Evolving Electricity Demand Modelling in Microgrids Using a Kolmogorov-Arnold Network
Stefano Sanfilippo
José Juan Hernández-Gálvez
José Juan Hernández-Cabrera
José Évora-Gómez
Octavio Roncal-Andrés
Mario Caballero-Ramirez
Pub. online: 8 April 2025
Type: Research Article
Open Access
Open Access
Received
1 December 2024
1 December 2024
Accepted
1 March 2025
1 March 2025
Published
8 April 2025
8 April 2025
Abstract
Electricity demand estimation is vital for the optimal design and operation of microgrids, especially in isolated, unelectrified, or partially electrified areas where demand patterns evolve with electricity adoption. This study proposes a causal model for electricity demand estimation that explicitly considers the electrification process along with key factors such as hour, month, weekday/weekend distinction, temperature, and humidity, effectively capturing both temporal and environmental demand patterns.
To capture the electrification process, a “Degree of Adoption” factor has been included, making it a distinctive feature of this approach. Through this variable, the model accounts for the evolving growth in electricity usage, an essential consideration for accurately estimating demand in newly electrifying areas as consumers gain access to electricity and integrate new electrical appliances. Another key contribution of this study is the successful application of the Kolmogorov–Arnold Network (KAN), an architecture explicitly designed to model complex nonlinear relationships more effectively than conventional neural networks that rely on standard activation functions, such as ReLU or sigmoid.
To validate the effectiveness of the proposed electricity demand modelling approaches, comprehensive experiments were conducted using a dataset covering 578 days of electricity consumption from El Espino, Bolivia. This dataset enabled robust comparisons among KAN and conventional neural network architectures, such as Deep Feedforward Neural Network (DFNN) and Multi-Layer Perceptron (MLP), while also assessing the impact of incorporating the Degree of Adoption factor. The empirical results clearly demonstrate that KAN, combined with the Degree of Adoption, achieved superior performance, obtaining an error of 0.042, compared to DFNN (0.049) and MLP (0.09). Additionally, integrating the Degree of Adoption significantly enhanced the model by reducing DFNN estimation error by approximately 10%.
These findings validate the effectiveness of explicitly modelling electricity adoption dynamics and confirm KAN’s relevance for electricity demand estimation, highlighting its potential to support microgrid design and operation.
References
Agrawal, S., Harish, S.P., Mahajan, A., Thomas, D., Urpelainen, J. (2020). Influence of improved supply on household electricity consumption – evidence from rural India. Energy, 211, 118544. https://doi.org/10.1016/j.energy.2020.118544. https://www.sciencedirect.com/science/article/pii/S0360544220316522.
Baba, A. (2021). Advanced AI-based techniques to predict daily energy consumption: a case study. Expert Systems with Applications, 184, 115508. https://doi.org/10.1016/j.eswa.2021.115508. https://www.sciencedirect.com/science/article/pii/S0957417421009180.
Balderrama Subieta, S.L. (2022). Optimal design and deployment of isolated energy systems: the Bolivian pathway to 100% rural electrification. PhD thesis, ULiège – Université de Liège, Liège, Belgium. Académie de Recherche et d’Enseignement Supérieur (Belgique). Coopération au Développement – ARES. CCD.
Barelli, L., Bidini, G., Cherubini, P., Micangeli, A., Pelosi, D., Tacconelli, C. (2019). How hybridization of energy storage technologies can provide additional flexibility and competitiveness to microgrids in the context of developing countries. Energies, 12(16). https://doi.org/10.3390/en12163138. https://www.mdpi.com/1996-1073/12/16/3138.
Bhuyan, M.K., Mohapatra, D.P., Sethi, S. (2016). Software reliability assessment using neural networks of computational intelligence based on software failure data. Baltic Journal of Modern Computing, 4(4), 1016–1037. https://doi.org/10.22364/bjmc.2016.4.4.26.
