Energy Consumption Forecasting with Artificial Intelligence Models

Abstract

Artificial intelligence (AI) currently enjoys significant preference and popularity among researchers, representing a highly sought-after research domain. It is envisaged that in the foreseeable future, numerous tasks traditionally executed by humans will be executed with greater efficiency, reliability and cost-effectiveness through the utilization of advanced AI techniques and applications. AI finds extensive application across various domains, including classification, prediction, generation and control. One notable application within the realm of production planning and control is demand forecasting. In this paper, the estimation of electricity energy demand is conducted by leveraging AI models, which involved the evaluation of weather data alongside various parameters. For this real-life application, a dataset sourced from Spain, obtained from an open data-sharing platform, is utilized as the primary input. Throughout the study, AI models such as Artificial Neural Networks (ANN), LightGBM and transformers are deployed to generate predictions. The findings generally indicated that all models demonstrated efficacy in predicting both increasing and decreasing values. Nonetheless, the LightGBM AI model emerged as the most competent demand forecasting model, boasting a Mean Absolute Percentage Error (MAPE) value of 8.76%.

Keywords

• Energy consumption estimation
• Artificial intelligence
• AI model
• LightGBM

References

1. Anghel A, Papandreou N, Parnell T, De Palma A, Pozidis H. 2018. Benchmarking and optimization of gradient boosting decision tree algorithms In: Workshop on Systems for ML and Open Source Software at NeurIPS, December 03-08, Montréal, Canada, pp: 1809.
2. Anonymous. 2025a. About our forecasts. URL: https://www.ecmwf.int/en/forecasts/documentation-and-support (accessed date: 25 August, 2025).
3. Anonymous. 2025b. Entso-e transparency platform. URL: https://transparency.entsoe.eu/dashboard/show (accessed date: 25 August 2025).
4. Anonymous. 2025c. Markets and prices. URL: https://www.esios.ree.es/en/market-and-prices?date=24-08-2025 (accessed date: 25 August 2025).
5. Anonymous. 2025d. Hourly energy demand generation and weather. URL: https://www.kaggle.com/datasets/nicholasjhana/energy-consumption-generation-prices-and-weather (accessed date: 25 August 2025).
6. Anonymous. 2025e. Weather API. URL: https://openweathermap.org/api (accessed date: 25 August 2025).
7. Başakın EE, Ekmekçioğlu Ö, Özger M. 2019. Makine öğrenmesi yöntemleri ile kuraklık analizi. Pamukkale Univ Muh Bilim Derg, 25(8): 985-991.
8. Botchkarev A. 2018. Performance metrics (error measures) in machine learning regression, forecasting and prognostics: properties and typology. Interdiscip J Inf Know Manag, 14: 45-76.

