Wanxing Sheng

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.

This paper addresses voltage fluctuation issues in distribution networks under high penetration of renewable energy. It proposes a collaborative voltage regulation method for multi-microgrid systems considering operational economy. To mitigate voltage violations and fluctuations caused by intermittent distributed generation such as photovoltaics, this paper develops a bi-level coordinated optimization framework with bidirectional feedback. At the upper level, the distribution network acts as the global regulator, suppressing voltage fluctuations by optimizing the active power output of microgrids while dynamically issuing voltage constraints and power exchange boundaries. At the lower level, each microgrid serves as a local response agent. While complying with the regulation requirements from the upper level, it coordinates its internal distributed resources, including PV, energy storage, and electric vehicles, and optimizes electricity market purchases to minimize its own operating cost. The framework moves beyond traditional one-way command models, achieving bidirectional coordination between global optimization and local autonomy. Simulations based on a modified IEEE 33-bus system show that the proposed method maintains all node voltages within the allowable range, significantly reduces voltage fluctuations, and lowers the total electricity purchase cost of the microgrids by approximately 11%, thereby enhancing both voltage stability and economic efficiency of the system.

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.

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.

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.

Digitalized distribution substation areas constructed with intelligent transformer terminals can realize various advanced application scenarios using IoT technology, which provides a new perspective for fault diagnosis problem solving in power distribution systems. This paper briefly introduces the principle of fault diagnosis based on a digitalized substation area. Then, we propose a fault diagnosis effectiveness evaluation index system containing first priority qualification indices, second priority performance indices, and an index weight calculation method based on the hierarchical analysis method and improved entropy weight method. Through a fuzzy comprehensive evaluation method, a comprehensive evaluation of the fault diagnosis effectiveness is carried out. At the end of this article, the effectiveness of the proposed evaluation method and index system is verified through example analysis.

Digitalized distribution substation area that constructed with intelligent transformer terminal could realize various advanced application scenarios by the use of IoT technology, which provides a new perspective for the fault diagnosis problem solving in power distribution system. This paper briefly introduces the principle of fault diagnosis based on digitalized substation area. Then propose a fault diagnosis effectiveness evaluation index system containing the first priority qualification index and the second priority performance index, and its index weight calculation method based on hierarchical analysis method and improved entropy weight method. And through the fuzzy comprehensive evaluation method, the comprehensive evaluation of the fault diagnosis effectiveness is carried out. At the end of this article, the effectiveness of the proposed evaluation method and index system is verified through example analysis.

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.