On Multi-Access Edge Computing: A Survey of the Emerging 5G Network Edge Cloud Architecture and Orchestration

Analysis

Why This Paper Matters

This survey on Multi-Access Edge Computing (MEC) is a seminal work that systematically organizes the emerging field of edge cloud computing for 5G networks. Published in IEEE Communications Surveys & Tutorials in 2017, it has garnered over 1748 citations, reflecting its role as a key reference for researchers and practitioners. The paper addresses the critical need to converge telecommunication and IT services by placing cloud computing resources at the edge of the radio access network, thereby reducing latency and improving backhaul efficiency. As 5G deployment accelerated, MEC became essential for enabling low-latency applications like autonomous vehicles, augmented reality, and industrial IoT. This survey provided the first comprehensive taxonomy of MEC enabling technologies, orchestration strategies, and deployment scenarios, making it indispensable for understanding the architectural foundations of edge computing.

Technical Contributions

The paper makes several key technical contributions:

• Enabling Technologies: It identifies and explains fundamental technologies such as network function virtualization (NFV), software-defined networking (SDN), and cloud-native principles that underpin MEC.
• Orchestration Analysis: It elaborates on MEC orchestration for both individual services and networks of MEC platforms, covering mobility management and different orchestration deployment options (e.g., centralized vs. distributed).
• Reference Architecture: The paper analyzes the ETSI MEC reference architecture, detailing components like the MEC orchestrator, platform manager, and virtualization infrastructure, and how they support multitenancy for application developers and third parties.
• Deployment Scenarios: It categorizes deployment models (e.g., at base stations, aggregation points, or central offices) and discusses trade-offs in latency, scalability, and resource utilization.
• Standardization Overview: The survey reviews ongoing standardization efforts by ETSI, 3GPP, and other bodies, highlighting gaps and open challenges.

Results

As a survey paper, no experimental results or quantitative metrics are presented. Instead, the paper provides a structured comparative analysis of orchestration options and deployment scenarios. Its main output is a comprehensive framework that categorizes MEC approaches, enabling researchers to identify suitable architectures for specific use cases. The paper's impact is measured by its citation count (1748) and its influence on subsequent MEC research and standardization.

Significance

This survey has had a profound impact on the AI and networking communities by establishing a common vocabulary and architectural blueprint for edge computing in 5G. It has guided the development of MEC platforms in industry (e.g., AWS Wavelength, Azure Edge Zones) and influenced standards from ETSI and 3GPP. For AI practitioners, MEC is critical for deploying inference models at the edge, reducing latency for real-time applications. The paper's taxonomy of orchestration and deployment options remains relevant as edge AI evolves, making it a foundational reference for anyone working on distributed AI systems in mobile networks.