Comparison of Load Demand Forecasting Using Machine Learning and Classical Multivariate Regression Analysis
Abstract
To avoid an energy catastrophe, variable electrical load and ever-increasing load demand must be predicted or projected. Both suppliers and consumers benefit from forecasting the day-ahead electrical load. With precise load estimates, the reduction of electricity waste and the sensible dispatch of electric generator units can be considerably enhanced. This article is focused on comparing Artificial Neutral Network ANN (nonlinear model) and classical Multivariate linear Regression MLR (linear model) techniques for Short Term Load Forecasting (STLF). The live load data from a sub-station of the Abuja Electricity Distribution Company (AEDC), situated in the Federal Capital of Abuja, and is procured for the presented simulation study. For the simulation study using a neural network and MLR methodology, the obtained live data is divided into three categories: validation, training, and testing. The simulation results were checked against live load data from the chosen site and confirmed to be within allowable limits. The Coefficient of Determinate (R2), Correlation Coefficient (R), Mean Square Error (MSE), and Root-Mean-Square Error (RMSE) were calculated to demonstrate the effectiveness of the proposed machine learning based STLF, and it can be safely concluded that ANN (nonlinear models) gives far more accurate results than MLR (linear model), and is reliable in predicting the load forecast. This would aid in determining the variation in electric load well in advance and providing an opportunity or scope for preparedness to meet the abrupt spike in load demand, thereby achieving the requirements of active load forecasting in the power system arena.
Full Text:
PDFReferences
S. Mill, “Electric load forecasting: advantages and challenges,” Electrical engineering Community. 2018.
K. Zor, O. Timur, and A. Teke, “A state-of-the-art review of artificial intelligence techniques for short-term electric load forecasting,” 2017 6th Int. Youth Conf. Energy IYCE 2017, 2017, doi: 10.1109/IYCE.2017.8003734.
Wikipedia, “Electricity sector in Nigeria.” 2018.
P. U. Okorie and D. M. Ezekiel, “Overview of Abuja Electricity Distribution Undertaking,” vol. 3, no. 2, pp. 2446–2450, 2014.
“[PDF] Mid-Term Load Forecasting Based on Neural Network Algorithm_ a Comparison of Models _ Semantic Scholar.”
P. Bunnoon, K. Chalermyanont, and C. Limsakul, “Mid-term load forecasting: Level suitably of wavelet and neural network based on factor selection,” Energy Procedia, vol. 14, pp. 438–444, 2012, doi: 10.1016/j.egypro.2011.12.955.
N. A. Abd Jalil, M. H. Ahmad, and N. Mohamed, “Electricity load demand forecasting using exponential smoothing methods,” World Appl. Sci. J., vol. 22, no. 11, pp. 1540–1543, 2013, doi: 10.5829/idosi.wasj.2013.22.11.2891.
A. Sambo, “Matching electricity supply with demand in Nigeria,” Int. Assoc. Energy Econ., no. 4, pp. 32–36, 2008.
I. Kollia and S. Kollias, “A Deep Learning Approach for Load Demand Forecasting of Power Systems,” Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018. pp. 912–919, 2019. doi: 10.1109/SSCI.2018.8628644.
K. G. Boroojeni, M. H. Amini, S. Bahrami, S. S. Iyengar, A. I. Sarwat, and O. Karabasoglu, “A novel multi-time-scale modeling for electric power demand forecasting: From short-term to medium-term horizon,” Electric Power Systems Research, vol. 142. pp. 58–73, 2017. doi: 10.1016/j.epsr.2016.08.031.
M. Q. Raza and A. Khosravi, “A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings,” Renewable and Sustainable Energy Reviews, vol. 50. pp. 1352–1372, 2015. doi: 10.1016/j.rser.2015.04.065.
