ALAA ALZAILAA

Dr. ALAA ALZAILAA

Electronics, Telecom. and Informatics (DETI), Universidade de Aveiro, Aveiro, Portugal
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 July 2025 in IEEE Access
Verified
Journal Article
Open access
ALAA ALZAILAAALAA ALZAILAA
ALAA ALZAILAA
JCJulio Camejo Corona
Julio Camejo Corona
RTRafael Teixeira
Rafael Teixeira
Hao Ran ChiHao Ran Chi
Hao Ran Chi
Mário AntunesMário Antunes
Mário Antunes
RARui L. Aguiar
Rui L. Aguiar
Future cellular communication is envisioned to rely on intelligent networks enabled by Artificial Intelligence (AI)/Machine Learning (ML) methods. However, research on AI/ML-based networks is still in its infancy, and existing works do not address the full process of integrating AI technologies into 5G and beyond networks. This systematic review assesses the current state of AI and ML applications for future wireless networks, where it focuses on four main topics, namely task offloading, resource allocation, spectrum management, and channel estimation. This work confirms that research in this area faces numerous challenges, including the lack of reliable datasets, limited information on tools and libraries, hardware impact, and simulation platforms. These factors make it difficult to compare and validate the performance of different AI/ML approaches, impairing their progress into standardized solutions. Additionally, the cost of deploying AI is often overlooked, undermining the reported gains’ credibility. Moreover, current surveys rarely analyze the types of datasets used, the runtime cost of models, or the simulation and ML tools adopted. These omissions hinder reproducibility and obscure the trade-offs between performance and implementation cost. The outcome of this review emphasized the need for more efforts to address these challenges and advance the field of AI/ML-based network research.

Verified
Journal Article
Open access
PDF file
ALAA ALZAILAAALAA ALZAILAA
ALAA ALZAILAA
Hao Ran ChiHao Ran Chi
Hao Ran Chi
Ayman RadwanAyman Radwan
Ayman Radwan
Rui L. AguiarRui L. Aguiar
Rui L. Aguiar
Fog–cloud-based hierarchical task-scheduling methods are embracing significant challenges to support e-Health applications due to the large number of users, high task diversity, and harsher service-level requirements. Addressing the challenges of fog–cloud integration, this paper proposes a new service/network-aware fog–cloud hierarchical resource-mapping scheme, which achieves optimized resource utilization efficiency and minimized latency for service-level critical tasks in e-Health applications. Concretely, we develop a service/network-aware task classification algorithm. We adopt support vector machine as a backbone with fast computational speed to support real-time task scheduling, and we develop a new kernel, fusing convolution, cross-correlation, and auto-correlation, to gain enhanced specificity and sensitivity. Based on task classification, we propose task priority assignment and resource-mapping algorithms, which aim to achieve minimized overall latency for critical tasks and improve resource utilization efficiency. Simulation results showcase that the proposed algorithm is able to achieve average execution times for critical/non-critical tasks of 0.23/0.50 ms in diverse networking setups, which surpass the benchmark scheme by 73.88%/52.01%, respectively.

1 June 2021
Verified
Conference Paper
Closed access
ALAA ALZAILAAALAA ALZAILAA
ALAA ALZAILAA
Hao Ran ChiHao Ran Chi
Hao Ran Chi
Ayman RadwanAyman Radwan
Ayman Radwan
RARui Aguiar
Rui Aguiar
5G wireless networks have been designed to provide high reliability, ultra-low latency, and support of massive amount of connected devices, in the scope of the Internet of Things (IoT). Advances in electronics and networking are enabling the wide adoption of multiple types of verticals, under the umbrella of IoT. One area of IoT, which is gaining lots of attention, is e-Health. Within e-Health, users’ monitoring in general, and monitoring of vital signs, such as heartbeat rate, are very useful in saving many lives; however, they require ultra-low latency. Cloud-based networking and computing have been proposed to achieve the required low latency. Furthermore, fog computing was proposed to further decrease the achieved latency for critical tasks and services; however, this adds more complexity to the control of the network, in addition to the task scheduling among both the cloud and fog layer. In this paper, we tackle this problem by proposing a task classification and scheduling scheme in a fog-cloud networking environment, by considering comprehensively modeled characteristics of tasks, user profile, environmental exposure and networking features, targeting the improvement of overall latency for higher priority critical tasks. Moreover, we perform an analytical study on the execution comparison between cloud and fog computing services, which paves the way to further develop an orchestrator for task scheduling, among the multi-layer fog-cloud based e-Health systems. Simulation results show that the proposed task scheduling scheme outperforms the benchmark, by guaranteeing ultra-low latency for critical tasks (high-priority), while ensuring sufficient latency performance for latency-tolerant tasks.

12 October 2023
Verified
Conference Paper
Closed access
ALAA ALZAILAAALAA ALZAILAA
ALAA ALZAILAA
Hao Ran ChiHao Ran Chi
Hao Ran Chi
ARAyman Radwan
Ayman Radwan
RARui L. Aguiar
Rui L. Aguiar
This article presents the Energy-Time Efficient Device Selection (ETEDS) algorithm for net federation IoT devices, for an AI-reliant environment. The novel approach focuses on device selection in each Federated Learning (FL) round, considering IoT devices' computation capacity and proximity to the BS, aiming to limit energy use, preserve communication time, and maintain high accuracy of the FL method. It formulates the device selection problem as an optimization task and provides a heuristic algorithm to solve it. The ETEDS algorithm identifies convergence points and suggests stopping training at specific epochs, leading to significant energy and time savings while maintaining satisfactory accuracy levels. Experimental results demonstrate the superiority of the ETEDS algorithm in terms of energy efficiency and overall performance in dynamic IoT scenarios, showcasing approximately 10% savings in total energy and time consumption.

13 March 2026 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
ALAA ALZAILAAALAA ALZAILAA
ALAA ALZAILAA
Hao Ran ChiHao Ran Chi
Hao Ran Chi
Ayman RadwanAyman Radwan
Ayman Radwan
Rui L. AguiarRui L. Aguiar
Rui L. Aguiar
The integration of Internet of Things (IoT) and Federated Learning (FL) marks a significant step towards pervasiveness, supported by distributed computational resources and enhanced by 5G advancements. However, the efficient and sustainable operation of IoT-enabled FL systems faces critical challenges, particularly in selecting devices that balance energy consumption and system performance. To address this, we propose the Battery-Aware Dynamic and Automated Device Selection (DADS) framework, a novel solution specifically designed for IoT-enabled FL environments. DADS introduces an innovative adaptive mechanism that dynamically adjusts optimization parameters, such as inertia weights and crossover/mutation rates, ensuring a seamless balance between exploration and exploitation. Unlike conventional optimization approaches, DADS employs uniquely developed Adaptive Particle Swarm Optimization (APSO) and Adaptive Genetic Algorithm (AGA) within a cohesive framework. This design enables DADS to respond to dynamic IoT network conditions, such as fluctuating battery levels and device capabilities, ensuring energy-efficient device selection while preserving robust performance. Through extensive performance analysis, DADS demonstrates its novelty by achieving a 20% reduction in energy consumption and a 30% improvement in FL training time compared to state-of-the-art methods. Moreover, DADS significantly enhances battery lifespan, reducing degradation by more than 50%, and optimizes communication efficiency, extending the operational sustainability of IoT devices. These results position DADS as a groundbreaking framework, setting a new benchmark for energy-aware and sustainable IoT-enabled FL systems.