Chicco, G., Mazza, A. (2020). Impact of the time resolution for data gathering on loss calculation and demand side flexibility. In: 2020 International Conference on Smart Energy Systems and Technologies (SEST), pp. 1–6. https://doi.org/10.1109/SEST48500.2020.9203295.
Christensen, R. (1996). One-Way ANOVA. Springer New York, New York, NY, pp. 79–93. 978-1-4757-2477-6. https://doi.org/10.1007/978-1-4757-2477-6_4.
Chung, J., Jang, B. (2022). Accurate prediction of electricity consumption using a hybrid CNN-LSTM model based on multivariable data. PLOS ONE, 17(11), 1–16. https://doi.org/10.1371/journal.pone.0278071.
Dubey, S.R., Singh, S.K., Chaudhuri, B.B. (2022). Activation functions in deep learning: a comprehensive survey and benchmark. Neurocomputing, 503, 92–108. https://doi.org/10.1016/j.neucom.2022.06.111. https://www.sciencedirect.com/science/article/pii/S0925231222008426.
Evora, J., Hernandez, J.J., Hernandez, M. (2015). A MOPSO method for direct load control in Smart Grid. Expert Systems with Applications, 42(21), 7456–7465. https://doi.org/10.1016/j.eswa.2015.05.056. https://www.sciencedirect.com/science/article/pii/S0957417415003929.
Evora-Gomez, J., Hernandez, J.J., Hernandez, M., Dzemyda, G., Kurasova, O., Kremers, E. (2015). Swarm intelligence for frequency management in Smart Grids. Informatica, 26, 419–434. https://doi.org/10.15388/Informatica.2015.56.
Fan, G.-F., Han, Y.-Y., Li, J.-W., Peng, L.-L., Yeh, Y.-H., Hong, W.-C. (2024). A hybrid model for deep learning short-term power load forecasting based on feature extraction statistics techniques. Expert Systems with Applications, 238, 122012. https://doi.org/10.1016/j.eswa.2023.122012. https://www.sciencedirect.com/science/article/pii/S0957417423025149.
Faraji, J., Hashemi-Dezaki, H., Ketabi, A. (2020). Multi-year load growth-based optimal planning of grid-connected microgrid considering long-term load demand forecasting: a case study of Tehran, Iran. Sustainable Energy Technologies and Assessments, 42, 100827. https://doi.org/10.1016/j.seta.2020.100827. https://www.sciencedirect.com/science/article/pii/S2213138820312546.
Fodstad, M., Crespo del Granado, P., Hellemo, L., Knudsen, B.R., Pisciella, P., Silvast, A., Bordin, C., Schmidt, S., Straus, J. (2022). Next frontiers in energy system modelling: a review on challenges and the state of the art. Renewable and Sustainable Energy Reviews, 160, 112246. https://doi.org/10.1016/j.rser.2022.112246. https://www.sciencedirect.com/science/article/pii/S136403212200168X.
Ghalehkhondabi, I., Ardjmand, E., Weckman, G.R., Young, W.A. (2017). An overview of energy demand forecasting methods published in 2005–2015. Energy Systems, 8(2), 411–447. https://doi.org/10.1007/s12667-016-0203-y.
Ha, S., Jeong, H. (2021). Unraveling hidden interactions in complex systems with deep learning. Scientific Reports, 11(1), 12804. https://doi.org/10.1038/s41598-021-91878-w.
Hirsch, A., Parag, Y., Guerrero, J. (2018). Microgrids: a review of technologies, key drivers, and outstanding issues. Renewable and Sustainable Energy Reviews, 90, 402–411. https://doi.org/10.1016/j.rser.2018.03.040. https://www.sciencedirect.com/science/article/pii/S136403211830128X.
Hu, Y.-C. (2017). Electricity consumption prediction using a neural-network-based grey forecasting approach. Journal of the Operational Research Society, 68(10), 1259–1264. https://doi.org/10.1057/s41274-016-0150-y.
