The fault characteristics of an inverter interfaced distributed generator (IIDG) depend on its control strategy and are closely related to whether it has a low voltage ride-through (LVRT) capability, which cannot be a simple equivalent to a constant power or current source. Thus, it is necessary to consider the specific control strategy of IIDGs and perform specific research on the fault detection method of a microgrid. Based on the fault models of a grid-connected PQ controlled DG (PQ-DG) with an LVRT capacity, this paper analyzed the fault component characteristics of a microgrid under different operating conditions, such as high-impedance faults (HIFs) and low-impedance faults (LIFs). The fault point is located using a new fault detection method, which is based on the phase differences between the positive-sequence fault component of the bus voltage and the positive-sequence fault components of the currents in the feeders. Finally, PSCAD/EMTDC is used in the simulation analysis, and the simulation results verified the validity of the fault detection method.

Cognitive Radio (CR) is a promising technology to overcome spectrum scarcity, which currently faces lots of unsolved problems. One of the critical challenges for setting up such systems is how to coordinate multiple protocol layers such as routing and spectrum access in a partially observable environment. In this paper, a deep reinforcement learning approach is adopted for solving above problem. Firstly, for the purpose of compressing huge action space in the cross-layer design problem, a novel concept named responsibility rating is introduced to help decide the transmission power of every Secondary User (SU). In order to deal with problem of dimension curse while reducing replay memory, the Prioritized Memories Deep Q-Network (PM-DQN) is proposed. Furthermore, PM-DQN is applied to solve the joint routing and resource allocation problem in cognitive radio ad hoc network for minimizing the transmission delay and power consumption. Simulation results illustrates that our proposed algorithm can reduce the end-to-end delay, packet loss ratio and estimation error while achieving higher energy efficiency compared with traditional algorithm.

Deep reinforcement learning (DRL) has been successfully used for the joint routing and resource management in large-scale cognitive radio networks. However, it needs lots of interactions with the environment through trial and error, which results in large energy consumption and transmission delay. In this paper, an apprenticeship learning scheme is proposed for the energy-efficient cross-layer routing design. Firstly, to guarantee energy efficiency and compress huge action space, a novel concept called dynamic adjustment rating is introduced, which regulates transmit power efficiently with multi-level transition mechanism. On top of this, the Prioritized Memories Deep Q-learning from Demonstrations (PM-DQfD) is presented to speed up the convergence and reduce the memory occupation. Then the PM-DQfD is applied to the cross-layer routing design for power efficiency improvement and routing latency reduction. Simulation results confirm that the proposed method achieves higher energy efficiency, shorter routing latency and larger packet delivery ratio compared to traditional algorithms such as Cognitive Radio Q-routing (CRQ-routing), Prioritized Memories Deep Q-Network (PM-DQN), and Conjecture Based Multi-agent Q-learning Scheme (CBMQ).

In this paper, based on the practice of implementing bilingual teaching in Digital Signal Processing Course of Anhui Xinhua University, the project team systematically studied, analyzed and summarized the necessity and feasibility of bilingual teaching, the formulation of teaching program and the implementation of teaching organization, and the assessment and evaluation of courses. Through the concrete actual effect testing, the result is pretty well, which has the extensibility.