ABSTRACT Addressing the issues of limited endurance and load capacity in unmanned aerial vehicle (UAV) inspection of distribution networks, the lack of dynamic adaptability in charging networks and insufficient multi‐objective collaborative optimisation, this paper proposes a four‐dimensional collaborative system architecture consisting of ‘digital twin‐UAV‐charging facility‐communication network’. It clarifies the essential differences between digital twins and traditional simulation/data‐driven platforms and constructs a full‐element, high‐fidelity, closed‐loop iterative digital twin operation mechanism. This architecture achieves precise replication and trend prediction of inspection scenarios, equipment status and grid operation through full‐element modelling of digital twins, real‐time synchronisation between virtual and real worlds, and dynamic deduction. On this basis, a multi‐objective optimisation model is constructed with the goals of minimising the total life cycle cost of the charging network, minimising the waiting time for UAV charging, and minimising the operational fluctuations in the distribution network. A dynamic weight coefficient is introduced to coordinate the objectives and achieve balance. An innovative approach is proposed to integrate digital twin deduction with an improved nondominated sorting genetic algorithm (DT‐NSGA‐II). This method enhances solution efficiency and convergence accuracy through heuristic population initialisation driven by twin data, adaptive genetic operations involving virtual–real interaction, and population optimisation strategies based on closed‐loop feedback. Additionally, the computational complexity and convergence properties of the algorithm are analysed. A digital twin simulation verification is conducted using a 120‐km 2 complex terrain distribution network in East China as a case study, and cross‐validation is performed with actual distribution network operation and maintenance data. The results show that the robustness and adaptability of the proposed method are improved by 40% (quantified based on multi‐objective optimisation standard evaluation metrics) compared to traditional methods in complex scenarios. This provides an engineering paradigm for the precise configuration and dynamic optimisation of UAV intelligent inspection and charging networks in distribution networks.

This article proposes a functional design scheme for a new virtual power plant terminal measurement and control device to meet the demand of the real-time spot market. This device integrates functions such as data acquisition, communication, control, and management, aiming to improve virtual power plants’ operational efficiency and responsiveness in real-time spot markets. The research focused on exploring the device’s functional requirements and hardware and software design and verified its performance through simulation. The results indicate that the device can effectively support virtual power plants in real-time spot market transactions, providing technical support for the power system’s stable operation and market-oriented reform.

This paper proposes a power grid information attack identification method based on a combination of maximum relevance minimum redundancy and XGBoost to address the problem of accurately identifying attack types based on changes in measurement data after the smart grid is subjected to information attacks. Firstly, by using the K-means-smote oversampling method, the measurement data containing attack samples is balanced and preprocessed to solve the problem of imbalanced attack samples. Secondly, utilizing the Maximum Relevance Minimum Redundancy feature selection method, the optimal subset of representation features for information attack events is extracted, reducing data dimensionality and improving the recognition efficiency of information attacks. Then, establish an XGBoost classifier to classify and recognize three types of attack states and normal states, and evaluate the recognition performance of the model using indicators such as accuracy and recall. Finally, experimental validation demonstrates that the developed cyber-threat detection framework achieves marked enhancement in identification precision for adversarial interventions in smart grid networks, while maintaining robust generalization capabilities across varied attack scenarios.

A optimization strategy based on an improved deep Q-network (DQN) is proposed to address the configuration issue of unmanned aerial vehicle inspection and charging system. Firstly, a model of unmanned aerial vehicle (UAV) inspection and charging system is constructed, taking into account factors such as UAV power consumption, inspection task priority, and charging facility layout. On the basis of traditional DQN algorithm, dual Q-learning is introduced to reduce the problem of Q-value overestimation, and a priority experience replay mechanism is adopted to improve sample utilization efficiency. Through simulation experiments in different scenarios, the results show that the improved DQN algorithm can effectively optimize the configuration of unmanned aerial vehicle inspection and charging systems, improve the completion rate of inspection tasks, and reduce charging costs. Compared with traditional algorithms, it has better performance and provides effective technical support for practical engineering applications.

