FreeGNN: Continual Source-Free Graph Neural Network Adaptation for Renewable Energy Forecasting

• URL: http://arxiv.org/abs/2603.01657v1
• Date: Mon, 02 Mar 2026 09:43:11 GMT
• Title: FreeGNN: Continual Source-Free Graph Neural Network Adaptation for Renewable Energy Forecasting
• Authors: Abderaouf Bahi, Amel Ourici, Ibtissem Gasmi, Aida Derrablia, Warda Deghmane, Mohamed Amine Ferrag,
• Abstract summary: FreeGNN is a Continual Source-Free Graph Domain Adaptation framework.<n>It enables adaptive forecasting on unseen renewable energy sites without requiring source data or target labels.<n>It achieves an MAE of 5.237 and an RMSE of 7.123 on the GEFCom dataset, an MAE of 1.107 and an RMSE of 1.512 on the Solar PV dataset, and an MAE of 0.382 and an RMSE of 0.523 on the Wind dataset.
• Score: 0.5233775397457061
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate forecasting of renewable energy generation is essential for efficient grid management and sustainable power planning. However, traditional supervised models often require access to labeled data from the target site, which may be unavailable due to privacy, cost, or logistical constraints. In this work, we propose FreeGNN, a Continual Source-Free Graph Domain Adaptation framework that enables adaptive forecasting on unseen renewable energy sites without requiring source data or target labels. Our approach integrates a spatio-temporal Graph Neural Network (GNN) backbone with a teacher--student strategy, a memory replay mechanism to mitigate catastrophic forgetting, graph-based regularization to preserve spatial correlations, and a drift-aware weighting scheme to dynamically adjust adaptation strength during streaming updates. This combination allows the model to continuously adapt to non-stationary environmental conditions while maintaining robustness and stability. We conduct extensive experiments on three real-world datasets: GEFCom2012, Solar PV, and Wind SCADA, encompassing multiple sites, temporal resolutions, and meteorological features. The ablation study confirms that each component memory, graph regularization, drift-aware adaptation, and teacher--student strategy contributes significantly to overall performance. The experiments show that FreeGNN achieves an MAE of 5.237 and an RMSE of 7.123 on the GEFCom dataset, an MAE of 1.107 and an RMSE of 1.512 on the Solar PV dataset, and an MAE of 0.382 and an RMSE of 0.523 on the Wind SCADA dataset. These results demonstrate its ability to achieve accurate and robust forecasts in a source-free, continual learning setting, highlighting its potential for real-world deployment in adaptive renewable energy systems. For reproducibility, implementation details are available at: https://github.com/AraoufBh/FreeGNN.

