Hybrid Optimization based on Deep Learning Approach for Short-Term Load Forecast of Electricity Demand in Buildings

Majlesi Journal of Electrical Engineering

مقاله 9، دوره 18، شماره 2، شهریور 2024، صفحه 1-13   

نوع مقاله: Reseach Article

شناسه دیجیتال (DOI): 10.57647/j.mjee.2024.1802.32

چکیده

Due to the growing popularity of microgrids in buildings, the foreseeable electricity demand for a building draws the attention of many researchers. The precise short-term demand forecast efficiently directs building managers and operators for interactions with electrical distribution systems, daily operational decisions, and energy conservation. This research proposes a hybrid optimization-based deep learning (DL) approach to increase the accuracy of short-term forecasts. The present work employs the Bilateral Long Short-Term Memory (BiLSTM) network-based DL technique because the BiLSTM technique has an exceptional ability to manage nonlinear interactions in data and learn the temporal dependencies. The performance of the BiLSTM technique is improved by using the optimally determined hyperparameters via a hybrid optimization algorithm that combines particle swarm optimization (PSO) and grey wolf optimization (GWO). The exploration ability of GWO and exploitation ability of PSO are effectively combined in the hybrid optimization GWO-PSO. The performance of the recommended approach is assessed using a case study of an educational building. The performance of the proposed model is compared to existing nonoptimal BiLSTM and single optimization-based BiLSTM for short-term load forecast. 

کلیدواژه‌ها

Bilateral Long Short Term Memory؛ Buildings؛ GWOPSO؛ Hyperparameter Optimization؛ Short Term Load forecast

