Hybrid Deep Learning and Transformer-Based Framework for Multivariate Electricity Consumption Forecasting

Accurate forecasting of multivariate time series is essential for energy management, grid optimisation, and policy planning. This study presents a hybrid deep learning and Transformer-based forecasting framework for predicting hourly electricity consumption across Turkey using nationwide data from Energy Exchange Istanbul (EPİAŞ) between 2018 and 2025. The dataset comprises 15 variables representing diverse energy sources and market indicators, including consumption, generation, and the market-clearing price (MCP). The proposed hybrid model integrates Long Short-Term Memory (LSTM), Bidirectional LSTM (BLSTM), and Gated Recurrent Unit (GRU) layers to capture both short- and long-term temporal dependencies, while a Transformer model leveraging multi-head self-attention mechanisms is used for comparison. All models were trained using standardised preprocessing, a 24 h lookback window, and optimised hyperparameters via GridSearchCV. Experimental results reveal that the hybrid model achieved the best overall performance, with MAE = 464.01, RMSE = 663.39, and R2 = 0.9902, significantly outperforming the baseline and Transformer models. The Transformer demonstrated robust long-horizon learning capability (R2 = 0.9257) but at a higher computational cost. These results confirm that combining multiple recurrent architectures enhances predictive accuracy and stability for large-scale, real-time energy forecasting. The proposed framework offers a reliable foundation for smart grid operations, demand prediction, and data-driven energy policy development.