Acceleration of a decentralized radial AC-OPF on GPU

Distribution networks are currently hosting a major share of the energy transition and require the development of new management mechanisms. Their tuning requires numerous simulations to get closer to the optimal performance set by optimal power flow results. In radial networks, this problem admits specific resolutions. However, these algorithms are still hampered by prohibitive computing times for large-scale problems, which is typically the case for a distribution network. Specific implementations are, therefore, crucial to make the most of heterogeneous CPU GPU computing architectures. This contribution focuses on two distributed OPF algorithms in radial networks. The speed-up by a factor of 3 is observed, particularly on the largest systems. Nevertheless, in several study cases, GPU methods failed to converge due to the lack of numerical stability of the algorithms.