Under the background of the rapid change of energy technology and the deep integration of artificial intelligence into the power system, it is of great significance to study the intelligent decision-making method of security-constrained unit commitment (SCUC) with high adaptability and high accuracy. Thus, in this article, an expanded sequence-to-sequence (E-Seq2Seq)-based data-driven SCUC expert system for dynamic multiple-sequence mapping samples is proposed. First, dynamic multiple-sequence mapping samples of SCUC are reconstructed by analyzing the input–output sequence characteristics. Then, an E-Seq2Seq approach with a multiple-encoder–decoder architecture and a fully connected extension layer is proposed. On this basis, the simple recurrent unit is introduced as a neuron of the E-Seq2Seq approach to construct deep learning models, and an intelligent data-driven expert system for SCUC is further developed. The proposed approach has been simulated on a typical IEEE 118-bus system and a practical system in Hunan province in China. The results indicate that the proposed approach could possess strong generality, high solution accuracy, and efficiency over traditional methods.

A kind of interleaved non‐isolated high step‐up DC/DC converter is presented in this study. The converter consists of two basic Boost cells and some diode–capacitor multiplier (DCM) cells as needed. Because of the DCM cells, the voltage conversion ratio is enlarged and the extreme large duty ratio can be avoided in the high step‐up applications. Moreover, the voltage stress of all the power devices is greatly lower than the output voltage. As a result, lower‐voltage‐rated power devices can be employed, and higher efficiency can be expected. Since the two basic Boost cells are controlled by the interleaving method, which means the phase difference between the two pulse width moderlation (PWM) signals is 180° and the input current is the sums of the two inductor currents, the input current ripple is decreased and the size of the input filter could be reduced, which make it a suitable choice in the photovoltaic power generation system and hybrid electric vehicles, etc. Finally, the experimental results from a 300 W, 30–400 V laboratory prototype are presented to validate the effectiveness of the proposed converter.

A dual-input high step-up DC/DC converter with zero voltage turn-off (ZVT) auxiliary circuit is presented in this paper. The cost of whole photovoltaic (PV) power could be decreased significantly by the proposed converter because it allows two PV panels to be connected at the same time. ZVT auxiliary circuit provides soft switching in a wide range of load variations with six passive components. Turn-off switching losses could be decreased and the efficiency of whole converter could be improved. In section II, the operation principle and performance characteristics of the proposed converter have been analyzed and a 800W experimental prototype has been built to validate the analytical results in section III. In section IV, a dual-input maximum power point tracking (DMPPT) control algorithm has been designed for the proposed converter. Experimental results show that two PV panels can achieve the maximum power output state separately by the proposed DMPPT control algorithm.

The voltage conversion ratio of basic DC/DC converters is limited due to the influence of parasitic elements of circuits and components. In this paper, a family of passive circuits termed as “coat circuits” are proposed for conventional DC/DC converters. Not only voltage step-up capacity can be improved but also the voltage stress of components can be decreased by adding coat circuits to basic DC/DC converters. Moreover, no additional active switches are needed in the coat circuits, that means the control and driver circuits of the converters are not changed. Cuk converter with the coat circuit has been analyzed as an example, and a 200W experimental prototype has been built to verify the validity of the theoretical analysis.

With the rapid development of microgrids, the types of users and loads in microgrids are increasing. Comprehensively reflecting the value of loads in load shedding decisions is one of the main challenges for the intelligent control of an islanded microgrid. However, the existing load shedding schemes ignore the user’s subjective preference for multiple attributes of loads, which are insufficient for reflecting the comprehensive value of loads. To address the aforementioned problem, an underfrequency load shedding (UFLS) scheme based on the comprehensive weight of loads is proposed. This scheme evaluates the multiple attributes of loads and the user’s preference for load attributes based on the entropy method with high adaptability (EMHA) and the analytical hierarchy process (AHP) to obtain the objective and subjective weights of loads. Then, the comprehensive weight of loads is calculated based on the relative entropy to determine the sequence of load shedding. Furthermore, the optimal objective function of the comprehensive cost of load shedding is constructed, and gray wolf optimization (GWO) is used to solve the objective function and obtain the optimal load shedding scheme. Ultimately, the effectiveness of the proposed scheme is verified based on a modified standard IEEE 37-bus system.