A unified specification to design and operate the stability control device in smart substation has not been formed yet, which has greatly affected the promotion and application of stability control device in smart substation. Thus, referring to the technical specifications of protection device and combining to the specificity of stability control device, a full and detailed configuration scheme is proposed to meet the requirement, including the device configuration principle, the access configuration of SV and GOOSE for variable primary connection types, the virtual terminal and soft switch. This solution is beneficial to standardize the R&D of stability control device in smart substation, and to facilitate on-site debugging, operation and maintenance.
This paper proposes an equivalent modeling method for photovoltaic (PV) power stations via a particle swarm optimization (PSO) K-means clustering (KMC) algorithm with passive filter parameter clustering to address the complexities, simulation time cost and convergence problems of detailed PV power station models. First, the amplitude–frequency curves of different filter parameters are analyzed. Based on the results, a grouping parameter set for characterizing the external filter characteristics is established. These parameters are further defined as clustering parameters. A single PV inverter model is then established as a prerequisite foundation. The proposed equivalent method combines the global search capability of PSO with the rapid convergence of KMC, effectively overcoming the tendency of KMC to become trapped in local optima. This approach enhances both clustering accuracy and numerical stability when determining equivalence for PV inverter units. Using the proposed clustering method, both a detailed PV power station model and an equivalent model are developed and compared. Simulation and hardware-in-loop (HIL) results based on the equivalent model verify that the equivalent method accurately represents the dynamic characteristics of PV power stations and adapts well to different operating conditions. The proposed equivalent modeling method provides an effective analysis tool for future renewable energy integration research.
Enhancing the accuracy of short-term wind power forecasting helps mitigate the adverse impacts of prediction errors on grid dispatch. Wind power exhibits a significantly nonlinear dependence on multiple influencing factors. However, existing methods struggle to effectively resolve multi-dimensional feature redundancy and multi-scale non-stationary evolutionary characteristics inherent in far-offshore wind power forecasting tasks. This leads to bottlenecks such as insufficient feature discriminability and temporal dependency focus shift under complex marine environments, ultimately limiting further improvements in prediction accuracy. To address these challenges, this paper proposes a federated learning-based adaptive multi-head attention model for wind power forecasting (Fed-AMHA). The proposed framework operates as follows: First, each wind farm client utilizes a Bidirectional Long Short-Term Memory (BiLSTM) network to model input sequences bidirectionally, capturing long-term temporal dependencies. Subsequently, linear projection and parallel one-dimensional convolution operations are introduced to mine multi-scale local temporal features from each time step and its neighborhood. Building upon this, channel attention and multi-head temporal feature attention mechanisms are stacked. The model adaptively adjusts the weights of different time slices and feature channels by learning the importance of each channel to the forecasting task. The central server then aggregates the model parameters uploaded by the clients via averaging, enabling cross-site collaborative training without directly sharing raw data. Simulation results based on public datasets and actual wind farm data under various short-term forecasting scenarios demonstrate that the proposed model consistently achieves lower prediction errors and superior stability compared to existing forecasting models under identical settings.
In response to an actual super-synchronous oscillation event in an offshore wind farm, this paper proposes a full-topology real-time simulation (FTRT) scheme based on a self-developed universal link library execution device. The technical challenges of FTRT are systematically analyzed, and a complete modeling and implementation methodology is established. Using this scheme, a hardware-in-the-loop real-time simulation platform incorporating the same type of field controller is built, and the 70 Hz voltage oscillation is accurately reproduced. The analysis reveals that the submarine-cable-based transmission network possesses an inherent resonance point in the super-synchronous frequency band. The system stability boundary is then evaluated by comparing the phase–frequency characteristics of the grid-side and wind-farm impedances. Finally, oscillation suppression measures, including controller parameter unification, impedance reshaping, and SVG (Static Var Generator) deployment, are proposed and verified. The adopted FTRT technology overcomes the accuracy limitations of conventional offline simulations and simplified mechanism analyses, and the results can provide reliable, direct engineering decision support for the planning, design, and operation of offshore wind farms.