مراجع

[1] I. Hamilton and O. Rapf. “Executive summary of
the 2020 global status report for buildings and construction.”. United Nations Environment Programme,
, 2020. DOI: https://doi.org/20.500.11822/34572.
[2] M. Santamouris and K. Vasilakopoulou. “Present
and future energy consumption of buildings: challenges and opportunities towards decarbonisation.”. e-Prime, 1(8):pp. 100002, 2021. DOI:
https://doi.org/10.1016/j.prime.2021.100002.
[3] Inger Andersen. “Global status report for buildings and construction: towards a zero-emission,
efficient and resilient buildings and construction
sector.”. United Nations Environment Programme, ,
2022.
[4] N. Amjady, F. Keynia, and H. Zareipour. “Shortterm load forecast of microgrids by a new
bilevel prediction strategy.”. IEEE Trans.
Smart Grid, 1(3):pp. 286–294, 2010. DOI:
https://doi.org/10.1109/TSG.2010.2078842.
[5] EIA. “CBECS 2018 building characteristics flipbook.”. EIA, , 2018.
[6] L. Hernandez et al. “A survey on electric power
demand forecasting: future trends in smart grids,
microgrids and smart buildings.”. IEEE Commun.
Surv. Tutorials, 16.
[7] J. P. Catala and Ed. “ ˜ ELECTRIC POWER SYSTEMS advanced forecasting techniques and optimal generation scheduling, 2012th ed.”. Boca Raton:
CRC PRESS, :pp. 3.1–3.2., 2017.
[8] R. Weron. “Modeling and forecasting electricity
loads and prices.”. Chichester: Wiley, :pp. 67–100,
2006.
[9] K. Li, C. Hu, G. Liu, and W. Xue. “Building’s electricity consumption prediction using optimized artificial neural networks and principal component
analysis.”. Energy Build, 108:pp. 106–113, 2015.
DOI: https://doi.org/10.1016/j.enbuild.2015.09.002.
[10] E. Ofori-Ntow Jnr and Y. Y. Ziggah. “Electricity
demand forecasting based on feature extraction and optimized backpropagation neural network.”. e-Prime - Adv. Electr. Eng. Electron. Energy., 6(9):pp. 100293, 2023. DOI:
https://doi.org/10.1016/j.prime.2023.100293.
[11] V. Gundu and S. P. Simon. “PSO–LSTM for
short term forecast of heterogeneous time series
electricity price signals.”. J. Ambient Intell. Humaniz. Comput., 12(2):pp. 2375–2385, 2021. DOI:
https://doi.org/10.1007/s12652-020-02353-9.
[12] T. Y. Kim and S. B. Cho. “Particle swarm
optimization-based CNN-LSTM networks for
forecasting energy consumption.”. 2019 IEEE
Congress on Evolutionary Computation, CEC 2019
- Proceedings, :pp. 1510–1516, 2019. DOI:
https://doi.org/10.1109/CEC.2019.8789968.
[13] J. Sauer, V. C. Mariani, L. dos Santos Coelho, M. H.
D. M. Ribeiro, and M. Rampazzo. “Extreme gradient boosting model based on improved Jaya optimizer applied to forecasting energy consumption in residential buildings.”. Evol. Syst., 13(4):pp.
577–588, 2022. DOI: https://doi.org/10.1007/s12530-
021-09404-2.
[14] A. M. Althahabi, H. M. Abed, R. Khalid, A. Ryadh,
and A. Al. “Prediction of the electricity demand in the market an application of optimization and machine learning.”. Majlesi J.
Electr. Eng., 17(2):pp. 109–115, 2023. DOI:
https://doi.org/10.30486/mjee.2023.1986619.1140.
[15] C. Li. “Designing a short-term load forecasting model in the urban smart grid system.”.
Appl. Energy., 266(1):pp. 114850, 2020. DOI:
https://doi.org/10.1016/j.apenergy.2020.114850.[16] U. B. Tayab, A. Zia, F. Yang, J. Lu, and M. Kashif.
“Short-term load forecasting for microgrid energy management system using hybrid HHO-FNN
model with best-basis stationary wavelet packet
transform.”. Energy, 203:pp. 117857, 2020. DOI:
https://doi.org/10.1016/j.energy.2020.117857.
[17] S. K. Panda, P. Ray, and S. R. Salkuti. “Hybrid
techniques for short term load forecasting.”. Majlesi J. Electr. Eng., 17(1):pp. 55–61, 2023. DOI:
https://doi.org/10.30486/mjee.2023.1970200.0.
[18] A. Irankhah, M. H. Yaghmaee, and S. ErshadiNasab. “Optimized short-term load forecasting in residential buildings based on deep learning methods for different time horizons.”. J.
Build. Eng., 84(1):pp. 108505, 2024. DOI:
https://doi.org/10.1016/j.jobe.2024.108505.
[19] S. Afzal, A. Shokri, B. M. Ziapour, H. Shakibi, and
B. Sobhani. “Building energy consumption prediction and optimization using different neural
network-assisted models; comparison of different networks and optimization algorithms.”. Eng.
Appl. Artif. Intell., 127:pp. 107356, 2024. DOI:
https://doi.org/10.1016/j.engappai.2023.107356.
[20] K. P. Amber, M. W. Aslam, and S. K. Hussain.
“Electricity consumption forecasting models for administration buildings of the UK higher education
sector.”. Energy Build, 90:pp. 127–136, 2015. DOI:
https://doi.org/10.1016/j.enbuild.2015.01.008.
[21] J. Massana, C. Pous, L. Burgas, J. Melendez, and
J. Colomer. “Short-term load forecasting in a
non-residential building contrasting models and
attributes.”. Energy Build, 92:pp. 322–330, 2015.
DOI: https://doi.org/10.1016/j.enbuild.2015.02.007.
[22] Y. T. Chae, R. Horesh, Y. Hwang, and Y. M. Lee.
“Artificial neural network model for forecasting
sub-hourly electricity usage in commercial buildings.”. Energy Build, 111:pp. 184–194, 2016. DOI:
https://doi.org/10.1016/j.enbuild.2015.11.045.
