This paper proposes a resilient and secure configuration for coastal distribution grids by integrating the security constraint unit commitment (SCUC) mobile marine microgrids (MMMGs). In proposed configuration, MMMGs can be connected to in both normal post-disaster operations. It is assumed that SCUC networks include dispatchable (e.g., gas turbines diesel generators) nondispatchable generators photovoltaics wind turbines). The problem consists of realistic formulations seek minimize total...

This paper proposes a new deep learning-based framework for fault detection, classification, and location identification simultaneously in shipboard power systems (SPS). Specifically, three different neural networks based detection methods, including network, gated recurrent unit, long short-term memory, are developed compared to detect faults SPS. The models use realtime line voltages of all SPS buses the entire network. trained tested on simulated data from an 8-bus Results show that...

Shipboard power systems are evolving into sophisticated networks with automated protection and predictive control infrastructure. The need for real-time fault monitoring detection in such can be facilitated by employing deep learning techniques. Taking consideration the characteristic graph nature of network, this paper solves classification problem using convolutional neural networks. proposed methodology translates dynamic voltage measurements at busbars a shipboard network along topology...

Naval shipboard power systems (SPS) are rapidly embracing electrification, resulting in loads that generate pulsation currents and encounter substantial transients. However, conventional time-based features alone inadequate for effectively monitoring safeguarding these against faults. This highlights the critical requirement advanced machine learning based methods to discern differentiate between various transient stages within load profile. In this paper, we propose a Wavelet Graph Neural...

The transition to low-carbon electrical grids has enabled a rapid growth in offshore wind energy. In the meantime, producing green hydrogen from farms also gained wide attention recent years. Among many challenges, energy transferring (especially for those deep water) shoreline infrastructure been explored various ways. this paper, unmanned surface ships are as mobile resources replace pipelines transfer generated water, conjunction with battery electricity transmission. hydrogen/battery...

This paper develops a non-intrusive load monitoring (NILM) method in future shipboard power systems (SPS) using discrete wavelet transform-based convolutional neural networks (CNN). We have applied the proposed NILM to two-zone medium voltage direct current (MVDC) SPS, with multiple appliances each zone such as pulsed load, radar motor and hotel load. The input model only includes signal of generators, which will be first processed by transform, form coefficient matrix that represents status...

The maritime industry, responsible for approximately 3% of global greenhouse gas emissions, is under increasing pressure to decarbonize. Integrated power systems and all-electric ships have emerged as pivotal technologies enhance efficiency reduce emissions. This article investigates the potential small modular reactors (SMRs) zero-emission sources future vessels. It examines SMR technologies, models their integration into shipboard systems, explores dynamic energy management strategies....

The emerging Small Modular Reactor (SMR) technology can potentially provide a reliable source of energy for All-Electric Ships (AES) with reduced greenhouse gas emissions. successful drive the electric propulsion systems in SMR-based AES needs high maneuverability supply power, which is however constrained by physical and safety limits SMR. SMR may not be able to precisely match supply/demand on its own, especially during rapid load changes such as pulse loads. An effective solution leverage...

The concept of ship-to-grid has been explored in recent years, which allows electric ships to supply a part power demand the terrestrial grid during normal operations or extreme conditions under disruptive events. While this could potentially enhance resiliency events, interconnected may pose certain threats special equipment on shipboard system. To better evaluate dynamic feasibility interconnection, paper investigates use DC-link for safely integrating medium voltage AC (MVAC) ship grid....

In this paper, a new configuration security framework is developed for reliability and resiliency improvement of distribution networks by the coordination security-constraint unit commitment (SCUC) mobile marine power sources (MMPSs) under both post-disaster normal restoration operations. It assumed that MMPS contains non-dispatchable distributed generators (DGs), e.g., photovoltaics (PV), as well dispatchable DGs, gas turbines diesel generators. A mixed-integer linear programming model...

Abstract While preventive maintenance is crucial in wind turbine operation, conventional condition monitoring systems face limitations terms of cost and complexity when compared to innovative signal processing techniques artificial intelligence. In this paper, a cascading deep learning framework proposed for the generator winding conditions, specifically promptly detect identify inter-turn short circuit faults estimate their severity real time. This encompasses high-resolution current...

Abstract Flourished wind energy market pushes latest turbines (WTs) to further and harsher inland offshore environment. Increased operation maintenance cost calls for more reliable effective condition monitoring systems. In this paper, a bi-level framework inter-turn short circuit faults (ITSCFs) in WT generators is proposed. A benchmark dataset, consisting of 75 ITSCF scenarios generator current signals specific WT, has been created made publicly available on Zenodo. The data simulated at...

<p>In this study, a non-intrusive load monitoring (NILM) framework is developed for next generation shipboard power systems (SPS) based on discrete wavelet transform and convolutional neural network (CNN). We have applied the NILM method to four-zone medium voltage direct current (MVDC) SPS evaluate effectiveness of proposed method. Each zone MVDC consists multiple components, such as propulsion load, pulsed high ramp rate cooling hotel load. The signals from main generators are inputs...

The integration of different energy carriers is a key factor to improve the network performance. A micro-energy hub (μEH) concept has recently been proposed in integrated electricity and natural gas distribution systems (IENGDSs), for generating, converting, storing, managing types at customer level. To performance μEH, this paper proposes hierarchical optimization-based model optimize sizes μEH components locations μEHs IENGDS. operation structural sizing constraints are first determined....

<p>In this study, a non-intrusive load monitoring (NILM) framework is developed for next generation shipboard power systems (SPS) based on discrete wavelet transform (DWT) and convolutional neural network (CNN). We have applied the NILM method to four-zone medium voltage direct current (MVDC) SPS evaluate effectiveness of proposed method. Each zone MVDC consists multiple components, such as propulsion load, pulsed high ramp rate cooling hotel load. The signals from main generators are...

<p>In this study, a non-intrusive load monitoring (NILM) framework is developed for next generation shipboard power systems (SPS) based on discrete wavelet transform (DWT) and convolutional neural network (CNN). We have applied the NILM method to four-zone medium voltage direct current (MVDC) SPS evaluate effectiveness of proposed method. Each zone MVDC consists multiple components, such as propulsion load, pulsed high ramp rate cooling hotel load. The signals from main generators are...

This paper presents a thermal-electrical model for all-electric ships with small modular reactors as the prime mover. The impact of cooling system on propulsion motor and generator's performance has been investigated. study emphasizes importance considering system's design operation in ship's energy system. shows that neglecting effect may cause temperature rise up to 4°C degrees an overload generator by 5 % less than 10 seconds. activation pumps leads slight drop voltage, which can overall...

<p>In this study, a non-intrusive load monitoring (NILM) framework is developed for next generation shipboard power systems (SPS) based on discrete wavelet transform and convolutional neural network (CNN). We have applied the NILM method to four-zone medium voltage direct current (MVDC) SPS evaluate effectiveness of proposed method. Each zone MVDC consists multiple components, such as propulsion load, pulsed high ramp rate cooling hotel load. The signals from main generators are inputs...