Explore the vast range of titles available.

In order to deal with the problems of complex optimisation model and computing speed in the multi‐objective operation control of the power distribution network, this paper is oriented to the basic model and process of the feeder partition decoupling method for the distribution network. Firstly, the necessity of developing partition decoupling for the distribution network is expounded according to the development status and control mode of the complex distribution network. Secondly, the objective models commonly used in the distribution network optimisation control are given to illustrate the importance of partition decoupling for the complex distribution network, including line loss and voltage offset. Finally, three general decoupling equivalent models are presented, namely Ward equivalent model, virtual generator equivalent model, and radial equivalent independent model, and then the partition decoupling equivalent process is proposed. This research focusses on the model and basic process of the partition decoupling method for the complex distribution network with DG, which provides the foundation for the distributed parallel optimal power flow.

In this study, a partition optimisation method for distribution network is proposed to realise decoupling coordination, which provides a research basis for optimising power flow and operation regulation. Firstly, a partition model of distribution network is established, in which the electrical distance, parallel computing efficiency, and operation stability indexes are considered at the same time; Secondly, the AHC algorithm is used to realise the automatic search partition of the distribution network, and the class spacing measurement factors of point‐to‐point, cluster‐to‐cluster are considered in this method. Finally, the Distributed Sequential Quadratic Programming for Distributed Generation (DSQP‐DG) is introduced, and the parallel decoupling coordination of the distribution network is realised by alternate iteration of its inner and outer layers. In this paper, a partition decoupling method of distribution network is proposed, which provides a research basis for the subsequent optimal power flow calculation and distributed operation control of distribution network. Two research directions are focussed, that is, the distribution network partition method based on AHC and the sub‐region decoupling coordination based on DSQP.

Generating air-conditioning system load data is crucial for tasks such as power grid scheduling and intelligent energy management. Air-conditioning load data exhibit strong non-stationarity. Their load curves are influenced by seasonal variations and highly correlated with outdoor meteorological conditions, indoor activity patterns, and equipment operational strategies. These characteristics lead to pronounced periodicity, sudden shifts, and diverse data patterns. Existing load generation models tend to produce averaged distributions, which often leads to the loss of specific temporal patterns inherent in air-conditioning loads. Moreover, as purely data-driven models, they lack explicit physical constraints, resulting in generated data with limited physical interpretability. To address these issues, this paper proposes a hybrid generation framework that integrates the DTW clustering algorithm, a physically-constrained TimeGAN model, and an LSTM-based model selection mechanism. Specifically, DTW clustering is first employed to achieve structured data partitioning, thereby enhancing the model’s ability to recognize and model diverse temporal patterns. Subsequently, to overcome the dependency on detailed building parameters and extensive sensor networks, a parameter-free physical constraint mechanism based on intrinsic temperature-load correlations is incorporated into the TimeGAN supervised loss. This design ensures thermodynamic consistency even in sensor-scarce environments where only basic operational data is available. Finally, to address adaptability challenges in long-term sequence generation, an LSTM-based selection mechanism is designed to evaluate and select from clustered submodels dynamically. This approach facilitates adaptive temporal fusion within the generation strategy. Extensive experiments on air-conditioning load datasets from Southeast China demonstrate that the framework achieves a local similarity score of 0.98, outperforming the state-of-the-art model and the original TimeGAN by 11.4% and 13.3%, respectively.

In new distribution systems with high penetration of renewable energy, inverter-based sources exhibit significant differences in fault characteristics compared to traditional power sources due to the absence of a constant electromotive force and their operation under nonlinear control links, rendering conventional fault current calculation methods inadequate. To address these challenges, a full-time-domain analysis-based method for modelling and calculating fault transient characteristics is proposed. First, a dynamic model of inverter-based sources accounting for current loop saturation effects is established, and phase plane analysis is employed to resolve nonlinear control regions. On this basis, a full-time-domain fault current calculation method is proposed, wherein the steady-state operating point after a fault is determined by iteratively solving the network node voltage equations. By integrating control strategies and derived transient differential equations, the fault current expression across the full-time-domain scope is formulated. Furthermore, a multi-objective optimization control strategy is proposed to achieve effective fault current suppression, and an improved Simulated Annealing-Particle Swarm Optimization (SA-IPSO) hybrid algorithm is adopted for efficient solution. Finally, SIMULINK-based simulation experiments validate the accuracy and effectiveness of the proposed method in transient characteristic analysis and current suppression.

Modern active distribution networks are increasingly characterized by high complexity, uncertainty, and distributed clustering, posing challenges for traditional model-based simulations in capturing nonlinear dynamics and stochastic variations. This study develops a data–model hybrid-driven simulation architecture that integrates a Federated Evolutionary Monte Carlo Optimization (FEMCO) algorithm for distribution network optimization. The model-driven module employs spectral clustering to decompose the network into multiple autonomous subsystems and performs distributed reconstruction through gradient descent. The data-driven module, built upon Long Short-Term Memory (LSTM) networks, learns temporal dependencies between load curves and operational parameters to enhance predictive accuracy. These two modules are fused via a Random Forest ensemble, while FEMCO jointly leverages Monte Carlo global sampling, Federated Learning-based distributed training, and Genetic Algorithm-driven evolutionary optimization. Simulation studies on the IEEE 33 bus distribution system demonstrate that the proposed framework reduces power losses by 25–45% and voltage deviations by 75–85% compared with conventional Genetic Algorithm and Monte Carlo approaches. The results confirm that the proposed hybrid architecture effectively improves convergence stability, optimization precision, and adaptability, providing a scalable solution for the intelligent operation and distributed control of modern power distribution systems.

