Photovoltaic power generation relies on sunlight conditions, and traditional prediction models find it difficult to capture the deep features of power data, resulting in low prediction accuracy. In addition, there are problems such as outliers and missing values in the data collected on site. This article proposes an ultra-short-term photovoltaic power generation prediction model based on wavelet decomposition, a dual attention mechanism, and a bidirectional long short-term memory network (W-DA-BiLSTM), aiming to address the limitations of existing deep learning models in processing nonlinear data and automatic feature extraction and optimize for the common problems of outliers and missing values in on-site data collection. This model uses the quartile range method for outlier detection and multiple interpolation methods for missing value completion. In the prediction section, wavelet decomposition is used to effectively handle the volatility and nonlinear characteristics of photovoltaic power generation data, while the bidirectional long short-term memory network (LSTM) structure and dual attention mechanism enhance the model’s comprehensive learning ability for time series data. The experimental results show that compared with the SOTA method, the model proposed in this paper has higher accuracy and efficiency in predicting photovoltaic power generation and can effectively address common random fluctuations and nonlinear problems in photovoltaic power generation.
The island microgrid is composed of a large number of inverters and various types of power equipment, and the interaction between inverters with different control methods may cause system instability, which will cause the power equipment to malfunction. Therefore, effective methods for analyzing the stability of the microgrid system have become particularly important. Generally, impedance modeling methods are used to analyze the stability of power electronic converter systems. In this paper, the impedance models of a PQ-controlled inverter and droop-controlled inverter are established in d-q frame. In view of the difference of output characteristics between the two control methods, the island microgrid is equivalent to a double closed-loop system. The impedance model of the parallel system is derived and the open loop transfer function of the system is extracted. Based on the generalized Nyquist criterion (GNC), the stability of parallel system working in island microgrid mode is analyzed using this proposed impedance model. The simulation and experiment results are presented to verify the analysis.
Different from the extant power flow analysis methods, this paper discusses the power flows for the unified power quality conditioner (UPQC) in three-phase four-wire systems from the point of view of impedance matching. To this end, combined with the designed control strategies, the establishing method of the UPQC impedance model is presented, and on this basis, the UPQC system can be equivalent to an adjustable impedance model. After that, a concept of impedance matching is introduced into this impedance model to study the operation principle for the UPQC system, i.e., how the system changes its operation states and power flow under the grid voltage variations through discussing the matching relationships among node impedances. In this way, the nodes of the series and parallel converter are matched into two sets of impedances in opposite directions, which mean that one converter operates in rectifier state to draw the energy and the other one operates in inverter state to transmit the energy. Consequently, no matter what grid voltages change, the system node impedances are dynamically matched to ensure that output equivalent impedances are always equal to load impedances, so as to realize impedance and power balances of the UPQC system. Finally, the correctness of the impedance matching-based power flow analysis is validated by the experimental results.
The power grid has the characteristics of a weak grid with an increase in new energy penetration in the power system. Power electronic-based renewable generation brings issues that weaken the entire system, including the loss of inertia. Low inertia and weak damping cause system oscillation. Virtual synchronous generator (VSG) technology gives power electronic equipment inertia-support capability but increases the complexity of control system parameter design. Many researchers have studied the design method of VSG considering the frequency disturbance of the power grid. The traditional VSG parameter design method ignores the influence of source-side and grid-side fluctuations on the transient stability of the system, resulting in the difference between the actual dynamic and static indicators and the design indicators of VSG in a weak grid. This paper analyzes a small-signal model based on power fluctuations and frequency fluctuations and proposes a control parameter design method that combines the influence of grid impedance to ensure the dynamic stability of the system under a weak power grid. The simulation and experimental results verify the correctness and feasibility of the control method.
With the higher penetration of renewable energy, the influence of grid equivalent distribution cable impedance on grid-connected inverter stability is attracting increasing attention. In order to suppress the interaction between grid distribution cable impedance and output impedance of the grid-connected system, the active damping strategy is often used. When a capacitive current loop is used, the damping coefficient increases with the grid impedance increasing. However, the excessive damping coefficient will cause the unstable operation of the system. In order to enhance the robustness of the system, a novel control strategy which is suitable for wide-range grid impedance variation is proposed. In this strategy, the capacitor current inner loop is combined with the grid current inner loop, and grid voltage feedforward is included. Since the virtual impedance, active damping and voltage feed-forward are normalized, the changing tendency of the damping coefficient of the grid-current inner loop is opposite to that of capacitor current inner-loop. The overall damping coefficient of the system remains relatively constant when the grid impedance changes, and this effectively suppresses the resonance of the system. In this paper, the method is analyzed and the parameters are designed and optimized. Finally, the simulation and experiment are presented to verify the analysis.
25 January 2026 in Journal of Intelligent Information Systems