False data injection attacks (FDIAs) significantly disrupt the secure operation of smart grids by manipulating the measured values collected by intelligent instruments. Existing studies have utilized deep learning techniques to enhance the detection of FDIAs, however, these studies often overlook the spatial correlation between power grid topology and measurement data. Meanwhile, the high complexity of deep neural network severely impedes the interpretability of detection models, resulting in the incredibility of detection results. To address the above challenges, this paper proposes an interpretable deep learning FDIAs detection method, named dual-attention multi-head graph attention network, DAMGAT. The DAMGAT introduces a dual-attention mechanism that incorporates both node feature attention and spatial topology attention into a multi-head graph attention network. This mechanism efficiently aggregates attack characteristics and spatial topology information by dynamically capturing the potential correlations between FDIAs detection and measurement data. Furthermore, the proposed model can provide clear and credible interpretations for high-accuracy detection results via analyzing features and spatial topology attention weights. Extensive simulations are performed using the IEEE 14-bus and 118-bus test systems. The experimental results demonstrate that the proposed model outperforms state-of-the-art FDIA detection methods in terms of accuracy, while also providing reasonable interpretability for features and spatial dimensions.

For the energy storage system (ESS) with lossy communication networks of packet loss in DC microgrid, the multiagent distributed secondary control strategy is proposed to manage the ESS. The multiagent dynamic-tracking consensus protocol (DCP) based on the random packet loss model is constructed to estimate the global information for the dynamic network with lossy communication. Then the adaptive current sharing algorithm (ACSA) is designed to balance the state of charge (SoC) for ESSs with different capacities. Furthermore, the data-driven model-free adaptive control (MFAC) scheme is proposed for the single-input multiple-output (SIMO) nonlinear ESS to provide accurate voltage tracking and current sharing. Finally, the real-time simulation tests of different case studies are carried out through the OPAL-RT platform to verify the effectiveness of the designed control strategy. Simulation results can prove that the favorable capabilities of current sharing and voltage regulation as well as robustness to communication packet loss and communication faults can be achieved.

Effective monitoring and early warning of gearbox operating status are of great significance to the operation and maintenance (O&M) of offshore wind turbines (WTs). This study proposes a normal behaviour modelling (NBM) method based on the spatial‐temporal attention module and the gated recurrent unit (GRU), for the condition monitoring of offshore WT gearboxes. The proposed method has a superior performance by extracting the spatial and temporal features from the supervisory control and data acquisition (SCADA) system, and also has the unique advantage of model interpretability. Specifically, in the NBM training stage, the spatial features of offshore wind farm SCADA data are extracted by the spatial attention module firstly. Then, the temporal features of the spatial feature sequences above are extracted and fused by the GRU network. Afterwards, the temporal attention module is applied to strengthen the expression of key time points. In the NBM testing stage, the output residual between the predicted and the measured values is calculated and monitored by the exponential weighted moving average (EWMA) control chart. Finally, the effectiveness and superiority of the proposed NBM method are verified by detailed simulations on the Donghai Bridge offshore wind farm.

The uncertainty of renewable energy source (RES) and load may bring huge challenge to the operation of power systems. In order to meet the balance of supply and demand, a game bidding strategy considering uncertainty is proposed for the electric-hydrogen shared energy storage system (SESS). Firstly, based on Wasserstein distance in extreme scenarios, a reduced scale fuzzy set is constructed for the uncertainty of supply and demand. Secondly, Vickrey-Clarke-Groves (VCG) mechanism is introduced to deal with the misreporting and valuation behavior of microgrids (MGs). Then a two-stage distributed robust optimization (DRO) game model is designed for SESS—MGs through game bidding. The aim of Stage I can maximize the benefits of SESS, while the social welfare of each microgrid (MG) may be maximized in Stage II, which can achieve a unique Stackelberg equilibrium. So the DRO model is transformed into a solvable mathematical model by taking advantage of dual theory and adaptive McCormick algorithm. Finally, the case studies are simulated by using the IEEE 33 node power grid together with a 20 node hydrogen network, which can validate the effectiveness of the proposed model.

Due to frequency and voltage fluctuation resulting from the parameter uncertainties and system disturbances, the novel coordinated control strategy is designed to improve the stability for isolated wind-diesel hybrid power system. Frequency and voltage are both controlled by taking advantage of adaptive sliding mode (SM) method and disturbance observer (DOB) based on established whole hybrid system mathematical model. Firstly, the disturbance observer is constructed to estimate the source-load disturbance for isolated wind-diesel power system model. Furthermore, an adaptive coordinated control strategy, which can regulate frequency and voltage simultaneously through synchronous generator (SG) and static compensator (STATCOM) respectively, is designed for the hybrid system based on the estimated value and state variables by using adaptive sliding mode algorithm. Experiments studies are performed by real-time digital simulator (RTDS) to validate the effectiveness of the proposed strategy for the isolated hybrid system under different operation points.

The worldwide acceptance of plug-in electric vehicles (PEVs) is expected to tremendously grow in the next few years. Uncoordinated PEV charging can cause serious grid issues such as overloading of transformers and unacceptable voltage drops. Single-phase residential charging can also initiate or contribute to voltage unbalance in distribution networks. A potential solution for the PEV integration is shifting the charging activities from peak to valley periods. Therefore, this paper firstly investigates the impacts of uncoordinated single-phase PEV charging at residential houses on three-phase distribution networks. Then, it proposes a novel PEV charging coordination strategy based on heuristic genetic algorithm (GA) to perform online centralized charging considering transformer loading and bus voltage profiles. Based on this, a decentralized PEV reactive power discharging approach is presented where the reactive power is discharged at selected nodes for further reduction of voltage unbalance. The impacts of uncoordinated PEV charging as well as the performance of the proposed centralized PEV charging and decentralized var discharging strategies are tested on a real unbalanced Western Australian distribution network under the Perth Solar City project over 24 hours.