Abstract
Electricity outages in South Africa have become a growing concern for businesses and individuals. Despite improvements in supply, planned outages are becoming regular and manual load reduction is an ever-increasing concern for utility electricity agencies. This study presents a heterogeneous ensemble technique for classifying manual load reduction based on the contributing features of electricity generation sources and demand. Classical Random Forest (RF), Sparse Partial Least Squares (SPLS), and Averaged Neural Network (AvNNet) machine learning techniques were used as benchmarks. Three ensemble approaches were explored. Our results showed that the weighted average technique outperforms every other technique investigated. This is true for Precision 65.40%, F1 score 78.52%, Balanced Accuracy 97.15%, Kappa 76.53%, and Confusion Matrix. The only exception is Recall 98.24%, slightly outperformed by the majority voting 98.81%. It correctly classified 89.3% and 6.9% for Eskom no-load reduction (normal) and load reduction (anomaly), respectively. 3.7% and 0.1% accounted for the type-I and type-II errors, respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kademeteme, E., Twinomurinzi, H.: The ineffectiveness of technology adoption models in the 4IR era: a case of SMEs in South Africa. In: 2019 Open Innovations Conference, OI 2019, pp. 252–261 (2019). https://doi.org/10.1109/OI.2019.8908220
Motepe, S., Hasan, A.N., Twala, B., Stopforth, R., Alajarmeh, N.: South African power distribution network load forecasting using hybrid ai techniques: ANFIS and OP-ELM. In: Proceedings 2019 International Aegean Conference on Electrical Machines and Power Electronics, ACEMP 2019 and 2019 International Conference on Optimization of Electrical and Electronic Equipment, OPTIM 2019, pp. 557–562 (2019). https://doi.org/10.1109/ACEMP-OPTIM44294.2019.9007218
Motepe, S., Hasan, A.N., Shongwe, T.: Forecasting the total South African unplanned capability loss factor using an ensemble of deep learning techniques. Energies (Basel). 15 (2022). https://doi.org/10.3390/en15072546
Mabugu, T., Inglesi-lotz, R.: The effect of mismatched supply and demand of electricity on economic growth in South Africa. Energy Sour. Part B: Econ. Plann. Policy 1–18 (2022). https://doi.org/10.1080/15567249.2022.2038731
Shettar, S.N., Kinger, R., Tharun Kumar, S.I., Preetham, N.V.R., Ramya, K.: Blackout prediction in smart grids using machine learning. In: Proceedings of the 2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022, pp. 210–214 (2022). https://doi.org/10.1109/ICAIS53314.2022.9742882
Rahnamay-naeini, M., Wang, Z., Mammoli, A., Hayat, M.M.: A probabilistic model for the dynamics of cascading failures and blackouts in power grids, pp. 1–8 (2012)
Worship, N., David, O.: Munich personal RePEc archive electricity consumption and population growth in South Africa: a panel approach (2022)
Ali, M., Bosse, T., Hindriks, K. V, Hoogendoorn, M., Jonker, C.M., Treur, J.: Recent Trends in Applied Artificial Intelligence. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38577-3
Cawood, P., van Zyl, T.L.: Feature-weighted stacking for nonseasonal time series forecasts: a case study of the COVID-19 epidemic curves. In: 2021 8th International Conference on Soft Computing and Machine Intelligence, ISCMI 2021, pp. 53–59 (2021). https://doi.org/10.1109/ISCMI53840.2021.9654809
Syed, A.H., Khan, T., Hassan, A., Alromema, N.A., Binsawad, M., Alsayed, A.O.: An ensemble-learning based application to predict the earlier stages of Alzheimer’s disease (AD). IEEE Access 8, 222126–222143 (2020). https://doi.org/10.1109/ACCESS.2020.3043715
Mahendran, N., et al.: Sensor-assisted weighted average ensemble model for detecting major depressive disorder. Sens. (Switz.) 19 (2019). https://doi.org/10.3390/s19224822
Shashvat, K., Basu, R., Bhondekar, A.P., Kaur, A.: A weighted ensemble model for prediction of infectious diseases. Curr. Pharm. Biotechnol. 20, 674–678 (2019)
Wang, H., Yu, Y., Cai, Y., Chen, X., Chen, L., Li, Y.: Soft-weighted-average ensemble vehicle detection method based on single-stage and two-stage deep learning models. IEEE Trans. Intell. Veh. 6, 100–109 (2021). https://doi.org/10.1109/TIV.2020.3010832
Aloysius, N., Geetha, M.: A scale space model of weighted average CNN ensemble for ASL fingerspelling recognition. Int. J. Comput. Sci. Eng. 22, 154–161 (2020)
Tibshirani, R.: Regression Shrinkage and Selection via the Lasso. J. R. Stat. Soc. Ser. B (Methodol.) 58, 267–288 (1995)
Ripley, B.D.: Pattern Recognition and Neural Networks. Cambridge University Press, Cambridge (2007)
Dutta, S., Arunachalam, A., Misailovic, S.: To seed or not to seed? An empirical analysis of usage of seeds for testing in machine learning projects. In: 2022 IEEE Conference on Software Testing, Verification and Validation (ICST), pp. 151–161. IEEE (2022). https://doi.org/10.1109/ICST53961.2022.00026
Clemen, R.T.: Combining forecasts: a review and annotated bibliography. Int. J. Forecast. 5, 559–583 (1989). https://doi.org/10.1016/0169-2070(89)90012-5
Pruengkarn, R., Fung, C.C., Wong, K.W.: Using misclassification data to improve classification performance. In: ECTI-CON 2015 - 2015 12th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (2015). https://doi.org/10.1109/ECTICon.2015.7206950
Viera, A.J., Garrett, J.M.: Understanding interobserver agreement: the kappa statistic. Fam. Med. 37, 360–363 (2005)
Kuhn, M.: Building predictive models in R using the caret package. J. Stat. Softw. 28, 1–26 (2008). https://doi.org/10.18637/jss.v028.i05
Acknowledgement
The authors would like to thank Eskom, South Africa for providing electricity demand, generation sources and load reduction dataset.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Akinola, S.O., Wang, QG., Olukanmi, P., Mawala, T. (2023). Heterogeneous Ensemble for Classifying Electrical Load Reduction in South Africa. In: Fujita, H., Wang, Y., Xiao, Y., Moonis, A. (eds) Advances and Trends in Artificial Intelligence. Theory and Applications. IEA/AIE 2023. Lecture Notes in Computer Science(), vol 13926. Springer, Cham. https://doi.org/10.1007/978-3-031-36822-6_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-36822-6_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36821-9
Online ISBN: 978-3-031-36822-6
eBook Packages: Computer ScienceComputer Science (R0)