Aiming at the insufficient capture of temporal dependence and weak coupling of external factors in multivariate load forecasting, this paper proposes a Transformer model integrating timestamp-based positional embedding and convolution-augmented attention. The model enhances temporal modeling capability through timestamp-based positional embedding, optimizes local contextual representation via convolution-augmented attention, and achieves deep fusion of load data with external factors such as temperature, humidity, and electricity price. Experiments based on the 2018 full-year load dataset for a German region show that the proposed model outperforms single-factor and multi-factor LSTMs in both short-term (24 h) and long-term (cross-month) forecasting. The research results verify the model’s accuracy and stability in multivariate load forecasting, providing technical support for smart grid load dispatching.

In this paper, a neural network model called Long Short-Term Temporal Convolutional Network (LST-TCN) model is proposed for short-term load forecasting. This model refers to the 1-D fully convolution network, causal convolution, and void convolution structure. In the convolution layer, a residual connection layer is added. Additionally, the model makes use of two networks to extract features from long-term data and periodic short-term data, respectively, and fuses the two features to calculate the final predicted value. Long Short-Term Memory (LSTM) and Temporal Convolutional Network (TCN) are used as comparison algorithms to train and forecast 3 h, 6 h, 12 h, 24 h, and 48 h ahead of daily electricity load together with LST-TCN. Three different performance metrics, including pinball loss, root mean squared error (RMSE), and mean absolute error (RASE), were used to evaluate the performance of the proposed algorithms. The results of the test set proved that LST-TCN has better generalization effects and smaller prediction errors. The algorithm has a pinball loss of 1.2453 for 3 h ahead forecast and a pinball loss of 1.4885 for 48 h ahead forecast. Generally speaking, LST-TCN has better performance than LSTM, TCN, and other algorithms.

As distributed generators (DGs) and flexible adjustable loads (FALs) further penetrate distribution networks (DNs), to reduce regulation complexity compared with traditional centralized control frameworks, DGs and FALs in DNs should be packed in several clusters to enable their dispatch to become standard in the industry. To mitigate the negative influence of DGs’ and FALs’ spatiotemporal distribution and uncertain output characteristics on dispatch, this paper proposes an intelligent dynamic cluster partitioning strategy for DNs, from which the DN’s resources and loads can be intelligently aggregated, organized, and regulated in a dynamic and optimal way with relatively high implementation efficiency. An environmental model based on the Markov decision process (MDP) technique is first developed for DN cluster partitioning, in which a continuous state space, a discrete action space, and a dispatching performance-oriented reward are designed. Then, a novel random forest Q-learning network (RF-QN) is developed to implement dynamic cluster partitioning by interacting with the proposed environmental model, from which the generalization and robust capability to estimate the Q-function can be improved by taking advantage of combining deep learning and decision trees. Finally, a modified IEEE-33-node system is adopted to verify the effectiveness of the proposed intelligent dynamic cluster partitioning and regulation strategy; the results also indicate that the proposed RF-QN is superior to the traditional deep Q-learning (DQN) model in terms of renewable energy accommodation rate, training efficiency, and portioning and regulation performance.

The large-scale integration of Distributed Generators (DGs) has significantly altered fault characteristics in distribution networks, posing challenges to conventional fault location methods. To address these limitations, this paper presents a novel approach that combines dynamic cluster partitioning with the arithmetic optimization algorithm (AOA). The proposed method first divides the network into autonomous clusters based on electrical coupling, facilitating preliminary fault area identification. Subsequently, the AOA optimizes fault section identification through current matching analysis. Using MATLAB simulations on an IEEE 33-node system with various DG types and fault scenarios, the method demonstrates superior accuracy and faster convergence compared to traditional approaches. Results confirm its effectiveness in improving fault location performance for modern distribution networks with high DG penetration.

Fleet electrification is increasingly recognized as a cornerstone of urban decarbonization in high-density megacities. This study introduces a multi-scenario simulation framework integrating high-resolution mobile signaling data with traffic modeling to quantify the systemic environmental and energy impacts of road-based battery electric vehicle (BEV) integration in Shanghai. By evaluating both a fixed-fleet baseline and dynamic-fleet growth scenarios focused on the urban road network, we find that aggressive fleet electrification leads to a profound reduction in aggregate carbon emissions and criteria pollutants, effectively decoupling transit-related environmental burdens from urban growth. However, results also highlight a significant energy trade-off: while fossil fuel displacement accelerates, grid-based electricity demand increases under fleet growth conditions. Within this context, the expanded vehicle population exacerbates urban congestion, which disproportionately inflates the fuel consumption of remaining internal combustion vehicles. Their operational efficiency is severely compromised by frequent stop-and-go cycles, leading to an intensification of idling losses. Ultimately, this research highlights the capability of the proposed simulation framework to provide granular insights into urban emission dynamics, offering a quantitative foundation for policymakers to harmonize electrification targets with proactive traffic management and grid infrastructure strengthening to evaluate the systemic trade-offs toward achieving long-term urban sustainability.