No abstract

No abstract

Virtual synchronous generator (VSG) control scheme, which can be regarded as an extension of droop control, has received much attention from researchers as the introduction of rotational inertia to inverters. This study discusses an active and reactive power decoupling technique for VSGs in microgrid, as an important aspect of VSG. The traditional power decoupling mechanism is initially analysed. Subsequently, the properties of the line impedance at different voltage degrees are compared. Results indicate that the traditional power decoupling method is unsuitable for medium-and low-voltage microgrids. Thus, an improved power decoupling method is proposed. By estimating the voltage at the point of common coupling and tracking their reference values, the output active and reactive power of inverters can perform dynamic decoupling. Furthermore, the stability of the new control structure and selection of relevant coefficients are analysed. The simulation and experimental results verify the enhanced decoupling strategy for VSGs.

This paper investigates the extent to which the damping region of a digitally controlled LCL-type grid connected inverter is influenced by the ratio between sampling and switching frequencies, the grid impedance variation and changes in the LCL filter. Based on this analysis, an improved capacitor-current feedback is proposed to preserve stability by extending the damping region under the critical conditions identified. The attention is focused on the case when the system switching frequency is higher than one-half of the system sampling frequency, which is not covered in the existing literature. In this case, the undamped region is obviously expanded and a conventional capacitor-current feedback will not provide sufficient damping region. An improved capacitor-current feedback active damping method is proposed to increase the system critical frequency greatly and to obtain a wider damping region for all possible LCL resonances. With a reasonable parameter design, the extended system damping region is able to cover almost all possible resonance frequencies even when the switching frequency is the same as sampling frequency. A high robustness to grid-impedance variation is achieved in the system as a result of this improved feedback control. The effectiveness of the theoretical analysis and proposed method are verified by the experimental results.

Electricity price is an important indicator of the market operation. Accurate prediction of electricity price will facilitate the maximization of economic benefits and reduction of risks to the power market. At the same time, because of the excellent performance of deep learning models, using long-short term memory neural network (LSTM) and other deep learning models to predict time series has gradually become a research hotspot. In this paper, an optimized heterogeneous structure LSTM model is proposed to solve the problems of the single network structure and hyperparameter selection existing in the current research on LSTM. The heterogeneous structure LSTM is constructed based on the decomposed and reconstructed electricity price data, and sequence model-based optimization (SMBO) is used to optimize its hyperparameters. In order to verify the proposed model, online hourly forecasting and day-ahead hourly forecasting are tested on the electricity markets of Pennsylvania-New Jersey-Maryland (PJM). The experimental results show that the performance of the proposed model is much better than that of the general LSTM model and traditional models in accuracy and stability, providing a new idea for the use of LSTM for time series prediction. INDEX TERMS Long short-term memory neural network, neural network structure, hyperparameter optimization, time series analysis, electricity price forecasting.