様々な形状を有する電力ネットワークにおける電力融通のための最適制御手法 (通信方式)

Because demands of electricity due to to rapid increasing of population growth, depletion of fossil fuels, and reducing greenhouse gas emissions, the renewable energy have widely been studied. Then, the renewable energy systems are inplemented into many fields such as houses or buildings. Basically, supplying electric power by the renewable energies often becomes unstable. Then, implementation of sophisticated control strategy to maintain the supply systems stably is needed. From this view point, M.E.Gamez et al. proposed an optimal control method using recurrent neural networks for the smart grid systems. In the conventional control method, the optimization problems for the smart grid system are regarded as the linear programming problems, and they solved the problems by the recurrent neural networks. Results indicate that the control method has much possibility to implement into the real-world systems. However, only small sizes of the smart grid systems are evaluated in the previous works. Then, we evaluated the control method by the extended smart grid systems in this report. From the results of computational experiments, we found that the performance of the optimization method depends on the topologies of the power grid.