Predicting Thermoelectric Power Plants Diesel/Heavy Fuel Oil Engine Fuel Consumption Using Univariate Forecasting and XGBoost Machine Learning Models
Author:
Siqueira-Filho Elias Amancio12ORCID, Lira Maira Farias Andrade2ORCID, Converti Attilio3ORCID, Siqueira Hugo Valadares4ORCID, Bastos-Filho Carmelo J. A.1ORCID
Affiliation:
1. Polytechnic School of Pernambuco, Pernambuco University, Benfica St., 455, Madalena, Recife 50720-001, Brazil 2. Advanced Institute of Technology and Innovation (IATI), Potyra St., 31, Prado, Recife 50751-310, Brazil 3. Department of Civil, Chemical and Environmental Engineering, Pole of Chemical Engineering, University of Genoa, Via Opera Pia 15, 16145 Genoa, Italy 4. Department of Electronics, Federal University of Technology—Paraná (UTFPR), Dr. Washington Subtil Chueire St., 330, Jardim Carvalho, Ponta Grossa 84017-220, Brazil
Abstract
Monitoring and controlling thermoelectric power plants (TPPs) operational parameters have become essential to ensure system reliability, especially in emergencies. Due to system complexity, operating parameters control is often performed based on technical know-how and simplified analytical models that can result in limited observations. An alternative to this task is using time series forecasting methods that seek to generalize system characteristics based on past information. However, the analysis of these techniques on large diesel/HFO engines used in Brazilian power plants under the dispatch regime has not yet been well-explored. Therefore, given the complex characteristics of engine fuel consumption during power generation, this work aimed to investigate patterns generalization abilities when linear and nonlinear univariate forecasting models are used on a representative database related to an engine-driven generator used in a TPP located in Pernambuco, Brazil. Fuel consumption predictions based on artificial neural networks were directly compared to XGBoost regressor adaptation to perform this task as an alternative with lower computational cost. AR and ARIMA linear models were applied as a benchmark, and the PSO optimizer was used as an alternative during model adjustment. In summary, it was possible to observe that AR and ARIMA-PSO had similar performances in operations and lower error distributions during full-load power output with normal error frequency distribution of −0.03 ± 3.55 and 0.03 ± 3.78 kg/h, respectively. Despite their similarities, ARIMA-PSO achieved better adherence in capturing load adjustment periods. On the other hand, the nonlinear approaches NAR and XGBoost showed significantly better performance, achieving mean absolute error reductions of 42.37% and 30.30%, respectively, when compared with the best linear model. XGBoost modeling was 8.7 times computationally faster than NAR during training. The nonlinear models were better at capturing disturbances related to fuel consumption ramp, shut-down, and sudden fluctuations steps, despite being inferior in forecasting at full-load, especially XGBoost due to its high sensitivity with slight fuel consumption variations.
Funder
the Programa de Pesquisa e Desenvolvimento da Agência Nacional de Energia Elétrica TPP Energética Suape II S.A. Desenvolvimento de dispositivo utilizando hidrogênio e oxigênio para a redução dos gases poluentes no ciclo de combustão carburante the Brazilian National Council for Scientific and Technological Development Araucaria Foundation
Subject
Energy (miscellaneous),Energy Engineering and Power Technology,Renewable Energy, Sustainability and the Environment,Electrical and Electronic Engineering,Control and Optimization,Engineering (miscellaneous),Building and Construction
Reference54 articles.
1. Energy Research Company (2022). Brazilian Energy Balance—Year 2021, Ministry of Mines and Energy. Technical Report. 2. National Electric Systems Operator (2022, July 01). Plano da Operação Energética 2021/2025. Technical Report RT—ONS DPL 0492/2021, Available online: https://www.epe.gov.br/pt/publicacoes-dados-abertos/publicacoes/revisoes-quadrimestrais-da-carga#:~:text=Planejamento%20Anual%20da%20Opera%C3%A7%C3%A3o%20Energ%C3%A9tica%202021%2D2025&text=Para%20o%20per%C3%ADodo%202021%2D2025,pelo%20carregamento%20estat%C3%ADstico%20de%202020. 3. Santos, T.N., Diniz, A.L., Sabóia, C.H., Vilas Boas, C.E., Ferreira, J.M.F., Mourão, F., Cabral, R., Cerqueira, L.F., and Araújo Junior, C.A. (2019, January 10–13). Incorporação de restrições operativas detalhadas utilizadas na elaboração do Programa Diário de Operação do Operador Nacional do Sistema (ONS) no modelo de Despacho Hidrotérmico de Curto Prazo. Proceedings of the XXV SNPTEE—Seminário Nacional de Produção e Transmissão de Energia Elétrica, Belo Horizonte, Brazil. 4. Hourly pricing and day-ahead dispatch setting in Brazil: The dessem model;Santos;Electr. Power Syst. Res.,2020 5. KPMG (2022, July 01). Energética Suape II S.A.: Demonstrações Financeiras em 31 de Dezembro de 2020. Tech. Rep. KPDS 758824, KPMG Auditores Independentes. Available online: https://suapeenergia.com.br/df/DF_2020.pdf.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|