International Journal of communication and computer Technologies

Exploring Challenges and Solutions for Seamless Integration in IoT-Enabled Smart Factory Systems

Dahlan Abdullah — 2025-02-03

The challenges and possible solutions of the smooth and efficient use of Internet of Things (IoT) technologies within smart factory systems are rigorously reviewed in this paper. The increasing adoption and implementation of IoT solutions across disparate industries results in an immensely high potential for huge gains in the production efficiency and corresponding decline in operational costs. Yet there are numerous significant hurdles to overcome such as tackling complex interoperability problems, top-notch security issues, and horrible scalability problems to achieve complete functionality and operational perfection. The study demonstrates the vital necessity of using the most commonly adopted open standards and effective middleware solutions in order to boost the integration capabilities along with the seamless interoperability between different systems. Also, it requires the establishment of strongly effective cybersecurity intervention systems meant to cover for data security and protect against any threats such as a cyber breach. In addition,
it is crucial to use the flexible network architecture, in conjunction with sophisticated information handling, so that a further development in the field of electronics can be ensured for an optimal scalability and flexibility of the network. The research makes use of a comprehensive and thick analysis of existing literature and relevant case studies which strongly stresses that it is imperative for overcoming successfully these challenges to leverage the many benefits that IoT can bring in manufacturing. Not only has the study
shown that with right strategic actions, organizations can not only enhance their operational efficiency significantly while maintaining a competitive edge strategically too in increasingly dynamic and evolving technological environment, these changes stay with them.

Hybrid Energy Storage Management in Microgrids to Mitigate SOC Deviation and Improve System Stability

Sadulla Shaik — 2025-02-23

The integration of renewable energy sources into microgrids at a high speed has changed generation and resulted in fluctuations in the power generation and State of Charge (SOC) regulation of energy storage systems (ESS). Typical high frequency charge discharge cycles have so far proven to be a challenge for conventional single storage solutions to effectively address. This paper presents an adaptive architecture of a hybrid energy storage system (HESS) using a battery energy storage system (BESS) and a supercapacitor energy storage system (SCESS). In this work, a fuzzy logic based energy management system (FLEMS) is proposed to dynamically allocate the power to the two storage components based on the demand for load at defined thresholds, and rate changes of SOC. A mathematical model of the microgrid including renewable generation, loads, and HESS is developed in a comprehensive form. The reduction in SOC deviation and improvement in system frequency stability provided by the Simulink results of this work is compared to traditional BESS only configurations and shown to be 35% lower for the SOC deviation and 22% better for system frequency stability for a range of load and renewable generation scenarios. Experimental validations with real timed SPACE and scaled microgrid testbed are observed to have a deviation of only 9.8 % in SOC and 0.31 Hz in frequency variance which shows that the proposed approach is practically realistic. While these findings present some compelling implications for future research on microgrid, they also make it clear that for addressing the most critical stability challenges, hybrid energy storage is indeed effective. This study augments the general discussion in designing resilient microgrid systems that can react to the rising reliance on a progressively intermittent renewable energy sources through showing how intelligently managed hybrid storage systems can improve reliability, efficiency, and control Flexibility. The results call for the continuation of HESS architectures, as they prove useful for further exploration of sustainable energy solutions in the microgrid context.

Neuromile: A Continual Meta-Learning-Based AI Deployment Framework for Energy-Aware Personalized Inference at the Edge

Doris Klein — 2025-02-18

NeuroMile is an alternatives-based, new AI architecture that combines continual learning, meta-learning, and dynamic energy optimization to perform real-time and accurate inference on markets and end gadgets. Engineered to address the resource limitation of embedded and wearable systems, the task-aware memory encoder and the adaptive-modulation of inference depth and quantization level, NeuroMile has been developed to support a modularized architecture. Such adaptations have dynamic contextual feedback, such as battery level, activity and complexity of task.

Relative evaluations in three edge-related benchmarks, PAMAP2 (human activity recognition), EdgeSpeech (voice command recognition), and CIFAR-100 (few-shot image classification) show that NeuroMile can reach 88.9% at 1.1W power consumption as opposed to the full-precision baseline of 89.6% accuracy at 2.8W power consumption. This shows a decrease of 60 percent of energy consumed with less than 1 percent loss of accuracy. Besides, NeuroMile can train much faster in terms of task-specific fine-tuning, with only 7.8s required compared to conventional meta-learning baselines, including MAML (10.3s) and FedAvg (18.1s).

These findings put NeuroMile as a feasible and smart edge inference architecture that trades-off among accuracy, energy-efficiency, and flexibility. It is applicable to mobile robotics, wearable health-monitors, as well as real-time IoT installations. The future work will consist of a federated learning to enable edge adaptation to be secretive and reinforcement learning-based self-optimizing edge control policies to further enlarge the sustainability and personalization aspect in this Computational model.

