Adéquation Algorithme Architecture pour la gestion des réseaux électriques

The growth of distributed energy resources raises the challenge of scaling up network management algorithms. This difficulty may be overcome in operating conditions with the help of a rich literature that frequently calls upon the distribution of computations. However, this issue persists during preliminary simulations validating the performances, the operation's safety, and the infrastructure's sizing. A hardware-software co-design approach is conducted here for a Peer-to-Peer market to address this scaling issue while computing simulations on a single machine. With the increasing number of distributed agents, the impact on the grid cannot be neglected anymore. Thus, this work will focus on an endogenous market. The mapping between several algorithms and different partitioning models on Central and Graphic Processing Units (CPU-GPU) has been conducted. The complexity and performance of these algorithms have been analyzed on CPU and GPU. The implementations have shown that the GPU is more numerically unstable than the CPU. Nevertheless, when precision is not critical, GPU gives substantial speedup. Thus, markets without grid constraints are 98% faster on GPU. Even with the grid constraints, the GPU is 1000 times faster with the DC hypothesis and ten times faster on the AC radial grid. This dimension-dependent acceleration increases with the grid size and the agent's count.