Search Results (105)

Photovoltaic (PV) systems are key renewable energy sources due to their ease of implementation, scalability, and global solar availability. Enhancing their lifespan and performance is vital for wider adoption. Identifying degradation root causes is essential for improving PV design and maintenance, thus extending lifespan. This paper proposes a hybrid fault diagnosis method combining a bond graph-based PV cell model with empirical degradation models to simulate faults, and a deep learning approach for root-cause detection. The experimentally validated model simulates degradation effects on measurable variables (voltage, current, ambient, and cell temperatures). The resulting dataset trains an Optimized Feed-Forward Neural Network (OFFNN), achieving 75.43% accuracy in multi-class classification, which effectively identifies degradation processes. Full article

Accurate topological connectivity is critical for the safe operation and management of low-voltage distribution grids (LVDGs). However, due to the complexity of the structure and the lack of measurement equipment, obtaining and maintaining these topological connections has become a challenge. This paper proposes a topology identification strategy for LVDGs based on a feature-enhanced graph attention network (F-GAT). First, the topology of the LVDG is represented as a graph structure using measurement data collected from intelligent terminals, with a feature matrix encoding the basic information of each entity. Secondly, the meta-path form of the heterogeneous graph is designed according to the connection characteristics of the LVDG, and the walking sequence is enhanced using a heterogeneous skip-gram model to obtain an embedded representation of the structural characteristics of each node. Then, the F-GAT model is used to learn potential association patterns and structural information in the graph topology, achieving a joint low-dimensional representation of electrical attributes and graph semantics. Finally, case studies on five urban LVDGs in the Wuhan region are conducted to validate the effectiveness and practicality of the proposed F-GAT model. Full article

To enhance the adaptability of grid partitioning under transient scenarios, this paper proposes a two-stage dynamic partitioning strategy based on structure–function coupling. Electrical coupling strength is first characterized using short-circuit impedance and the sensitivity between reactive power and voltage, while transient voltage correlation is incorporated through cosine similarity as edge weights in a graph model. Grid partitioning is then conducted by maximizing modularity through a staged approach that ensures network connectivity and automatically determines partition numbers. Case studies on the modified IEEE 39-bus system demonstrate that compared with transient voltage-based partitioning and conventional complex network methods, the proposed approach improves modularity by 69%, reduces the maximum post-fault voltage deviation by 38.6%, and achieves the highest regional decoupling rate. The result shows strong intra-regional cohesion and weak inter-regional connectivity, verifying the strategy’s effectiveness in enhancing adaptability and decoupling under transient conditions. Full article

Wire electrical discharge machining (WEDM) enables the production of complex parts with tight tolerances, although maintaining dimensional accuracy in corners and tapers remains challenging due to wire deflection and vibration. This study optimizes WEDM parameters for achieving high accuracy in machining complex geometrical parts and taper cuts in 6061 aluminum alloy using an Excetek W350G WEDM machine with a copper wire electrode. Parameters including wire tension, pulse on-time, pulse off-time, wire feed rate, open circuit voltage, and flushing pressure were varied using a L18 Taguchi orthogonal array and the response graph method to identify optimal cutting conditions. Experimental results indicated that feature-specific optimization is crucial, as different geometrical features (rectangular fins, triangular fins, gears) exhibited varying critical parameters. Key findings highlighted the importance of wire tension and pulse on-time in maintaining cutting accuracy, although at varying levels for specific features. Response graphs demonstrated the effects of major WEDM parameters on corner and profile accuracies, whereas Taguchi analysis provided the optimum settings of parameters for each feature and taper cutting. These findings will help enhance precision, efficiency, and versatility of the WEDM process in machining complex profiles and corners, contributing to precision manufacturing. Full article