S. Hassan, A. Khosravi, J. Jaafar, and M. A. Khanesar, “A systematic design of interval type-2 fuzzy logic system using extreme learning machine for electricity load demand forecasting,” International Journal of Electrical Power and Energy Systems, vol. 82. pp. 1–10, 2016. doi: 10.1016/j.ijepes.2016.03.001.
A. K. Singh and S. Khatoon, “An Overview of Electricity Demand Forecasting Techniques,” Natl. Conf. Emerg. Trends Electr. Instrum. Commun. Eng., vol. 3, no. 3, pp. 38–48, 2013.
L. Wen, K. Zhou, and S. Yang, “Load demand forecasting of residential buildings using a deep learning model,” Electric Power Systems Research, vol. 179. 2020. doi: 10.1016/j.epsr.2019.106073.
“Load forecasting techniques and methodologies_ A review _ IEEE Conference Publication _ IEEE Xplore.”
A. Arjmand, R. Samizadeh, and M. Dehghani Saryazdi, “Meta-learning in multivariate load demand forecasting with exogenous meta-features,” Energy Efficiency, vol. 13, no. 5. pp. 871–887, 2020. doi: 10.1007/s12053-020-09851-x.
N. A. Mohammed, “Modelling of unsuppressed electrical demand forecasting in Iraq for long term,” Energy, vol. 162. pp. 354–363, 2018. doi: 10.1016/j.energy.2018.08.030.
Y. Ren, P. N. Suganthan, N. Srikanth, and G. Amaratunga, “Random vector functional link network for short-term electricity load demand forecasting,” Information Sciences, vol. 367–368. pp. 1078–1093, 2016. doi: 10.1016/j.ins.2015.11.039.
N. J. Johannesen, M. Kolhe, and M. Goodwin, “Relative evaluation of regression tools for urban area electrical energy demand forecasting,” Journal of Cleaner Production, vol. 218. pp. 555–564, 2019. doi: 10.1016/j.jclepro.2019.01.108.
A. Marinescu, C. Harris, I. Dusparic, S. Clarke, and V. Cahill, “Residential electrical demand forecasting in very small scale: An evaluation of forecasting methods,” 2013 2nd International Workshop on Software Engineering Challenges for the Smart Grid, SE4SG 2013 - Proceedings. pp. 25–32, 2013. doi: 10.1109/SE4SG.2013.6596108.
T. Ahmad and H. Chen, “Short and medium-term forecasting of cooling and heating load demand in building environment with data-mining based approaches,” Energy and Buildings, vol. 166. pp. 460–476, 2018. doi: 10.1016/j.enbuild.2018.01.066.
“Support vector regression based electricity peak load forecasting _ IEEE Conference Publication _ IEEE Xplore.”
N. Phuangpornpitak; W. Prommee, “A Study of Load Demand Forecasting Models in Electric Power System Operation and Planning,” GMSARN Int. J., vol. 10, no. Electric load Forecasting, p. 5, 2016.
Anas Faskari, S., Ojim, G., Falope, T. ., Badamasi Abdullahi, Y., & Abba, S. I (2022). A novel machine learning based computing algorithm in Modelling of Soiled Photovoltaic Module. Knowledge-based Engineering and Science, 3(1), 28-36 doi:10.51526/kbes.2022.3.1.28-36
Abba, S. I., Pham, Q. B., Saini, G., Linh, N. T. T., Ahmed, A. N., Mohaja
ne, M., & Bach, Q. V. ''Implementation of data intelligence models coupled
with ensemble machine learning for prediction of water quality index''. En
vironmental Science and Pollution Research, 1 -1 6. | 2020
S.I. Abba; Sagir Jibrin Kawu; Hamza Sabo Maccido; S.M. Lawan; Gafai Najashi; Abdullahi Yusuf Sada " Short-term load demand forecasting using nonlinear dynamic grey-blackbox and kernel optimization models: a new generation learning algorithm" https://www.researchgate.net/publication/356442149
Refbacks
- There are currently no refbacks.