# Leveraging Graph Neural Networks to Forecast Electricity Consumption

arXiv: https://arxiv.org/abs/2408.17366 · HTML: https://mlsanity.com/paper/2408.17366/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 30 Aug 2024.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Neural Additive Models: Interpretable Machine Learning with Neural Nets](https://mlsanity.com/paper/2004.13912/) (2020)
- [Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models](https://mlsanity.com/paper/1612.08468/) (2016)
- [A Second-order Bound with Excess Losses](https://mlsanity.com/paper/1402.2044/) (2014)
- [Fast calibrated additive quantile regression](https://mlsanity.com/paper/1707.03307/) (2017)
- [Building Energy Load Forecasting using Deep Neural Networks](https://mlsanity.com/paper/1610.09460/) (2016)
- [Smoothing parameter and model selection for general smooth models](https://mlsanity.com/paper/1511.03864/) (2015)
- [Adaptive Methods for Short-Term Electricity Load Forecasting During COVID-19 Lockdown in France](https://mlsanity.com/paper/2009.06527/) (2020)
- [Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean](https://mlsanity.com/paper/2301.11862/) (2023)
- [Online Hierarchical Forecasting for Power Consumption Data](https://mlsanity.com/paper/2003.00585/) (2020)
- [Adaptive Probabilistic Forecasting of Electricity (Net-)Load](https://mlsanity.com/paper/2301.10090/) (2023)
- [BUAA_BIGSCity: Spatial-Temporal Graph Neural Network for Wind Power Forecasting in Baidu KDD CUP 2022](https://mlsanity.com/paper/2302.11159/) (2023)
- [State-Space Models Win the IEEE DataPort Competition on Post-covid Day-ahead Electricity Load Forecasting](https://mlsanity.com/paper/2110.00334/) (2021)

## Built on by (most cited first, 2 of 2)

- [Enhancing Nuclear Reactor Core Simulation through Data-Based Surrogate Models](https://mlsanity.com/paper/2511.16148/) (2025)
- [GraphToolbox: A Configurable Python Framework for Graph Neural Network Forecasting](https://mlsanity.com/paper/2609.24609/) (2026)

## Abstract (arXiv)

Accurate electricity demand forecasting is essential for several reasons, especially as the integration of renewable energy sources and the transition to a decentralized network paradigm introduce greater complexity and uncertainty. The proposed methodology leverages graph-based representations to effectively capture the spatial distribution and relational intricacies inherent in this decentralized network structure. This research work offers a novel approach that extends beyond the conventional Generalized Additive Model framework by considering models like Graph Convolutional Networks or Graph SAGE. These graph-based models enable the incorporation of various levels of interconnectedness and information sharing among nodes, where each node corresponds to the combined load (i.e. consumption) of a subset of consumers (e.g. the regions of a country). More specifically, we introduce a range of methods for inferring graphs tailored to consumption forecasting, along with a framework for evaluating the developed models in terms of both performance and explainability. We conduct experiments on electricity forecasting, in both a synthetic and a real framework considering the French mainland regions, and the performance and merits of our approach are discussed.