European Journal of Electrical Engineering and Computer Science

Understanding the Predictive Relationship Between Wireless Network Experience and Customer Churn

Michael Dienhart — 2025-04-03

Wireless networks have transformed society, and their evolving capabilities support numerous economic and social goals. Continued investments in wireless technologies and network coverage by mobile network operators (MNOs) depends on their achieving a favorable return on investment. Retaining existing customers by reducing churn is the most financially efficient means to improve economic returns, however the causes of customer churn are not fully understood due to the lack of studies on the relationship between wireless network quality and customer churn. This quantitative study leveraged existing secondary data from one MNO containing nine network quality factors, which formed three network quality constructs in the model, measured in 646 counties for one month in combination with a partial least squares structural equation modeling methodology to evaluate the predictive value of the network quality factors on customer churn. The study further assessed the degree to which the predictive value varies based on the population density of each county. The surprising findings suggest that network quality does not predict a meaningful amount of customer churn (p < 0.001), but that the relationship between the network quality factors and customer churn differs meaningfully depending on population density. These findings suggest ways that MNOs may fine-tune their network investments to achieve improvements in customer churn and financial results.

Enhancing Vulnerability Assessments for Electronic Voting Systems through an Augmented CVSS 3.1 Model

Demetrice Rogers — 2025-03-19

This paper explores the application of the Common Vulnerability Scoring System (CVSS) to electronic voting systems, highlighting how unique considerations in these environments can be more accurately captured with an enhanced model. By incorporating criteria from the Voluntary Voting System Guidelines (VVSG), this research addresses the limitations of traditional IT-based evaluations in assessing vulnerabilities within electronic voting systems. The enhanced model was validated using a dataset of real-world vulnerabilities, showing significant improvements in accuracy and prioritization through statistical analyses. The findings offer a repeatable and extensible method for cybersecurity practitioners and election officials to assess operational risks and implement mitigation strategies to protect electrical integrity.

Dynamic Modeling of on Grid-Connected Photovoltaic Setup in Pakistan using MATLAB

Waseem Ijaz — 2025-03-11

This research presents a computational modeling and simulation framework for grid-connected photovoltaic (PV) systems in Pakistan utilizing MATLAB/Simulink. Employing a Perturb and Observe (P&O) MPPT algorithm, the research develops a detailed model of a 7.5 kW PV installation in Lahore, analytically examining power generation dynamics, inverter efficiency, and grid interaction. The simulation demonstrates the system’s capability to mitigate grid dependency, with results showing effective power optimization and smooth transitions between solar generation, grid supply, and battery storage. The study bridges knowledge gaps by providing empirical insights into real-time PV system electrical characteristics, presenting a methodological approach for optimizing renewable energy system design and deployment. By quantitatively analyzing power flow, inverter performance, and battery efficiency, the research contributes valuable computational strategies for enhancing solar energy integration in regions with high solar irradiation potential.

Low-Power 5G Protocols for Sustainable Communication in Rural and Remote Networks

Shaman Bhat — 2025-02-13

While 5G technology has the ability to offer unparalleled connectivity and data speeds, high power consumption prevents its usage in rural and remote areas, where energy resources are often scarce and infrastructure is minimal. This paper provides a set of low-power 5G protocols designed to improve energy efficiency while maintaining reliable communication standards in under-served localities. Our proposed protocols incorporate adaptive protocol layering, energy-efficient modulation techniques, and advanced power-saving mechanisms, such as sleep modes and intelligent wake-up functionalities. This helps to reduce overall energy demand without compromising network performance. The findings suggest that, combined with renewable energy sources, these protocols offer a viable solution for extending 5G coverage to rural and remote areas, promoting greater digital inclusion and aligning with the aim of global sustainability.

Revolutionizing Wireless Networks with Federated Learning: A Comprehensive Review

Sajjad Emdadi Mahdimahalleh — 2024-12-31

These days, with the rising computational capabilities of wireless user equipment such as smartphones, tablets, and vehicles, along with growing concerns about sharing private data, a novel machine learning model called federated learning (FL) has emerged. FL enables the separation of data acquisition and computation at the central unit, which is different from centralized learning that occurs in a data center. FL is typically used in a wireless edge network where communication resources are limited and unreliable. Bandwidth constraints necessitate scheduling only a subset of UEs for updates in each iteration, and because the wireless medium is shared, transmissions are susceptible to interference and are not assured. The article discusses the significance of Machine Learning in wireless communication and highlights Federated Learning (FL) as a novel approach that could play a vital role in future mobile networks, particularly 6G and beyond.