Energy Consumption Forecasting with Artificial Intelligence Models

Authors : İlker Karadağ, Kaan Sağtaş

Pages : 1780-1793

Doi:10.34248/bsengineering.1758772

View : 172 | Download : 357

Publication Date : 2025-11-15

Article Type : Research Paper

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

ORIGINAL ARTICLE URL