GET THE APP

Edge Computing: Addressing Challenges, Unleashing Potential
Journal of Computer Science & Systems Biology

Journal of Computer Science & Systems Biology

ISSN: 0974-7230

Open Access

Short Communication - (2025) Volume 18, Issue 6

Edge Computing: Addressing Challenges, Unleashing Potential

Nour Hassan*
*Correspondence: Nour Hassan, Department of Computer Science,, American University of Beirut, Beirut 1107 2020, Lebanon, Lebanon, Email:
Department of Computer Science,, American University of Beirut, Beirut 1107 2020, Lebanon, Lebanon

Received: 28-Oct-2025, Manuscript No. jcsb-25-176465; Editor assigned: 03-Nov-2025, Pre QC No. P-176465; Reviewed: 11-Nov-2025, QC No. Q-176465; Revised: 18-Nov-2025, Manuscript No. R-176465; , DOI: 10.37421/0974-7230.2025.18.611
Citation: Hassan, Nour. ”Edge Computing: Addressing Challenges, Unleashing Potential.” J Comput Sci Syst Biol 18 (2025):611.
Copyright: © 2025 Hassan N. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution and reproduction in any medium, provided the original author and source are credited.

Abstract

    

Introduction

Edge computing is a transformative paradigm, deeply exploring foundational concepts, architectural models, and key enabling technologies. This approach meticulously outlines inherent challenges, including security, privacy, resource management, and network latency. The field continually points out promising future research directions, offering a broad perspective on how it will evolve and address limitations in current distributed systems [1].

Here, we thoroughly examine privacy-preserving machine learning techniques specifically for edge computing environments. This work categorizes existing solutions, directly addressing challenges of data privacy, computational overhead, and communication costs at the edge. It outlines how methods such as federated learning, differential privacy, and homomorphic encryption adapt to protect sensitive data, all while enabling effective model training and inference near data sources [2].

Another area explores the significant role of edge computing within Intelligent Transportation Systems (ITS). It details how these technologies enhance real-time data processing, low-latency communication, and critical decision-making for applications like autonomous vehicles, traffic management, and smart parking. This area highlights the unique architectures, key enabling technologies, and challenges of integrating edge computing into the complex ITS ecosystem, proposing future research pathways for smart city development [3].

The application of edge computing in Internet of Things (IoT)-based healthcare systems is also examined. Processing data closer to its source notably improves real-time monitoring, reduces latency for critical alerts, and enhances data privacy for sensitive medical information. This exploration covers various edge architectures suitable for healthcare, addressing associated challenges such as interoperability and data security, and suggests future research areas for pervasive health solutions [4].

Attention here turns to strategies for energy-efficient resource management within edge computing environments. This work explores various techniques designed to minimize power consumption while upholding optimal performance for edge devices and servers. It covers aspects such as task offloading, resource allocation, and dynamic power management, identifying key challenges and offering insights into future research avenues for greener, more sustainable edge deployments [5].

The integration of Blockchain technology to enhance secure and transparent data sharing in edge computing environments is investigated. A novel framework is proposed, leveraging Blockchain's immutability and decentralization to address security and trust issues inherent in distributed edge systems. The aim is to protect data integrity, ensure accountability, and facilitate reliable transactions at the network edge [6].

Moving on, this survey explores the symbiotic relationship between edge computing and Mobile Augmented Reality (MAR). It highlights how edge processing can overcome computational and latency constraints of MAR applications, thus enabling more immersive and responsive user experiences. The paper covers various system architectures, task offloading mechanisms, and resource allocation strategies tailored for MAR on the edge, also discussing challenges and future research pathways [7].

This systematic review specifically focuses on integrating Federated Learning (FL) within edge computing architectures. It details how FL enables collaborative machine learning model training across distributed edge devices without centralizing raw data, enhancing privacy and reducing communication overhead. The paper categorizes existing FL-edge solutions, discusses challenges tied to heterogeneity, communication, and security, and outlines future research opportunities for robust, efficient decentralized Artificial Intelligence (AI) at the edge [8].