With the continuous expansion of Photovoltaic power plants, drone inspection has become an important means to ensure their efficient operation. It is crucial to optimize the trajectory of drones in complex and special scenarios to improve inspection efficiency and accuracy. This article proposes an improved method for optimizing the trajectory of unmanned aerial vehicles (UAVs) in special scenarios of photovoltaic power plants based on the A algorithm. By improving the traditional A algorithm, it can better adapt to the special environmental requirements of photovoltaic power plants, effectively reduce the length of UAV flight paths, and improve inspection coverage.

With the widespread application of drone technology in the field of inspection, the reasonable configuration of charging networks has become the key to improving inspection efficiency and coverage. This article proposes a charging network optimization configuration method based on multi energy collaboration for unmanned aerial vehicle inspection tasks in complex environments. Considering various forms of energy such as photovoltaic power generation, wind power generation, and grid access, an optimization model is constructed with the goal of minimizing the construction cost, operating cost, and energy consumption cost of charging facilities for unmanned aerial vehicles. By introducing an improved particle swarm optimization algorithm to solve the model, the collaborative optimization of site selection, capacity configuration, and energy allocation of various charging facilities in the charging network can be achieved. The case analysis results show that the proposed method can effectively reduce the total system cost, improve the reliability and energy utilization efficiency of the charging network, and provide a scientific basis for the planning and design of unmanned aerial vehicle inspection of the charging network.

To address the structural parsing challenge of multi-type entities and complex hierarchical relationships in power grid fault handling plan, this paper proposes an intelligent parsing method for power grid dispatch fault handling plan based on knowledge graph technology. First, we establish a knowledge unit tagging system for fault handling plan, which generates standardized definitions for entity types and attribute features. Subsequently, we propose a Domain Knowledge-enhanced Universal Information Extraction (DK-UIE) framework to train the mapping relationships between fault handling plan entities and their labels in high-dimensional space. Following the logical association rules of dispatch fault handling plan, we construct a structured knowledge graph for power grid dispatch fault handling management. Furthermore, an application scheme for entity information recognition in power grid dispatch fault handling plan is developed based on the knowledge graph. Validation using data from a dispatch control center demonstrates that the proposed knowledge extraction model achieves average precision, recall, and F1-scores of 97.50%, 96.62%, and 97.05% respectively, showing superior recognition accuracy compared with existing methods. The constructed knowledge graph effectively supports risk identification in power grid dispatch fault handling.

Abstract With the rapid construction and development of photovoltaic power plants, unmanned operation and maintenance has emerged as a trend and direction in the industry. Addressing the characteristics and needs of photovoltaic power plants in specific scenarios, this study proposes research on an applicable intelligent flight control system and implements it through system design. The research primarily encompasses the information fusion technology and decision-making methods of unmanned aerial vehicles in complex photovoltaic power plant environments. Additionally, it innovatively explores path planning and obstacle avoidance, high-precision motion control, and multi-machine collaborative work methods of unmanned aerial vehicles in complex environments. The research findings possess universal applicability and can provide guidance and inspiration for similar research projects.

This article explores the key technologies and research of unmanned aerial vehicles in intelligent operation and maintenance of new energy power plants in special scenarios. With the rapid development of new energy power plants, traditional operation and maintenance methods face many challenges in complex terrain and harsh environments. Drone technology, with its flexibility and efficiency, provides new solutions for the operation and maintenance of new energy power plants. This study focuses on analyzing the application advantages of drones in special scenarios, exploring relevant key technologies, and verifying their effectiveness through case studies. The research results indicate that drone technology can significantly improve the efficiency and safety of new energy power plant operation and maintenance, providing important references for the development of future smart operation and maintenance systems.

The modern new power system presents characteristics of large scale, wide range, and high technical requirements, and the power grid dispatch and command system urgently needs to be improved based on these characteristics. On the basis of analyzing the problems existing in traditional power grid dispatch and command systems, a functional design and implementation of a power grid dispatch and command system are proposed based on artificial intelligence technology innovation. The system integrates the electric energy management system, the protection signal substation system, the dispatch and operation management system, the power grid equipment asset management system, the weather system, and other professional systems. Combined with the needs of power grid dispatch and command, it effectively realizes the full process collaborative management of power grid situation awareness, intelligent coordination and handling, and on-site operation collaboration, which can significantly improve the efficiency of power grid dispatch and command and the level of safe operation of the power grid. This system technology has universal applicability and has promotion and application value in similar power grids.

