Fast and Efficient Very Short-Term Load Forecasting Using Analogue and Moving Average Tools

Authors

Keywords:

Real-time, Analogues, green algorithms, very short-term load forecast

Abstract

The electricity market’s continuous and secure operation depends on accurately predicting real-time demand. This study presents an innovative Analogue Moving Average (AnMA) method that uses classical statistical techniques like correlation, regression, and moving averages to improve the accuracy of load demand forecasting. AnMA is designed to correct for biases and unforeseen changes in load demand and offers several desirable attributes, such as high accuracy, speed, robustness, low maintenance, repeatability, and a low computational cost. The study evaluates the performance of AnMA against Naïve, exponential smoothing, and Autoregressive Moving Average (ARMA) benchmarks for forecasting horizons ranging from five minutes to two hours multi-step ahead, using data from the preceding four months. The results show that AnMA is competitive with the benchmarks in terms of accuracy while offering dramatically lower computational costs, making it an efficient and highly attractive method.

Downloads

Download data is not yet available.

Author Biographies

Uriel Iram Lezama Lope, Universidad Autonoma de Nuevo Leon

Uriel earned a Bachelor of Science degree in Electrical Engineering, specializing in Electrical Power Systems, in 2003. Later, in 2010, he completed a Master's in Systems Engineering from the National Polytechnic Institute in Mexico. In 2009, he joined the National Institute of Electricity and Clean Energy as a researcher, where he developed advanced software for power system operations and contributed to the development of tools for managing the Mexican Electricity Market, including real-time systems. Currently, Uriel is a doctoral candidate in Systems Engineering at UANL in Mexico.

Alberto Benavides-Vázquez, Universidad Autónoma de Nuevo León

Alberto has a bachelor's degree in Philosophy and another in Multimedia. After that, he got a master's degree in System Engineering and is currently a doctoral student in the Department of Mechanical and Electrical Engineering at UANL, Mexico. His areas of interest are data science, time series forecasting, natural language processing, and data visualization for academic and business applications.

Guillermo Santamaría-Bonfil, BBVA

Guillermo holds a Ph.D. in Computer Science from Tecnologico de Monterrey. He has extensive experience in time series forecasting, feature selection, machine learning, and complexity analysis using information-based measures, with a decade of research experience at CONACYT-UADY. Currently, he holds an Expert Data Scientist position at BBVA, where he leverages his expertise to provide key insights and data-driven decision-making models and algorithms.

Roger Z. Ríos-Mercado, Universidad Autónoma de Nuevo León

Roger is a professor of Operations Research at UANL in Mexico, holding a Ph.D. in the same field from the University of Texas at Austin. He has held visiting scholar positions at the University of Colorado, Barcelona Tech, and University of Texas at Austin. His research focuses on designing efficient solutions to complex discrete optimization problems. His work covers districting, location analysis, healthcare, transportation systems, and scheduling, and has been published in top journals in the field. He is an Area Editor for Computers and Operations Research, and a Fellow of the Mexican System of Research Scientists, the Mexican Academy of Sciences, and the Mexican Academy of Computer Sciences.

References

L. Dannecker, Energy Time Series Forecasting: Efficient and Accurate Forecasting of Evolving Time Series from the Energy Domain. Springer Fachmedien Wiesbaden, 2015.

J. Y. Fan and J. D. McDonald, “A real-time implementation of short-term load forecasting for distribution power systems,” IEEE Transactions on Power Systems, vol. 9, no. 2, pp. 988–994, 1994.

S. Yadav, B. Tondwal, and A. Tomar, “Models of load forecasting,” in Prediction Techniques for Renewable Energy Generation and Load Demand Forecasting (A. Tomar, P. Gaur, and X. Jin, eds.), vol. 956 of Lecture Notes in Electrical Engineering, ch. 7, pp. 111–130, Singapore, Singapore: Springer, 2023.

Y. Yang, T. Nishikawa, and A. E. Motter, “Small vulnerable sets determine large network cascades in power grids,” Science, vol. 358, no. 6365, p. 3184, 2017.

I. K. Nti, M. Teimeh, O. Nyarko-Boateng, and A. F. Adekoya, “Electricity load forecasting: a systematic review,” Journal of Electrical Systems and Information Technology, vol. 7, no. 13, pp. 2314–7172, 2020.

A. Azeem, I. Ismail, S. M. Jameel, and V. R. Harindran, “Electrical load forecasting models for different generation modalities: A review,” IEEE Access, vol. 9, pp. 142239–142263, 2021.

I. Bari ́c, R. Grbi ́c, and E. K. Nyarko, “Short-term forecasting of electricity consumption using artificial neural networks – an overview,” in 42nd International Convention on Information and Communication Technology, Electronics And Microelectronics (MIPRO), (Opatija, Croatia), pp. 1076–1081, May 2019.

J. Gunawan and C.-Y. Huang, “An extensible framework for short-term holiday load forecasting combining dynamic time warping and LSTM network,” IEEE Access, vol. 9, pp. 106885–106894, 2021.

M. Capuno, J.-S. Kim, and H. Song, “Very short-term load forecasting using hybrid algebraic prediction and support vector regression,” Mathematical Problems in Engineering, vol. 2017, p. 8298531, 2017.

B. Ibrahim, L. Rabelo, E. Gutierrez-Franco, and N. Clavijo-Buritica,“Machine learning for short-term load forecasting in smart grids,” Energies, vol. 15, no. 21, 2022.

S. Makridakis, E. Spiliotis, and V. Assimakopoulos, “The M4 competition: 100 000 time series and 61 forecasting methods,” International Journal of Forecasting, vol. 36, no. 1, pp. 54–74, 2020.

