The absence of electricity is among the gravest problems preventing a nation’s development. Hybrid renewable energy systems (HRES) play a vital role to reducing this issue. The major goal of this study is to use the non-dominated sorting genetic algorithm (NSGA)-II and hybrid optimization of multiple energy resources (HOMER) Pro Software to reduce the net present cost (NPC), cost of energy (COE), and CO₂ emissions of proposed power system. Five cases have been considered to understand the optimal HRES system for Kutubdia Island in Bangladesh and analyzed the technical viability and economic potential of this system. To demonstrate the efficacy of the suggested strategy, the best case outcomes from the two approaches are compared. The study’s optimal solution is also subjected to a sensitivity analysis to take into account fluctuations in the annual wind speed, solar radiation, and fuel costs. According to the data, the optimized PV/Wind/Battery/DG system (USD 711,943) has a lower NPC than the other cases. The NPC obtained by the NSGA-II technique is 2.69% lower than that of the HOMER-based system.

This study explores Bangladesh’s present energy condition, renewable energy (RE) possibilities and designs an optimal 100% RE-based off-grid power system for St. Martin’s Island, Bangladesh. The optimal size of a hybrid renewable microgrid based on photovoltaic (PV) cells, a battery energy storage system (BESS), fuel cells (FC), and an electrolysis plant (EP) is proposed. Advanced direct load control (ADLC) and rooftop PV meet the energy demand at the lowest cost, and profits are maximized by selling chemical products produced by seawater electrolysis. Four cases are explored with the mixed-integer linear programming (MILP) optimization technique using MATLAB® software to demonstrate the efficacy of the suggested power system. The system cost in case 1 is lower than in the other cases, but there is no chance of profiting. Cases 2, 3, and 4 have greater installation costs, which may be repaid in 8.17, 7.72, and 8.01 years, respectively, by the profits. Though the revenue in case 3 is 6.23% higher than in case 2 and and 3.85% higher than in case 4, case 4 is considered the most reliable power system, as it can meet the energy demand at the lowest cost while increasing profits and not putting a burden on customers.

Federated learning (FL) makes it possible to train models across distributed data sources without collecting raw data in one place. However, even in federated settings, trained models may still leak sensitive information at inference time. This problem is particularly evident for Gaussian Process regression (GPR), where predictive uncertainty is explicitly returned and can differ between training and non-training samples. Such differences can be exploited for membership inference. In this work, we examine inference-time privacy and robustness in federated GPR by focusing on the behavior of predictive variance. To enable scalable training, we employ a Random Fourier Feature approximation together with an Alternating Direction Method of Multipliers (ADMM) based distributed optimization scheme. On top of this learning framework, we apply key-dependent orthogonal feature transformations that enable multi-key inference time access control. When inference is performed using the correct key, prediction accuracy and uncertainty behavior remain close to those of plaintext federated GPR. When incorrect or mismatched keys are used, prediction errors increase sharply and predictive variance becomes uniformly large. Experimental results show that this variance inflation removes the usual gap between training and unseen samples, reducing the effectiveness of variance-based membership inference. Importantly, this effect arises without adding noise or relying on cryptographic operations. These findings suggest that predictive uncertainty can play a practical role in enforcing inference-time access control and improving privacy robustness in federated Gaussian Process models.

As artificial intelligence (AI) systems become increasingly embedded in sensitive domains such as healthcare and finance, they face heightened vulnerabilities to privacy threats. A prominent type of attack against AI is the membership inference attack (MIA), which aims to determine whether specific data instances were used in a model’s training set, thereby posing a serious risk of sensitive information disclosure. This study focuses on Gaussian Process (GP) models, which are widely adopted for their probabilistic interpretability and ability to quantify predictive uncertainty, and examines their susceptibility to MIAs. To mitigate this threat, a novel defense mechanism based on Random Unitary Transformation (RUT) is introduced, which encrypts training and testing inputs using orthonormal matrices. Unlike Differential Privacy-based Gaussian Processes (DP-GPR), which rely on noise injection and often degrade model performance, the proposed method preserves both the structural integrity and predictive fidelity of the GP model without injecting noise into the learning process. Two configurations are evaluated: i) encryption applied to both training and test data, and ii) encryption applied only to training data. Experimental results on a medical dataset demonstrate that the framework significantly reduces the effectiveness of MIAs while maintaining high predictive accuracy. Comparative analysis with DP-GPR models further confirms that the proposed method achieves competitive or stronger privacy protection with less impact on model utility. These findings underscore the potential of structure-preserving transformations as a practical and effective alternative to noise-based privacy mechanisms in GP models, particularly in privacy-critical machine learning applications.