Enhanced Load Forecasting with GAT-LSTM: Leveraging Grid and Temporal Features

Ugochukwu Orji, Çiçek Güven, Dan Stowell
2/12/2025
cs.LGeess.SP

No official code found. Best implementation: ugoorji12/Load-Forecasting-using-GAT-LSTM (32 stars, GPL-3.0, last commit 2025-09-22).

Abstract

Accurate power load forecasting is essential for the efficient operation and planning of electrical grids, particularly given the increased variability and complexity introduced by renewable energy sources. This paper introduces GAT-LSTM, a hybrid model that combines Graph Attention Networks (GAT) and Long Short-Term Memory (LSTM) networks. A key innovation of the model is the incorporation of edge attributes, such as line capacities and efficiencies, into the attention mechanism, enabling it to dynamically capture spatial relationships grounded in grid-specific physical and operational constraints. Additionally, by employing an early fusion of spatial graph embeddings and temporal sequence features, the model effectively learns and predicts complex interactions between spatial dependencies and temporal patterns, providing a realistic representation of the dynamics of power grids. Experimental evaluations on the Brazilian Electricity System dataset demonstrate that the GAT-LSTM model significantly outperforms state-of-the-art models, achieving reductions of 21. 8% in MAE, 15. 9% in RMSE and 20. 2% in MAPE. These results underscore the robustness and adaptability of the GAT-LSTM model, establishing it as a powerful tool for applications in grid management and energy planning.

View on arXivView PDF

Code Implementations(1)

ugoorji12/Load-Forecasting-using-GAT-LSTMCommunity100%
GPL-3.0

This repository implements the GAT-LSTM model, which combines Graph Attention Networks (GAT) and Long Short-Term Memory Networks (LSTM) for hourly power load forecasts. It leverages spatio-temporal dependencies in energy systems, using graph-structured data (e.g., grid topology) and temporal sequences (e.g., historical consumption and weather).

324PythonDec 16, 20241 years agoGPL-3.0

Similar Papers

Load Forecasting in the Era of Smart Grids: Opportunities and Advanced Machine Learning Models

86% match2025

Explainability-Driven Feature Engineering for Mid-Term Electricity Load Forecasting in ERCOT's SCENT Region

86% match2025

Short-Term Load Forecasting Using A Particle-Swarm Optimized Multi-Head Attention-Augmented CNN-LSTM Network

85% match2023

In Search of Deep Learning Architectures for Load Forecasting: A Comparative Analysis and the Impact of the Covid-19 Pandemic on Model Performance

85% match2023

Graph Neural Networks for Electricity Load Forecasting

85% match1 repo32025

From ARIMA to Attention: Power Load Forecasting Using Temporal Deep Learning

85% match2026

Cite this paper

@article{orji2025enhanced,
  title  = {Enhanced Load Forecasting with GAT-LSTM: Leveraging Grid and Temporal Features},
  author = {Ugochukwu Orji and Çiçek Güven and Dan Stowell},
  year   = {2025},
  eprint = {2502.08376},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.08376v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.08376.svg)](https://codeofpaper.com/paper/2502.08376)

Discussion