This paper presents a non-intrusive method for identifying the load state of a distribution network. The method focuses on continuously varying loads. By considering the load onoff state switching points and the continuous features at on state, a deep convolutional method considering non-local spatiotemporal features is proposed. The addition of an attention component to the convolutional network enhances the non-local feature extraction capability of the convolutional network. Ultimately, the effectiveness of the method is demonstrated in an experimental setting. In addition, this paper demonstrates that the proposed method can effectively integrate switching point features as well as persistent features through neural network visualization techniques.
As one of the core technologies of distributed feeder automation (DFA), line current differential protection (LCDP) can locate faults quickly and accurately and have the ability to cope with multi-directional flow. However, LCDP algorithm has high requirements for communication speed, and is sensitive to communication quality. In order to apply the LCDP algorithm to a real project, the communication system and its impacts on LCDP need to be studied in depth. In this paper, the design method of a communication system for LCDP, including communication mode, topology, communication protocol, and synchronization, is analyzed in detail. For better parameter determination, the communication models are investigated, and the impact of time delay, data loss, and jitter on LCDP are discussed. Further, the distribution network based on a real project is built in a cyber-physical co-simulation environment, and the impact of electrical fails and communication fails on LCDP are studied. The results show that the design method and parameters determination method proposed in this paper are effective.
A modified structure internal model robust control method for the integration of active front steering and direct yaw moment control SCIENCE CHINA Technological Sciences 58, 75 (2015); Theoretical analysis of the harmonic characteristics of modular multilevel converters
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.