Ir al contenido

Documat

Predicción de Consumo y Demanda de Electricidad Mediante Redes Neuronales Artificiales y Algoritmo Iterativo

  • Montero Laurencio, Reineris [2] ; Torres Breff, Orlys [3] ; Marrero Ramirez, Secundino [1] ; Jiménez jiménez, Diego [1]
    1. [1] Universidad Técnica de Cotopaxi

      Universidad Técnica de Cotopaxi

      Latacunga, Ecuador

    2. [2] Universidad de Moa, Centro de Estudio de Energía y Tecnologías Avanzadas de Moa, Cuba
    3. [3] Universidad Tecnológica de La Habana, Centro de Investigaciones y Ensayos Electroenergéticos, La Habana, Cuba
    Mostrar afiliaciones +
  • Localización: Revista Politécnica, ISSN-e 2477-8990, Vol. 54, Nº. 3, 2024 (Ejemplar dedicado a: Revista Politécnica), págs. 45-58
  • Idioma: español
  • DOI: 10.33333/rp.vol54n3.05
  • Títulos paralelos:
    • Electricity Consumption and Demand Forecasting Using Artificial Neural Networks and Iterative Algorithm
  • Enlaces
  • Resumen
    • español

      En los nuevos escenarios urbanos de generación y distribución de electricidad, con incidencia de las fuentes renovables de energía, resulta necesario conocer el comportamiento de la demanda y el pronóstico del consumo mediante modelos predictivos confiables para garantizar la operación eficaz y eficiente del sistema. La presente investigación se propone utilizar las redes neuronales artificiales (RNA) mediante aprendizaje automático basado en un algoritmo iterativo (ML). En el caso de la demanda se determinó el modelo predictivo de potencia activa de un circuito de distribución primaria, donde las cargas residenciales están localizadas en edificios multifamiliares y constituyen el 64 % de todo el consumo de electricidad. Para realizar la modelación de la demanda se utilizaron los datos recolectados por un dispositivo de protección y medición, y como entradas las variables estacionarias: estación del año, día del año, día de la semana y la hora del día. El ajuste del modelo fue del 94.5 %, mejorando los resultados logrados mediante modelación paramétrica y de regresión múltiple. Se utilizó el mismo algoritmo y los mismos pasos para modelar el consumo de energía eléctrica diario de una empresa de proyectos, constituida por un edificio, donde el mejor coeficiente de correlación obtenido entre los datos de salida medidos y los predichos es de 0.9435. Los resultados de la investigación reflejan la utilidad del aprendizaje iterativo automático basado en la determinación de modelos predictivos, lo cual favorece los procesos de toma decisiones en cuanto a operación de las redes eléctricas y la planificación energética.

    • English

      In the new urban scenarios of electricity generation and distribution, with the incidence of renewable energy sources, it is necessary to know the behavior of demand and consumption forecasting through reliable predictive models to ensure the effective and efficient operation of the system. The present research proposes to use artificial neural networks (ANN) by means of machine learning based on an iterative algorithm (ML). In the case of demand, the predictive model of active power of a primary distribution circuit was determined, where residential loads are located in multifamily buildings and constitute 64 % of all electricity consumption. To perform the demand modeling, data collected by a protection and metering device were used, and as inputs the stationary variables: season of the year, day of the year, day of the week and time of the day. The model fit was 94.5 %, improving the results achieved by parametric and multiple regression modeling. The same algorithm and the same steps were used to model the daily electrical energy consumption of a project company, consisting of a building, where the best correlation coefficient obtained between the measured and predicted output data is 0.9435. The results of the research reflect the usefulness of automatic interactive learning based on the determination of predictive models, which favors the decision-making processes in terms of operation of electrical networks and energy planning.

    • português

      Nos novos cenários urbanos de geração e distribuição de energia elétrica, com a incidência de fontes renováveis de energia, é necessário conhecer o comportamento da demanda e do consumo através de modelos preditivos confiáveis para garantir a operação eficaz e eficiente dos sistemas. Nesse sentido, esta pesquisa propõe a utilização de redes neurais artificiais (RNAs) por meio de aprendizado de máquina (ML) baseado em um algoritmo iterativo. No caso da demanda, foi determinado o modelo preditivo de potência ativa de um circuito primário de distribuição, onde as cargas residenciais estão localizadas em edifícios multifamiliares e constituem 64 % de todo o consumo de energia elétrica. Para realizar a modelação da procura, foram utilizados os dados recolhidos por um dispositivo de proteção e medida, e como entradas as variáveis estacionárias: estação do ano, dia do ano, dia da semana e hora do dia. O ajuste do modelo foi de 94,5 %, melhorando os resultados obtidos pela modelação paramétrica e de regressão múltipla. O mesmo algoritmo e passos foram utilizados para modelar o consumo diário de energia de uma empresa de projectos de edifícios. O melhor coeficiente de correlação obtido entre os dados de saída medidos e previstos é de 0,9435. Os resultados da investigação reflectem a utilidade da aprendizagem automática baseada em RNA na determinação de modelos preditivos, o que favorece os processos de tomada de decisão relativos ao funcionamento das redes eléctricas e ao planeamento energético.