A deep reinforcement learning (DRL) approach for efficient resource allocation in dynamic edge computing environments is also proposed. It tackles the challenge of optimizing computational and communication resources to meet the varying demands of edge applications, all while minimizing latency and energy consumption. The authors demonstrate how DRL agents can learn optimal policies for task offloading and resource scheduling in real-time, improving overall system performance and adaptability [9].

Finally, a detailed examination of security and privacy challenges unique to edge computing environments is provided. It classifies various threats, including data breaches, denial-of-service attacks, and insider threats, which arise from the distributed nature and resource constraints of edge devices. The paper also reviews existing countermeasures and solutions, offering a comprehensive overview of how to build more secure and trustworthy edge deployments [10].

 

Description

Edge computing fundamentally transforms data processing by moving computation closer to data sources, directly addressing latency, bandwidth, and privacy concerns in traditional cloud models. It explores foundational concepts, architectural models, and key enabling technologies. The inherent challenges, such as security, privacy, resource management, and network latency, are central to its development. The field continually identifies future research directions, aiming to evolve and overcome limitations in current distributed systems [1].

A significant body of work focuses on privacy-preserving machine learning techniques within edge computing environments. This includes categorizing existing solutions and tackling challenges of data privacy, computational overhead, and communication costs at the edge. Methods like Federated Learning (FL), differential privacy, and homomorphic encryption are adapted to protect sensitive data while enabling effective model training and inference close to data sources [2]. Furthermore, the integration of Blockchain technology is key to enhancing secure and transparent data sharing. Novel frameworks leverage blockchain's immutability and decentralization to address security and trust, ensuring data integrity, accountability, and reliable transactions at the network edge [6]. Overall, a detailed examination of security and privacy challenges specific to edge computing environments classifies various threats—data breaches, denial-of-service attacks, insider threats—that stem from distributed nature and resource constraints. It reviews existing countermeasures, offering a comprehensive overview for building secure, trustworthy edge deployments [10].

Edge computing proves vital across several application domains. In Intelligent Transportation Systems (ITS), edge technologies enhance real-time data processing, low-latency communication, and decision-making for autonomous vehicles, traffic management, and smart parking. This highlights unique architectures and challenges within the complex ITS ecosystem, proposing future research for smart city development [3]. For Internet of Things (IoT)-based healthcare systems, processing data closer to the source improves real-time monitoring, reduces latency for critical alerts, and enhances data privacy for sensitive medical information. Various edge architectures suitable for healthcare are explored, addressing interoperability and data security concerns [4]. Additionally, a symbiotic relationship exists between edge computing and Mobile Augmented Reality (MAR), where edge processing overcomes computational and latency constraints, enabling immersive and responsive user experiences through tailored system architectures and resource allocation strategies [7].

Effective resource management is crucial for sustainable edge deployments. Studies focus on strategies for energy-efficient resource management, exploring techniques to minimize power consumption while maintaining optimal performance for edge devices and servers. This includes task offloading, resource allocation, and dynamic power management, identifying challenges and offering insights for greener edge deployments [5]. In this vein, Federated Learning (FL) enables collaborative machine learning model training across distributed edge devices without centralizing raw data, which enhances privacy and reduces communication overhead. Existing FL-edge solutions are categorized, with challenges in heterogeneity, communication, and security discussed, alongside future research for robust, efficient decentralized Artificial Intelligence (AI) at the edge [8]. A deep reinforcement learning (DRL) approach is also proposed for efficient resource allocation in dynamic edge computing environments, optimizing computational and communication resources to meet varying demands while minimizing latency and energy consumption. DRL agents learn optimal policies for task offloading and scheduling in real-time, improving overall system performance and adaptability [9].