The quantity of wind and photovoltaic power-based distributed generators (DGs) is continually rising within the distribution network, presenting obstacles to its safe, steady, and cost-effective functioning. Active distribution network dynamic reconfiguration (ADNDR) improves the consumption rate of renewable energy, reduces line losses, and optimizes voltage quality by optimizing the distribution network structure. Despite being formulated as a highly dimensional and combinatorial nonconvex stochastic programming task, conventional model-based solvers often suffer from computational inefficiency and approximation errors, whereas population-based search methods frequently exhibit premature convergence to suboptimal solutions. Moreover, when dealing with high-dimensional ADNDR problems, these algorithms often face modeling difficulties due to their large scale. Deep reinforcement learning algorithms can effectively solve the problems above. Therefore, by combining the graph attention network (GAT) with the deep deterministic policy gradient (DDPG) algorithm, a method based on the graph attention network deep deterministic policy gradient (GATDDPG) algorithm is proposed to online solve the ADNDR problem with the uncertain outputs of DGs and loads. Firstly, considering the uncertainty in distributed power generation outputs and loads, a nonlinear stochastic optimization mathematical model for ADNDR is constructed. Secondly, to mitigate the dimensionality of the decision space in ADNDR, a cyclic topology encoding mechanism is implemented, which leverages graph-theoretic principles to reformulate the grid infrastructure as an adaptive structural mapping characterized by time-varying node–edge interactions Furthermore, the GATDDPG method proposed in this paper is used to solve the ADNDR problem. The GAT is employed to extract characteristics pertaining to the distribution network state, while the DDPG serves the purpose of enhancing the process of reconfiguration decision-making. This collaboration aims to ensure the safe, stable, and cost-effective operation of the distribution network. Finally, we verified the effectiveness of our method using an enhanced IEEE 33-bus power system model. The outcomes of the simulations demonstrate its capacity to significantly enhance the economic performance and stability of the distribution network, thereby affirming the proposed method’s effectiveness in this study. Full article

Traditional proportional–integral–derivative (PID) controllers are often utilized in industrial control applications due to their simplicity and ease of implementation. This study presents a novel control strategy that integrates the Groupers and Moray Eels Optimization (GMEO) algorithm with a Dual-Stream Multi-Dependency Graph Neural Network (DMGNN) to optimize PID controller parameters. The approach addresses key challenges such as system nonlinearity, dynamic adaptation to fluctuating conditions, and maintaining robust performance. In the proposed framework, the GMEO technique is employed to optimize the PID gain values, while the DMGNN model forecasts system behavior and enables localized adjustments to the PID parameters based on feedback. This dynamic tuning mechanism enables the controller to adapt effectively to changes in input voltage and load variations, thereby enhancing system accuracy, responsiveness, and overall performance. The proposed strategy is assessed and contrasted with existing strategies on the MATLAB platform. The proposed system achieves a significantly reduced settling time of 100 ms, ensuring rapid response and stability under varying load conditions. Additionally, it minimizes overshoot to 1.5% and reduces the steady-state error to just 0.005 V, demonstrating superior accuracy and efficiency compared to existing methods. These improvements demonstrate the system’s ability to deliver optimal performance while effectively adapting to dynamic environments, showcasing its superiority over existing techniques. Full article

In this study, electrically conductive polymer composites based on repellent N,N-diethyl-3-methylbenzamide with concentrations ranging from 6 to 30 wt% were developed. The electrical resistivity of repellent composites, as determined by electrochemical impedance spectra, ranges from 150 to 171 Ohm, which allows such materials to be used when a low voltage is applied. The study of the rheological properties of the obtained repellent composites and the analysis of the TGA curves demonstrated that the dynamic viscosity of the materials has a significant effect on the thermal diffusion of the repellent. The study of the thermal diffusion of N,N-diethyl-3-methylbenzamide demonstrated that a higher yield of repellent (up to 36.4 × 10⁻⁸ mol) is achieved when the material is applied in the form with the shortest conductor length of 14 mm. The graphs showing the relationship between the electrical flux and the concentration of N,N-diethyl-3-methylbenzamide, which was calculated via the Peltier and Thompson equations, show that, according to Onsager’s theory, the total flux of the substance is highest when a voltage is applied to the material with the shortest conductor length. Thus, the developed repellent composite is a promising material for protection against blood-sucking insects. Full article