Huang, Z., Zhu, T. (2016). Real-time data and energy management in microgrids. In: 2016 IEEE Real-Time Systems Symposium (RTSS), pp. 79–88. https://doi.org/10.1109/RTSS.2016.017.
Huckebrink, D., Bertsch, V. (2021). Integrating behavioural aspects in energy system modelling—a review. Energies, 14(15). https://doi.org/10.3390/en14154579. https://www.mdpi.com/1996-1073/14/15/4579.
Jaramillo, M., Pavón, W., Jaramillo, L. (2024). Adaptive forecasting in energy consumption: a bibliometric analysis and review. Data, 9(1). https://doi.org/10.3390/data9010013. https://www.mdpi.com/2306-5729/9/1/13.
Kaur, N., Kaur, A. (2016). Predictive modelling approach to data mining for forecasting electricity consumption. In: 2016 6th International Conference – Cloud System and Big Data Engineering (Confluence), pp. 331–336. https://doi.org/10.1109/CONFLUENCE.2016.7508138.
Kaveh, M., Mesgari, M.S. (2023). Application of meta-heuristic algorithms for training neural networks and deep learning architectures: a comprehensive review. Neural Computing and Applications, 35, 12215–12239. https://doi.org/10.1007/s00521-023-08589-4.
Ke, Z., Liu, B., Wang, H., Shu, L. (2021). Continual Learning with Knowledge Transfer for Sentiment Classification. arXiv preprint. https://doi.org/10.48550/arXiv.2112.10021.
Kingma, D.P., Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv preprint. Published as a conference paper at the 3rd International Conference for Learning Representations, San Diego, 2015. https://doi.org/10.48550/arXiv.1412.6980.
Lazzari, F., Mor, G., Cipriano, J., Gabaldon, E., Grillone, B., Chemisana, D., Solsona, F. (2022). User behaviour models to forecast electricity consumption of residential customers based on smart metering data. Energy Reports, 8, 3680–3691. https://doi.org/10.1016/j.egyr.2022.02.260. https://www.sciencedirect.com/science/article/pii/S2352484722005078.
Liu, H., Xiong, X., Yang, B., Cheng, Z., Shao, K., Tolba, A. (2023). A power load forecasting method based on intelligent data analysis. Electronics, 12(16). https://doi.org/10.3390/electronics12163441. https://www.mdpi.com/2079-9292/12/16/3441.
Liu, Z., Wang, Y., Vaidya, S., Ruehle, F., Halverson, J., Soljačić, M., Hou, T.Y., Tegmark, M. (2024). KAN: Kolmogorov-Arnold Networks. arXiv preprint. https://doi.org/10.48550/arXiv.2404.19756.
Ma, Y.-J., Zhai, M.-Y. (2019). Day-ahead prediction of microgrid electricity demand using a hybrid artificial intelligence model. Processes, 7(6). https://doi.org/10.3390/pr7060320. https://www.mdpi.com/2227-9717/7/6/320.
Mir, A.A., Alghassab, M., Ullah, K., Khan, Z.A., Lu, Y., Imran, M. (2020). A review of electricity demand forecasting in low and middle income countries: the demand determinants and horizons. Sustainability, 12(15). https://doi.org/10.3390/su12155931. https://www.mdpi.com/2071-1050/12/15/5931.
Morales, R., Marín, L.G., Roje, T., Caquilpan, V., Sáez, D., Nuñez, A. (2024). Microgrid planning based on computational intelligence methods for rural communities: a case study in the José Painecura Mapuche community, Chile. Expert Systems with Applications, 235, 121179. https://doi.org/10.1016/j.eswa.2023.121179. https://www.sciencedirect.com/science/article/pii/S0957417423016810.
Norouzi, R., Kosari, A., Sabour, M.H. (2019). Investigating the generalization capability and performance of neural networks and neuro-fuzzy systems for nonlinear dynamics modeling of impaired aircraft. IEEE Access, 7, 21067–21093. https://ieeexplore.ieee.org/document/8633913.
