Deep learning-based post-disaster energy management and faster network reconfiguration method for improvement of restoration time

Abstract

Natural disasters in the world often cause power outages. To improve post-disaster response and restoration time, a method for energy management and network reconfiguration in emergencies has been proposed, where energy storages systems (ESSs) in distribution networks are used to support the system balance immediately and then the network reconfiguration is accelerated based on deep learning techniques. First, when power failures occur, the outputs of ESSs are calculated optimally in terms of the proposed optimization model under the constraints of minimizing line losses. After the injections of ESSs in emergencies, the network reconfiguration is still needed due to the limitation of ESS capacities. To avoid calculations of power flow repeatedly, a deep-learning based reconfiguration method for distribution networks has been proposed, where the deep-learning model is trained offline and can output the parameters of power flow immediately when a state combination of distribution generators (DGs), loads and power lines, which is an effective way to accelerate the network reconfiguration. If many reconfiguration schemes are found, a decision-making method with preferences are used to select one according to different situations. Finally, cases are designed, and simulation results show that the calculation time of a reconfiguration schemes are reduced significantly by almost one hundred multiples.