A Comparative Study on the Performances of Power Systems Load Forecasting Algorithms

Year 2021, Volume: 1 Issue: 2, 99 - 107, 31.10.2021

Titus Ajewole , Abdulsemiu Olawuyi , Mutiu Kolawole Agboola Opeyemi Onarinde

https://doi.org/10.5152/tepes.2021.21043

https://izlik.org/JA99CB78MP

Abstract

In this study, the efficiencies of three different neural network load forecasting algorithms are compared to determine the best performance. The algo- rithms––Levenberg–Marquardt, gradient descent, and gradient descent with momentum and adaptive learning rate backpropagation are used to train a neural network (NN) model for energy demand prediction on a power system. Prior loads, weather parameters (temperature, relative humidity, and precipitation), and customer population of the supplied region are employed as training inputs. To ascertain the accuracy of the predictions, mean absolute error and mean square error are used as evaluation indices, and the algorithm with the least index values is deployed on a transmission substation. The Levenberg–Marquardt algorithm was found to be the most efficient candidate, and this algorithm is therefore recommended for adequate and proper system management, planning, and expansion, to enhance the efficiency, effectiveness, and accessibility of power supply.

Keywords

Algorithm , comparison , load forecasting , model training , neural network , transmission substation.

Thanks

The authors thank the Regional Control Center, Osogbo, for providing the necessary data on the electrical load utilization of the area from 2011 to 2015. The authors also appreciate the National Aeronautics and Space Administration (NASA), for providing the weather parameters needed for the study.

References

• 1. E. A. Feilat, D. T. Al-Sha’abi and M. A. Mo-mani, “Long-term load fore- casting using neural network approach for Jordan’s power system,” Eng. Press, vol. 1, no. 2, pp. 43–50, 2017.
• 2. T. O. Ajewole, O. D. Momoh, O. D. Ayedun and M. O. Omoigui, “Optimal component configuration and capacity sizing of a mini integrated power supply system,” Environ. Qual. Manag., vol. 28, no. 4, pp. 57–62, 2019.
• 3. R. Patel, M. R. Patel and R. V. Patel, “A review: Introduction and understanding of load forecasting,” J. Appl. Sci. Comput., vol. 4, pp. 1449–1457, 2019.
• 4. W. Aribowo and S. Muslim, “Long-term electricity load forecasting based on cascade forward backpropagation neural network,” J. Telecommun. Electron. Comput. Eng., vol. 12, no. 2, pp. 1449–1457, 2020.
• 5. P. Dixit, “Daily peak load forecast using artificial neural network,” Int. J. Electr. Comput. Eng., vol. 9, no. 4, p. 2256, 2019.
• 6. A. Amini, “6S191_MIT_DeepLearning_L1.pdf - Introduction to Deep Learning Alexander Amini MIT,” 6.S191 Introduction to Deep Learning | Course Hero, 2020. [Online]. Available: https://www.coursehero.com/fil e/54813875/6S191-MIT-DeepLearning-L1pdf/.
• 7. S. Singh, S. Hussain and M. A. Bazaz, “Short-term load forecasting using artificial neural network,” in Fourth International Conference on Image Information Processing (ICIIP), 2017, pp. 1–5.
• 8. O. Olabode, O. Amole, T. Ajewole and I. Okakwu, “Medium-term load forecasting in a Nigerian electricity distribution region using regression analysis techniques,” in International Conference in Mathematics, Computer Engineering and Computer Science (ICMCECS), 2020,pp. 1–5.
• 9. H. Matsila and P. Bokoro, “Load forecasting using statistical time series model in a medium voltage distribution network,” in IECON 2018-44th Annual Conference of the IEEE Industrial Electronics Society, 2018, pp. 4974–4979.
• 10. A. Y. Saber and A. R. Alam, “Short-term load forecasting using multiple linear regression for big data,” in IEEE Symposium Series on Computational Intelligence (SSCI), 2017, pp. 1–6.
• 11. A. Baliyan, K. Gaurav and S. K. Mishra, “A review of short-term load forecasting using artificial neural network models,” Procedia Comput. Sci., vol. 48, pp. 121–125, 2015.
• 12. S. Khatoon and A. K. Singh, “Effects of various factors on electric load forecasting: An overview,” in 6th IEEE Power India International Conference (PIICON), 2014, pp. 1–5.
• 13. Z. Zhang, “A gentle introduction to artificial neural networks,” Ann. Transl. Med., vol. 4, no. 19, p. 370, 2016.
• 14. S. H. Han, K. W. Kim, S. Kim and Y. C. Youn, “Artificial neural network: Understanding the basic concepts without mathematics,” Dement. Neurocogn. Disord., vol. 17, no. 3, pp. 83–89, 2018.
• 15. T. Anwar, B. Sharma, K. Chakraborty and H. Sirohia, “Introduction to load forecasting,” Int. J. Pure Appl. Math., vol. 119, pp. 1527–1538, 2018.
• 16. G. M. U. Din and A. K. Marnerides, “Short-term power load forecasting using deep neural networks,” in International Conference on Computing, Networking and Communications (ICNC), 2017, pp. 594–598.
• 17. S. M. Elgarhy, M. M. Othman, A. Taha and H. M. Hasanien, “Short-term load forecasting using ANN technique,” in Nineteenth International Middle East Power Systems Conference (MEPCON) [Internet]. Cairo: IEEE Publications, 2017, pp. 1385–1394. Available:http://ieeexplore.ieee.org/document/8301364/.
• 18. N. Ammar, M. Sulaiman and A. F. M. Nor, “Long-term load forecasting of power systems using artificial neural network and ANFIS,” ARPN J. Eng. Appl. Sci., vol. 13, no. 3, pp. 828–834, 2018.
• 19. H. Sangrody, N. Zhou, S. Tutun, B. Khorramdel, M. Motalleb and M. Sarailoo, “Long-term forecasting using machine learning methods,” in IEEE Power and Energy Conference at Illinois (PECI), 2018, pp. 1–5.
• 20. M. Buhari and S. S. Adamu, “Short-term load forecasting using artificial neural network,” in Proceedings of the International Multi-Conference of Engineers and Computer Scientists, Hongkong, vol. 1, pp. 1–71, March 14–16, 2012.
• 21. X.-S. Yang, “Optimization techniques and applications with examples,”Optim. Tech. Appl. Examples, 2018.
• 22. S. H. Haji and A. M. Abdulazeez, “Comparison of optimization tech- niques based on gradient descent algorithm: A review,” PalArchs J. Archaeol. Egypt Egyptology, vol. 18, no. 4, pp. 2715–2743, 2021.
• 23. H. Yu and B. M. Wilamowski, “Levenberg–Marquardt training,” in Intelligent systems. Boca Raton: CRC Press, 2018, pp. 12–11.
• 24. P. Netrapalli, “Stochastic gradient descent and its variants in machine learning,” J. Indian Inst. Sci., vol. 99, no. 2, pp. 201–213, 2019.
• 25. MathWorks. MATLAB (R2018a). USA: MathWorks, 2018.
• 26. M. O. Lawal, T. O. Ajewole and O. S. Babalola, “Fortification of the 330- KV Nigerian network using renewable energy resources,” Niger. J. Eng., vol. 26, no. 1, pp. 33–40, 2019.