Optimisation des prévisions énergétiques à Boma: étude des algorithmes PSO et Leap-Nemo (2023-2053)

Contenu principal de l'article

André Mampuya Nzita
Bernard Ndaye Nkanka
Guyh Dituba Ngoma
Clément N’zau Umba-di-Mbudi

Résumé

L'optimisation de la demande énergétique est essentielle au développement durable des pays en développement, où les déséquilibres entre production et consommation sont fréquents. Dans le contexte de la commune de Boma, en République démocratique du Congo, cette étude examine les défis liés à la prévision de la consommation énergétique face aux coupures de courant récurrentes. L'objectif principal est de développer un modèle de prévision de la demande énergétique utilisant les algorithmes PSO et LEAP-Nemo afin d'optimiser la production énergétique de 2023 à 2053. La méthodologie comprend la collecte de données qualitatives et quantitatives sur les infrastructures de la Société nationale d'électricité (SNEL) et les consommateurs, ainsi qu'une analyse statistique des résultats par corrélation et tests t. Les résultats montrent que le modèle PSO tend à surestimer la demande énergétique, avec une erreur moyenne significative, tandis que le scénario BALU offre des prévisions plus réalistes et cohérentes. En conclusion, cette étude souligne l'importance d'ajuster les modèles de prévision pour en améliorer la précision et recommande l'intégration de nouvelles variables afin de mieux saisir la dynamique de la demande énergétique à Boma.

Details de l'article

Rubrique

Articles

Références

Abdel-Basset M, Mohamed R, Mirjalili S, Chakrabortty RK, & Ryan M. (2021). An Efficient Algorithm for Solving Multi-Objective Optimization Problems: Analysis and Validations. IEEE Access, 2021(9), 42817–42844. https://doi.org/10.1109/ACCESS.2021.3066323.

Al Hasibi, R.A, Bawan, E.K. (2023). An analysis of the impact of the Covid-19 pandemic on the implementation of renewable energy in electricity supply. International Journal of Sustainable Energy Planning and Management, 39, 3-21. https://doi.org/10.54337/ijsepm.7659

Akpahou R, Mensah LD, Quansah DA, & Kemausuor F. (2024) Long-term energy demand modeling and optimal evaluation of solutions to renewable energy deployment barriers in Benin: A LEAP-MCDM approach. Energy Reports, 12, 1888-1904. https://doi.org/10.1016/j.egyr.2024.07.055.

Ambarayana, I. W., Giriantari, I. A., & Setiawan, I. N. (2022). Projection of electric power needs in Rembang Regency using LEAP software. J-Proteksion, 6(2), 56-61. https://doi.org/10.32528/jp.v6i2.6823

Ayyash, N, Hejazi F. (2022). Development of a hybrid optimization algorithm for structures equipped with seismic damping devices using particle swarm optimization method and gravity search algorithm, Terreq. Eng. Vib., 21 (02): pp. 455-474. https://doi.org/10.1007/s11803-022-2088-1.

Deng W, Xu J, Zhao H. (2019). An improved ant colony optimization algorithm based on hybrid strategies for the scheduling problem. IEEE Access,7: pp. 20281-20292. https://doi.org/10.1109/ACCESS.2019.2897580.

Eseye AT, Lehtonen M, Tukia T, Uimonen S, Millar RJ. (2019). Machine learning based integrated feature selection approach for improved electricity demand forecasting in distributed energy systems, IEEE Acces, 7: pp. 91463-91475. https://doi.org/10.1109/ACCESS.2019.2924685

Gao W. (2025). Application of improved particle swarm optimization algorithm combined with genetic algorithm in shear wall design. Systems and Soft Computing; 7: 200198. https://doi.org/10.1016/j.sasc.2025.200198.

Gad AG. (2022). Particle swarm optimization algorithm and its applications: a systematic review. Archives of Computational Methods in Engineering, 29 (5): 2531-2561. https://doi.org/10.1007/s11831-021-09694-4

He L., Li F., Guo C., Gao B, Liu J, Shi Q. (2022) An adaptive PI controller using particle swarm optimization for electric steering angle tracking. IEEE/ASME Trans. Mechatron, 27 (5): pp. 3830-3840. https://doi.org/10.1109/TMECH.2021.3137848.

Khan R, Alam M.M, Paso T, and Haapola J.Throughput and Channel Aware MAC Scheduling for SmartBAN Standard. IEEE Access, pp. 63133–63145, 2019. https://doi.org/10.1109/ACCESS.2019.2916159.

Khalil R, El-Kordy A, Sobh H. (2022). A review of the use of swarm intelligence in architectural engineering. Int. J. Archit. Comput,20 (2): pp. 254–276. https://doi.org/10.1177/14780771211039.

Koledzi, K. E., Baba, G., Feuillade, G., Guy, M. (2011). Physical characterization of urban solid waste in Lomé, Togo, with a view to decentralized composting in neighborhoods. Environment, Engineering and Development. https://doi.org/10.4267/dechets-sciences-techniques.2851

Li X, Li XL, Wang K, Li Y. A. (2019) .Multi-Objective Particle Swarm Optimization Algorithm Based on Improved Selection. IEEE Access, 7: pp. 168091–168103. https://doi.org/10.1109/ACCESS.2019.2954542.

Mustofa, A., Setiawan, H. (2023). Electricity Energy Demand in Banjarnegara District for the Year 2021-2030 Using Linear Regression Method and LEAP Software. Journal of Global Informatics, 14(3), 51-61. https://doi.org/10.36982/jiig.v14i3.3436

Nurwahyudin, D.S., Trihastuti, N., & Utama, N.A. (2022). Energy planning in West Java using software LEAP (Long-range Energy Alternatives Planning). E3S Web of Conferences, 359, 01001. https://doi.org/10.1051/e3sconf/202235901001

Raza, M.A., Khatri, K.L., Hussain, A. (2022). Sector-wise optimal energy demand forecasting for a developing country using LEAP software. Engineering Procedures, 20(1):6. https://doi.org/10.3390/engproc2022020006

Rivera-González, L., Bolonio, D., Luis, F.M., Valencia-Chapi, R. (2019). Long-term electricity supply and demand forecast (2018–2040): A LEAP model application towards a sustainable power generation system in Ecuador. Sustainability, 11, 5316. https://doi.org/10.3390/su11195316

Wanga, B.M., Wafula, M.D., Mafuana, L.C., and Z. Victorine Mbandu, Z.V. (2015). Kalamu River in the town of Boma in the DRC: a disappearing tourist site. International Journal of Innovation and Applied Studies, Vol. 11 No. 1 Apr. 2015, pp. 118-128

Yulianto, E. D., Kholistianingsih, Wahjudi, D. (2022). Analysis of projection of electrical energy needs in 2021-2031 in Banyumas Regency using LEAP software. Teodolita: Scientific Communication Media in the Engineering Field, 23 (1), 102-114. https://doi.org/10.53810/jt.v23i1.443

Zhao J, Zhu X, Chanson T. (2022). Optimal trajectory planning based on hybrid IWOA-PSO algorithm. IEEE Access, 10 (1): pp. 6592-6604. https://doi.org/10.1109/ACCESS.2022.3141448