Special Issue on Intelligent Edge: When Machine Learning Meets Edge Computing
摘要截稿:
全文截稿: 2020-03-15
影响因子: 2.816
期刊难度:
CCF分类: C类
中科院JCR分区:
• 大类 : 计算机科学 - 3区
• 小类 : 计算机:信息系统 - 3区
• 小类 : 工程:电子与电气 - 3区
• 小类 : 电信学 - 3区
Overview
The explosion of the big data generated by ubiquitous edge devices motivates the emergence of a new computing paradigm: edge computing. It has attracted attention from both academia and industry in recent years. In edge computing, computations are deployed mainly at the local network edge rather than at remote central computing infrastructures, thereby considerably reducing latency and possibly improving computation efficiency. This computing model has been applied in many areas such as mobile access networks, Internet of Things (IoT), and microservices, enabling novel applications that drastically change our daily lives. As a second trend, a new era of Artificial Intelligence (AI) research has delivered novel machine learning techniques that have been utilized in applications such as healthcare, industry, environment engineering, transportation, smart home and building automation, all of which heavily rely on technologies that can be deployed at the network’s edge. Therefore, intuitively, marrying machine learning techniques with edge computing has high potential to further boost the proliferation of truly intelligent edges.
In light of the above observations, in this special issue, we look for original work on intelligent edge computing, addressing the particular challenges of this field. On one hand, conventional machine learning techniques usually entail powerful computing infrastructures (e.g., cloud computing platforms), while the entities at the edge may have only limited resources for computations and communications. This suggests that machine learning algorithms or, at least, the implementations of machine learning algorithms, should be revisited for edge computing, which represents a considerable risk and challenge at once. On the other hand, the adapted deployments of machine learning algorithms at the edge empower the “smartification” across different layers, e.g., from network communications to applications. This in turn allows new applications of machine learning and artificial intelligence, opening up new opportunities. The goal of this special issue is to offer a venue for researchers from both academia and industry to present their solutions for re-designing machine learning algorithms compatible to edge computing, and for building intelligent edge by machine learning techniques, possibly revealing new, compelling use cases.
Relevant topics include, but are not limited to:
l System architectures of intelligent edge computing
l Modeling, analysis and measurement of intelligent edge computing
l Machine learning algorithms and systems for edge computing
l Machine learning-assisted networking and communication protocols for or using edge computing
l Intelligent mobile edge computing
l Architectures, techniques and applications of intelligent edge cloud
l Resource management for intelligent edge computing
l Security and privacy of intelligent edge computing
l Data management and analytics of intelligent edge computing
l Intelligent edge-cloud collaborations
l Programming models and toolkits for intelligent edge computing
l Distributed machine learning algorithms for edge computing