This study describes a power grid construction site surveillance system that includes wireless power transmission and an improved Yolo V3 detection model. An artificial intelligence and wireless power transfer methodology is employed used for continuous monitoring. Improved Yolo V3 detection is optimized using Hierarchical Particle Swarm Optimization (HPSO) for enhanced efficacy in detecting power grid development threats. The methodology is compared to existing methods in terms of precision, accuracy, recall, and speed. The findings indicate that the proposed method is achieved a real-time and accurate power grid development site monitoring. Experiments on test sets in various situations improved the detection accuracy, and indicate that the proposed technique is quite robust. Also the detection accuracy and speed of the proposed method have improved over existing approaches, indicate that the strategy provides superior detection efficacy. This method considerably improves risk source detection, that's critical for assuring safety on power grid building sites.

With the development of a green and low-carbon economy, distributed renewable generation (DRG) is growing rapidly, with obvious advantages and disadvantages. DRG has characteristics such as volatility, randomness, and uncontrollability, which may have an impact and adverse impact on the safe operation of the power grid. If it can accurately predict and grasp its power generation law, it has significant significance for improving the safe operation of the power grid. This article innovatively proposes a K-means based DRG typical output mode analysis method. The method first collects the DRG output of two regions over a long period of time, uses isolated forest algorithm to normalize and fuse the collected data, and uses K-MEANS method to cluster the processed data. Finally, 16 representative output modes of these regions are obtained, These models can be used to guide the output prediction and analysis of corresponding types of weather days. The example analysis shows that this method is generally effective and has good robustness, and can be used to guide the analysis of DRG output patterns in similar regions.

Microgrid has been extensively applied in the modern power system as a supplementary mode for the distributed energy resources. The microgrid with wind energy is usually vulnerable to the intermittence and uncertainty of the wind energy. To increase the robustness of the microgrid, the energy storage system (ESS) is necessary to compensate the power imbalance between the power supply and the load. To further maximize the economic efficiency of the system, the system level control for the microgrid is desired to be optimized when it is integrated with the utility grid. Aiming at the aforementioned problem, this paper comprehensively analyzes the power flow of a typical loop microgrid. A transformer-based wind power prediction (WPP) algorithm is proposed and compared with recurrent neural networks algorithm. With the historical weather data, it can accurately predict the 24 h average wind energy. Based on the predicted wind energy and the time-of-use (TOU) electricity price, a day-ahead daily cycling profile of the ESS with particle swarm optimization algorithm is introduced. It comprehensively considers the system capacity constraints and the battery degree of health. The functionality of the proposed energy management strategy is validated from three levels. First, WPP is conducted with the proposed algorithm and the true historical weather data. It has validated the accuracy of the transformer algorithm in prediction of the hourly level wind energy. Second, with the predicted wind energy, a case study is given to validate the day-ahead daily cycling profile. A typical 1 MVA microgrid is utilized as the simulation model to validate performance of the daily cycling optimization algorithm. The case study results show that the ESS daily cycling can effectively reduce the daily energy expense and help to shave the peak power demand in the grid.

Hydrogen energy has clean and low-carbon properties, and has enormous potential for application in multiple industries. It is an important strategic choice for achieving low-carbon energy transformation. The mainstream technologies for hydrogen to electricity conversion include three main forms, both domestically and internationally, namely hydrogen fuel cell power generation, hydrogen mixed with gas power generation and coal-ammonia co-firing power generation. Firstly, it was provided that a detailed analysis of the basic principles and mainstream technology routes of various hydrogen power generation technologies. Furthermore, the current development status of important technical parameters at home and abroad has been clarified through comparison. Finally, summarized the demonstration and application of hydrogen power generation technology domestically and internationally. These studies can provide technical references for the application and development of hydrogen power generation in China.

