Artificial Intelligence for renewable energy systems
The worldwide expansion of alternative energy sources, particularly solar photovoltaic energy, is escalating. However, solar energy solutions present challenges due to the variable nature of the solar resource. To effectively address the uncertainty associated with solar photovoltaic production, the...
- Autores:
-
Narváez Morales, Gabriel Esteban
- Tipo de recurso:
- Doctoral thesis
- Fecha de publicación:
- 2024
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/73548
- Acceso en línea:
- https://hdl.handle.net/1992/73548
- Palabra clave:
- Renewable Energy
Artificial Intelligence
Microgrid
Climate Change
Ingeniería
- Rights
- embargoedAccess
- License
- https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf
Summary: | The worldwide expansion of alternative energy sources, particularly solar photovoltaic energy, is escalating. However, solar energy solutions present challenges due to the variable nature of the solar resource. To effectively address the uncertainty associated with solar photovoltaic production, the implementation of an optimal management system is essential. This management system must not only handle energy storage systems or alternate available sources in off-grid systems but also effectively manage the connection to the power grid in on-grid solutions. This is where the application of artificial intelligence techniques becomes crucial, enabling the construction of precise models for optimal management. Therefore, this thesis proposes the implementation of artificial intelligence techniques to address the challenges of renewable energy systems with a focus on solar photovoltaic energy, exploring current solutions, proposing new ones, and discussing future directions. In particular, we focus on three main problems: data analytics, data processing, and optimal management in renewable energy systems. Data analytics involves gathering meteorological data, integrating both in-situ and historical satellite data along with climate change scenarios. After cleaning and validating the collected data, an analysis of the photovoltaic potential is carried out. Data processing focuses on improving the historical data by combining the best of in-situ and satellite data through site-adaptation techniques. The improved database feeds a solar irradiance forecasting model. Finally, the irradiance forecasting model and optimal battery scheduling are combined to achieve the optimal management of renewable energy systems. The research presented in this thesis is the result of joint work between the Universidad de los Andes and the Laboratory for Analysis and Architecture of Systems (LAAS-CNRS), aiming to contribute to the development of a sustainable and clean energy future. |
---|