Long-Term Electricity Load Forecasting Using Artificial Neural Network: The Case Study of Benin

Abstract:

Africans in general and specially Beninese’s low rate access to electricity requires efforts to set up new electricity production units. To satistfy the needs, it is therefore very important to have a prior knowledge of the electrical load. In this context, knowing the right need for the electrical energy to be extracted from the Beninese network in the long term and in order to better plan its stability and reliability, a forecast of this electrical load is then necessary. The study has used the annual power grid peak demand data from 2001 to 2020 to develop, train and validate the models. The electrical load peaks until 2030 are estimated as the output value. This article evaluates three algorithms of a method used in artificial neural networks (ANN) to predict electricity consumption, which is the Multilayer Perceptron (MLP) with backpropagation. To ensure stable and accurate predictions, an evaluation approach using mean square error (MSE) and correlation coefficient (R) has been used. The results have proved that the data predicted by the Bayesian regulation variant of the Multilayer Perceptron (MLP), is very close to the real data during the training and the learning of these algorithms. The validated model has developed high generalization capabilities with insignificant prediction deviations.

• Periodical: Advanced Engineering Forum (Volume 48)
• Pages: 117-136
• DOI: https://doi.org/10.4028/p-zq4id8
• Online since: January 2023
• Authors: Habib Conrad Sotiman Yotto*, Patrice Chetangny, Victor Zogbochi, Jacques Aredjodoun, Sossou Houndedako, Gerald Barbier, Vianou Antoine, Didier Chamagne
• Keywords: Artificial Neural Network, Bayesian Regularization, Forecasting Peak Electricity, Multi-Layer Perceptron

References

[1] M. Hambali and S. Yakub, Artificial Neural Network Approach For Electric Load Forecasting In Power Distribution Company,, Nov. (2017).

[2] Clustering Time Related Data: A Regression Tree Approach., http://pubs.sciepub.com/ajams/10/1/4/index.html (accessed Aug. 21, 2022).

[3] Electrical Load Forecasting Using Fuzzy System." https://www.scirp.org/ (S(lz5mqp453edsnp55rrgjct55))/journal/paperinformation.aspx,paperid=94904 (accessed Aug. 21, 2022).

[4] A. Das and A. Sengupta, Forecasting Electrical Energy Consumption using Artificial Neural Networks,, Int. J. Eng. Res., vol. 8, no. 11, p.8.

[5] M. S. AL-Musaylh, R. C. Deo, J. F. Adamowski, and Y. Li, Short-term electricity demand forecasting using machine learning methods enriched with ground-based climate and ECMWF Reanalysis atmospheric predictors in southeast Queensland, Australia,, Renew. Sustain. Energy Rev., vol. 113, p.109293, Oct. 2019,.

DOI: 10.1016/j.rser.2019.109293

[6] E. Vivas, H. Allende-Cid, and R. Salas, A Systematic Review of Statistical and Machine Learning Methods for Electrical Power Forecasting with Reported MAPE Score,, Entropy, vol. 22, no. 12, p.1412, Dec. 2020,.

DOI: 10.3390/e22121412

[7] la division d'analyse des systèmes d'énergie de KTH en collaboration avec SNV, VOIES D'ELECTRIFICATION POUR LE BENIN: Une analyse spatiale d'électrification basée sur l'Outil d'électrification spatiale Open Source (OnSSET),, la Direction Générale des Ressources Energétiques du Bénin, BENIN, Dec. (2018).

DOI: 10.1051/larsg:2005029

[8] K. Gajowniczek, R. Nafkha, and T. Ząbkowski, Electricity peak demand classification with artificial neural networks,, Sep. 2017, p.307–315.

DOI: 10.15439/2017f168

[9] M. M. Dalvand, S. B. Z. Azami, and H. Tarimoradi, Long-term load forecasting of Iranian power grid using fuzzy and artificial neural networks,, in 2008 43rd International Universities Power Engineering Conference, Padova, Sep. 2008, p.1–4.

DOI: 10.1109/upec.2008.4651538

[10] Mr. EL MAKRINI Aboubakr, Amélioration De L'intégration De L'énergie Éolienne Au Réseau Électrique De Transport Marocain," Centre d'Etudes Doctorales : Sciences et Techniques de l'Ingénieur/MAROC, N° d,ordre : 13/2018, (2018).

[11] M. E. Günay, Forecasting annual gross electricity demand by artificial neural networks using predicted values of socio-economic indicators and climatic conditions: Case of Turkey,, Energy Policy, vol. 90, p.92–101, Mar. 2016,.