  • Referencias bibliográficas
    • Ahmad, J., Larijani, H., Emmanuel, R., Mannion, M., Javed, A., & Phillipson, M. (2017). Energy demand prediction through novel random...
    • Akarslan, E., & Hocaoglu, F. O. (2018). Electricity demand forecasting of a micro grid using ANN. 9th International Renewable Energy Congress...
    • Alobaidi, M. H., Chebana, F., & Meguid, M. A. (2018). Robust ensemble learning framework for day-ahead forecasting of household based...
    • Amber, K., Ahma, R., Aslam, M., Kousar, A., Usman, M., & Khan, M. (2018). Intelligent techniques for forecasting electricity consumption...
    • Aurangzeb, K. (2019). Short Term Power Load Forecasting using Machine Learning Models for energy management in a smart community. International...
    • Azadeh, A., Ghaderi, S., Tarverdian, S., & Saberi, M. (2007). Integration of artificial neural networks and genetic algorithm to predict...
    • Barman, M., Choudhury, N. D., & Sutradhar, S. (2018). A regional hybrid GOA-SVM model based on similar day approach for short-term load...
    • Beale, M. H., Hagan, M. T., & Demuth, H. B. (1992). Neural network toolbox user’s guide. Natick, Massachusetts: The MathWorks Inc.
    • Dash, S. K., & Patel, D. (2015). Short-term electric load forecasting using Extreme Learning Machine-a case study of Indian power market...
    • Deng, J. (2010). Modeling and prediction of China's electricity consumption using artificial neural network. Sixth International Conference...
    • Edwards, R. E., New, J., & Parker, L. E. (2012). Predicting future hourly residential electrical consumption: A machine learning case...
    • Escrivá- Escrivá, G., Álvarez-Bel, C., Roldán-Blay, C., & Alcázar-Ortega, M. (2011). New artificial neural network prediction method for...
    • Eseye, A. T., Lehtonen, M., Tukia, T., Uimonen, S., & Millar, R. J. (2019). Machine learning based integrated feature selection approach...
    • Gonzalez, J. M., & Zamarreno, P. A. (2005). Prediction of hourly energy consumption in buildings based on a feedback artificial neural...
    • Hippert, H. S., Pedreira, C. E., & Souza, R. C. (2001). Neural networks for short-term load forecasting: A review and evaluation. IEEE...
    • Hossen, T., Plathottam, S. J., Angamuthu, R. K., Ranganathan, P., & Salehfar, H. (2017). Short-term load forecasting using deep neural...
    • IEA. (12 de Diciembre de 2019a). International Energy Agency. Retrieved 2023, from Electricity Statistics: detailed, comprehensive annual...
    • IEA. (2019b, Septiembre 26). International Energy Agency. Retrieved 2023, from Key World Energy Statistics: key statistics on the supply,...
    • Ismail, N., & Abdullah, S. (2016). Principal component regression with artificial neural network to improve prediction of electricity...
    • Jain, R. K., Smith, K. M., Culligan, P. J., & Taylor, J. E. (2014). Forecasting energy consumption of multi-family residential buildings...
    • Jaisumroum, N., & Teeravaraprug, J. (2017). Forecasting uncertainty of Thailand's electricity consumption compare with using artificial...
    • Kalogirou, S. A. (2000). Applications of artificial neural-networks for energy systems. Applied energy, 67(1-2),17-35. https://doi.org/https://doi.org/10.1016/S0306-2619(00)00005-2
    • Karunathilake, S. L., & Nagahamulla, H. R. (2017). Artificial neural networks for daily electricity demand prediction of Sri Lanka. Seventeenth...
    • Kaysal, A., Köroglu, S., Oguz, Y., & Kaysal, K. (2018). Artificial Neural Networks and Adaptive Neuro-Fuzzy Inference Systems Approaches...
    • Khan, G. M., Khattak, A. R., Zafari, F., & Mahmud, S. A. (2013). "Electrical load forecasting using fast learning recurrent neural...
    • Kher, V., & Joshi, S. (2003). Short-Term Electrical Load Forecasting Using Artficial Neural Network,. University of Baroda, Department...
    • Kim J. Y., C. S. (2019). Electric energy consumption prediction by deep learning with state explainable autoencoder Energies, vol. 12, no....
