Driven by the strategic goals of "dual carbon" and "rural revitalization", and in response to issue such as low rural energy efficiency and a low proportion of clean energy in rural areas, the green transition of rural energy has become an urgent priority. As an effective approach to improve energy utilization efficiency and reduce carbon emissions, the rural integrated energy system has emerged as a current research focus. However, researches on the benefit evaluation of this system remains insufficient. To address this gap, a rural integrated energy evaluation method is proposed based on a variable-weight extension cloud model with combined weighting. Firstly, an evaluation index system covering four dimensions is constructed: rural economy, technology, ecology, and society. Secondly, the improved analytic hierarchy process (AHP) is adopted for subjective weighting to reduce computational complexity, while the anti-entropy method is used for objective weighting. Subsequently, the optimal combined weights are obtained by minimizing the deviation between subjective and objective weights. Finally, the improved extension cloud model is applied to evaluate the index data of the rural integrated energy system, and the adaptive variable weighting of index data is implemented to better highlight the system's shortcomings and advantageous indicators. Taking the data of the demonstration project in Gula Town, Guangxi as an example, the evaluation is conducted. The results show that the method proposed is effective and scientific.

To address the challenges of complex terrain, significant noise interference in wind speed and power data for small-scale distributed wind farms in rural areas, an improved WaveNet prediction algorithm integrating enhanced isolation forest data cleaning and spatiotemporal feature mining is proposed to enhance ultra-short-term power prediction accuracy. Firstly, an enhanced isolation forest （EIF） algorithm is employed for data cleaning. This algorithm incorporates dynamic quantile threshold optimization, path length window smoothing, and a multimodal correction strategy to effectively identify and eliminate anomalous data points. Subsequently, the maximal information coefficient （MIC） is utilized to screen highly correlated input features. A temporal attention mechanism combined with a Transformer module captures critical temporal dependencies, while a spatial attention mechanism integrated with a graph convolutional network （GCN） models spatial correlations among wind turbines for spatiotemporal feature fusion. Next, an ultra-short-term single-turbine power prediction model based on WaveNet architecture is constructed，which accurately captures the dynamic patterns of the fused feature sequence through its dilated convolution and skip connections, and outputs the single-turbine power prediction results. Finally, the total cluster power output is aggregated from single-turbine prediction results by considering the positional weights and spatial correlations of each turbine. A case study is conducted on three-small-turbine distributed wind farms with a single turbine capacity of 10 kW deployed in a certain rural area. The results demonstrate that the proposed method achieves high prediction accuracy.

The rural multi-energy system (RMES) can effectively advance the energy transition in rural areas and holds the potential to enhance economic and environmental benefits. Nevertheless, the existing rural energy systems fail to fully account for the coupled utilization of energy equipment and lack consideration of the impacts of market policies. This paper proposes a low-carbon economic optimization model that takes into account the combined operation of pyrolysis equipment and biogas digesters, the coupling mechanism of carbon emission trading (CET) and green certificate trading (GCT), as well as life-cycle environmental assessment. Firstly, an operation framework of RMES based on the joint operation of pyrolysis devices and biogas digesters is constructed to clarify the coupling relationships among various energy flows and equipments. Secondly, a coupled market trading mechanism integrating carbon and green certificates is introduced to raise the utilization rate of renewable energy via market regulation. Thirdly, a life cycle assessment (LCA) procedure for the system is established with environmental factors taken into consideration, which quantifies carbon emissions and standard pollutant discharges at different stages and incorporates these indicators into the model optimization system. Finally, comparative analysis is conducted through numerical examples under multiple scenarios. The results demonstrate that the proposed method can effectively boost environmental benefits, facilitate the consumption of renewable energy and improve the economic performance of the system.

