A new energy management framework for multi-microgrid (MMG) systems composed of high renewable energy sources (RES) is proposed in this paper. In traditional energy management system (EMS), battery energy storage system (BESS) is only considered in a single microgrid (MG) optimization model, which leads to underutilization of storage devices and waste of resources. Considering the advantages of local consumption of RES, this paper develops a hierarchical multi-agent energy management strategy. A two-step model aiming at maximizing the usage of RES is established to help determine the strategy. In the first step, the strategy is developed to maximize the local consumption of RES based on the demand response programs (DRP) and BESS within the independent MG. In the second step, the community BESS and BESSs are used to share the RES of multiple MGs for increasing the utilization ratio of RES. Simultaneously, the output of each controllable distributed generator (CDG) and the transaction with power grid are determined through a distributed adjustable power generation plan query library (DGPS). Moreover, the simulation with a three-MG system proves that the strategy can effectively increase the utilization ratio of RES and reduce the transaction with power grid compared to the traditional strategy.

To increase the output voltage stability and improve the operating efficiency of proton exchange membrane fuel cells (PEMFCs), a data-driven cooperative method for controlling the PEMFC output voltage is proposed in this paper. The proposed method adapts centralized learning and decentralized implementation, which can nonlinearly and adaptively realize optimal coordinated control over the hydrogen valve and the DC/DC converter. Additionally, a champion multiagent double delay deep deterministic policy gradient (CMA-4DPG) algorithm is proposed in this method, the design of which incorporates the policies of the champion selection mechanism, cooperative exploration, imitation learning guidance and curriculum guidance to improve the robustness of the cooperative method. The method cooperates with multiple controller to prevent output voltage fluctuation. The experimental results show that by simultaneously regulating the hydrogen flow through the hydrogen valve and the duty ratio of the DC/DC converter, the proposed method achieves better robustness and can improve the tracking performance of the PEMFC output voltage.

This study aims to overcome the complication that deep learning-based pattern recognition in partial discharge (PD) diagnosis of gas-insulated switchgear (GIS) can only identify single-source partial discharge but not multi-source partial discharge. Specifically, a GIS multi-source partial discharge detection algorithm based on Deep Convolution Generative Adversarial Networks and You Only Look Once (DCGAN-YOLOv5) is proposed. First, the Phase Resolved Partial Discharge (PRPD) features of multi-source PD are analyzed, a GIS experiment platform is established, and four typical PD defects are simulated. Besides, sample data are collected, and the DCGAN network is used for sample expansion. Then, a YOLOv5 network model is designed, and a spatial and channel attention mechanism is added to the feature extraction network with a positive sample equilibrium strategy. Finally, the effectiveness of the proposed algorithm is verified using laboratory data and field data collected from a 220 kV substation. The experimental results demonstrate that the proposed algorithm can effectively detect the multi-source PD features in PRPD patterns under complex noise and thus successfully identify the types of multi-source PD. The mean Average Precision (mAP) can reach 98.4%. The precision of single-source PD and multi-source PD can reach 95.2% and 89.3%, when testing with field data.

This paper introduces a new rural microgrid model, including residents and agricultural greenhouses. Based on the new model framework, the precise energy scheduling of a rural microgrid is realized by means of load classification and load forecasting. Moreover, we also adopt a new energy-storage mode, cloud energy storage (CES), as the shared energy-storage unit of rural microgrid, and analyze the service and operation mechanism of CES in detail. The shared storage characteristic and adjustable storage capacity of CES are helpful for the precise management of power dispatching. At the same time, in order to accurately implement energy scheduling, we fully consider the load characteristics of rural areas and divide the load into residential load and agricultural load. Then the extreme gradient boosting (XGBoost) algorithm is used to predict the short-term power consumption of the two types of load respectively, which can effectively alleviate the uncertainty of load power consumption and improve the accuracy of scheduling. Finally, an illustrative example of rural energy scheduling is given. The example studies the impact of energy-storage capacity on the cost of the scheduling scheme, and designs a power-dispatching scheme based on load forecasting, which accurately solves the energy charging and discharging planning and grid energy trading planning.

In wind farms, the energy storage system can realize the time and space transfer of energy, alleviate the intermittency of renewable energy and enhance the flexibility of the system. However, the high cost limits its large‐scale application. Cloud energy storage (CES) can provide users with leasing energy storage service at a relatively lower price, and can provide energy trading service. Wind farms can lease CES and participate in energy transaction to reduce the cost of energy storage and suppress wind power fluctuations. This paper proposes a framework of wind farm system based on CES service, and designs a power allocation strategy. Considering whole‐life‐cycle cost of the self‐built energy storage, leasing and trading cost of the CES and penalty cost of wind abandonment and smooth power shortage, an optimal configuration model of combined energy storage capacity in wind farms based on CES service was established to minimize the total annual cost. Taking a wind farm in Germany as a case study, it is verified that the model in this paper can effectively reduce the cost, extend the service life of self‐built energy storage equipment and suppress the wind power fluctuations.

This paper proposes a microgrid optimal scheduling strategy based on the reactive power compensation of electric vehicles to address the issue of interactive fluctuation of voltage and power resulting from a high proportion of new energy integration into the grid. Firstly, for accurate prediction of electric vehicle charging and discharging behavior, the Monte Carlo simulation method was employed for day-ahead prediction. Secondly, an optimization method for reactive power compensation was developed, considering distributed sources such as wind turbines, photovoltaics, and electric vehicles, with the objective of minimizing network loss and power generation costs. Additionally, user-side prices and electric vehicle charging prices were taken into consideration. Finally, utilizing the IEEE14 bus simulation, a comparison was made between the microgrid with and without electric vehicle reactive support capacity. Results demonstrated that, while maintaining a power factor greater than 0.95, the proposed method reduced the average daily generation cost by 0.35%, average daily network loss by 7.0%, average daily bus voltage fluctuation by 48.60%, average electricity price by 2.88%, and EV user charging cost by 21.29%. These findings illustrate that the proposed reactive power compensation optimization method effectively mitigates voltage and power fluctuations resulting from new energy integration, ensuring system safety, reliability, and economic efficiency.