Conclusion

This collection of research thoroughly examines the broad landscape of edge computing, detailing its core concepts, architectures, and the technologies that make it work. A common theme is how edge computing mitigates challenges found in centralized systems, specifically by tackling issues like security, privacy, resource management, and network latency. The papers consistently point towards future research needs, offering a holistic view of edge computing's development and its ability to overcome limitations in current distributed systems. Significant attention is given to privacy concerns, exploring techniques such as federated learning, differential privacy, and homomorphic encryption to protect sensitive data at the edge. The integration of blockchain technology also emerges as a key strategy for secure and transparent data sharing, reinforcing trust and accountability in distributed edge environments. Various application domains showcase the impact of edge computing. It enhances Intelligent Transportation Systems (ITS) by enabling real-time processing for autonomous vehicles and traffic management. In Internet of Things (IoT)-based healthcare, edge processing improves real-time monitoring and data privacy. Mobile augmented reality (MAR) also benefits from edge capabilities, achieving more immersive user experiences by addressing computational and latency constraints. Resource management and energy efficiency are critical topics. Papers discuss strategies to optimize computational and communication resources, minimize power consumption, and adapt to dynamic environments. Deep reinforcement learning approaches are proposed for efficient task offloading and scheduling. Finally, the research broadly surveys security and privacy challenges, classifying threats and reviewing countermeasures to foster trustworthy edge deployments. This body of work underlines edge computing's transformative potential across diverse sectors.

Acknowledgement

None

Conflict of Interest

None

References

Qing Y, Liang L, Wei Z. "A Comprehensive Survey on Edge Computing: Challenges, Research Directions, and Future Perspectives".IEEE Communications Surveys & Tutorials 24 (2022):1109-1144.

Indexed at, Google Scholar, Crossref

Yang L, Lei Z, Ximeng L. "Privacy-preserving machine learning in edge computing: A survey".Pervasive and Mobile Computing 74 (2021):101402.

Indexed at, Google Scholar, Crossref

Yu-Chiang L, Chi-Chiang L, Hsiao-Hui C. "Edge computing for intelligent transportation systems: A comprehensive survey".Journal of Parallel and Distributed Computing 172 (2023):11-30.

Indexed at, Google Scholar, Crossref

Arindam B, Swarnajyoti G, Sourav KA. "Edge computing for IoT-based healthcare: A review".Journal of Systems Architecture 111 (2020):101822.

Indexed at, Google Scholar, Crossref

Yuancheng L, Shuchang X, Ning Z. "Energy-efficient resource management in edge computing: A survey".Sustainable Computing: Informatics and Systems 35 (2022):100720.

Indexed at, Google Scholar, Crossref

Xiaoyan S, Qingzhong L, Yifei L. "Blockchain-based secure and transparent data sharing in edge computing".Information Sciences 618 (2023):161-177.

Indexed at, Google Scholar, Crossref

Yu Z, Yulei W, Qipeng W. "Edge computing for mobile augmented reality: A survey".Journal of Network and Computer Applications 181 (2021):103009.

Indexed at, Google Scholar, Crossref

Bin N, Jun W, Yang L. "Federated learning in edge computing: A systematic review".Computer Networks 209 (2022):108920.

Indexed at, Google Scholar, Crossref

Yu Z, Yulei W, Guohui L. "Resource allocation in edge computing: A deep reinforcement learning approach".Journal of Network and Computer Applications 209 (2023):103525.

Indexed at, Google Scholar, Crossref

Muhammad N, Saqib A, Muhammad S. "Security and privacy challenges and solutions in edge computing: A survey".Future Generation Computer Systems 108 (2020):1088-1104.

Indexed at, Google Scholar, Crossref

Google Scholar citation report
Citations: 2279

Journal of Computer Science & Systems Biology received 2279 citations as per Google Scholar report

Journal of Computer Science & Systems Biology peer review process verified at publons

Indexed In

arrow_upward arrow_upward