Abstract
The current paper is focusing on daily load consumption forecasting. This is a very important issue for every distribution system operator. Several methods are applied to achieve this goal: artificial neural networks and three conventional methods. The latter ones are based on linear approximation, curve fitting and decision. The starting point is represented by a big data set belonging to a real distribution system operator within our country. Thus, the authors are dealing with real data, extracted from the distribution network. In the following, a software tool has been developed, in Matlab environment for artificial intelligence based method and also for the conventional ones. A huge amount of data has been processed and the forecast has been performed for all the distribution branches belonging to that operator. Several indices have been computed in order to be able to provide related comments. Once all the forecasts have been carried-out, detailed analyses have been performed. Also, a hierarchy based on performance characteristics has been provided.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Baliyana, A., Gaura, K., Mishra, S.K.: A review of short term load forecasting using artificial neural network models. Procedia Comput. Sci. 48, 121–125 (2015)
Muhammad, A., Alam, K.A., Hussain, M.: Application of data mining using artificial neural network: survey. Int. J. Database Theory Appl. 8(1), 245–270 (2015)
Dudek, G.: Neural networks for pattern-based short-term load forecasting: a comparative study. Neurocomputing 205, 64–74 (2016)
Nuchprayoon, S.: Forecasting of daily load curve on monthly peak day using load research data and harmonics model. In: Proceedings of the 6th IEEE International Conference on Control System, Computing and Engineering, Malaysia, pp. 338–342 (2016)
Elgarhy, S.M., Othman, M.M., Taha, A., Hasanien, H.M.: Short term load forecasting us-ing ANN technique. In: Proceedings of the IEEE 19th International Middle East Power Systems Conference (MEPCON), Egypt, pp. 1385–1394 (2017)
Hui, X., Qun, W., Yao, L., Yingbin, Z., Lei, S., Zhisheng, Z.: Short-term load forecasting model based on deep neural network. In: Proceedings of the 2nd IEEE International Conference on Power and Renewable Energy, pp. 589–591 (2017)
Lin, J., Wang, F., Cai, A., Yan, W., Cui, W., Mo, J., Shao, S.: Daily load curve forecasting using factor analysis and RBF neural network based on load segmentation. In: Proceedings of the IEEE China International Electrical and Energy Conference (CIEEC), China, pp. 589–594 (2017)
Akarslan, E., Hocaoglu, F.O.: A novel short-term load forecasting approach using adaptive neuro-fuzzy inference system. In: Proceedings of the IEEE 6th International Istanbul Smart Grids and Cities Congress and Fair (ICSG), pp. 160–163 (2018)
Han, X., Li, X., Zhao, H., Bai, W.: Power load forecasting based on improved Elman neural network. In: Proceedings of the IEEE International Conference on Energy Internet, pp. 152–156 (2018)
Ozerdema, O.C., Olaniyi, E.O., Oyedotun, O.K.: Short term load forecasting using particle swarm optimization neural network. Procedia Comput. Sci. 120, 382–393 (2018)
Wang, L., Wang, Z., Qu, H., Liu, S.: Optimal forecast combination based on neural networks for time series forecasting. Appl. Soft Comput. 66, 1–17 (2018)
Chis, V.E.: Artificial intelligence techniques applied for load forecasting studies in power engineering field. Politehnica University Timisoara, Romania, Ph.D. thesis (2015). (in Romanian)
Kilyeni, S.T.: Numerical methods. Algorithms, Computing Programs, Power Engineering Application, 4th edn. Orizonturi Universitare Publishing House, Timisoara (2016). (in Romanian)
Eremia, M., Petricica, D., Bulac, C., Tristiu, I.: Artificial intelligence techniques. Concepts and applications in power systems. Agir Publishing House, Bucharest (2001). (in Romanian)
Csorba, L.M., Craciun, M.: An application of the multi period decision trees in the sustainable medical waste investments. In: Proceedings of the 7th International Workshop Soft Computing Applications (SOFA 2016), vol. 2, pp. 540–556 (2018)
Acknowledgment
This work was partial supported by the Politehnica University Timisoara research grants PCD-TC-2017.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Barbulescu, C., Kilyeni, S., Chis, V., Craciun, M., Simo, A. (2021). Daily Load Curve Forecasting. Comparative Analysis: Conventional vs. Unconventional Methods. In: Balas, V., Jain, L., Balas, M., Shahbazova, S. (eds) Soft Computing Applications. SOFA 2018. Advances in Intelligent Systems and Computing, vol 1221. Springer, Cham. https://doi.org/10.1007/978-3-030-51992-6_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-51992-6_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-51991-9
Online ISBN: 978-3-030-51992-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)