Hybrid Metaheuristic-Optimized Support Vector Regression for Electricity Consumption Prediction: A Comparative Performance Analysis

Hong JIANG, Chen LI

Abstract


The particular applications of metaheuristic algorithms like biogeography-based optimization for predicting electricity usage have always been considered in the literature. As buildings consume a significant part of the world's energy now, accurate models for predicting electricity usage are essential. Hence, this exploration aims to project the electricity usage based on the experimental data and training data using four optimizers: PSO, shuffled frog-leaping algorithm (SFLA), ant colony optimization (ACO), and BBO. Notably, the problem is solved considering three Support Vector Regression (SVR) models, including linear, Gaussian, and polynomial methods. The performance criteria, including Standard Error, MSE, RMSE, MAPE, MAE, Correlation Coefficient, Relative Absolute Error, Normalized Mean Square Error, and Coefficient of Determination, are assessed for the selected optimizers and networks. The results obtained illustrate that BBO achieved the highest prediction accuracy and the best final convergence quality, while ACO required the fewest iterations to reach convergence. Also, the statistical results in the training and experimental data emphasize the acceptable performance of Gaussian and linear networks, respectively.


Keywords


electricity usage prediction; optimization methods; BBO; Gaussian network; regression method

Full Text:

PDF

References


K. Amasyali and N. M. El-Gohary, “A review of data-driven building energy consumption prediction studies,” Renewable and Sustainable Energy Reviews, vol. 81, pp. 1192–1205, 2018.

C. Li, Z. Ding, D. Zhao, J. Yi, and G. Zhang, “Building energy consumption prediction: An extreme deep learning approach,” Energies (Basel)., vol. 10, no. 10, p. 1525, 2017.

H. Zhao and F. Magoulès, “A review on the prediction of building energy consumption,” Renewable and Sustainable Energy Reviews, vol. 16, no. 6, pp. 3586–3592, 2012.

P. Lajevardy, F.-A. Parand, H. Rashidi, and H. Rahimi, “A hybrid method for load forecasting in smart grid based on neural networks and cuckoo search optimization approach,” International Journal of Renewable Energy Resources, vol. 5, no. 1, pp. 13–20, 2015.

A. Borriello, P. F. Burke, and J. M. Rose, “If one goes up, another must come down: a latent class hybrid choice modelling approach for understanding electricity mix preferences among renewables and non-renewables,” Energy Policy, vol. 159, p. 112611, 2021.

H. Yousaf, A. Amin, A. Baloch, and M. Akbar, “Investigating household sector’s non-renewables, biomass energy consumption and carbon emissions for Pakistan,” Environmental Science and Pollution Research, vol. 28, no. 30, pp. 40824–40834, 2021.

P. Ekins, “Step changes for decarbonising the energy system: research needs for renewables, energy efficiency and nuclear power,” Energy Policy, vol. 32, no. 17, pp. 1891–1904, 2004.

N. A.-H. K. Hussein and O. M. Basel, “Integrating Renewable Energy Systems into Urban Planning for Sustainable Cities,” ESTIDAMAA, vol. 2024, pp. 15–21, Feb. 2024, doi: 10.70470/ESTIDAMAA/2024/003.

L. Lei, W. Chen, B. Wu, C. Chen, and W. Liu, “A building energy consumption prediction model based on rough set theory and deep learning algorithms,” Energy Build., vol. 240, p. 110886, 2021.

Z. Wu and W. Chu, “Sampling strategy analysis of machine learning models for energy consumption prediction,” in 2021 IEEE 9th International Conference on Smart Energy Grid Engineering (SEGE), IEEE, 2021, pp. 77–81.

M. H. M. N. M. L. N. H. Bakiri Hussein Abubakar, “Towards the Establishment of a Robust Load Forecasting Mechanism in Tanzania Grid: A Study to Investigate Effect of Air Temperature and Daytime on Electricity Consumption in Residential Buildings,” International Journal of Smart grid, Mar. 2021, doi: 10.20508/ijsmartgrid.v5i1.159.g140.

I. Karijadi and S.-Y. Chou, “A hybrid RF-LSTM based on CEEMDAN for improving the accuracy of building energy consumption prediction,” Energy Build., vol. 259, p. 111908, 2022.

Q. Qiao, A. Yunusa-Kaltungo, and R. E. Edwards, “Towards developing a systematic knowledge trend for building energy consumption prediction,” Journal of Building Engineering, vol. 35, p. 101967, 2021.

A. Almalaq and J. J. Zhang, “Evolutionary deep learning-based energy consumption prediction for buildings,” ieee access, vol. 7, pp. 1520–1531, 2018.

M. Bairami, H. Khajavi, and A. Rastgoo, “Assessing groundwater behavior and future trends in the Ardabil Aquifer: A comparative study of groundwater modeling system and categorical gradient boosting hybrid model,” Expert Syst. Appl., vol. 255, p. 124728, 2024.

