A wind power short-term forecasting method based on discrete wavelet transform and long short-term memory networks (DWT_LSTM) is proposed. The LSTM network is designed to effectively exhibit the dynamic behavior of the wind power time series. The discrete wavelet transform is introduced to decompose the non-stationary wind power time series into several components which have more stationarity and are easier to predict. Each component is dug by an independent LSTM. The forecasting results of the wind power are obtained by synthesizing the prediction values of all components. The prediction accuracy has been improved by the proposed method, which is validated by the MAE (mean absolute error), MAPE (mean absolute percentage error), and RMSE (root mean square error) of experimental results of three wind farms as the benchmarks. Wind power forecasting based on the proposed method provides an alternative way to improve the security and stability of the electric power network with the high penetration of wind power.

Reliable online transient stability assessment (TSA) is fundamentally required for power system operation security. Compared with time-costly classical digital simulation methods, data-driven deep learning (DL) methods provide a promising technique to build a TSA model. However, general DL models show poor adaptability to the variation of power system topology. In this paper, we propose a new graph-based framework, which is termed as recurrent graph convolutional network based multi-task TSA (RGCN-MT-TSA). Both the graph convolutional network (GCN) and the long short-term memory (LSTM) unit are aggregated to form the recurrent graph convolutional network (RGCN), where the GCN explicitly integrate the bus (node) states with the topological characteristics while the LSTM subsequently captures the temporal features. We also propose a multi-task learning (MTL) scheme, which provides joint training of stability classification (Task-1) as well as critical generator identification (Task-2) in the framework, and accelerate the process with parallel computing. Test results on IEEE 39 Bus system and IEEE 300 Bus system indicate the superiority of the proposed scheme over existing models, as well as its robustness under various scenarios.

Data-driven transient stability assessment (TSA) models are usually sensitive to system scale changes and require dynamic information from time-domain simulation (TDS) as inputs. We propose a S ystem-sc A le- F re E T ransient C ontingency S creening (SAFE-TCS) scheme based on only the steady-state measurements. An analytical model is set up to estimate the state variation at fault occurrence ( $t_{0+}$ ) snapshot, which forms multi-graph inputs together with the steady-state information. A novel pooling-ensemble multi-attention graph convolutional network (PE-MAGCN) realizes the spatio-temporal graph embedding, in which an inter-graph convolution link works for the temporal abstraction. Following a pooling-ensemble mechanism, PE-MAGCN derives a fixed-size expressive vector for task-specific networks. This promotes the robustness of the model against system extension. The advantages of SAFE-TCS also benefit from the coordination of various training tricks, including channel attention, category-balanced sampling and joint-decoupling learning, etc. Test results on IEEE 39 Bus system and IEEE 300 Bus system indicate the superiority of the proposed scheme over existing models and its adaptability under various scenarios.

This paper proposes a data-driven based optimization method for var-voltage sequential control (V2SC). First, power system var-voltage control characteristics, defined as the function be-tween the reactive power injections and the bus voltages, is ap-proximated by the var-voltage sensitivities (V2S). Then V2S is estimated online using the noise-assisted ensemble regression method. Subsequently, an optimal model is proposed for V2SC based on the V2S estimation. To avoid frequent back and forth control actions, a hysteresis control strategy is employed. The performance of the proposed method is statistically validated in the 8-generator 36-node system and the Nordic32 system with test data measured from real power systems.

Increasing penetration of distributed generators (DGs) brings new challenges to the control and protection of distribution networks. This article proposes a control and protection framework based on Multi-agent System (MAS), in which situation awareness of zone agents plays an important role. The main protection is designed to locate and isolate faults based on the peer-to-peer communication among the zone agents. Fault-tolerant mechanisms, including self-inspection and backup protection, are developed to cope with the malfunction of individual MAS and local communication failure. An automatic parallel restoration scheme that doesn't require complete grid information is proposed to restore the power supply. Comprehensive simulation studies are carried out on a 71-bus distribution network with DGs using DIgSILENT, and the results have shown the effectiveness of the proposed self-healing framework.