[Objective] With the extensive integration of distributed nodes in new power systems into distribution networks， frequent data interactions increase the risk of false data injection attacks（FDIA） on the distribution networks. Conventional data-driven detection methods tend to treat all data holistically when mining data features， usually ignoring individual characteristics in data from different nodes. To address this problem， this paper proposes a personalized federated training method based on maximum information coefficient for false data injection attack detection in distributed renewable energy scenarios. [Methods] The proposed method deploys the detection model in distributed edge nodes， which improves the network security protection and local data privacy protection of the edge nodes. Multi-layer neural networks subjected to personalized federated training are separated into distinct feature layers to decouple common and individual features， thereby enhancing the feature processing of heterogeneous node data on the basis of distributed detection. Considering the temporal features in the measurement data， the potential regular features in the data are deeply mined by introducing the maximum information coefficient， and the analysis results are fused into the personalized federated training in order to improve the ability of extracting the personality features of the nodes' own data. [Results] The park data containing distributed renewable energy nodes is taken as an example for simulation analysis， and the proposed method improves the detection accuracy， precision， recall， and F1 score compared to the traditional federated framework and the detection method that does not consider correlation analysis. Maximum information coefficient demonstrates better personality feature extraction when dealing with periodic data. [Conclusions] The proposed method enhances the separation and extraction of common and individual features of the data， and the detection model exhibits a faster convergence rate when there are a large number of clients， rendering it more suitable for FDIA detection in distributed renewable energy scenarios.

[Objective] Aiming at the problems of adversarial attack risks and insufficient offensive-defense coordination of data-driven algorithms in new power systems， a theoretical framework for co-optimization of adversarial attacks and defense is established. This framework aims to enhance attack targeting， defense robustness， and the capability to identify complex attack features， thereby establishing a closed-loop optimization mechanism for offensive-defense co-evolution. [Methods] In the adversarial attack generation module， a self-attention mechanism is utilized to quantify node feature contributions， and a Top-K strategy is combined to screen key nodes. An encoder-decoder architecture and reinforcement learning are employed to dynamically optimize perturbation strategies， and a filter retains perturbations on key nodes to improve attack efficiency. In the adversarial defense model， a stacked autoencoder extracts static structural features， while a convolutional neural network-long short-term memory network fuses spatiotemporal features. These multi-modal features are then integrated via a dynamic weighting strategy and fed into a support vector machine classifier to distinguish attack samples from normal samples. [Results] Compared with random node attacks， the fast gradient sign method， and projected gradient descent attacks， the proposed attack method maintains a high success rate while demonstrating robustness across the entire attack intensity range that better aligns with the practical requirements of power system adversarial attacks. Furthermore， perturbations can be concentrated on key nodes， verifying the advantage of attack targeting. On the defense side， the fusion model's performance significantly surpasses that of single models， highlighting the strong identification capability of multi-modal feature fusion for complex attack patterns. [Conclusions] On the attack side， the integration of self-attention and reinforcement learning achieves targeted perturbation on key nodes. On the defense side， the adoption of multi-modal feature fusion enhances the identification capability for complex attacks. Furthermore， a dynamic co-evolution of offensive and defensive strategies is realized through a closed-loop feedback mechanism.

[Objective] Power system data demonstrates features of high stochasticity， strong interaction， and multi-dimensional coupling. Traditional mechanistic modeling and simulation analyses， which rely on conditional assumptions and model simplifications， fail to meet the real-time defense requirements of large-scale power grids in terms of timeliness. By fully leveraging wide-area spatiotemporal sequence information from power grids， we can enhance analysis accuracy and timeliness while transcending the limitations of mechanistic models. This approach enables multi-level situational awareness of the physical operational states of power systems， facilitating more effective real-time defense strategies. [Methods] This paper presents a method to promote the safe and stable operation of the power grid. Based on the dynamic characteristics of the power grid， the spatiotemporal data are analyzed and excavated by random matrix theory. This method overcomes the limitations of the traditional grid-based physical topology， realizing the real-time assessment and identification of critical nodes in the system. According to assessment results of critical nodes， the disturbance propagation is predicted based on data-driven Markov chain. The method achieves the personalized risk assessment of grid nodes and collective predictive analysis of grid situations. [Results] This paper focuses on personalized risk assessment of nodes in the power grid， identifying risk nodes or key nodes in the system. By using the method proposed in this paper to explore the transition from monitoring and warning to predictive warning. The effectiveness and rationality of the proposed method can be verified through case analysis by using Markov chain to predict the propagation of disturbances relative to disturbed nodes. This study enables early warning of the disturbance propagation when the power grid disturbance occurs， and focuses on the critical nodes that will cause serious accidents in advance. Compared with other identification methods， the proposed approach takes into account both the electrical characteristics and topological properties of the system， with its identification results dynamically adapting to changes in system operating conditions. [Conclusions] Prevention and control are conducted in advance to ensure the safe and stable operation of the system， which is of great significance to the defense of blackouts.

[Objective] This paper proposes a collaborative dispatch and control strategy for electric bus fleets to enhance the emergency supply capacity of power systems under extreme weather conditions. [Methods] The proposed approach leverages electric buses as mobile storage units during their idle periods to support distribution network operation. First， an electric-bus traffic-network model is developed based on operational scheduling data， enabling the formulation of a vehicle reallocation strategy that captures route-specific characteristics and operational patterns. Then， a mixed-integer linear programming model is established to coordinately optimize the distribution network and the electric-bus fleet. The model minimizes operating cost under disaster conditions， subject to operational constraints of both the distribution network and the electric buses. [Results] Case studies on an extended IEEE 33-node system and the IEEE 118-node system demonstrate that the proposed strategy enables rapid grid integration of electric buses and V2G power supply coverage within one hour after a fault. The approach significantly reduces load loss， and exhibits excellent performance in response speed， migration efficiency， and economic viability， thereby significantly enhancing the resilience of the power grid. [Conclusions] The research results offer effective solutions for emergency power supply under extreme weather conditions and contribute to improving urban disaster preparedness and resilience. The strategy also supports broader efforts toward achieving carbon peak and carbon neutrality goals.