DOI: 10.1016/j.enpol.2015.12.019

[12] K. Panklib, C. Prakasvudhisarn, and D. Khummongkol, Electricity Consumption Forecasting in Thailand Using an Artificial Neural Network and Multiple Linear Regression,, Energy Sources Part B Econ. Plan. Policy, vol. 10, no. 4, p.427–434, Oct. 2015,.

DOI: 10.1080/15567249.2011.559520

[13] V. Gil-Vera, Pronóstico De La Demanda Mensual De Electricidad Con Series De Tiempo,, Rev. EIA, vol. 13, no. 26, p.111–120, Mar. 2017,.

DOI: 10.24050/reia.v13i26.749

[14] G. A. Adepoju, S. O. A. Ogunjuyigbe, K. O. Alawode, and B. Tech, Application of Neural Network to Load Forecasting in Nigerian Electrical Power System,, . Number, vol. 8, no. 1, p.6, (2007).

[15] A. Al-Shareef, E. Mohamed, and E. Al-Judaibi, Next 24-Hours Load Forecasting Using Artificial Neural Network (ANN) for the Western Area of Saudi Arabia,, J. King Abdulaziz Univ.-Eng. Sci., vol. 19, no. 2, p.25–40, 2008,.

DOI: 10.4197/eng.19-2.2

[16] F. Kaytez, A hybrid approach based on autoregressive integrated moving average and least-square support vector machine for long-term forecasting of net electricity consumption,, Energy, vol. 197, p.117200, Apr. 2020,.

DOI: 10.1016/j.energy.2020.117200

[17] A. J. del Real, F. Dorado, and J. Durán, Energy Demand Forecasting Using Deep Learning: Applications for the French Grid,, Energies, vol. 13, no. 9, Art. no. 9, Jan. 2020,.

DOI: 10.3390/en13092242

[18] R. Porteiro, L. Hernández-Callejo, and S. Nesmachnow, Electricity demand forecasting in industrial and residential facilities using ensemble machine learning,, Rev. Fac. Ing. Univ. Antioquia, (2020).

DOI: 10.17533/udea.redin.20200584

[19] J. Hao, X. Sun, and Q. Feng, A Novel Ensemble Approach for the Forecasting of Energy Demand Based on the Artificial Bee Colony Algorithm,, Energies, vol. 13, no. 3, Art. no. 3, Jan. 2020,.

DOI: 10.3390/en13030550

[20] B. Birecikli, Ö. A. Karaman, S. B. Çelebi, and A. Turgut, Failure load prediction of adhesively bonded GFRP composite joints using artificial neural networks,, J. Mech. Sci. Technol., vol. 34, no. 11, p.4631–4640, Nov. 2020,.

DOI: 10.1007/s12206-020-1021-7

[21] R. Houimli, M. Zmami, and O. Ben-Salha, Short-term electric load forecasting in Tunisia using artificial neural networks,, Energy Syst., vol. 11, no. 2, p.357–375, May 2020,.

DOI: 10.1007/s12667-019-00324-4

[22] M.-R. Kazemzadeh, A. Amjadian, and T. Amraee, A hybrid data mining driven algorithm for long term electric peak load and energy demand forecasting,, Energy, vol. 204, p.117948, Aug. 2020,.

DOI: 10.1016/j.energy.2020.117948

[23] M. C. Pegalajar, L. G. B. Ruiz, M. P. Cuéllar, and R. Rueda, Analysis and enhanced prediction of the Spanish Electricity Network through Big Data and Machine Learning techniques,, Int. J. Approx. Reason., vol. 133, p.48–59, Jun. 2021,.

DOI: 10.1016/j.ijar.2021.03.002

[24] P. Ramsami and R. King, Neural Network Frameworks for Electricity Forecasting in Mauritius and Rodrigues Islands,, Aug. 2021, p.1–5.

DOI: 10.1109/powerafrica52236.2021.9543176

[25] U. Şahin, S. Ballı, and Y. Chen, Forecasting seasonal electricity generation in European countries under Covid-19-induced lockdown using fractional grey prediction models and machine learning methods,, Appl. Energy, vol. 302, p.117540, Nov. 2021,.

DOI: 10.1016/j.apenergy.2021.117540

[26] M. Saglam, C. Spataru, and O. A. Karaman, Electricity Demand Forecasting with Use of Artificial Intelligence: The Case of Gokceada Island,, Energies, vol. 15, no. 16, Art. no. 16, Jan. 2022,.

DOI: 10.3390/en15165950

[27] E. Cebekhulu, A. J. Onumanyi, and S. J. Isaac, Performance Analysis of Machine Learning Algorithms for Energy Demand–Supply Prediction in Smart Grids,, Sustainability, vol. 14, no. 5, Art. no. 5, Jan. 2022,.

