Evaluation of Graph Neural Networks as Surrogate Model for District Heating Networks Simulation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Evaluation of Graph Neural Networks as Surrogate Model for District Heating Networks Simulation

Résumé

District heating networks have proven their higher conversion efficiency, economic viability and environmental benefits when compared to decentralized and individual heating systems. These benefits are achieved through the ability to incorporate a wide variety of production means, including renewable intermittent sources but also via the use of short-term and/or inter-seasonal storage. Due to the numerous interactions between these components, their different dynamic aspects and operating constraints, physical simulations are computationally heavy so that running optimization tasks become prohibitively expensive and time consuming. Therefore, new control optimization schemes need to be drawn up to accelerate the predictive control and to facilitate the decision-making process. In the present work, we assess the application of geometric deep learning as a surrogate modeling framework for district heating simulations. Beyond processing non-Euclidian data, this deep learning approach aims to encode geometric and topological understandings of data as inductive biases in deep learning models. More precisely we trained Graph Neural Networks to emulate a thermo-hydraulic simulator of district heating network. This statistical inference method allows us to drastically reduce simulation time, hence unlocking further optimization loops and parametric space exploration. In addition, their permutation equivariance and stability to perturbations are assessed to discuss their scalability to more complex network topologies and control schemes.
Fichier principal
Vignette du fichier
069564-0286open.pdf (2.86 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04228699 , version 1 (04-10-2023)

Identifiants

Citer

Taha Boussaid, François Rousset, Vasile-Marian Scuturici, Marc Clausse. Evaluation of Graph Neural Networks as Surrogate Model for District Heating Networks Simulation. 36th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems (ECOS 2023), Jun 2023, Las Palmas De Gran Canaria, Spain. pp.3182-3193, ⟨10.52202/069564-0286⟩. ⟨hal-04228699⟩
98 Consultations
92 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More