Ogunmolu, O., Gu, X., Jiang, S., Gans, N. (2016). Nonlinear Systems Identification Using Deep Dynamic Neural Networks. arXiv preprint. https://doi.org/10.48550/arXiv.1610.01439.
Sanfilippo, S., Hernández Cabrera, J.J., Évora, J., Kébé, C.M.F., Kremers, E., Péchiné, B. (2023). Microgrid design optimization in Benin within the LEOPARD project: evaluating the impact of inaccurate load profile estimation. In: 2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), pp. 1–6. https://doi.org/10.1109/ICECCME57830.2023.10252234.
Shankar, V.K., Gopikanna, A., Shankar, S., Rajan, G., Vijayaraghavan, V. (2018). Intelligent system design optimization with dynamic load profile for a stand-alone rural Indian microgrid. In: 2018 IEEE Texas Power and Energy Conference (TPEC), pp. 1–6. https://doi.org/10.1109/TPEC.2018.8312050.
Shufian, A., Mohammad, N. (2022). Modeling and analysis of cost-effective energy management for integrated microgrids. Cleaner Engineering and Technology, 8, 100508. https://doi.org/10.1016/j.clet.2022.100508. https://www.sciencedirect.com/science/article/pii/S2666790822001136.
Stevanato, N., Lombardi, F., Guidicini, G., Rinaldi, L., Balderrama, S.L., Pavičević, M., Quoilin, S., Colombo, E. (2020). Long-term sizing of rural microgrids: accounting for load evolution through multi-step investment plan and stochastic optimization. Energy for Sustainable Development, 58, 16–29. https://doi.org/10.1016/j.esd.2020.07.002. https://www.sciencedirect.com/science/article/pii/S0973082620302635.
Tajbakhsh, N., Shin, J.Y., Gurudu, S.R., Hurst, R.T., Kendall, C.B., Gotway, M.B., Liang, J. (2017). Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? arXiv preprint. https://doi.org/10.48550/arXiv.1706.00712.
Venkataramanan, G., Marnay, C. (2008). A larger role for microgrids. IEEE Power and Energy Magazine, 6(3), 78–82. https://doi.org/10.1109/MPE.2008.918720.
Verwiebe, P.A., Seim, S., Burges, S., Schulz, L., Müller-Kirchenbauer, J. (2021). Modeling energy demand—a systematic literature review. Energies, 14(23). https://doi.org/10.3390/en14237859.
Verwimp, E., Aljundi, R., Ben-David, S., Bethge, M., Cossu, A., Gepperth, A., Hayes, T.L., Hüllermeier, E., Kanan, C., Kudithipudi, D., Lampert, C.H., Mundt, M., Pascanu, R., Popescu, A., Tolias, A.S., van de Weijer, J., Liu, B., Lomonaco, V., Tuytelaars, T., van de Ven, G.M. (2024). Continual Learning: Applications and the Road Forward. arXiv preprint. https://doi.org/10.48550/arXiv.2311.11908.
Wassie, Y.T., Ahlgren, E.O. (2023). Determinants of electricity consumption from decentralized solar PV mini-grids in rural East Africa: an econometric analysis. Energy, 274, 127351. https://doi.org/10.1016/j.energy.2023.127351. https://www.sciencedirect.com/science/article/pii/S0360544223007454.
Yan, P., Zhou, Y. (2024). Application of recommendation algorithm based on matrix dimensionality reduction model in network information analysis model. Informatica, 48(9), 177–190. https://doi.org/10.31449/inf.v48i9.5969.
Yukseltan, E., Yucekaya, A., Bilge, A.H. (2020). Hourly electricity demand forecasting using Fourier analysis with feedback. Energy Strategy Reviews, 31, 100524. https://doi.org/10.1016/j.esr.2020.100524. https://www.sciencedirect.com/science/article/pii/S2211467X20300778.
Zippenfenig, P. (2023). Open-Meteo.com Weather API. https://doi.org/10.5281/zenodo.7970649. https://open-meteo.com/.
