The rapid growth of electric vehicles (EVs) poses significant challenges to the safe operation of charging stations and distribution networks. Variations in charging power across different EV manufacturers lead to substantial load fluctuations at charging stations. In some tourist cities in China, charging loads can surge at specific times, yet existing research mainly focuses on optimizing station location and basic capacity configuration, neglecting sudden peak load management. To address this, we propose a method that enhances charging station carrying capacity (CSCC) by coordinating multi-flexibility resources. This method optimizes the configuration of soft open points (SOPs) to enable flexible interconnections between feeders and incorporates elastic load scheduling for data centers. An optimization model is developed to coordinate these flexible resources, thereby improving the CSCC. Case studies demonstrate that this approach effectively increases CSCC at lower costs, facilitates the utilization of renewable energy, and enhances the overall system economy. The results validate the feasibility and effectiveness of the proposed approach, offering new insights for urban grid planning and EV charging stations optimization.

With the widespread integration of renewable energy sources and distributed energy storage systems, intraday dispatch of distribution networks (DNs) has gradually evolved into a multistage sequential decision-making problem with intertemporal state coupling and progressively revealed uncertainty. Stochastic optimization under the stagewise independence assumption and limited horizon prediction cannot adequately capture temporal transition characteristics, which may lead to biased future cost estimation and myopic decisions. To address this obstacle, this paper proposes a conditional-cut-enhanced Markov chain stochastic dual dynamic programming strategy (MC-SDDP-CC) for multistage intraday dispatch of DNs. Feature encoding and scenario-lattice-driven trajectory sampling with Markovian path dependence are introduced to accurately characterize the temporal dependence in DNs. To improve computational efficiency, a node-wise conditional cut management scheme is developed to accelerate the recursion and tighten the conditional value function approximation. Numerical studies on modified IEEE 33-bus and 123-bus networks, as well as a practical system in a southwestern province of China, verify the effectiveness of the proposed method in terms of optimality, scalability and ablation performance.

The integration of data centers (DCs) into distribution systems introduces new challenges for reliability assessment. It also provides operational flexibility through the spatial migration of computational workloads. However, existing reliability assessment methods have not sufficiently captured the joint effects of DC workload flexibility, post-fault network reconfiguration, and multiple heterogeneous faults. To address this gap, this paper proposes an optimization model-based reliability assessment framework for distribution systems with integrated DCs. A DC workload dispatch model is first developed by considering server operation, cooling demand, backup requirements, and inter-DC workload transfer limits. The post-fault operation process is then formulated as a two-stage optimization problem, including fault isolation and service restoration. The proposed framework co-optimizes network reconfiguration and DC workload migration under line faults, node faults, and remote-controlled switch failures. The resulting problem is reformulated as a mixed-integer linear programming model and solved using commercial solvers. Case studies on a modified IEEE 123-node test feeder show that DC workload migration can significantly reduce expected energy not supplied by exploiting the spatial flexibility of interconnected DCs. The results also demonstrate that neglecting node faults and switch failures may lead to overly optimistic reliability estimates. Additional tests on a modified 356-node regional distribution system further verify the applicability and scalability of the proposed framework. The proposed method provides a physically interpretable reliability assessment tool for active distribution systems with DC integration and heterogeneous fault mechanisms.

Deep learning-based Non-Intrusive Load Monitoring (NILM) methods have been widely applied to residential load identification. However, photovoltaic (PV) loads exhibit strong non-stationarity, high dependence on weather conditions, and strong coupling with multi-source data, which limit the accuracy and generalization of existing models. To address these challenges, this paper proposes a multi-scale and multi-feature fusion framework for PV disaggregation, consisting of three modules: Multi-Scale Time Series Decomposition (MTD), Multi-Feature Fusion (MFF), and Temporal Attention Decomposition (TAD). These modules jointly capture short-term fluctuations, long-term trends, and deep dependencies across multi-source features. Experiments were conducted on real residential datasets from southern China. Results show that, compared with representative baselines such as SGN-Conv and MAT-Conv, the proposed method reduces MAE by over 60% and SAE by nearly 70% for some users, and it achieves more than 45% error reduction in cross-user tests. These findings demonstrate that the proposed approach significantly enhances both accuracy and generalization in PV load disaggregation.

Accurate evaluation of demand response (DR) potential at the individual user level is critical for the effective implementation and optimization of demand response programs. However, existing data-driven methods often suffer from insufficient feature representation, limited characterization of load profile dynamics, and ineffective fusion of heterogeneous features, leading to suboptimal evaluation performance. To address these challenges, this paper proposes a novel demand response potential evaluation method based on multivariate heterogeneous features and a Stacking-based ensemble mechanism. First, multidimensional indicator features are extracted from historical electricity consumption data and external factors (e.g., weather, time-of-use pricing), capturing load shape, variability, and correlation characteristics. Second, to enrich the information space and preserve temporal dynamics, typical daily load profiles are transformed into two-dimensional image features using the Gramian Angular Difference Field (GADF), the Markov Transition Field (MTF), and an Improved Recurrence Plot (IRP), which are then fused into a single RGB image. Third, a differentiated modeling strategy is adopted: scalar indicator features are processed by classical machine learning models (Support Vector Machine, Random Forest, XGBoost), while image features are fed into a deep convolutional neural network (SE-ResNet-20). Finally, a Stacking ensemble learning framework is employed to intelligently integrate the outputs of base learners, with a Decision Tree as the meta-learner, thereby enhancing overall evaluation accuracy and robustness. Experimental results on a real-world dataset demonstrate that the proposed method achieves superior performance compared to individual models and conventional fusion approaches, effectively leveraging both structured indicators and unstructured image representations for high-precision demand response potential evaluation.