Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Hybrid renewable energy system optimization incorporating AI-driven energy management techniques

Galyfianakis Nikolaos

Full record


URI: http://purl.tuc.gr/dl/dias/626BF9EC-ADE9-49E9-9232-5C435DD526A9
Year 2024
Type of Item Diploma Work
License
Details
Bibliographic Citation Nikolaos Galyfianakis, "Hybrid renewable energy system optimization incorporating AI-driven energy management techniques", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2024 https://doi.org/10.26233/heallink.tuc.101211
Appears in Collections

Summary

Due to the ever-increasing demand for electricity and the rising cost of operating distribution networks, the use of methods and technologies for energy management systems is deemed necessary. The integration of Renewable Energy Sources (RES) is of utmost importance for achieving the reduction of energy costs. However, the use of RES presents its own challenges, as their energy production is dispersed, introducing technical difficulties, and increasing the complexity of the system. This thesis studies the optimization of a hybrid Renewable Energy Sources system by applying techniques based on artificial intelligence technologies. Initially, meteorological data from the NASA website and PVGIS, as well as hourly electricity consumption data, are collected to determine the energy profile of the study area. Then, the data is utilized by the Homer Pro software, seeking the optimal solution for reducing energy costs. The main regulatory parameters of the simulation scenarios addressed the energy production sources (Photovoltaic panels, wind turbines, hydrokinetic generators), as well as the application or absence Net Metering technology. Subsequently, optimization was performed using Genetic Algorithms (GA), and the two methods were compared based on economic indicators. The simulation results are presented in detail, aiming to evaluate the effectiveness of the Genetic Algorithms (GA) method. Finally, indicative ideas for future research are mentioned.

Available Files

Services

Statistics