Application of Intelligent Techniques for Optimal Management of Weakly Connected Microgrids
The decarbonization and the climate change mitigation have become a priority for many countries and governments. One of the main tools for accomplishing these objectives is the growth of renewable generation sources in the power system, but their inclusion constitutes a great challenge for the netwo...
| Autor: | |
|---|---|
| Tipo de documento: | tese |
| Estado: | Versão publicada |
| Data de publicação: | 2022 |
| País: | España |
| Recursos: | Universidad de Sevilla (US) |
| Repositório: | idUS. Depósito de Investigación de la Universidad de Sevilla |
| OAI Identifier: | oai:idus.us.es:11441/134588 |
| Acesso em linha: | https://hdl.handle.net/11441/134588 |
| Access Level: | Acceso aberto |
| Palavra-chave: | Short-term forecasting deterministic forecasting stochastic forecasting probabilistic forecasting machine learning distributed generation renewable energy sources microgrid smart grid Predicción a corto plazo predicción determinista predicción estocástica predicción probabilística aprendizaje automático generación distribuida fuentes de energía renovables microrredes redes inteligentes |
| Resumo: | The decarbonization and the climate change mitigation have become a priority for many countries and governments. One of the main tools for accomplishing these objectives is the growth of renewable generation sources in the power system, but their inclusion constitutes a great challenge for the network operation due to their high variability and their stochastic behavior. In this context, the management of the power system and microgrids can be treated as optimization problems in which the resources are operated with the aim of minimizing the cost function. This cost function and the corresponding operative restrictions depend on each specific situation, for example, on which are the power consumption requirements, how weak is the connection with the power grid, and how critical are the loads to be fed in the zone. In this sense, despite the large variety of optimization approaches, these have in common the importance of counting on a high-quality forecasting system for predicting the uncertainties of the microgrid (or network) to operate. The main existing approaches for predicting the uncertainties are deterministic and stochastic (which in many cases is also called probabilistic) forecasting. Considering the importance of forecasting systems for performing the optimization of microgrids and, in general, power networks, this doctoral thesis is focused on the design of a microgrid-oriented forecasting framework that includes a wide range of forecasting approaches, which makes possible its integration with other applications, for example, energy management optimization systems. This framework includes several deterministic and stochastic methods and is able to handle the training and selection of the models for performing the forecast according to the type of uncertainty representation that is required in each case. |
|---|