To address the renewable energy accommodation challenge caused by the large-scale integration of distributed renewable energy into rural distribution networks, a data-knowledge hybrid-driven electricity-hydrogen coordinated dispatch strategy is proposed. Firstly, XGBoost is used to extract key features, which are then input into a BiLSTM model to forecast the hydrogen refueling demand of hydrogen fuel cell vehicles, providing accurate data boundaries for coordinated dispatch. Then, a bi-level rolling optimization framework coupling the power and transportation networks is developed. The upper level establishes an energy hub model considering hydrogen transportation delays to determine the optimal dispatch strategy of the distribution network and the inter-station hydrogen mutual-aid quantities. The lower level constructs a dynamic route planning model based on macroscopic traffic flow to update the optimal hydrogen delivery routes according to county-township road traffic states, and feeds the transportation delay information back to the upper level in real time to trigger rolling dispatch revisions. Comparative results show that the proposed strategy effectively improves the renewable energy accommodation rate of rural distribution networks.

With the large-scale integration of rural renewable energy, such energy sources, influenced by natural conditions, exhibit significant randomness and intermittency. This not only exacerbates power grid fluctuations but may also triggers issues like voltage rise or drop at access points, frequency exceeding limits, and other problems, affecting the normal operation of electrical equipment and the overall power quality of the grid. To address the above challenges, a differentiated coordinated power dispatch strategy for multi-microgrids based on Stackelberg bi-level game theory is proposed.Firstly, a complementary model comprising two types of rural multi-microgrids—high-penetration and medium-penetration—is constructed. By differentially configuring the installed capacity of gas turbines, the power source structure is optimized. Secondly, a hierarchical flexible load regulation mechanism is designed, incorporating shiftable loads, transferable loads, and reducible loads, to enhance system flexibility and provide multi-level regulation means for mitigating power fluctuations. Finally, a "local autonomy-inter-grid mutual support" dispatch strategy is established based on the Stackelberg bi-level game. RT-LAB simulation experiments show that, compared to a single load regulation strategy, the proposed strategy reduces the peak-to-valley difference of renewable energy output by 5.6 %. Compared to a no-inter-grid mutual support strategy, the system operation cost is reduced by 22%. This method provides an effective solution for energy system development under the rural revitalization strategy.

Accurate short-term load forecasting of rural integrated energy systems is of great significance for the safe and stable operation of rural power grids and local renewable energy consumption. However, due to the coupled effects of agricultural production rhythms, sudden weather changes, and other factors, the load of rural integrated energy systems exhibits strong randomness, non-stationarity, and multi-time-scale characteristics, which limit the forecasting accuracy of traditional methods. To address this issue, a short-term load forecasting method is proposed based on the VMD-Informer-BiGRU model. Firstly, a multidimensional feature set including farming periods, ambient temperature, and holidays is constructed to accurately characterize the unique energy consumption patterns in rural areas. Variational mode decomposition (VMD) is then used to decompose the original load sequence into modal components with different frequency characteristics, effectively reducing random fluctuation interference. On this basis, the Informer model is introduced to extract global long-term temporal dependencies, while the bidirectional gated recurrent unit (BiGRU) is employed to capture local mutation features, achieving deep fusion of multi-scale temporal features. Finally, a combined forecasting model is established. Using an actual rural energy consumption scenario in China as the case study, the results show that the proposed model achieves higher forecasting accuracy than other models.

Under the "dual carbon" goals, rural energy systems urgently need to balance the efficient utilization of renewable energy with the coordinated supply of diverse loads. To address the complex multi-energy coupling relationships (electricity, heat, hydrogen, oxygen) in aquaculture scenarios and the significant seasonal fluctuations of renewable energy, a rural energy system coupling model is developed, integrating photovoltaic, hydropower, biomass, grid, and electrolyzer-hydrogen tank-fuel cell, electrochemical energy storage, and byproduct oxygen utilization components. A multi-objective optimization model is established, aiming to minimize comprehensive costs and maximize overall energy utilization efficiency, with constraints on equipment operation and electro-hydrogen-oxygen-heat balance. At the solution level, an improved NSGA-II method incorporating temporal production simulation is proposed to evaluate the hourly operation process over extended time scales. Using a demonstration zone in southern China as a case study, simulations are conducted over a 552-hour period covering all four seasons. Results show that compared to the baseline scenario S0, the proposed method reduces system operation costs by approximately 12%, increases renewable energy utilization from 91.2% to 98.5%, and achieves an overall energy utilization efficiency of 81%. Additionally, it enables seasonal hydrogen regulation, matches electrolyzer byproduct oxygen with nighttime aeration loads, and synergistically provides heating through biomass and waste heat recovery. The results validate the effectiveness and practical applicability of the proposed method in the clean transition of rural energy systems.

