Comparison between radial basis neural network improvement method with SALP optimization algorithm (RBF-SSA) with other hybrid optimization algorithms

Document Type : Research Paper

Authors

Faculty of Electrical Engineering and Computer, Hakim Sabzevari University, Sabzevar, Iran

Abstract

In the electricity industry, load forecasting is one of the most important tasks in planning, distribution, operations management, and providing appropriate solutions for power systems. Power consumption plays an important role in the planning and optimal use of power systems. With the existing technology, it is not yet possible to store this energy in large dimensions, so accurate forecasting of consumption can play an important role in the economic use of electricity. The amount of electrical charge consumption is not constant but is complex and nonlinearly a function of several parameters. Due to the variable amount of electrical charge consumption, power companies must anticipate it in different timelines of the information needed to make decisions. In this article, a new method is presented according to the efficiency of short-term load prediction, which can be from the next few hours to a week or a few weeks. Due to the efficiency of evolutionary methods in setting the parameters of forecasting methods, in this paper, the SALP optimization algorithm is used as an algorithm with high convergence accuracy to improve the neural network of the radial base function. Therefore, in this paper, a comparison between the method of improving the neural network of the radial base function with the SALP optimization algorithm for short-term load prediction by considering meteorological factors with other combined methods of optimization algorithms is shown. The results of comparison between predictions in the proposed model (improved neural network with SALP algorithm) compared to other combined methods of load prediction, show that the proposed neural network method improves the radial base function with SALP (RBF-SSA) better. Other combined methods improve the results.

Keywords

[1] A.Z. Ala’M, A.A. Heidari, M. Habib, H. Faris, I. Aljarah and M.A. Hassonah, SALP chain-based optimization of
support vector machines and feature weighting for medical diagnostic information systems, Evolutionary Machine
Learning Techniques, (2020), 11–34.
[2] I. Aljarah, H. Faris, S. Mirjalili and N. Al-Madi, Training radial basis function networks using biogeography-based
optimizer, Neural Comput. Appl. 29 (2016), no. 7, 529–553.
[3] M. Barman, N.D. Choudhury and S. Sutradhar, A regional hybrid SSA-SVM model based on similar day approach
for short-term load forecasting in Assam, India, Energy 145 (2018), 710–720.
[4] G. Cervone, L. Clemente-Harding, S. Alessandrini and L. Delle Monache, Short-term photovoltaic power forecasting using artificial neural networks and an analog ensemble, Renew. Energy 108 (2017), 274–286.
[5] G.W. Chang, H.J. Lu, Y.R. Chang and Y.D. Lee, An improved neural network-based approach for short-term
wind speed and power forecast, Renew. Energy 105 (2017), 301–311.
[6] S. Ding, K.W. Hipel and Y.G. Dang, Forecasting China’s electricity consumption using a new grey prediction
model, Energy 149 (2018), 314–328.
[7] Y. Liang, D. Niu and W.C. Hong, Short term load forecasting based on feature extraction and improved general
regression neural network model, Energy 166 (2019), 653–663.
[8] Y. Liu, W. Wang and N. Ghadimi, Electricity load forecasting by an improved forecast engine for building level
consumers, Energy 139 (2017), 18–30.
[9] M. Meng, L. Wang and W. Shang, Decomposition and forecasting analysis of China’s household electricity consumption using three-dimensional decomposition and hybrid trend extrapolation models, Energy 165 (2018), 143–
152.
[10] S. Mirjalili, A.H. Gandomi, S.Z. Mirjalili, S. Saremi, H. Faris and S.M. Mirjalili, SALP swarm algorithm: a
bio-inspired optimizer for engineering design problems, Adv. Engin. Software 114 (2017), 163–191.
[11] M.Q. Raza, M. Nadarajah, D.Q. Hung and Z. Baharudin, An intelligent hybrid short-term load forecasting model
for smart power grids, Sustain. Cities Soc. 31 (2017), 264–275.
[12] S.R. Salkuti, Short-term electrical load forecasting using radial basis function neural networks considering weather
factors, Electr. Eng. 100 (2018), no. 3, 1985–1995.
[13] A. Tarsitano and I.L. Amerise, Short-term load forecasting using a two-stage sarimax model, Energy 133 (2017),
108–114.
[14] W. Yang, J. Wang, T. Niu and P. Du, A hybrid forecasting system based on a dual decomposition strategy and
multi-objective optimization for electricity price forecasting, Appl. Energy 235 (2019), 1205–1225.
[15] W. Yin, Y. Han, H. Zhou, M. Ma, L. Li and H. Zhu, A novel non-iterative correction method for short-term
photovoltaic power forecasting, Renew. Energy 159 (2020), 23–32.
[16] J. Zhang, Y.M. Wei, D. Li, Z. Tan and J. Zhou, Short term electricity load forecasting using a hybrid model,
Energy 158 (2018), 774–781.
Volume 13, Issue 2
July 2022
Pages 2923-2932
  • Receive Date: 14 March 2022
  • Revise Date: 30 April 2022
  • Accept Date: 06 May 2022