[Paper Review] Big Data Analytics for Large Scale Wireless Networks: Challenges and Opportunities

Hong‐Ning Dai, Raymond Chi-Wing Wong+3 more|arXiv (Cornell University)|Sep 2, 2019

IoT and Edge/Fog Computing201 references58 citations

TL;DR

This paper surveys big data analytics (BDA) for large-scale wireless networks, organizing the BDA process into four stages and analyzing BDA across four representative network types.

ABSTRACT

The wide proliferation of various wireless communication systems and wireless devices has led to the arrival of big data era in large scale wireless networks. Big data of large scale wireless networks has the key features of wide variety, high volume, real-time velocity and huge value leading to the unique research challenges that are different from existing computing systems. In this paper, we present a survey of the state-of-art big data analytics (BDA) approaches for large scale wireless networks. In particular, we categorize the life cycle of BDA into four consecutive stages: Data Acquisition, Data Preprocessing, Data Storage and Data Analytics. We then present a detailed survey of the technical solutions to the challenges in BDA for large scale wireless networks according to each stage in the life cycle of BDA. Moreover, we discuss the open research issues and outline the future directions in this promising area.

Motivation & Objective

• Define the 4-stage life cycle of big data analytics (data acquisition, preprocessing, storage, analytics) for large-scale wireless networks.
• Categorize BDA challenges and solutions by wireless network type (mobile, vehicular, mobile social, IoT).
• Identify open research issues and future directions in BDA for large-scale wireless ecosystems.

Proposed method

• Systematic literature review of 249 references from 2002-2018 using keyword-based search and snowballing (backward and forward).
• Taxonomy development aligning BDA stages with four network types (mobile, vehicular, mobile social, IoT).
• Synthesis of data sources, necessities, and solutions for each BDA stage and network type.

Experimental results

Research questions

• RQ1 What are the key data sources and necessities driving BDA in large-scale wireless networks?
• RQ2 How do data acquisition, preprocessing, storage, and analytics address the challenges across different wireless network types?
• RQ3 What are the open research issues and future directions in BDA for large-scale wireless networks?
• RQ4 How does the IoT context influence BDA approaches compared to other networks?
• RQ5 What is the state-of-the-art in applying BDA techniques to improve operation, security, and management of large-scale wireless systems?

Key findings

• Big data in wireless networks exhibits 4Vs: volume, variety, velocity, and value, with data flows spanning multiple sources and real-time requirements.
• A four-stage BDA life cycle (data acquisition, preprocessing, storage, analytics) plus cross-stage feedback captures the workflow and its challenges.
• IoT and HetNets emerge as hotspots for BDA research due to heterogeneous data and real-time needs.
• BDA benefits include improved QoS/QoE, cost and energy optimization, network security, and smarter ITS/traffic management.
• Data sources span mobile networks, vehicular networks, MSNs, and IoT, each with unique data types and latency constraints.
• The study highlights open issues and outlines future directions across data representation, collection, transmission, storage, and analytics.