As a crucial carrier for supporting the implementation of the "dual carbon" goals and empowering rural revitalization, rural microgrids can effectively enhance overall system operational efficiency by integrating distributed energy with traditional power generation resources. To this end, this paper proposes a optimal operation strategy for source-grid-load-storage in rural microgrids based on an improved twin delayed deep deterministic policy gradient (TD3) algorithm. Firstly, an optimal operation model for rural microgrids incorporating biogas is constructed by comprehensively considering operating costs and renewable energy utilization. Secondly, a compound assessment scored attention-weighted critic(CASA-Critic)is designed to dynamically extract and focus on key state features, thereby enhancing the evaluation accuracy of the value network. Then, a dynamic perception strategy is introduced to adaptively adjust the intensity of action exploration based on the temporal progression and environmental state uncertainties during training, improving the balance between exploration and exploitation. Finally, simulation analysis is conducted based on a typical rural microgrids source-grid-load-storage operation scenario. The results demonstrate that, compared to optimization strategies based on other deep reinforcement learning, the proposed method exhibits better convergence and optimization performance, while also showing significant superiority in improving system operational economy and promoting renewable energy accommodation.

Load capacity and operating life are governed by the hot spot temperature of the transformer windings. A three-dimensional electromagnetic-temperature-fluid coupling model including the shell heat sink is established with an S20-M-630 kVA/10 kV oil-immersed distribution transformer as the research object. Aiming at the problems of complex internal structure of the winding, poor mesh quality of the fluid-solid boundary layer, and low computational efficiency, a winding parameter equivalence method and a hybrid mesh profiling technique combining mapping profilings and free profilings are proposed. The method not only significantly improves the accuracy of the calculation of the winding hot-spot temperature, but also optimises the mesh quality of the fluid-solid boundary layer, which significantly improves the calculation efficiency. The results show that in actual transformer operation, the winding temperature distribution can be effectively reflected by the winding parameter equivalence method, and compared with free profiling, hybrid profiling reduces the overall number of 3D meshes and simulation time by 73.60% and 82.50%. The relative error between the simulated and experimental values of the winding hot-spot temperature shall not exceed 1%.

For the strong electromagnetic pulse(EMP) simulation device using a coaxial Tesla transformer as a pulse driving source, synchronous injection into the Tesla primary winding is an effective way to enhance the output effect, which is of great significance to optimize the performance of the EMP simulation device. In this paper, focusing on the primary injection structure of a typical coaxial-type Tesla transformer, the current distribution and corresponding resistance and inductance parameters of the primary winding under different injection conditions are studied, and the advantages and parameter requirements of multiple injections are analysed. Based on the reverse-polarity capacitor-discharge trigger, the trigger simulation model is established to analyse the influence of loop isolation parameters on the triggering effect, and it is appropriate to use capacitive isolation, and the capacitance value should be much larger than the capacitance value of the switching structure. Multiple injections can significantly reduce the resistance value of the primary winding, improve the uniformity of current distribution, and reduce the inductance of the primary winding, in order to improve the output efficiency and reduce the weight of the magnetic core.

To reduce the operational costs of multi-microgrids and address the issues of optimal configuration and fair cost allocation of shared energy storage, a dual-layer optimization configuration for shared energy storage under time-of-use pricing of the main grid and an improved Shapley value method for fair allocation of shared energy storage are proposed. Firstly, a dual-layer optimization configuration model for shared energy storage in multi-microgrids is established. The upper layer aims to minimize the annual investment and configuration costs of shared energy storage, while the lower layer aims to minimize the operational costs of multi-microgrids incorporating shared energy storage. This model determines the charging/discharging strategy of shared energy storage, the optimized configuration capacity, and the operational costs of multi-microgrids. Secondly, based on the emergent benefits derived from minimizing the operational costs of the multi-microgrids system, a contribution evaluation model is constructed. Finally, an improved Shapley value method based on contribution is applied to allocate the cost savings generated by the shared energy storage configuration. Case simulations demonstrate that this method provides theoretical support for fair cooperation among multi-microgrids, effectively resolves the challenge of equitable cost and benefit allocation during interactions between the main grid and microgrids, and holds practical value for fair collaboration among multi-microgrids.

