With the increasing penetration of renewable energy generation, grid-forming (GFM) converters that simulate the dynamics of synchronous generator (SG) and actively participate in grid voltage and frequency regulation are increasingly employed. In GFM converter dominated power system, similar transient synchronization stability that is common in conventional power system also exists, which is closely related with the control dynamics of GFM converters. In this paper, the transient synchronization stability of GFM converters with virtual synchronous generator (VSG) control is focused on, with the influence of transient switched operation mode (TSOM) introduced by current saturation limitation considered especially. First, a novel transient equivalent motion model of VSG is developed. The model is a switched system and TSOM significantly changes the power angle characteristics. Based on power angle curve analysis and equal area method, the transient stability analysis is carried out from non-existence of equilibrium point and non-matching of accelerating-decelerating area. Analysis indicates that TSOM imposes another constraint to equilibrium point and reduces deceleration area, which worsens the transient stability. Further, employing the stability region theory of nonlinear dynamic systems, the stability region of VSG is visually displayed in phase plane. It is identified that the TSOM reduces the stability region and worsens the stability. Finally, the influence factors including power reference, grid voltage sag and grid impedance are discussed.

Renewable energy hydrogen production technology is an effective way to improve the utilization of renewable energy and alleviate the problem of wind and light abandonment. However, there are many challenges in the system structure design and “Source-Load-Storage” coordination control strategy for large-scale, megawatt-scale renewable energy hydrogen production. In this paper, a hybrid wind-solar-energy storage hydrogen production system based on Medium Voltage Direct Current (MVDC) structure is proposed. HOMER software is used to plan and study the storage capacity to achieve long-term power balance and matching of the system. In addition, A decentralized coordinated control energy management system with active power following and state of charge (SOC) recovery capability is proposed and implemented for transient power regulation. An electromagnetic transient simulation was established in PSCAD/EMTDC, and semi-physical experiments were designed using StarSim to verify the effectiveness of the control strategy. Theoretical analysis and experiments show that the island MVDC network with decentralized coordinated control has technical feasibility in realizing hydrogen production from renewable energy in the 20MW level class. In addition, the power consumed by the load can realize the seconds level tracking of the output power of renewable energy.

In recent years, with the development of ship intelligence and unmanned technology, autonomous path planning of unmanned surface vehicle (USV) has become very important. However, most of the existing studies ignore the limitation of the endurance and speed of USV to voyage, and only consider the course planning at the fixed speed. To this end, we propose a path planning method based on deep reinforcement learning (DRL): Firstly, we establish a USV motion model. Then, we propose a new USV energy consumption model. Existing research typically builds USV energy consumption model by considering the combined effects of currents, winds, and waves, which needs precise ocean data and involves a complex modeling process. Moreover, it fail to account for the influence of USV’s own speed on energy consumption. In contrast, based on the relationship between speed, marine environment, and propulsion load, we propose a new USV energy consumption model. This model simplifies the modeling process and links USV energy consumption with sailing speed and ocean environmental conditions. Next, the original Soft-Actor-Critic (SAC) algorithm use the Multi-Layer Perceptron (MLP) as the action network. However, Convolutional Neural Networks (CNN) excel in capturing spatial and local features. Compared to MLP, CNN have stronger information acquisition capabilities. Therefore, we propose a model (FRCF) that combines fully connected layers with CNN to replace MLP as the action network of the SAC agent, aiming to enhance the agent’s convergence speed and performance. Finally, utilizing SAC with FRCF as the action network (SAC-FRCF), along with the motion models and the new USV energy consumption model, we achieved multi-objective cooperative intelligent path planning for energy, speed, and heading. Unlike traditional path planning methods that control the USV heading based on discrete heading angular, we adjust USV speed and heading based on continuous acceleration and angular velocity. Meanwhile, we impose constraints on the USV’s speed, heading angle, acceleration, and angular velocity to ensure that its motion complies with kinematic constraints. Experimental results show that SAC-FRCF reduces the exploration time by 46.40% and has stronger convergence performance as well as better path planning effect compared with SAC algorithm using MLP as action network (SAC-MLP). Compared with SAC-MLP without considering the optimal energy consumption, it reduces the energy consumption by 28.38%. The experimental results verify the effectiveness and superiority of the proposed method. Furthermore, the method we propose exhibits significant advantages over traditional path planning methods. In addition, our proposed method demonstrates significant superiority compared to existing path planning methods, and its robustness and adaptability also have been verified in a more complex environment.

