Spatiotemporal Graph Neural Networks in short term load forecasting: Does adding Graph Structure in Consumption Data Improve Predictions?

TL;DR

This paper addresses the potential of spatiotemporal graph neural networks to improve short-term load forecasting by capturing inter-household dependencies. It provides a literature overview of STGNN architectures (TTS and T&S) and graph-formation strategies (predefined vs learnable), and benchmarks a set of representative models on residential and aggregate forecasting tasks. The findings show that incorporating graph structure yields meaningful improvements at the household level but yields limited or negative gains at the aggregate level, where simple baselines can dominate. The work highlights practical implications for deploying STGNNs in STLF and points to future directions, including exploring exogenous variables and diverse forecasting horizons.

Abstract

Short term Load Forecasting (STLF) plays an important role in traditional and modern power systems. Most STLF models predominantly exploit temporal dependencies from historical data to predict future consumption. Nowadays, with the widespread deployment of smart meters, their data can contain spatiotemporal dependencies. In particular, their consumption data is not only correlated to historical values but also to the values of neighboring smart meters. This new characteristic motivates researchers to explore and experiment with new models that can effectively integrate spatiotemporal interrelations to increase forecasting performance. Spatiotemporal Graph Neural Networks (STGNNs) can leverage such interrelations by modeling relationships between smart meters as a graph and using these relationships as additional features to predict future energy consumption. While extensively studied in other spatiotemporal forecasting domains such as traffic, environments, or renewable energy generation, their application to load forecasting remains relatively unexplored, particularly in scenarios where the graph structure is not inherently available. This paper overviews the current literature focusing on STGNNs with application in STLF. Additionally, from a technical perspective, it also benchmarks selected STGNN models for STLF at the residential and aggregate levels. The results indicate that incorporating graph features can improve forecasting accuracy at the residential level; however, this effect is not reflected at the aggregate level

Figures (4)

• Figure 1: tts architecture.
• Figure 2: tas architecture.
• Figure 3: Train-validation-test split settings.
• Figure 4: Distribution of differences between forecasts and ground truth.