With the incredible and fast development of a low-carbon economy, the power supply of China's power system is rapidly shifting towards renewable energy sources, which also poses certain challenges to the use and consumption of new energy.The article analyzes some daily-seasonal-spatial deviation cas

The new power system requires corresponding production simulation analysis. Through analysis, the power timing production simulation system will become a necessary choice. By analyzing the characteristics of large-scale integration of new energy into the new power system, this paper proposes the application scenarios and main classification features of power sequence production simulation. In response to the requirements, a large-scale power sequence production simulation system is innovatively proposed, and its theoretical basis, algorithm implementation, and solution are analyzed one by one. Finally, the effectiveness of this method has been demonstrated through engineering application practice. The research results have universal applicability and can provide guidance and inspiration for similar research projects.

For protective relay vendors, traditionally, before evaluating the performance of new protection algorithms, it was necessary to develop the corresponding hardware and generate various electrical signals in different operating scenarios, such as voltage and current signals at protection terminals under fault conditions, through techniques including electromagnetic transient programs. This was done to test and improve protection algorithms and devices. This method was time-consuming, labor-intensive, costly, and constrained by testing equipment, such as protective relay test sets and real-time digital simulator, making it a cumbersome and inconvenient process. This paper proposes a simulation-based method for the development of protection devices, and is applied to the development of localized distribution line protection device development. This method simulates the localized protective relays deployed in distribution lines using software tools such as PSCAD, and then verifies and improves the accuracy of the software simulation model by comparing it with the performance of actual devices. Once the accuracy of the simulation model is validated, for the development of new protection principles, simulation based on the protection principles can be performed first, and then the electrical fault signals generated by electromagnetic transient simulation software can be used to verify and improve the new protection principles. With this method, there is no need to produce hardware in the early stages of developing new protection principles and devices when the principles are not yet mature. Instead, thorough accurate modeling, improvement and the formation of mature solutions can be accomplished, reducing device development costs and improving development efficiency.

Wind power is one of the main forms of renewable energy generation. Safe operation of wind farms is of significant importance to the reliable operation of modern electrical systems. China has successively established multiple large-scale wind power bases in regions such as Inner Mongolia, Hebei, and southeastern coastal areas. The protection of collector lines in wind farms commonly employs traditional overcurrent element. However, with this method, a fault at any point along the collector lines could result in the entire line being disconnected, resulting in the interruption of renewable energy absorption, power outage for un-faulted areas and long outage recovery duration. This paper analyzes the characteristics of collector line faults, and then proposes a new collector line protection scheme based on localized protection principle. Electromagnetic transient program is used to verify the effectiveness of the proposed protection scheme.

With the expansion of the scale of the power grid, the types and quantities of new equipment put into operation continue to increase. It is necessary to develop an intelligent, standardized and universal operation management system to meet the development needs of the large power grid and ensure safe and stable operation objectives. Therefore, a smart grid new equipment startup management system is proposed. The intelligent dispatching platform adopts the B/S architecture system, intelligently obtains various data, analyzes the operation types of new equipment startup and the characteristics of the startup scheme, intelligently forms the new equipment startup operation scheme, and completes the preparation, review and verification functions through the system, thus building an intelligent management system for the startup of new equipment in the power grid. The practice shows that the system can significantly reduce the workload of operators, improve the risk control level of new equipment startup, and play an important role in ensuring the safe and stable operation of the power system.

With the expansion of the installed capacity of offshore wind power, its impact on the safe operation of the power grid is increasingly obvious, and improving the prediction accuracy of offshore wind power power has become a key problem to be solved in the industry. The improvement of prediction accuracy, on the one hand, can facilitate the operation control of power grid, on the other hand, can also significantly improve the economic benefits of wind power plants. Based on power downscaling and deep learning methods, this paper carries out localized short-term and ultra-short-term power prediction modeling and optimization technologies for coastal offshore wind power. Comprehensive statistical prediction method, artificial intelligence prediction method, multi-model integration method and other combined prediction model, multi-source fusion information, to realize the refined prediction of Zhejiang offshore wind power, and improve the overall prediction accuracy. The research method is generally applicable and can guide the output prediction of the same type of offshore wind power.