    • Koprinska, I., Rana, M., Troncoso, A., & Martínez-Álvarez, F. (2013). Combining pattern sequence similarity with neural networks for forecasting...
    • Kumar, R., Aggarwal, R., & Sharma, J. (2013). Energy analysis of a building using artificial neural network: A review vol. 65, pp. , 2013....
    • Laganathan, N., & Lakshmi, K. (2014). Demand side energy management system using ANN based linear programming approach. IEEE International...
    • Li, C., Tao, Y., Ao, W., Yang, S., & Bai., Y. (2018). Improving forecasting accuracy of daily enterprise electricity consumption using...
    • Li, D., Tan, Z., Zhou, J., Zhang, J., & Wei, Y.-M. (2018). Short term electricity load forecasting using a hybrid model. Energy, 158,...
    • Li, K., Hu, C., Liu, G., & Xue, W. (2015). Building's electricity consumption prediction using optimized artificial neural networks...
    • Li, K., Su, H., & Chu, J. (2011). Forecasting building energy consumption using neural networks and hybrid neuro-fuzzy system: A comparative...
    • Mosavi, A., & Bahmani, A. (2019). Energy consumption prediction using machine learning: A review, Preprints. Energies, 11.
    • ONEI. (2019, Diciembre). Oficina Nacional de Estadística e Información. Electricidad en Cuba: Indicadores Seleccionados: http://www.one.cu/semestralelectricidad.htm.
    • Ray, P., Mishra, D. P., & Lenka, R. K. (2016). Short term load forecasting by artificial neural network. International Conference on Next...
    • Romero, F. T., Hernandez, J. C., & Lopez, W. G. (2011). Predicting Electricity Consumption Using Neural Networks. IEEE Latin America Transactions,...
    • Russel, S. J., & Norvig, P. (2016). Artificial intelligence: a modern approach. Malaysia. Pearson Education Limited.
    • Salam, A., & Hibaoui, A. E. (2018). Comparison of Machine Learning Algorithms for the Power Consumption Prediction:-Case Study of Tetouan...
    • Sandels, C., Widén, J., Nordström, L., & Andersson, E. (2015). Day-ahead predictions of electricity consumption in a Swedish office building...
    • Saravanan, S., Kannan, S., & Thangaraj, C. (2012). Forecasting India's electricity demand using artificial neural network. IEEE-International...
    • Seyedzadeh, S., Rahimian, F. P., Glesk, I., & Roper, M. (2018). Machine learning for estimation of building energy consumption and performance:...
    • Singh, R. P., Gao, P. X., & Lizotte, D. J. (2012). On hourly home peak load prediction IEEE Third International Conference on Smart Grid...
    • Sobrino, E. M., Santiago, A. V., & González., A. M. (2019). Forecasting the Electricity Hourly Consumption of Residential Consumers with...
    • Stein, B. V., Wang, H., & Bäck, T. (2019). Automatic Configuration of Deep Neural Networks with Parallel Efficient Global Optimization....
    • Tso, G. K., & Yau, K. K. (2007). Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural...
    • Tümer, A. E., Koçer, S., & Koca, A. (2016). Estimation of the electricity consumption of Turkey trough artificial neural networks. IEEE...
    • United Nation. (2019). UN, Sustainable Development Goal 7: Ensure access to affordable, reliable, sustainable and modern energy for all. Retrieved...
    • Yang, B., & Sun., Y. (2008). An improved neural network prediction model for load demand in day-ahead electricity market. 7th World Congress...
    • Yang, J., Rivard, H., & Zmeureanu, R. (2005). On-line building energy prediction using adaptive artificial neural networks vol. 37, no....
    • Yuan, J., Farnham, C., Azuma, C., & Emura, K. (2018). Predictive artificial neural network models to forecast the seasonal hourly electricity...
    • Zhao, H.-x., & Mogoules, F. (2012). A review on the prediction of building energy consumption. Renewable and Sustainable Energy Reviews,...
Fundación Dialnet

Mi Documat

Opciones de artículo

Opciones de compartir

Opciones de entorno