The key equipment lightweight of the flexible DC converter platform is a crucial problem for achieving economically efficient offshore wind power transmission. Starting from the existing design scheme of bridge arm reactors in the flexible DC converter valve, two lightweight bridge arm reactor schemes, namely the multiplexing and the distributed bridge arm reactor of flexible DC transformer are proposed. The design methods for bridge arm reactor parameters of two lightweight schemes is also elucidated. Based on PSCAD/EMTDDC simulation software, the models of the offshore wind power pseudo-bidirectional flexible DC transmission system based on two lightweight bridge arm reactor schemes are established, separately. And the steady-state and transient characteristics of lightweight bridge arm reactor schemes and the traditional bridge arm reactor schemes are compared and analyzed. The results indicate that after the DC double-pole short-circuit fault occurs, the maximum bridge arm current using two lightweight bridge arm reactor schemes does not exceed 1.2 p.u., and there is no significant drop in sub-module capacitor voltage. Further more, when the converter is locked, it shows that the transformer valve-side voltage of the lightweight bridge arm reactor scheme decreases significantly compared to that of traditional bridge arm reactor schemes.

Currently, the power grid primarily employs a method that combines real-time monitoring with a wildfire trip-out model beneath the transmission lines for trip-out risk assessment. Although this relies on the real-time and reliability of satellite wildfire monitoring, there are still discrepancies between the actual wildfire combustion scenarios and the simulated environment of the trip-out model in some cases. To address the aforementioned issues, a full-process prediction method for transmission lines trip-out probability based on a wildfire spread model is proposed. Firstly, the forest fire spread model is utilized to predict the wildfire combustion state and flame boundary of the real-time monitored fire point, and the spatial position relationship between the transmission lines and the flame is obtained by combining the location information of nearby towers. Secondly, based on meteorological and wildfire spread conditions, the impact of flames and smoke on the insulation of transmission lines is analyzed. Finally, according to the analysis conclusions, the critical conditions for wildfire-induced insulation breakdown of transmission lines under different scenarios are established, and the classification calculation method for the trip-out probability of transmission lines due to wildfires is refined. This scheme combines wildfire spread characteristics with the dynamics of wildfire spread and transmission lines trip-out, addressing the deficiencies in existing wildfire prevention measures such as over-reliance on monitoring methods and discrepancies between actual combustion scenarios and model preset scenarios, thereby further enhancing the power grid's resilience to wildfire disasters.

Coastal cities in China frequently suffer from super typhoon invasions, leading to frequent distribution network failures and significant economic losses due to power outages. To enhance the disaster resilience and power supply reliability of the distribution network, an optimization strategy is proposed based on typhoon forecast data, simulating strong winds and heavy rainfall disasters caused by typhoons, and using Monte Carlo sampling to simulate faults in lines and load nodes. The strategy optimizes the allocation of distributed power sources and limited main grid power resources, prioritizes the power supply to critical loads, and formulates an optimal load shedding scheme to achieve flexible adjustment of resources and load optimization during disasters. Post-disaster, the strategy utilizes distribution network reconfiguration and emergency power vehicle dispatch to reduce economic losses due to power shortages and enhance the utilization rate of renewable energy, optimizing line switch states and the access locations of emergency power vehicles. Simulation analysis is conducted on the IEEE 33 distribution system indicate that this strategy effectively reduces power outage losses during typhoons and expands the power restoration area post-disaster, enhancing restoration performance and emergency response capabilities. The proposed strategy provides an innovative solution for optimal load shedding during typhoon disasters and post-disaster power supply assurance, effectively enhancing the disaster resilience and power supply reliability of urban distribution networks facing extreme disasters.