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

2025-02-12

AI Summary

To address declining load forecasting accuracy caused by high-volatility renewable energy integration, this paper proposes a GAT-LSTM hybrid framework. The method jointly models spatial topology and temporal dynamics by early fusing graph-structured power grid data with time-series measurements. Specifically, it introduces physical edge attributes—such as line capacity and efficiency—into the graph attention mechanism for the first time, enabling physics-informed edge weighting that enhances model interpretability and enforces domain constraints. The graph attention network (GAT) captures topological dependencies among buses and lines, while the LSTM component models temporal dynamics in load patterns. Evaluated on a real-world Brazilian power system dataset, the framework achieves 21.8% lower MAE, 15.9% lower RMSE, and 20.2% lower MAPE compared to state-of-the-art methods, demonstrating the effectiveness of physics-guided spatiotemporal joint modeling for complex power grid load forecasting.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Accurate power load forecasting
• Handling renewable energy variability
• Dynamic spatial-temporal grid modeling

Innovation

• GAT-LSTM hybrid model
• Edge attributes integration
• Early fusion technique