Using Artificial Neural Network Model to Forecast the Electricity Consumption in Algeria
Abstract
Recent events, especially the Russian-Ukrainian War have demonstrated the significance of energy resource, which is generally regarded as one of the most fundamental components of global economies and is classified as a strategic component of economic development. In this study, we employed the artificial neural networks to predict the electricity consumption of Algeria using annual data 1980 to 2022. After discussing this method's methodology and the diagnostic phase, the model's Multi-Layer Perceptron neural networks (MLP) were chosen. MLP 3-1-1 was found to be the most effective model. In the forecasting phase, the electricity consumption energy in Algeria was predicted to be 76,83 billion TWh in 2023 and 79,47 billion TWh in 2024, an increase of 3,434%.
Downloads
References
Azadeh, Ghaderi and Gitiforouz. (2006). Estimating Electricity Demand Function in Residential Sector by Fuzzy Regression, IEEE ISIE 2006, July 9-12, Montreal, Quebec, Canada. doi: 10.1109/ISIE.2006.295625.
Bouznit, Pablo-Romero and Sánchez-Braza. (2018). Residential Electricity Consumption and Economic Growth in Algeria, Energies, 11, 1656. https://doi.org/10.3390/en11071656
Chekouri, S.M, and Sahed, A. (2022). Forecasting Electricity Consumption In Algeria Using Artificial Neural Networks, مجلة رؤى اقتصادية, 12, 1, p. 247-261. https://www.asjp.cerist.dz/en/article/205040
Fausett, Laurene. (1994). Fundamentals of neural networks: architectures algorithms, and applications, USA: Prentice-Hall, Inc. https://dl.matlabyar.com/siavash/Neural%20Network/Book/Fausett%20L.-Fundamentals%20of%20Neural%20Networks_%20Architectures,%20Algorithms,%20and%20Applications%20(1994).pdf
Ghomi, Moeti and Azimi. (2011). Introduction of Neural Network Model and Fuzzy Regression Method for Short Term Load Forecasting in The Center Regional of IRAN, 2011 International Conference on Network and Electronics Engineering IPCSIT vol.11 © IACSIT Press, Singapore.
Jaromir, Vrbka. (2021). Using Artifical Neural Networks for Timeseries Smoothing and Forecating: Case Studies in Economics, Institute of Technology and Business in Ceske, Volume 979. https://doi.org/10.1007/978-3-030-75649-9
Kavaklioglu, K, Ceylan, H, Ozturk, H.K, and Canyurt, O.E. (2009). Modeling and prediction of Turkey’s electricity consumption using Artificial Neural Networks, Energy Conversion and Management, Volume 50, Issue 11, Pages 2719-2727, https://doi.org/10.1016/j.enconman.2009.06.016
Li, Kai, and Tao Zhang. (2018). Forecasting Electricity Consumption Using an Improved Grey Prediction Model, Information 9, no. 8, 204. https://doi.org/10.3390/info9080204
Madouri, H., and Mékidiche, M. (2017). dirāsah muqāranah bayna bayna al-namādhij al-Ṭawīlah ARFIMA wa-al-shabakāt al-ʻaṣabīyah alāṣṭnāʻyh bāltnbʼ bsʻr ṣarf al-dīnār al-Jazāʼirī,. El-Bahith Review 17 (17), 159-171. https://www.asjp.cerist.dz/en/article/34422
Panklib, K, Prakasvudhisarn, C, and Khummongkol, D. (2015). Electricity Consumption Forecasting in Thailand Using an Artificial Neural Network and Multiple Linear Regression, Energy Sources, Part B: Economics, Planning, and Policy, 10, 4, 427-434, https://doi.org/10.1080/15567249.2011.559520
Pereira, F., Lou, B., Pritchett, B. et al. (2018). Toward a universal decoder of linguistic meaning from brain activation. Nat Commun 9, 963. https://doi.org/10.1038/s41467-018-03068-4
Sarkar, Rabbani, Khan and Hossain. (2015). Electricity Demand Forecasting of Rajshahi City in Bangladesh Using Fuzzy Linear Regression Model, 2nd Int'l Conf. on Electrical Engineering and Information & Communication Technology (ICEEICT) Jahangirnagar University, Dhaka-1342, Bangladesh, 21-23 May 2015. http://dx.doi.org/10.1109/ICEEICT.2015.7307424
Scarborough, D., & Somers, M. J. (2006). Neural networks in organizational research: Applying pattern recognition to the analysis of organizational behavior. American Psychological Association. https://doi.org/10.1037/11465-00
