Power network fault identification based on deep reinforcement learning
Mengshi Li, Huanming Zhang, Tianyao Ji, Qingyao Wu
Abstract
With the integration of alternative energy and renewables, the issue of stability and resilience of the power network has received considerable attention. The basic step of fault diagnosis and isolation is fault identification and location. The conventional intelligent fault identification method is supervised, where the characteristics are labelled manually and its hunger to large amount of labelled data. In order to enhance the ability of the intelligent method and get rid of the dependence on a large amount of labelled data, this paper investigates a novel fault identification method based on deep reinforcement learning (DRL), which has not received enough attention in the field of fault identification. The proposed method considers different faults as a kind of parameters of the model so as to expand the scope of fault identification. In addition, the DRL algorithm is able to intelligently modify the fault parameters according to the observations obtained from the environment of power network rather than tuning the parameters manually and mechanically. The methodology is tested on the IEEE 14 bus for several scenarios and the performance of the proposed method is compared with that of population-based optimization methods and supervised learning methods. The obtained results have confirmed the feasibility and effectiveness of proposed method.