Complementary thermal energy generation associated with renewable energies using Artificial Intelligence

Bruno Knevitz Hammerschmitt, Fernando Guilherme Kaehler Guarda, Felipe Cirolini Lucchese and Alzenira da Rosa Abaide

Energy, 2022, vol. 254, issue PB

Abstract: This work proposes a short-term modeling and simulation structure to predict the electrical energy generation capacity of an electrical system with centralized generation and load presenting a diversified mix of energy sources. This will be accomplished by analyzing the generation forecasting and highlighting the energy complementarity imposed on available and simulated thermal generation, taking into account operation historical series. In order to model the electrical energy generation forecasting, a structure of Multi-layer Perceptron (MLP) artificial neural networks was used and multi scenarios (critical, ideal and optimistic) were generated by the Monte Carlo (MC) method. The forecasting results obtained for MLP had for mean absolute error and root mean square error respectively the rates of 3.22% and 4.01% for hydro generation, and 5.36% and 6.31% for wind generation. Thus, it was possible to estimate the available complementary thermal generation and the natural gas thermal generation that were simulated to meet the system load. With the results from joining MLP and MC, it was possible to quantify the availability of energy in front generation system plants to adverse conditions and propose complementation, emphasizing the importance of the forecasting model to aid on the planning and operation of electrical systems.

Keywords: Energy generation forecasting; Complementary energy planning; Short-term forecasting; Thermal energy generation; Natural gas (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544222011677
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:254:y:2022:i:pb:s0360544222011677

DOI: 10.1016/j.energy.2022.124264

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().