Short-term load forecasting is viewed as one promising technology for demand prediction under the most critical inputs for the promising arrangement of power plant units. Thus, it is imperative to present new incentive methods to motivate such power system operations for electricity management. This paper proposes an approach for short-term electric load forecasting using long short-term memory networks and an improved sine cosine algorithm called MetaREC. First, using long short-term memory networks for a special kind of recurrent neural network, the dispatching commands have the characteristics of storing and transmitting both long-term and short-term memories. Next, four important parameters are determined using the sine cosine algorithm base on a logistic chaos operator and multilevel modulation factor to overcome the inaccuracy of long short-term memory networks prediction, in terms of the manual selection of parameter values. Moreover, the performance of the MetaREC method outperforms others with regard to convergence accuracy and convergence speed on a variety of test functions. Finally, our analysis is extended to the scenario of the MetaREC_long short-term memory with back propagation neural network, long short-term memory networks with default parameters, long short-term memory networks with the conventional sine-cosine algorithm, and long short-term memory networks with whale optimization for power load forecasting on a real electric load dataset. Simulation results demonstrate that the multiple forecasts with MetaREC_long short-term memory can effectively incentivize the high accuracy and stability for short-term power load forecasting.

Examination is a way to select talents, and a perfect invigilation strategy can improve the fairness of the examination. To realize the automatic detection of abnormal behavior in the examination room, the method based on the improved YOLOv3 (The third version of the You Only Look Once algorithm) algorithm is proposed. The YOLOv3 algorithm is improved by using the K-Means algorithm, GIoUloss, focal loss, and Darknet32. In addition, the frame-alternate dual-thread method is used to optimize the detection process. The research results show that the improved YOLOv3 algorithm can improve both the detection accuracy and detection speed. The frame-alternate dual-thread method can greatly increase the detection speed. The mean Average Precision (mAP) of the improved YOLOv3 algorithm on the test set reached 88.53%, and the detection speed reached 42 Frames Per Second (FPS) in the frame-alternate dual-thread detection method. The research results provide a certain reference for automated invigilation.

This article presents a comparison of inductive and resistive superconducting fault current limiter built with the same length of high temperature superconducting (HTS) tape. The resistive limiter is constructed as a noninductive bifilar winding. The inductive coreless limiter consists of primary winding and secondary shorted winding. Both limiters are connected parallel to the additional Cu primary winding, which helps to reduce the power dissipated in the HTS windings during and after a fault. It also ensures that in cases of an HTS tape failure, the protected circuit will not be disrupted. The limiters are very fast and the first peak is almost equally limited by both types of limiters.

In this work, we report on the design and tests results of a coreless inductive SFCL with a 600 A rated current for MV distribution system. The fault current limiter comprises of 4 identical units immersed in liquid nitrogen bath. Each unit consists of 3 windings. The primary and secondary windings made of 2G HTS tape SF12050 are magnetically coupled with the primary Cu winding. The high magnetic coupling between superconducting primary and secondary windings gives a low voltage drop on the limiter at nominal current. The presented solution reduces the size and the weight of the device. Tests performed at high power test facility prove the limiting capability of the coreless inductive SFCL.

The superconducting fault current limiters (SFCLs) are highly effective solutions to reduce fault current in electric power system. The process of quenching may occur in all superconducting devices, but in fault current limiters this process must be fully controlled. Uncontrolled transition of the superconducting tape from the superconducting state to the resistive state may cause overheating and burning of the high temperature superconductor (HTS) tape and, consequently, lead to the destruction of the entire superconducting device. In this study, we described a simulation model to analyze the electrical and thermal behavior of the SFCL. By using this simulation model, we evaluated the transition of temperature of the REBCO coated conductor during the fault current limitation. We determined and described maximal parameters for the HTS tapes that can be applied to the superconductor without thermal degradation during fault.

Superconducting fault current limiters (SFCL) are designed to protect the electrical grid from faults that result from lightning strikes, downed power lines and other system interruptions. The rapid increase of impedance of the SFCL reduces the short current in the circuit. Several coreless constructions of inductive SFCLs have been tested. The space between the windings is the thick of the polyimide film kapton insulation to increase the coupling and reduces the leakage reactance. Both primary and secondary windings have been immersed in liquid nitrogen. The presented solutions reduce the size and the weight of the device. A few limiters based on HTS 1G and HTS 2G tapes has been described, tested and compared.