A learning-based proactive scheme for improving distribution systems resilience against windstorms

This paper presents a proactive operation scheme for improving distribution system resiliency against natural hazards, specifically windstorms. In this context, important attributes associated with the windstorm consisting the distance from the windstorm route, the wind speed, the distance from tall trees and buildings, and cable type are used in a deep neural network (DNN) engine to identify the vulnerable branches and predict their failure during the windstorm. The DNN predictive model is integrated in the proposed scheme. Afterwards, a power flow-based optimization engine is employed to proactively enhance the grid resiliency. Grid resiliency is measured by the inevitable action of load shedding. For minimum load shedding, the optimization engine reconfigures the network topology, optimizes the droop parameter settings, and allocates mobile energy storage systems (ESSs) before the arrival of the windstorm. This optimization engine is integrated in the proposed scheme. To validate its performance, the proposed proactive scheme is tested on a 33-bus test system with a mix of diesel units (DUs), wind turbines (WTs), and photovoltaic units (PVs). The simulation results demonstrate that without the proposed learning mechanism, the load shedding can reach up to 36% for the system under study, while the learning-based scheme can reduce the load shedding to 13%. The proposed learning-based proactive operation scheme would substantially improve the distribution system resiliency during windstorms.