DOI: 10.3390/su14052546

[28] M. Saglam, C. Spataru, and O. A. Karaman, Electricity Demand Forecasting with Use of Artificial Intelligence: The Case of Gokceada Island,, Energies, vol. 15, no. 16, Art. no. 16, Jan. 2022,.

DOI: 10.3390/en15165950

[29] C. Touzet, Les Reseaux De Neurones Artificiels, Introduction Au Connexionnisme,, p.130.

[30] P. Lu, L. Ye, Y. Zhao, B. Dai, M. Pei, and Y. Tang, Review of meta-heuristic algorithms for wind power prediction: Methodologies, applications and challenges,, Appl. Energy, vol. 301, p.117446, Nov. 2021,.

DOI: 10.1016/j.apenergy.2021.117446

[31] eLtronics villa, Activation Function,, Medium, Jun. 03, 2019. https://medium.com/@eltronicsvilla17/activation-function-df184bbbbc63 (accessed Aug. 22, 2022).

[32] N. Ayoub, F. Musharavati, S. Pokharel, and H. A. Gabbar, ANN Model for Energy Demand and Supply Forecasting in a Hybrid Energy Supply System,, in 2018 IEEE International Conference on Smart Energy Grid Engineering (SEGE), Oshawa, ON, Aug. 2018, p.25–30.

DOI: 10.1109/sege.2018.8499514

[33] A. Laouafi, M. Mordjaoui, F. Laouafi, and T. E. Boukelia, Daily peak electricity demand forecasting based on an adaptive hybrid two-stage methodology,, Int. J. Electr. Power Energy Syst., vol. 77, p.136–144, May 2016,.

DOI: 10.1016/j.ijepes.2015.11.046

[34] A. Das and A. Sengupta, Forecasting Electrical Energy Consumption using Artificial Neural Networks,, Int. J. Eng. Res., vol. 8, no. 11, p.8.

[35] C. Dangbedji, P. Ngae, and A. Vianou, Modélisation de la consommation mensuelle de l'energie electrique au Benin,, J. Rech. Sci. Univ. Lome, vol. 13, 2011,.

DOI: 10.4314/jrsul.v13i1.68056

[36] C. Adjamagbo, P. Ngae, and A. Vianou, Modélisation de la demande en énergie électrique au Togo,, p.17.

[37] Olivier SIDLER, CONNAISSANCE ET MAîTRISE DES USAGES SPECIFIQUES DE L'ELECTRICITE DANS LE SECTEUR RESIDENTIEL,, ENERTECH, Note technique n°090401, Apr. (2009).

[38] Inovation energie dévéloppement, Etude pour la mise en place d'un environnement propice à l'électrification hors-réseau,, MAC-BENIN, (2017).

[39] wether_effet_energy.2021022.pdf.,.

[40] Our World in Data,, Our World in Data. https://ourworldindata.org (accessed Apr. 08, 2022).

[41] JEMT_Volume 2_Issue 3_Pages 42-59.pdf.,.

[42] A. Karimu and J. T. Mensah, Climate change and electricity consumption in Sub-Saharan Africa: assessing the dynamic responses to climate variability: Responses to climate variability,, OPEC Energy Rev., vol. 39, no. 3, p.322–345, Sep. 2015,.

DOI: 10.1111/opec.12054

[43] (PDF) ARTIFICIAL NEURAL NETWORK APPROACH FOR ELECTRIC LOAD FORECASTING IN POWER DISTRIBUTION COMPANY." https://www.researchgate.net/publication/328430346_ARTIFICIAL_NEURAL_NETWORK_APPROACH_FOR_ELECTRIC_LOAD_FORECASTING_IN_POWER_DISTRIBUTION_COMPANY,enrichId=rgreq-08570b22b0c980861fea576bafd50b3b-XXX&enrichSource=Y292ZXJQYWdlOzMyODQzMDM0NjtBUzo2ODQ1NTkxNDIyMjc5NzBAMTU0MDIyMzAyNjMxOA%3D%3D&el=1_x_3&_esc=publicationCoverPdf (accessed Aug. 21, 2022).

DOI: 10.1080/07313569708955782

[44] W. Zhang, L. Zhang, J. Wang, and X. Niu, Hybrid system based on a multi-objective optimization and kernel approximation for multi-scale wind speed forecasting,, Appl. Energy, vol. 277, p.115561, Nov. 2020,.

DOI: 10.1016/j.apenergy.2020.115561

[45] Mean Squared Error (MSE),, Statistics By Jim, Nov. 12, 2021. https://statisticsbyjim.com/ regression/mean-squared-error-mse/ (accessed Apr. 10, 2022).

DOI: 10.7551/mitpress/4931.003.0009

[46] L. Alkaiem, F. Keller, and H. Sternberg, Analysis of inclination measurement by means of artificial neural networks – A comparison of static and dynamic networks,, p.10.