9. Campagne E, Amara-Ouali Y, Goude Y, Kalogeratos A. 2024. Leveraging graph neural networks to forecast electricity consumption. In: Machine Learning for Sustainable Power Systems (ML4SPS) Workshop, Vilnius, Lithuania, September 09, pp: 188.
10. Chappells H, Shove E, 2005. Debating the future of comfort: environmental sustainability, energy consumption and the indoor environment. Build Res Inf, 33(1): 32-40.
11. Chen X, Liang C, Huang D, Real E, Wang K, Liu Y, Pham H, Dong X, Luong T, Hsieh C-J, Lu Y, Le QV. 2023. Symbolic discovery of optimization algorithms. In: Thirty-Seventh Conference on Neural Information Processing Systems, December 10, NY, USA, pp: 49205-49233.
12. Dehalwar V, Kalam A, Kolhe ML, Zayegh A. 2017. Electricity load forecasting for urban area using weather forecast information. In: 2016 IEEE International Conference on Power and Renewable Energy, October 21-23, Shanghai, China, pp: 355-359.
13. Ghahramani M, Qiao Y, Zhou MC, Hagan AO, Sweeney J. 2020. AI-based modeling and data-driven evaluation for smart manufacturing processes. IEEE/CAA J Autom Sinica, 7(4): 1026-1037.
14. Göde A, Doğan A, Özköse H. 2023. Enerji sektörünün dijital dönüşümünde yapay zekâ. Yönetim bilişim sistemleri: işletmelerde dijital dönüşüm yönetimi. Özgür Yayınları, Gaziantep, Türkiye, pp: 163-183.
15. Graves A, 2012. Supervised sequence labelling with recurrent neural networks. Springer, Berlin, Germany, 385: 37-45.
16. Günay ME. 2016. Forecasting annual gross electricity demand by artificial neural networks using predicted values of socio-economic indicators and climatic conditions: case of Turkey. Energy Policy, 90: 92-101.
17. Hasanuzzaman M, Rahim NA, 2020. Energy for sustainable development: Demand, supply, conversion and management. Elsevier, Kuala Lumpur, 1st ed, pp: 105-123.
18. Hernandez L, Baladron C, Aguiar JM, Carro B, Sanchez-Esguevillas AJ, Lloret J, Massana J. 2014. A survey on electric power demand forecasting: Future trends in smart grids, microgrids and smart buildings. IEEE Commun Surveys Tuts, 16(3): 1460-1495.
19. Herranz E. 2017. Unit root tests. WIREs Comp Stats, 9(3): e1396.
20. Hippert HS, Pedreira CE, Souza RC. 2001. Neural networks for short-term load forecasting: A review and evaluation. IEEE Trans Power Systems, 16(1): 44-55.
21. Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu T-Y. 2017. Lightgbm: a highly efficient gradient boosting decision tree. In: 31st Conference on Neural Information Processing Systems (NIPS 2017), December 04, Long Beach, USA, pp: 3149-3157.
22. Kerkkänen A, Korpela J, Huiskonen J. 2009. Demand forecasting errors in industrial context: measurement and impacts. Int J Prod Econ, 118(1): 43-48.
23. Kialashaki A, Reisel JR. 2014. Development and validation of artificial neural network models of the energy demand in the industrial sector of the United States. Energy, 76: 749-760.
24. Kwiatkowski D, Phillips PCB, Schmidt P, Shin Y. 1992. Testing the null hypothesis of stationarity against the alternative of a unit root: How sure are we that economic time series have a unit root?. J Econometrics, 54(1-3): 159-178.
25. Lee KY, Cha YT, Park JH. 1992. Short-term load forecasting using an artificial neural network. IEEE Trans Power Systems, 7(1): 124-132.
26. Lewis CD. 1997. Demand forecasting and inventory control: A computer aided learning approach. Taylor and Francis, Cornwall, 1st ed., pp: 176.
27. Liu Y, Wang Y, Xu P, Xue Y, Chen Y, Zhang D. 2025. Buildstg: a multi-building energy load forecasting method using spatio-temporal graph neural network. Energy Build, 347: 116190.
28. Mackinnon JG, 1994. Approximate asymptotic distribution functions for unit-root and cointegration tests. J Bus Econ Stat, 12(2): 167-176.
29. Navada A, Ansari AN, Patil S, Sonkamble BA. 2011. Overview of use of decision tree algorithms in machine learning. In: 2011 IEEE Control and System Graduate Research Colloquium, June 27-28, Shah Alam, Malaysia, pp: 37-42.
30. Nordhaus WD. 1979. Efficient use of energy resources. Nat Res J, 20(3): 161.
31. O’Shea K, Nash R. 2015. An introduction to convolutional neural networks. Int J Res Appl Sci Eng Technol, 10(12): 943-947.
32. Özkış, A. 2020. Türkiye’nin enerji talebinin tahmin edilmesi üzerine girdap arama algoritması temelli yeni bir model. Pamukkale Univ Muh Bilim Derg, 26(5), 959-965.
33. Park DC, El-Sharkawi MA, Marks RJ, Atlas LE, Damborg MJ. 1991. Electric load forecasting using an artificial neural network. IEEE Trans Power Systems, 6(2): 442-449.
34. Popescu M-C, Balas VE, Perescu-Popescu L, Mastorakis N. 2009. Multilayer perceptron and neural networks. WSEAS Trans Cir and Sys, 8(7): 579-588.
35. Rasamoelina AD, Adjailia F, Sincak P. 2020. A review of activation function for artificial neural network. In: 2020 IEEE 18th World Symposium on Applied Machine Intelligence and Informatics, January 23-25, Herlany Slovakia, pp: 281-286.
36. Raza MQ, Khosravi A. 2015. A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings. Renew Sustain Energy Rev, 50: 1352-1372.
37. Rolnick D, Donti PL, Kaack LH. 2023. Tackling climate change with machine learning. ACM Comput Surv, 55(2): 1-96.
38. Selahattin Y, Deveci M. 2012. Istatiksel normalizasyon tekniklerinin yapay sinir ağın performansına etkisi. ERU IIBFD, 40: 167-187.
39. Small SG, Medsker L. 2014. Review of information extraction technologies and applications. Neural Comput Appl, 25(3-4): 533-548.
40. Taylor JW, Buizza R. 2002. Neural network load forecasting with weather ensemble predictions. IEEE Trans Power Systems, 17(3): 626-632.
41. Toyoda J, Chen MS, Inoue Y. 1970. An application of state estimation to short-term load forecasting, part i: forecasting modeling. IEEE Trans Power App Syst, 89(7): 1678-1682.
42. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I. 2017. Attention is all you need. In: 31st Conference on Neural Information Processing Systems, December 04, Long Beach, USA, pp: 6000-6010.
43. Wang C, Li X, Shi Y, Jiang W, Song Q, Li X. 2024. Load forecasting method based on CNN and extended LSTM. Energy Rep, 12: 2452-2461.
44. Wang Z, Zhu Z, Xiao G, Bai B, Zhang Y. 2022. A transformer-based multi-entity load forecasting method for integrated energy systems. Front Energy Res, 10: 952420.
45. Yıldız C, Şekkeli M. 2016. Türkiye gün öncesi elektrik piyasasında rüzgar enerjisi ve pompaj depolamalı hidroelektrik santral için optimum teklif oluşturulması. Pamukkale Univ Muh Bilim Derg, 22(5): 361-366.
46. Ying X. 2019. An Overview of overfitting and its Solutions. J Phys: Conf Ser, 1168(2): 022022.
47. Zeng YR, Zeng Y, Choi B, Wang L. 2017. Multifactor-influenced energy consumption forecasting using enhanced back-propagation neural network. Energy, 127: 381-396.
48. Zor K, Timur O, Teke A. 2017. A state-of-the-art review of artificial intelligence techniques for short-term electric load forecasting. In: 2017 6th International Youth Conference on Energy, June 21-24, Budapest, Hungary, pp: 1-7.
49. Zou J, Han Y, So SS. 2008. Overview of artificial neural networks. Methods Mol Biol, 458: 14-22.