X. J. Luo, L. O. Oyedele, A. O. Ajayi, O. O. Akinade, H. A. Owolabi, and A. Ahmed, “Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings,” Renewable and Sustainable Energy Reviews, vol. 131, p. 109980, 2020.

A. Pîrjan, S.-V. Oprea, G. C?ru?a?u, D.-M. Petro?anu, A. Bâra, and C. Coculescu, “Devising hourly forecasting solutions regarding electricity consumption in the case of commercial center type consumers,” Energies (Basel)., vol. 10, no. 11, p. 1727, 2017.

J. Virote and R. Neves-Silva, “Stochastic models for building energy prediction based on occupant behavior assessment,” Energy Build., vol. 53, pp. 183–193, 2012.

D. C. Park, M. A. El-Sharkawi, R. J. Marks, L. E. Atlas, and M. J. Damborg, “Electric load forecasting using an artificial neural network,” IEEE transactions on Power Systems, vol. 6, no. 2, pp. 442–449, 2002.

T. Pinto, I. Praça, Z. Vale, and J. Silva, “Ensemble learning for electricity consumption forecasting in office buildings,” Neurocomputing, vol. 423, pp. 747–755, 2021.

T. Parhizkar, E. Rafieipour, and A. Parhizkar, “Evaluation and improvement of energy consumption prediction models using principal component analysis based feature reduction,” J. Clean. Prod., vol. 279, p. 123866, 2021.

H. Zhong, J. Wang, H. Jia, Y. Mu, and S. Lv, “Vector field-based support vector regression for building energy consumption prediction,” Appl. Energy, vol. 242, pp. 403–414, 2019.

G. K. F. Tso and K. K. W. Yau, “Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks,” Energy, vol. 32, no. 9, pp. 1761–1768, 2007.

S. Asadi, S. S. Amiri, and M. Mottahedi, “On the development of multi-linear regression analysis to assess energy consumption in the early stages of building design,” Energy Build., vol. 85, pp. 246–255, 2014.

P. Nie, M. Roccotelli, M. P. Fanti, Z. Ming, and Z. Li, “Prediction of home energy consumption based on gradient boosting regression tree,” Energy Reports, vol. 7, pp. 1246–1255, 2021.

H.-C. Chang, C.-C. Kuo, Y.-T. Chen, W.-B. Wu, and E. J. Piedad, “Energy consumption level prediction based on classification approach with machine learning technique,” in 4th World Congress on New Technologies, 2018, pp. 1–8.

J.-S. Pan, P. Hu, and S.-C. Chu, “Novel parallel heterogeneous meta-heuristic and its communication strategies for the prediction of wind power,” Processes, vol. 7, no. 11, p. 845, 2019.

S. Malik and D. Kim, “Prediction-learning algorithm for efficient energy consumption in smart buildings based on particle regeneration and velocity boost in particle swarm optimization neural networks,” Energies (Basel)., vol. 11, no. 5, p. 1289, 2018.

H. Khajavi, A. Rastgoo, and F. Masoumi, “Enhanced Streamflow Forecasting for Crisis Management Based on Hybrid Extreme Gradient Boosting Model,” Iranian Journal of Science and Technology, Transactions of Civil Engineering, pp. 1–22, 2025.

S. Dai, D. Niu, and Y. Li, “Forecasting of energy consumption in China based on ensemble empirical mode decomposition and least squares support vector machine optimized by improved shuffled frog leaping algorithm,” Applied Sciences, vol. 8, no. 5, p. 678, 2018.

K. Guleria and A. K. Verma, “Meta-heuristic ant colony optimization based unequal clustering for wireless sensor network,” Wirel. Pers. Commun., vol. 105, pp. 891–911, 2019.

D. Nanjundappan, “Hybrid weighted probabilistic neural network and biogeography based optimization for dynamic economic dispatch of integrated multiple-fuel and wind power plants,” International Journal of Electrical Power & Energy Systems, vol. 77, pp. 385–394, 2016.

E. J. Piedad and C. Kuo, “A 12-month data of hourly energy consumption levels from a commercial-type consumer,” Mendeley Data, vol. 1, 2018.




DOI (PDF): https://doi.org/10.20508/ijrer.v16i3.17154.g9254

Refbacks

  • There are currently no refbacks.


Online ISSN: 1309-0127

Publisher: Gazi University

IJRER is indexed in EI Compendex, SCOPUS, EBSCO, WEB of SCIENCE (Clarivate Analytics)and CrossRef.

IJRER has been indexed in Emerging Sources Citation Index from 2016 in web of science.

WEB of SCIENCE in 2026; 

h=38,

Average citation per item=7.69

Last three Years Impact Factor=(1768+1782+2085)/(146+78+80)=5635/304=18.53

Category Quartile:Q4