Shah, Ismail, Hasnain Iftikhar, and Sajid Ali. (2020). Modeling and Forecasting Medium-Term Electricity Consumption Using Component Estimation Technique, Forecasting, 2, no. 2, 163-179. https://doi.org/10.3390/forecast2020009
الثعلبي، ساهرة حسين زين، وعمران، خلود موسى. (2016). تحديد أفضل نموذج للتنبؤ باستهلاك الطاقة الكهربائية في المنطقة الجنوبية. مجلة العلوم الاقتصادية والإدارية، 22(90)، 437–457. https://search.emarefa.net/detail/BIM-699721
جباري، ل. (2016). طرق اتخاذ القرار باستخدام الذكاء الاصطناعي: دراسة مقارنة للتنبؤ بالطاقة الكهربائية لولاية تلمسان باستعمال الشبكات العصبية الاصطناعية [أطروحة دكتوراه غير منشورة]. جامعة أبي بكر بلقايد تلمسان. http://dspace.univ-tlemcen.dz/bitstream/112/8806/1/sonelgaz-prevision-decision-charge-electrique-intelligence-artificielle-neurones-box-jenkins.Doc.pdf
عتروس، سهيلة. (2018). استخدام منهجية جنكنز والشبكات العصبية الاصطناعية للتنبؤ باستهلاك الطاقة الكهربائية بمؤسسة سونلغاز: دراسة حالة ولاية بسكرة [أطروحة دكتوراه غير منشورة]. جامعة بسكرة. http://thesis.univ-biskra.dz/4485/1/Th%C3%A8se%20Atrous%20Souheila.pdf
شاهد، عبد القادر، وقهوي، حسين. (2022). التهجين بين شبكة دالة الأساس الشعاعية RBFN ونماذج ARIMA في التنبؤ باستهلاك الكهرباء في الجزائر للفترة 1980–2019. تنمية الموارد البشرية، 17(2)، 495–514. https://www.asjp.cerist.dz/en/article/192969
مدوري، حادة، ومكيديش، محمد. (2017). دراسة مقارنة بين النماذج طويلة الذاكرة ARFIMA والشبكات العصبية الاصطناعية بالتنبؤ بسعر صرف الدينار الجزائري. مجلة الباحث، 17، 17. https://www.asjp.cerist.dz/en/article/34422
Al-Thalabi, S. H. Z., & Omran, K. M. (2016). Tahdid afdal namudhaj lil-tanabbu' bi-istihlak al-taqah al-kahraba'iyyah fi al-mintaqah al-janubiyyah [Determining the best model for forecasting electrical energy consumption in the southern region]. Majallat al-Ulum al-Iqtisadiyyah wa-al-Idariyyah, 22(90), 437–457. https://search.emarefa.net/detail/BIM-699721
Atrous, S. (2018). Istikhdam manhajiyyat Jenkins wa-al-shabakat al-'asabiyyah al-istina'iyyah lil-tanabbu' bi-istihlak al-taqah al-kahraba'iyyah bi-mu'assasat Sonelgaz: Dirasat halat wilayat Biskra [Using the Box-Jenkins methodology and artificial neural networks to forecast electrical energy consumption at Sonelgaz: Case study of Biskra province] [Doctoral dissertation, University of Biskra]. http://thesis.univ-biskra.dz/4485/1/Th%C3%A8se%20Atrous%20Souheila.pdf
Djebbari, L. (2016). Turuq ittikhadh al-qarar bi-istikhdam al-dhaka' al-istina'i: Dirasah muqaranah lil-tanabbu' bi-al-taqah al-kahraba'iyyah li-wilayat Tilimsan bi-isti'mal al-shabakat al-'asabiyyah al-istina'iyyah [Decision-making methods using artificial intelligence: A comparative study of electricity forecasting for Tlemcen province using artificial neural networks] [Doctoral dissertation, Abou Bekr Belkaid University of Tlemcen]. http://dspace.univ-tlemcen.dz/bitstream/112/8806/1/sonelgaz-prevision-decision-charge-electrique-intelligence-artificielle-neurones-box-jenkins.Doc.pdf
Medouri, H., & Mekidiche, M. (2017). Dirasah muqaranah bayna al-namadhij al-tawilah ARFIMA wa-al-shabakat al-'asabiyyah al-istina'iyyah bi-al-tanabbu' bi-si'r sarf al-dinar al-jaza'iri [A comparative study between ARFIMA long-memory models and artificial neural networks in forecasting the Algerian dinar exchange rate]. Majallat al-Bahith, 17, 17. https://www.asjp.cerist.dz/en/article/34422
Sahed, A., & Gahoui, H. (2022). Al-Tahjin bayna shabakat dallat al-asas al-shu'a'iyyah RBFN wa-namadhij ARIMA fi al-tanabbu' bi-istihlak al-kahraba' fi al-Jaza'ir lil-fatrah 1980-2019 [Hybridization between radial basis function networks (RBFN) and ARIMA models in forecasting electricity consumption in Algeria for the period 1980-2019]. Tanmiyat al-Mawarid al-Bashariyyah, 17(2), 495–514. https://www.asjp.cerist.dz/en/article/192969
Copyright (c) 2024 Salaheddine SARI-HASSOUN , Mohamed Abdeldjalil NAMANE , Abdelghani MALIOUI
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
