Interpretable AI Hybrid Model for Electricity Demand Forecasting: Combining TFT and XGBoost in Smart Grid Data

Sobhan Manjili¹, Saeid Jafarzadeh Ghoushchi¹, Mohammad Reza Maghami^2,*, Mazlan Mohamed^3,*
1 Faculty of Industrial Engineering, Urmia University of Technology, Urmia, Iran
2 Strategic Research Institute (SRI), Asia Pacific University of Technology & Innovation (APU), Technology Park Malaysia, Bukit Jalil, Kuala Lumpur, Malaysia
3 Faculty of Artificial Intelligence and Cyber Security (FAIX), University Technical Malaysia Melaka, Melaka, Malaysia
* Corresponding Author: Mohammad Reza Maghami. Email: email ; Mazlan Mohamed. Email: email

Computer Modeling in Engineering & Sciences https://doi.org/10.32604/cmes.2026.076217

Received 16 November 2025; Accepted 30 January 2026; Published online 08 April 2026

Download PDF

Abstract

Accurate electricity load forecasting is crucial for optimizing power distribution networks, especially in rapidly growing cities like Tabriz (annual consumption growth of 7.2%). This study presents a hybrid AI framework integrating the Temporal Fusion Transformer (TFT) and XGBoost for residual error correction. The model is trained and evaluated using actual consumption data from Tabriz’s distribution network (2021–2023). Compared to a baseline TFT model, the proposed framework demonstrates a 11.2% reduction in RMSE (from 0.1249 to 0.1109) and a 10.7% decrease in MAE (from 0.0998 to 0.0891). Attention mechanism analysis reveals temperature (importance coefficient = 0.32), weekly patterns (0.18), and industrial activity (0.21) as key factors influencing electricity consumption in Tabriz. Achieving a MAPE of 4.2%, the framework provides actionable insights into consumption drivers. This research demonstrates the effectiveness of the proposed model in managing load fluctuations characteristic of medium-sized cities and offers potential for adaptation to similar urban contexts. The dual capability for accurate prediction and interpretable feature analysis establishes a new benchmark for smart grid analytics in emerging smart city environments.

Keywords

Electricity load forecasting; hybrid AI models; Temporal Fusion Transformer (TFT); XGBoost; interpretable machine learning; smart grid analytics; urban energy management; attention mechanisms

Downloads
- Full-Text PDF
Citation Tools
- BibTex
- EndNote
- RIS

71

View
10

Download
0

Like

Differentiate Xp11.2 Translocation Renal Cell Carcinoma from Computed Tomography Images and Clinical Data with ResNet-18 CNN and XGBoost
Yanwen Lu, Wenliang Ma, Xiang...
Novel Hybrid XGBoost Model to Forecast Soil Shear Strength Based on Some Soil Index Tests
Ehsan Momeni, Biao He, Yasin Abdi,...
A New Method for Diagnosis of Leukemia Utilizing a Hybrid DL-ML Approach for Binary and Multi-Class Classification on a Limited-Sized Database
Nilkanth Mukund Deshpande, Shilpa...
Early Detection of Colletotrichum Kahawae Disease in Coffee Cherry Based on Computer Vision Techniques
Raveena Selvanarayanan, Surendran...
Performance Prediction Based Workload Scheduling in Co-Located Cluster
Dongyang Ou, Yongjian Ren, Congfeng...

Interpretable AI Hybrid Model for Electricity Demand Forecasting: Combining TFT and XGBoost in Smart Grid Data

Abstract

Keywords

71

10

0

Further Information

Guidelines

Follow Us

Join Us

Contact Us

WhatsApp:

Share Link