Crewman Deployment Model for Improving the Resiliency of the Power System

This paper introduces a method to optimize the number of crewmen deployed at various faulty nodes within a city to boost power system resiliency to pre-calamitous values during the post-restorative period. The approach follows a case study wherein data has been created and analyzed and then predictions have been performed using a multivariate linear regression machine learning model and Artificial Neural Network (ANN). The results of both have then been tabulated and compared. The model proposed in this paper will be highly beneficial for power distribution companies because in case of future disasters power distribution companies just need to give the input parameters for the specific area and they will get the optimal number of crewmen required for the restoration of that area.