AI-Assisted Brillouin-Based Distributed Temperature and Strain Sensing in Hybrid Polymer-Silica Optical Fibers for Harsh Environments

Chuong Van — 2025-02-09

As a long-range, high-resolution monitoring technique of industrial and structural applications, distributed temperature and strain sensing (DTSS) based on Brillouin scattering has gained increasing attention. However, due to their superior spatial resolution, polymer optical fibers (POFs) suffer from poor performance in harsh environments where silicon fiber cannot be used, due to their susceptibility to environmental degradation, and poor thermal and strain cross sensitivity. Existing sensing cannot achieve higher sensitivity and higher rejection of sensing faults than optical fiber-based sensing technology due to intrinsic losses in the optical fibers and the susceptibility of the sensing head to vibration driven shock and fatigue failure, as opposed to mechanical fiber-based sensing technology. This study proposes a novel hybrid sensing architecture by combining alternating segments of polymer and silica optical fibers with an AI-enhanced Brillouin signal processing framework using Bidirectional Long Short-Term Memory (BiLSTM) neural networks. Using data driven modeling, the proposed system successfully decouples the temperature and strain induced Brillouin frequency shifts allowing for accurate, but real time multi parameter estimation. This is experimentally validated over a 50-meter hybrid fiber with temperature accuracy of ± 0.2 °C, strain resolution of ± 20 με, and spatial resolution of 2.5 cm with 45 % reduction in cross sensitivity to entropy. Moreover, the system operated in more stable way in the diagenetic conditions. To conclude, the proposed AI assisted hybrid fiber sensing turns out to be robust and scalable solution for distributed sensing in microwave photonic and optoelectronic systems under harsh environment.

Terahertz Bandgap Engineering in 2D Photonic Crystals for Optical Filtering Applications

Fasil Beyene — 2025-03-19

Terahertz (THz) photonics is a rapidly growing field of great importance to next generation of wireless communication, imaging and sensing. This work outlines a novel yet novel two-dimensional photonic crystal architecture that overcomes the performance limitations of present-day THz filters, namely an extremely limited operational bandwidth, with very limited spectral tuning, an excessively large device footprint, and absence of device integration features. The tunable photonic bandgaps covering a frequency range of 0.75–1.2 THz are realized by the lattice topology optimization and engineered defect cavities. The square lattice of air holes in a high refractive index dielectric substrate is designed to have transmission and resonant properties computed with the Plane Wave Expansion (PWE) method and the Finite Difference Time Domain (FDTD) simulation. The introduction of an extra strategically placed point defect introduces spectral selectivity and realizes high-Q resonant mode with the help of it. Simulated results indicate wide bandgap of approximate 0.45 THz, Q of greater than 850, and insertion losses less than 1 dB. The experimental measurements with fabricated silicon based photonic crystal slabs are corroborative to these impressive performance metrics. Such novel tunability, spectral resolution and compact integration enabled by this method make this a promising technique in adapting optics, THz channel filtering or THz reconfigurable photonic systems.

Self-Recovering Multi-View Edge Tracker (SMVET): A Transformer-Augmented Lightweight Architecture for Occlusion-Resilient Real-Time Surveillance at the Edge

Sungho Jeon — 2025-03-05

SMVET-Self-Recovering Multi-View Edge Tracker proposed in this paper is a low weight edge-friendly object monitoring framework particularly to deal the issue of occlusion and viewpoint change in real time surveillance systems. SMVET is a Transformer-enhanced feature fusion layer jointly used with a Siamese-based tracking back-bone to achieve this by dynamic adaptation of occlusion based upon self-recovery modes and multi-view contextualization. The use of quantized attention blocks and low power design philosophy has been applied to make its architecture efficient in implementation on edge computers.

A thorough analysis on both MOT17 and UAV123 datasets proves that SMVET provides a better performance in re-identification accuracy of 23 percent under severe occlusion conditions and makes a 31 percent improvement in latency relative to leading-edge tracking models. In addition, the system maintains real-time inference performance using power consumption of 1.5W, which is very appropriate to be used as embedded surveillance and autonomous drones. The suggested framework incorporates an efficient and elastic tool on intelligent edge-based tracking in the dynamic and resource-bounded settings. This structure is also the first one to integrate the quantized Transformer fusion, temporal self-recovery, and multi-view alignment into an end-to-end lightweight tracker capable of deployment on the edge. This combination allows a strong and power-efficient tracking even when there is an occlusion, motion blur and also on change of view, which provides a scalable solution to intelligent surveillance in dynamic settings.

Innovative Approaches for Seamless Integration of Solar Photovoltaic and Battery Storage Technologies in Smart Distribution Networks

Andrew Muyanja — 2025-03-26

This paper goes through various optimization strategies with great detail which are important for the right combination in smart distribution network context of solar photovoltaic (PV) and battery storage technologies. With the global energy landscape moving towards adoption of renewable energy sources and a synergy between solar PV systems and those advanced storage sculions becomes a real and inevitable means to tackle successfully those issues in diveresegeogrphical regions of the world, enabling sustainability, reliability and energy independence. It outlines several key strategies to maximize the output of the solar energy and includes the consideration on the best location and angle of the placement of the solar panel in order to take the most advantage from the sun, the installation of advanced smart inverters to increase the overall system efficiency, and effective strategy in the energy sharing via the demand side management to involve the participation and usage adjustment of the consumers that maximize the energy. In addition, the research refers to the importance of defining the correct size of the battery storage system to meet energy load requirements efficiently, the installation of advanced battery management system which improve the lifespan and performance storage systems, as well as the bringing real time energy management system to make them ready to respond in real time to the energy fluctuations. Finally, the paper discusses the multifaceted challenges encountered during the integration process, embracing the variability of energy generation caused by climatic reasons, the technical difficulties in system design and installation and the many procedural hindrances which oppose further development. It is shown in this research that according to these challenges, there exist innovative advances in the technologies of forecasting, which can forecast energy generation and consumption patterns with higher accuracy, communication protocols for standardizing connection of system components, and an economic and policy framework that encourages the use of renewable technologies. Overall, this thorough analysis of the different integration strategies indicates the necessity of proper integration strategies for the solar PV and battery storage in the future energy systems as a vital component to increase overall efficiency, resilience, and sustainability.