy system, which offers a unique context due to its strong dependence on renewable energy, especially hydropower. By combining electricity consumption analysis with hydropower production modeling, the research aims to contribute to a more integrated understanding of energy system dynamics and their role in supporting sustainable energy management.

A key aspect of the work involves investigating electricity load patterns across different regions, considering regional variability and the influence of environmental and climatic factors. In parallel, the research explores the modeling of hydropower systems, emphasizing their operational behavior and their importance in ensuring energy balance and system reliability.

To address these challenges, the research investigates a range of machine learning and data-driven approaches for forecasting and system modeling. Particular attention is given to the development of adaptive and optimized methods capable of improving prediction performance under changing and uncertain conditions.

The outcome of this work aims to provide practical insights and decision-support tools for energy forecasting, resource management, and long-term planning. This research contributes to ongoing efforts toward the integration of intelligent technologies in renewable energy systems and the development of resilient and sustainable power infrastructures.