[23] H. Dagdougui, F. Bagheri, H. Le, and L. Dessaint. “Neural network model for short-term
and very-short-term load forecasting in district
buildings.”. Energy Build, 203, 2019. DOI:
https://doi.org/10.1016/j.enbuild.2019.109408.
[24] C. Ghenai, O. A. A. Al-Mufti, O. A. M. AlIsawi, L. H. L. Amirah, and A. Merabet. “Shortterm building electrical load forecasting using
adaptive neuro-fuzzy inference system (ANFIS).”.
J. Build. Eng., 52:pp. 104323, 2022. DOI:
https://doi.org/10.1016/j.jobe.2022.104323.
[25] R. E. Edwards, J. New, and L. E. Parker.
“Predicting future hourly residential electrical
consumption: a machine learning case study.”.
Energy Build, 49:pp. 591–603, 2012. DOI:
https://doi.org/10.1016/j.enbuild.2012.03.010.
[26] N. Tsalikidis, A. Mystakidis, C. Tjortjis, P. Koukaras,
and D. Ioannidis. “Energy load forecasting: one-step
ahead hybrid model utilizing ensembling.”. Computing, 106(1), 2023.
[27] H. Chitsaz, H. Shaker, H. Zareipour, D. Wood,
and N. Amjady. “Short-term electricity
load forecasting of buildings in microgrids.”.
Energy Build, 99:pp. 50–60, 2015. DOI:
https://doi.org/10.1016/j.enbuild.2015.04.011.
[28] M. Cai, M. Pipattanasomporn, and S. Rahman. “Dayahead building-level load forecasts using deep
learning vs. traditional time-series techniques.”.
Appl. Energy., 236(12):pp. 1078–1088, 2019. DOI:
https://doi.org/10.1016/j.apenergy.2018.12.042.
[29] M. Sajjad et al. “A novel CNN-GRU-Based hybrid
approach for short-term residential load forecasting.”. IEEE Access, 8:pp. 143759–143768, 2020. DOI:
https://doi.org/10.1109/ACCESS.2020.3009537.
[30] P. Koukaras, N. Bezas, P. Gkaidatzis, D. Ioannidis, D. Tzovaras, and C. Tjortjis. “Introducing
a novel approach in one-step ahead energy
load forecasting.”. Sustain. Comput. Informatics Syst., 32:pp. 100616, 2021. DOI:
https://doi.org/10.1016/j.suscom.2021.100616.
[31] Y. X. Kong, Weicong, Zhao Yang Dong, David J.
Hill, and Fengji Luo. “Short-term residential load
forecasting based on resident behaviour learning.”.
IEEE Trans. Power Syst., 33(1):pp. 2017–2018, 2018.
[32] W. Kong, Z. Y. Dong, Y. Jia, D. J. Hill, Y. Xu, and
Y. Zhang. “Short-term residential load forecasting
based on LSTM recurrent neural network.”. IEEE
Trans. Smart Grid., 10(1):pp. 841–851, 2019. DOI:
https://doi.org/10.1109/TSG.2017.2753802.
[33] A. Rahman, V. Srikumar, and A. D. Smith.
“Predicting electricity consumption for commercial and residential buildings using
deep recurrent neural networks.”. Appl.
Energy., 212(10):pp. 372–385, 2018. DOI:
https://doi.org/10.1016/j.apenergy.2017.12.051.
[34] A. M. Mahmood et al. “Electricity demand prediction by a transformer-based model.”. Majlesi J. Electr. Eng., 16(4):pp. 97–102, 2022. DOI:
https://doi.org/10.30486/mjee.2022.696520.
[35] J. Wang, S. Zhu, W. Zhang, and H. Lu.
“Combined modeling for electric load forecasting with adaptive particle swarm optimization.”. Energy, 35(4):pp. 1671–1678, 2010. DOI:
https://doi.org/10.1016/j.energy.2009.12.015.
[36] W. S. McCulloch and W. Pitts. “A logical calculus of the ideas immanent in nervous activity.”.
Bull. Math. Biophys., 5(4):pp. 115–133, 1943. DOI:
https://doi.org/10.1007/BF02478259[37] S. Hochreiter and J. Schmidhuber. “Long short-term
memory.”. Neural Comput, 9(8):pp. 1735–1780, 1997.
DOI: https://doi.org/10.1162/neco.1997.9.8.1735.
[38] F. C. Felix, A. Gers, and Jurgen Schmidhuber.
“Learning to forget: continual prediction with
LSTM.”. Neural Comput, 12(10):pp. 2451–2471,
2000.
[39] N. Somu, G. Raman, M R, and K. Ramamritham. “A deep learning framework for building energy consumption forecast.”. Renew. Sustain. Energy Rev., 137(4):pp. 110591, 2021. DOI:
https://doi.org/10.1016/j.rser.2020.110591.
[40] N. Mughees, S. A. Mohsin, A. Mughees, and
A. Mughees. “Deep sequence to sequence Bi-LSTM
neural networks for day-ahead peak load forecasting.”. Expert Syst. Appl., 175(12):pp. 114844, 2021.
DOI: https://doi.org/10.1016/j.eswa.2021.114844.
[41] R. Masadeh, A. Alzaqebah, and A. Hudaib. “Grey
wolf algorithm for requirements prioritization.”.
Mod. Appl. Sci., 12(2):pp. 54, 2018. DOI:
https://doi.org/10.5539/mas.v12n2p54.
[42] M. Schuster and K. K. Paliwal. “Bidirectional recurrent neural networks.”. IEEE Trans. Signal Processing., 45(11):pp. 2673–2681, 1997.
[43] S. Mirjalili, S. M. Mirjalili, and A. Lewis.
“Grey wolf optimizer.”. Adv. Eng.
Softw., 69:pp. 46–61, 2014. DOI:
https://doi.org/10.1016/j.advengsoft.2013.12.007.
[44] M. A. M. Shaheen, H. M. Hasanien, and A. Alkuhayli.
“A novel hybrid GWO-PSO optimization technique
for optimal reactive power dispatch problem solution.”. Ain Shams Eng. J., 12(1):pp. 621–630, 2021.
DOI: https://doi.org/10.1016/j.asej.2020.07.011.
[45] J. Kennedy and R. Eberhart. “Particle swarm optimization.”. Proceedings of ICNN’95 - International Conference on Neural Networks, 4, 1995. DOI:
https://doi.org/10.1109/ICNN.1995.488968.
[46] Angizeh Farhad, Ghofrani Ali, and Jafari Mohsen A.
“Dataset on hourly load profiles for a set of 24 facilities from industrial, commercial, and residential
end-use sectors.”. Mendeley Data, 1, 2020. DOI:
https://doi.org/10.17632/rfnp2d3kjp.1.