The existing data-driven methods for the state of health (SOH) prediction of lithium-ion battery are limited by the data quantity, resulting in insufficient generalization performance, prediction accuracy and prediction stability. To tackle this challenge, this paper proposes a novel model, namely the CNN-MMHA, for SOH prediction. The CNN-MMHA incorporates mask mechanisms and multi-head attention mechanisms (MHA) to effectively capture the interdependencies within time series data (i.e. MMHA). Simultaneously, the utilization of the data conversion module and convolutional neural network (CNN) enables the capture of temporal sequences and local characteristics of battery states, accordingly enhancing the predictive ability of MMHA. In this study, This paper execute a sequence of simulation experiments on NASA and CALCE data sets, where this paper compare the performance of a variety of models: Multilayer Perceptron (MLP), Long Short-Term Memory Network (LSTM), CNN, CNN-LSTM, MMHA, and CNN-MMHA respectively. The results demonstrate that the proposed model yields optimal convergence and generalization performance. Furthermore, it has the utmost prediction accuracy and stability. Ultimately, the exceptional performance and real-world applicability of the proposed model are corroborated through its experiments on the real battery.

In the context of harsh emission control and ecological environment protection, the shipping industry is transforming and upgrading towards greening, decarburization, and electrification. Battery-powered all-electric inland ships have been attracting increasingly attention. However, its initial investment cost is much more expensive than a traditional diesel-driven mechanical ship because lithium-ion batteries are currently expensive. Hence, a suitable battery size and efficient energy management strategy for ship sailing are very important for a battery-powered ship. In this paper, a novel joint optimization method of the sailing speed and battery capacity, which considers the interaction between battery size and sailing speed as well as multiple operation factors, such as freight demand and battery life, and port electricity price, is proposed to fully exploit the battery-powered ships’ application potential. Moreover, a joint optimization model of the sailing speed and battery energy consumption model considers the battery-powered ship’s characteristics and waterway characteristics. Next, a solution algorithm for the proposed joint optimization model is established to achieve joint decision-making regarding the sailing speed and battery size. Finally, case studies are conducted to demonstrate the flexibility and effectiveness of the proposed method. The results show that the proposed method can obtain the optimal sailing speed and the corresponding battery capacity synchronously when the actual transportation scenario is fixed. Moreover, the battery initial investment cost can be effectively reduced with the prosed method.

When a fault occurs, driven by the reconfiguration strategy, the topology of ship power system (SPS) will be changed to isolate the fault area and restore the lost load. However, traditional optimization methods have limitations, such as getting stuck in suboptimal solutions or not offering real-time solutions. This paper proposes a novel deep reinforcement learning (DRL) method to address the dynamic fault reconfiguration problem in real-time for SPS. While considering the load priorities, the fault reconfiguration model is formulated with the goal of the maximum weighted load power and the minimum switching action. Then, a deep Q network (DQN) combined with action mask mechanism, what is called DQN-Mask algorithm, is applied to optimize the switch action. The proposed method enables end-to-end control from the fault node data to the switch sequences, and has migration capability in different scenarios. Two case studies are analyzed based on historical fault datasets of medium voltage DC (MVDC) SPS. The numerical results verify the effectiveness, real-time performance, migration and scalability of the proposed DQN-Mask algorithm.