https://www.um.edu.mt/library/oar/handle/123456789/16863 2026-08-11T19:56:02Z https://www.um.edu.mt/library/oar/handle/123456789/148468 Title: A spectral clustering method for dividing power grid regions considering inertia distribution Authors: Wang, Mingzhi; Wang, Xuan; Xiao, Zhaoxia; Zhang, Yifan; Fang, Hongwei; Li, Guangdi; Xiong, Junjie; Micallef, Alexander Abstract: With the large-scale integration of high proportion renewable energy into the power grid, the total inertia of the grid has been decreasing year by year, and the inertia distribution of each bus in different regions is uneven. This paper proposes a power system regional partitioning method based on spectral clustering, considering the characteristics of inertia distribution. Firstly, based on the distribution and inertia of synchronous generators in the grid, a node admittance matrix that can calculate the shortest electrical distance is employed; Then, based on the inertia differences of each generator and the shortest electrical distance matrix between them, a normalized Laplacian matrix is constructed using spectral clustering algorithm; Finally, the optimal partitioning of power grid is calculated using the triple index constraints of Calinski Harabasz index, silhouette coefficient, and Davidson index. The simulation results verify the correctness and effectiveness of the proposed method by IEEE 39 node case. 2026-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/148466 Title: Source-load joint prediction method based on iTransformer-LSTM for port microgrid Authors: Xiao, Zhaoxia; Zhang, Yifan; Wang, Xuan; Zhou, Weihao; Fang, Hongwei; Li, Guangdi; Xiong, Junjie; Micallef, Alexander Abstract: The green transformation of ports has led to the construction of a high proportion of renewable energy port microgrids becoming a key path for port decarbonization. High precision prediction of ship shore power load and high endowment renewable energy is an important prerequisite for achieving low-carbon economic operation of port microgrids. Therefore, this paper considers the “source tracing load” coupling characteristics of port microgrids and proposes a source-load joint prediction method based on inverted Transformer (iTransformer) and long short-term memory (LSTM) for port microgrids. Firstly, grey relationship analysis is used to analyse the coupling characteristics between sources and loads in port microgrids, as well as their correlation with influencing factors, in order to achieve feature dimensionality reduction. Secondly, using iTransformer for important features differentiation extraction, and utilizing self-attention mechanism to effectively capture multidimensional features dependency relationships. Finally, LSTM is used for nonlinear dynamic modeling of time series, and the weights of different prediction tasks are adaptively balanced through a multidimensional output gating mechanism to output the source-load joint prediction results. Verified by the actual operational data of Hukou Port Area in Jiujiang, Jiangxi Province, the results show that the proposed source-load joint prediction model can reduce the prediction errors of various prediction tasks and has higher prediction accuracy compared to existing mainstream models. 2026-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/148465 Title: An integrated analysis of bibliographic trends with AIS-based vessel operational data for the evaluation of alternative fuels Authors: Sadiq, Muhammad; Apap, Maurice; Licari, John; Caruana, Cedric; Su, Chun-Lien; Lin, Tzu-Chiao; Micallef, Alexander Abstract: The transition to low and zero-carbon fuels is essential for reducing emissions from shipping. This paper develops a combined framework to evaluate hydrogen and ammonia as alternatives to marine diesel oil by linking bibliographic research trends with vessel-level operational data. A bibliographic review of 1,174 publications published between 2000 and 2025 identifies clusters related to safety, performance, and infrastructure, with increasing activity influenced by international decarbonization policies. To complement this analysis, automatic identification system (AIS) data are used from two representative vessels: a high-speed ferry completing 2,265 annual trips and a deep-sea container ship with multiple long-haul voyages. The operational data are processed to reconstruct propulsion energy demand and compare fuel requirements in terms of mass, volume, and range. The results show hydrogen is more suitable for shortsea operations, while ammonia proves more practical for longhaul shipping. 2026-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/148036 Title: Hybrid Swin vision transformer with IMFCC for enhanced underwater acoustic noise reduction Authors: Ashok, P.; Tran, Tien Anh; Srithar, A.; Manimala, G. Abstract: Underwater wireless communication is essential for deep-sea exploration, environmental monitoring, and Autonomous Underwater Vehicle (AUV) coordination. Its performance is severely affected by ambient noise, multipath propagation, reverberation, and non-stationary interference, which degrade acoustic signal quality. Existing noise reduction techniques, such as Wiener filtering, spectral subtraction, and wavelet denoising, struggle to adapt to rapidly changing underwater conditions. Centralized Deep Learning (DL) based enhancement models are also unsuitable for distributed Underwater Wireless Sensor Networks (UWSNs) due to privacy, bandwidth, and real-time constraints. To overcome these challenges, this work proposes a Federated Learning–Driven Hybrid Swin Vision Transformer with Improved MFCCs (Fed-SVTIMFCC) for intelligent underwater acoustic noise reduction. Federated learning enables multiple underwater nodes to collaboratively train a denoising model without sharing raw acoustic data, ensuring data privacy and adaptability. The Swin Vision Transformer (SVT) captures local spectral cues and long-range dependencies to enhance reconstruction, while IMFCCs provide robust features for distinguishing noise from useful signals. Experimental results on real underwater datasets demonstrate significant improvements in SNR (26.94 dB), PSNR (33.28 dB), and SSIM (0.947), establishing Fed-SVT-IMFCC as a powerful solution for next-generation underwater communication systems. 2026-01-01T00:00:00Z