Cooperative UAV Scheduling for Power Grid Deicing Using Fuzzy Learning and Evolutionary Optimization

Abstract

Icing is one of the most serious threats to power grid security in cold seasons. This article studies a problem of cooperatively scheduling inspection unmanned aerial vehicles (UAVs) and deicing UAVs for power grid deicing, the aim of which is to minimize the total expected loss of outages and collapses caused by the icing disaster. Uncertain outage risk, collapse risk, and deicing workload of each power line are modeled as fuzzy values predicted by fuzzy deep learning models, and we transform the fuzzy optimization problem into a crisp optimization problem based on fuzzy arithmetics and uncertain theory. We propose an evolutionary algorithm, which combines global search without individual interaction and adaptive local search that uses a fuzzy inference system to determine the operator to be applied on each solution. The algorithm is fully parallelizable and therefore can solve the problem very efficiently based on GPU parallel acceleration. Computational results on real-world problem instances validate the performance of the proposed method compared to the state of the arts.