As the last link of power transmission, the safe operation of the distribution network directly affects the experience of power users, and short-time distribution network faults can cause huge economic losses. There are few fault recording devices in rural or suburban distribution networks, and it is difficult to upload information, which brings difficulties to accurate fault location. In order to improve the accuracy of fault location, this study proposes a fault location method for distribution networks based on electric field-coupled voltage sensing and multi-source information fusion. First, an optimized resource pool architecture is proposed, and a distribution network data fusion platform is established based on this architecture to effectively integrate voltage, current and other fault data. Second, in order to overcome the problem of expanding the fault location range that may be caused by the current-based matrix algorithm, this study proposes an improved directed graph-based matrix algorithm and combines it with the matrix algorithm of voltage quantities to form a joint location criterion, which improves the accuracy of fault location. Finally, for the single-ended ranging method, which is easily affected by the wave impedance discontinuity points in the system or the transition resistance in the line, this article introduces a fault ranging algorithm based on double-ended electrical quantities, which improves the accuracy and applicable range of fault ranging. Through simulation verification, we found that the matrix algorithm based on the electrical quantity can accurately locate the fault section in the case of a single fault with a single power supply. The proposed joint matrix algorithm can accurately locate the fault section in the case of a single fault with multiple power sources. The ranging algorithm based on double-ended electrical quantities has higher ranging accuracy in both interphase short circuits and grounded short circuits, and the ranging results are not affected by the fault type, fault location and transition resistance, which can effectively improve the efficiency and reliability of fault location. Full article

Power system stability prediction leveraging deep learning has gained significant attention due to the extensive deployment of phasor measurement units. However, most existing methods focus on predicting either transient or voltage stability independently. In real-world scenarios, these two types of instability often co-occur, necessitating distinct and coordinated control strategies. This paper presents a novel concurrent prediction framework for transient and voltage stability using a spatio-temporal embedding graph neural network (STEGNN). The proposed framework utilizes a graph neural network to extract topological features of the power system from adjacency matrices and temporal data graphs. In contrast, a temporal convolutional network captures the system’s dynamic behavior over time. A weighted loss function is introduced during training to enhance the model’s ability to handle instability cases. Experimental validation on the IEEE 118-bus system demonstrates the superiority of the proposed method compared to single stability prediction approaches. The STEGNN model is further evaluated for its prediction efficiency and robustness to measurement noise. Moreover, results highlight the model’s strong transfer learning capability, successfully transferring knowledge from an N-1 contingency dataset to an N-2 contingency dataset. Full article

With increasing power system complexity and distributed energy penetration, traditional voltage control methods struggle with dynamic changes and complex conditions. While existing deep reinforcement learning (DRL) methods have advanced grid control, challenges persist in leveraging topological features and ensuring computational efficiency. To address these issues, this paper proposes a DRL method combining Graph Convolutional Networks (GCNs) and soft actor-critic (SAC) for voltage control through load shedding. The method uses GCNs to extract higher-order topological features of the power grid, enhancing the state representation capability, while the SAC optimizes the load shedding strategy in continuous action space, dynamically adjusting the control scheme to balance load shedding costs and voltage stability. Results from the simulation of the IEEE 39-bus system indicate that the proposed method significantly reduces the amount of load shedding, improves voltage recovery levels, and demonstrates strong control performance and robustness when dealing with complex disturbances and topological changes. This study provides an innovative solution to voltage control problems in smart grids. Full article

Predicting the cooling capacity of converter valves is crucial for maintaining the stability and efficiency of high-voltage direct current (HVDC) systems. This task involves handling complex, multi-dimensional time-series data with strong inter-variable dependencies and temporal dynamics. Traditional machine learning methods, while effective in static scenarios, struggle to capture these dependencies, and existing deep learning models often lack the ability to jointly model spatial and temporal relationships. To address these challenges, we propose a novel framework that integrates Graph Neural Networks (GNNs) with temporal dynamics. The GNN component captures spatial dependencies by representing the data as a graph, where nodes correspond to system variables, and edges encode their relationships. Temporal dependencies are modeled using temporal convolutional layers and recurrent neural networks (RNNs), enabling the framework to learn both short-term variations and long-term trends. Additionally, a graph attention mechanism dynamically adjusts the importance of variable relationships, improving prediction accuracy and interoperability. The proposed method demonstrates superior performance over traditional machine learning and deep learning baselines on real-world cooling system data. These results validate the effectiveness of the framework for industrial applications such as cooling system monitoring and predictive maintenance. Full article

