In this paper, based on OpenFlow technology for software-defined networks, a QoS-ensure flow control strategy consisting of modules such as fault monitoring and QoS routing control is proposed. After that, a real-time route planning framework based on software-defined network (SDN) is designed, and then a QoS route planning method based on adaptive genetic ant colony is proposed by combining the characteristics of genetic algorithm and ant colony algorithm. Aiming at the problem of poor adaptability and anti-interference of genetic algorithm, an optimized genetic algorithm for fault node localization in power distribution network is proposed. Simulation results show that the adaptive genetic algorithm proposed in this paper can obtain better search performance than the max-min ant system and the basic ant colony algorithm, and it can search for routing solutions with lower cost than the traditional algorithms, but its convergence performance is a little worse than the max-min ant system. The improved genetic algorithm (IBPSO) in this paper can quickly and accurately locate faulty segments under multiple fault scenarios, such as single fault, multipoint fault, and end-of-feeder fault in the network, and it has strong fault-tolerance performance when the fault information is distorted.
