Blar i forfatter "Hansen, Jonas Berg"

Viser treff 1-4 av 4

    • Power Flow Balancing With Decentralized Graph Neural Networks 

      Hansen, Jonas Berg; Anfinsen, Stian Normann; Bianchi, Filippo Maria (Journal article; Tidsskriftartikkel; Peer reviewed, 2022-08-01)
      We propose an end-to-end framework based on a Graph Neural Network (GNN) to balance the power flows in energy grids. The balancing is framed as a supervised vertex regression task, where the GNN is trained to predict the current and power injections at each grid branch that yield a power flow balance. By representing the power grid as a line graph with branches as vertices, we can train a GNN that ...

    • Power Flow Optimization with Graph Neural Networks 

      Hansen, Jonas Berg (Mastergradsoppgave; Master thesis, 2021-06-01)
      Power flow analysis is an important tool in power engineering for planning and operating power systems. The standard power flow problem consists of a set of non-linear equations, which are traditionally solved using numerical optimization techniques, such as the Newton-Raphson method. However, these methods can become computationally expensive for larger systems, and convergence to the global optimum ...

    • The pure PV-EV energy system – A conceptual study of a nationwide energy system based solely on photovoltaics and electric vehicles 

      Boström, Tobias; Babar, Bilal; Hansen, Jonas Berg; Good, Clara (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-03-08)
      The objective of this conceptual study is to reveal the substantial potential and synergy of solar energy and electric vehicles (EVs) working together. This potential is demonstrated by studying the feasibility of a nationwide energy system solely reliant on solar energy and EVs. Photovoltaic (PV) solar energy is already an important energy source globally, but due to its intermittency it requires ...

    • Total Variation Graph Neural Networks 

      Hansen, Jonas Berg; Bianchi, Filippo Maria (Journal article; Tidsskriftartikkel, 2023-07)
      Recently proposed Graph Neural Networks (GNNs) for vertex clustering are trained with an unsupervised minimum cut objective, approximated by a Spectral Clustering (SC) relaxation. However, the SC relaxation is loose and, while it offers a closed-form solution, it also yields overly smooth cluster assignments that poorly separate the vertices. In this paper, we propose a GNN model that computes cluster ...