This paper proposes a novel approach for dynamic economic dispatch (DED) of distribution networks, based on graph-generative adversarial network (Graph-GAN) assisted inverse reinforcement learning (IRL) with human knowledge transfer via demonstration. Firstly, the proposed method utilizes graph convolutional network (GCN) to capture the complex and nonlinear relationships between dispatch decision and system state. Secondly, a GAN-based approach is proposed to imitate the reward function from expert demonstration data, which avoids the need for manually designed reward functions. The trained policy network is then used for decision-making in real-time optimal dispatch of distribution networks. Experimental results demonstrate that the proposed approach outperforms traditional IRL methods and achieves supply-demand balance. Computation efficiency of the proposed method is thoroughly analyzed and shows that it is practically scalable to large-scale distribution networks. Overall, the proposed approach presents a promising alternative by incorporating human knowledge into reinforcement learning for DED of distribution networks.

Power transformers are critical assets in power systems, and their reliable operation is essential for grid stability. Conventional fault diagnosis methods suffer from delayed response and limited adaptability, while existing artificial intelligence-based approaches face challenges related to data heterogeneity, limited interpretability, and weak integration of physical mechanisms. To address these issues, this paper proposes a physics-informed enhanced transformer-based framework for power transformer fault diagnosis. A unified temporal representation scheme is developed to integrate heterogeneous monitoring data using Dynamic Time Warping and physics-guided feature projection. Physical priors derived from thermodynamic laws and gas diffusion principles are embedded into the attention mechanism through multi-physics coupling constraints, improving physical consistency and interpretability. In addition, a multi-task diagnostic strategy is adopted to jointly perform fault classification, severity assessment, and fault localization. Experiments on 3000 samples from 76 power transformers demonstrate that the proposed method achieves high diagnostic accuracy and superior robustness under noise and interference, indicating its effectiveness for practical predictive maintenance applications.

This paper studies the online dispatch of distribution networks (DNs), which is formulated as a multi-stage dynamic programming (MSDP) to ensure the non-anticipativity of dispatch decisions. Existing approaches usually relegate expensive online optimization to offline learning (typically value function learning) using the given uncertainty distribution or training samples. However, practical DNs may encounter various scenarios where the distributions of uncertainty differ significantly. The optimality of these approaches may degrade substantially in out-of-distribution scenarios unless frequent re-training is conducted. To address this obstacle, this paper proposes a scenario-generalized MSDP (S-MSDP) scheme for online dispatch of DNs. Its main advantage is the ability to directly adapt to new scenarios with high optimality, without re-training or fine-tuning. S-MSDP extends MSDP by learning a universal value function that maps scenario contexts to the corresponding value functions, so that the optimal dispatch policies under different scenarios can be directly inferred by using the learned universal value function. To facilitate the computation and storage burdens brought by large scenario space, a sparse and low-rank tensor approximation is introduced for universal value function learning. Numerical studies verify the optimality, generalization, and scalability of S-MSDP.

Extreme events can lead to extensive blackouts, emphasising the crucial significance of power system black‐start restoration. In this paper, a two‐stage strategy coordinating deep reinforcement learning (DRL) and mixed‐integer linear programming (MILP) for power system black‐start restoration is proposed. In the first stage, a convolutional neural network‐based (CNN‐based) invalid action masking assisted proximal policy optimisation (CI‐PPO) algorithm is developed to determine component connections. Furthermore, a MILP model for optimal power dispatch is formulated with the objective of minimising generation costs in the second stage. The effectiveness of the proposed method is validated using the New England 10‐unit 39‐bus power system. The results show strong learning ability and computational efficiency for varying system conditions.

The evolution towards 6G is set to transform Vehicle-to-Everything (V2X) networks by introducing advanced technologies such as Six-Dimensional Movable Antenna (6DMA). This technology endows Roadside Units (RSUs) with dynamic beam-steering capabilities, enabling adaptive coverage. However, traditional RSU deployment strategies, optimized for static coverage, are fundamentally mismatched with these new dynamic capabilities, leading to a critical deployment–optimization mismatch. This paper addresses this challenge by proposing DyDO, a novel Dynamic Deployment and Optimization framework for the utilization of 6DMA-RSUs. Our framework strategically decouples the problem into two modules operating on distinct timescales. On a slow timescale, an offline deployment module analyzes long-term historical traffic data to identify optimal RSU locations. This is guided by a newly proposed metric, the Dynamic Potential Score (DPS), which quantifies a location’s intrinsic value for dynamic adaptation by integrating spatial concentration, temporal volatility, and traffic magnitude. On a fast timescale, an online control module employs an efficient Sequential Angular Search (SAS) algorithm to perform real-time, adaptive beam steering based on immediate traffic patterns. Extensive experiments on a large-scale, real-world trajectory dataset demonstrate that DyDO outperforms conventional static deployment methodologies. This work highlights the necessity of dynamic-aware deployment to fully unlock the potential of 6DMA in future V2X systems.