The study established that the application of graph theory enables the creation of a model of a country’s power system structure in the form of a tiered graph. This allows complex structural elements of the system, such as generating units, electrical substations, and power transmission lines, to be represented as nodes and edges in simulation models that can be used for analysis, dispatch control, and optimization of system operation. A simulation model of the unified power system has been developed to analyze operational efficiency and performance under various planned disturbance scenarios. To solve the given task, it is necessary to develop a model of the power system in the form of a tiered graph, where the nodes are generating equipment stations, transmission system substations with voltages from 330 kV to 750 kV, and distribution system substations with voltages from 110 kV to 220 kV, and the edges are power transmission lines with voltages from 110 kV to 750 kV. The model takes into account the generated and transmitted power, the nominal capacity and the number of transformers at the substations, the cross-section and maximum throughput of the power transmission lines, which made it possible to determine complex interconnections between its nodes and integrate the equipment into a unified power system for efficiency and performance analysis. Full article

To address the issues arising from the integration of a high proportion of distributed generation (DG) into the distribution network, which has led to the transition from traditional single-source to multi-source distribution systems, resulting in increased complexity of the distribution network topology and difficulties in fault localization, this paper proposes a fault localization method based on graph convolutional networks (GCNs) for distribution networks with a high proportion of distributed generation. By abstracting busbars and lines into graph structure nodes and edges, GCN captures spatial coupling relationships between nodes, using key electrical quantities such as node voltage magnitude, current magnitude, power, and phase angle as input features to construct a fault localization model. A multi-type fault dataset is generated using the Matpower toolbox, and model training is evaluated using K-fold cross-validation. The training process is optimized through early stopping mechanisms and learning rate scheduling. Simulations are conducted based on the IEEE 33-node distribution network benchmark, with photovoltaic generation, wind generation, and energy storage systems connected at specific nodes, validating the model’s fault localization capability under various fault types (single-phase ground fault, phase-to-phase short circuit, and line open circuit). Experimental results demonstrate that the proposed model can effectively locate fault nodes in complex distribution networks with high DG integration, achieving an accuracy of 98.5% and an AUC value of 0.9997. It still shows strong robustness in noisy environments and is significantly higher than convolutional neural networks and other methods in terms of model localization accuracy, training time, F1 score, AUC value, and single fault detection inference time, which has good potential for practical application. Full article

Digital-twin platforms are increasingly adopted in energy infrastructure management for smart grids. Novel opportunities arise from emerging artificial intelligence technologies to increase user trust by enhancing predictive and prescriptive analytics capabilities and by improving user interaction paradigms. This paper presents a novel data-driven and knowledge-based energy digital-twin framework and architecture. Data integration and mining based on machine learning are integrated into a knowledge graph annotating asset status data, prediction outcomes, and background domain knowledge in order to support a retrieval-augmented generation approach, which enhances a conversational virtual assistant based on a large language model to provide user decision support in asset management and maintenance. Components of the proposed architecture have been mapped to commercial-off-the-shelf tools to implement a prototype framework, exploited in a case study on the management of a section of the high-voltage energy infrastructure in central Italy. Full article

Accurate identification of network topology and line parameters is essential for effective management of distribution systems. An innovative joint estimation method for distribution network topology and line parameters is presented, utilizing a power flow graph convolutional network (PFGCN). This approach addresses the limitations of traditional methods that rely on costly voltage phase angle measurements. The node correlation principle is applied to construct a node correlation matrix, and a minimum distance iteration algorithm is proposed to generate candidate topologies, which serve as graph inputs for the parameter estimation model. Based on the topological dependencies and convolutional properties of AC power flow equations, a PFGCN model is designed for line parameter estimation. Parameter refinement is achieved through an alternating iterative process of pseudo-trend calculation and neural network training. Training convergence and loss function values are used as feedback to filter and validate candidate topologies, enabling precise joint estimation of both topologies and parameters. The proposed method’s accuracy, transferability, and robustness are demonstrated through experiments on the IEEE-33 and modified IEEE-69 distribution systems. Multiple metrics, including MAPE, IAE, MAE, and R², highlight the proposed method’s advantages over Adaptive Ridge Regression (ARR). In the C33 scenario, the proposed method achieves MAPEs of 4.6% for g and 5.7% for b, outperforming the ARR method with MAPEs of 7.1% and 7.9%, respectively. Similarly, in the IC69 scenario, the proposed method records MAPEs of 3.0% for g and 5.9% for b, surpassing the ARR method’s 5.1% and 8.3%. Full article