Related papers

• Digital Twin-Driven Pavement Health Monitoring and Maintenance Optimization Using Graph Neural Networks [5.876489372173655]
  We propose a unified Digital Twin (DT) and Graph Neural Network (GNN) framework for scalable, data-driven pavement health monitoring and predictive maintenance.<n>Our model achieves an R2 of 0.3798, outperforming baseline regressors and effectively capturing non-linear degradation.<n>This DT-GNN integration enhances forecasting precision and establishes a closed feedback loop for continuous improvement.
  arXiv  Detail & Related papers  (2025-11-04T19:59:17Z)
• Spatio-Temporal Graph Convolutional Networks for EV Charging Demand Forecasting Using Real-World Multi-Modal Data Integration [1.83159883923531]
  Transportation remains a major contributor to greenhouse gas emissions.<n>This study introduces TW-GCN, a-temporal forecasting framework that combines Graph Conal Networks with temporal architectures.<n>We utilize real-world traffic flows, weather conditions, and proprietary data to capture both spatial dependencies and temporal dynamics.
  arXiv  Detail & Related papers  (2025-10-10T06:31:17Z)
• Power Grid Control with Graph-Based Distributed Reinforcement Learning [60.49805771047161]
  This work advances a graph-based distributed reinforcement learning framework for real-time, scalable grid management.<n>A Graph Neural Network (GNN) is employed to encode the network's topological information within the single low-level agent's observation.<n>Experiments on the Grid2Op simulation environment show the effectiveness of the approach.
  arXiv  Detail & Related papers  (2025-09-02T22:17:25Z)
• PowerGrow: Feasible Co-Growth of Structures and Dynamics for Power Grid Synthesis [75.14189839277928]
  We present PowerGrow, a co-generative framework that significantly reduces computational overhead while maintaining operational validity.<n> Experiments across benchmark settings show that PowerGrow outperforms prior diffusion models in fidelity and diversity.<n>This demonstrates its ability to generate operationally valid and realistic power grid scenarios.
  arXiv  Detail & Related papers  (2025-08-29T01:47:27Z)
• PowerGNN: A Topology-Aware Graph Neural Network for Electricity Grids [0.0]
  This paper proposes a topology aware Graph Neural Network (GNN) framework for predicting power system states under high renewable integration.<n>We construct a graph based representation of the power network, modeling and integrating transmission lines as nodes and edges, and introduce a specialized GNN architecture that integrates GraphSAGE convolutions with Gated Recurrent Units (GRUs)<n>Our results show that the proposed GNN outperforms baseline approaches including fully connected neural networks, linear regression, and rolling mean models, achieving substantial improvements in predictive accuracy.
  arXiv  Detail & Related papers  (2025-03-26T01:22:31Z)
• Sustainable Greenhouse Microclimate Modeling: A Comparative Analysis of Recurrent and Graph Neural Networks [0.0]
  This study introduces a novel application of Spatio-Temporal Graph Neural Networks (STGNNs) to greenhouse microclimate modeling.<n>We compare their performance with traditional Recurrent Neural Networks (RNNs)<n>Our STGNN approach addresses this limitation by representing these relationships as directed graphs, enabling the model to capture both environmental dependencies and their directionality.
  arXiv  Detail & Related papers  (2025-02-24T17:52:01Z)
• Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction [84.26340606752763]
  In this paper, we introduce the conservation-informed GNN (CiGNN), an end-to-end explainable learning framework.<n>The network is designed to conform to the general symmetry conservation law via symmetry where conservative and non-conservative information passes over a multiscale space by a latent temporal marching strategy.<n>Results demonstrate that CiGNN exhibits remarkable baseline accuracy and generalizability, and is readily applicable to learning for prediction of varioustemporal dynamics.
  arXiv  Detail & Related papers  (2024-12-30T13:55:59Z)
• Climate Aware Deep Neural Networks (CADNN) for Wind Power Simulation [0.7783262415147654]
  Wind power forecasting plays a critical role in modern energy systems, facilitating the integration of renewable energy sources into the power grid.<n>This paper proposes the use of Deep Neural Network (DNN)-based predictive models that leverage climate variables to improve the accuracy of wind power simulations.
  arXiv  Detail & Related papers  (2024-12-11T14:22:52Z)
• SafePowerGraph: Safety-aware Evaluation of Graph Neural Networks for Transmission Power Grids [55.35059657148395]
  We present SafePowerGraph, the first simulator-agnostic, safety-oriented framework and benchmark for Graph Neural Networks (GNNs) in power systems (PS) operations. SafePowerGraph integrates multiple PF and OPF simulators and assesses GNN performance under diverse scenarios, including energy price variations and power line outages.
  arXiv  Detail & Related papers  (2024-07-17T09:01:38Z)
• Predicting Dynamic Stability of Power Grids using Graph Neural Networks [0.1539132101969243]
  We investigate the feasibility of applying graph neural networks (GNN) to predict dynamic stability of synchronisation in complex power grids. We generate two synthetic datasets for grids with 20 and 100 nodes respectively and estimate single-node basin stability (SNBS) using Monte-Carlo sampling. We show that SNBS can be predicted in general and the performance significantly changes using different GNN-models.
  arXiv  Detail & Related papers  (2021-08-18T16:43:06Z)
• Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective [52.497514255040514]
  This work develops a new approach that enables data-driven methods to continuously learn and optimize resource allocation strategies in a dynamic environment. We propose to build the notion of continual learning into wireless system design, so that the learning model can incrementally adapt to the new episodes. Our design is based on a novel bilevel optimization formulation which ensures certain fairness" across different data samples.
  arXiv  Detail & Related papers  (2021-05-03T07:23:39Z)
• Federated Learning in the Sky: Aerial-Ground Air Quality Sensing Framework with UAV Swarms [53.38353133198842]
  Air quality significantly affects human health, it is increasingly important to accurately and timely predict the Air Quality Index (AQI) This paper proposes a new federated learning-based aerial-ground air quality sensing framework for fine-grained 3D air quality monitoring and forecasting. For ground sensing systems, we propose a Graph Convolutional neural network-based Long Short-Term Memory (GC-LSTM) model to achieve accurate, real-time and future AQI inference.
  arXiv  Detail & Related papers  (2020-07-23T13:32:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.