S. Tiwari, A. Jain, N. M. O. S. Ahmed, Charu, L. M. Alkwai, A. K. Y. Dafhalla, and S. A. S. Hamad, “Machine learning-based model for prediction of power consumption in smart grid-smart way towards smart city,” Expert Systems, vol. 39, no. 5, p. e12832, 2022.

C. Tong, L. Zhang, H. Li, and Y. Ding, “Temporal inception convolutional network based on multi-head attention for ultra-short-term load forecasting,” IET Generation, Transmission & Distribution, vol. 16, no. 8, pp. 1680–1696, 2022.

A. M. N. C. Ribeiro, P. R. X. do Carmo, P. T. Endo, P. Rosati, and T. Lynn, “Short- and very short-term firm-level load forecasting for warehouses: A comparison of machine learning and deep learning models,” Energies, vol. 15, no. 3, p. 750, 2022.

H. Nano, S. New, A. Cohen, and B. Ramachandran, “Load forecasting using multiple linear regression with different calendars,” in Distributed Energy Resources in Microgrids (R. K. Chauhan and K. Chauhan, eds.), ch. 16, pp. 405–417, Greater Noida, India: Academic Press, 2019.

L. D. Monache, F. A. Eckel, D. L. Rife, B. Nagarajan, and K. Searight, “Probabilistic weather prediction with an analog ensemble,” Applied Energy, vol. 141, pp. 3498–3516, 2013.

S. Alessandrini, L. Delle Monache, S. Sperati, and G. Cervone, “An analog ensemble for short-term probabilistic solar power forecast,”Applied Energy, vol. 157, pp. 95–110, 2015.

S. Alessandrini, L. Delle Monache, S. Sperati, and J. Nissen, “A novel application of an analog ensemble for short-term wind power forecasting,” Renewable Energy, vol. 76, pp. 768–781, 2015.

M. Azevedo, R. Ruiz-Cárdenas, L. Brioschi, and M. Oliveira, “Dynamic time scan forecasting for multi-step wind speed prediction,” Renewable Energy, vol. 177, pp. 584–595, 2021.

R. B. D. Santis, T. S. Gontijo, and M. A. Costa, “Dynamic time scan forecasting: A benchmark with m4 competition data,” IEEE Latin America Transactions, vol. 21, no. 2, pp. 320–327, 2023.

P. G. Gould, A. B. Koehler, J. K. Ord, R. D. Snyder, R. J. Hyndman,and F. Vahid-Araghi, “Forecasting time series with multiple seasonal patterns,” European Journal of Operational Research, vol. 191, no. 1, pp. 207–222, 2008.

A. M. D. Livera, R. J. Hyndman, and R. D. Snyder, “Forecasting time series with complex seasonal patterns using exponential smoothing,”Journal of the American Statistical Association, vol. 106, no. 496,pp. 1513–1527, 2011.

G. Dudek, “Pattern similarity-based methods for short-term load forecasting — Part 1: Principles,” Applied Soft Computing, vol. 37, pp. 277–287, 2015.

G. Dudek, “Pattern-based local linear regression models for short-term load forecasting,” Electric Power Systems Research, vol. 130, pp. 139–147, 2016.

V. Ngo, W. Wu, B. Zhang, Z. Li, and Y. Wang, “Ultra-short-term load forecasting using robust exponentially weighted method in distribution networks,” in 2015 IEEE Power & Energy Society General Meeting,(Denver, USA), pp. 1–5, July 2015.

G. E. P. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control. New York: Wiley, 5th ed., 2015.

F. Martínez, M. P. Frías, M. D. Pérez, and A. J. Rivera, “A methodology for applying k-nearest neighbor to time series forecasting,” Artificial Intelligence Review, vol. 52, no. 3, pp. 2019–2037, 2019.

R. J. Hyndman and Y. Khandakar, “Automatic time series forecasting:the forecast package for R,” Journal of Statistical Software, vol. 26,no. 3, pp. 1–22, 2008.

F. Garza, M. M. Canseco, C. Challú, and K. G. Olivares, “StatsForecast:Lightning fast forecasting with statistical and econometric models.” Py-Con Salt Lake City, Utah, 2022. https://github.com/Nixtla/statsforecast.

C. Bergmeir, R. J. Hyndman, and B. Koo, “A note on the validity of cross-validation for evaluating autoregressive time series prediction,” Computational Statistics & Data Analysis, vol. 120, pp. 70–83, 2018.

S. Seabold and J. Perktold, “Statsmodels: Econometric and statistical modeling with Python,” in Proceedings of the 9th Python in Science Conference (SciPy 2010) (S. van der Walt and J. Millman, eds.),(Austin), pp. 92–96, 2010.

L. Lannelongue, J. Grealey, and M. Inouye, “Green algorithms: Quantifying the carbon footprint of computation,” Advanced Science, vol. 8,no. 12, p. 2100707, 2021. http://calculator.green-algorithms.org/

Downloads

Published

2023-06-22

How to Cite

Lezama Lope, U. I., Benavides-Vázquez, A., Santamaría-Bonfil, G., & Ríos-Mercado, R. Z. (2023). Fast and Efficient Very Short-Term Load Forecasting Using Analogue and Moving Average Tools. IEEE Latin America Transactions, 21(9), 1015–1021. Retrieved from https://latamt.ieeer9.org/index.php/transactions/article/view/7939

Issue

Vol. 21 No. 9 (2023): Special Issue on Sustainable Energy Sources for an Energy Transition

Section

Special Issue on Sustainable Energy Sources for an Energy Transition