The research and development (R&D) and the standardization of the 5th Generation (5G) mobile networking technologies are proceeding at a rapid pace all around the world. In this paper, we introduce the emerging concept of network slicing that is considered one of the most significant technology challenges for 5G mobile networking infrastructure, summarize our preliminary research efforts to enable end-to-end network slicing for 5G mobile networking, and finally discuss application use cases that should drive the designs of the infrastructure of network slicing.

End-to-end Network Slicing for 5G Mobile Networks

5G mobile systems are expected to meet different strict requirements beyond the traditional operator use cases. Effectively, to accommodate needs of new industry segments such as healthcare and manufacturing, 5G systems need to accommodate elasticity, flexibility, dynamicity, scalability, manageability, agility, and customization along with different levels of service delivery parameters according to the service requirements. This is currently possible only by running the networks on top of the same infrastructure, the technology called network function virtualization, through this sharing of the development and infrastructure costs between the different networks. In this article, we discuss the need for the deep customization of mobile networks at different granularity levels: per network, per application, per group of users, per individual users, and even per data of users. The article also assesses the potential of network slicing to provide the appropriate customization and highlights the technology challenges. Finally, a high-level architectural solution is proposed, addressing a massive multi-slice environment.

/pdf/permit-network-slicing-for-personalized-5g-mobile-1lt24zf8wf.pdf

PERMIT: Network Slicing for Personalized 5G Mobile Telecommunications

Software-defined networking (SDN) has attracted the attention of the research community in recent years, as evidenced by a large number of survey and review papers. The architecture of SDN clearly recognizes three planes: application, control, and data planes. The application plane executes network applications, the control plane regulates the rules for the entire network based on the requests generated by network applications, and based on the set rules, the controller configures the switches in the data plane. The role of the switch in the data plane is to simply forward packets based on the instructions given by the controller. By analyzing the SDN-related research papers, it is observed that research, from the very beginning, is insufficiently focused on the data plane. Therefore, this paper gives a comprehensive overview of the data plane survey with a particular emphasis on the problem of programmability and flexibility. The first part of the survey is dedicated to the evaluation of actual data plane architectures through several definitions and aspects of data plane flexibility and programmability. Then, an overview of the SDN-related research was presented with the aim of identifying the key factors influencing the gradual deviation from the original data plane architectures given with ForCES and OpenFlow specifications. In this paper, we used the term data plane evolution for this deviation. By establishing a correlation between the treated problem and the problem-solving approaches, the limitations of ForCES and OpenFlow data plane architectures were identified. Based on the identified limitations, a generalization of approaches to addressing the problem of data plane flexibility and programmability has been made. By examining the generalized approaches, open issues have been identified, establishing the grounds for future research directions proposal.

A Survey on Data Plane Flexibility and Programmability in Software-Defined Networking

Traffic classification acquired the interest of the Internet community early on Different approaches have been proposed to classify Internet traffic to manage both security and Quality of Service (QoS) However, traditional classification approaches consisting of modifying the Transmission Control Protocol/Internet Protocol (TCP/IP) scheme have not been adopted due to their complex management In addition, port-based methods and deep packet inspection have limitations in dealing with new traffic characteristics (eg, dynamic port allocation, tunneling, encryption) Conversely, machine learning (ML) solutions effectively classify traffic down to the device type and specific user action Another research direction aims to anonymize Internet traffic and thwart classification to maintain user privacy Existing traffic surveys focus on classification and do not consider anonymization Here, we review the Internet traffic classification and obfuscation techniques, largely considering the ML-based solutions In addition, this paper presents a comprehensive review of various data representation methods, and the different objectives of Internet traffic classification Finally, we present the key findings, limitations, and recommendations for future research

A review on machine learning–based approaches for Internet traffic classification

Network function virtualization (NFV) will simplify deployment and management of network and telecommunication services. NFV provides flexibility by virtualizing the network functions and moving them to a virtualization platform. In order to achieve its full potential, NFV is being extended to mobile or wireless networks by considering virtualization of radio functions. A typical network service setup requires the allocation of a virtual network function-forwarding graph (VNF-FG). A VNF-FG is allocated considering the resource constraints of the lower infrastructure. This topic has been well-studied in existing literature, however, the effects of variations of networks over time have not been addressed yet. In this paper, we provide a model of the adaptive and dynamic VNF allocation problem considering also VNF migration. Then we formulate the optimization problem as an integer linear programming (ILP) and provide a heuristic algorithm for allocating multiple VNF-FGs. The idea is that VNF-FGs can be reallocated dynamically to obtain the optimal solution over time. First, a centralized optimization approach is proposed to cope with the ILP-resource allocation problem. Next, a decentralized optimization approach is proposed to deal with cooperative multi-operator scenarios. We adopt AD3, an alternating direction method of multipliers-based algorithm, to solve this problem in a distributed way. The results confirm that the proposed algorithms are able to optimize the network utilization, while limiting the number of reallocations of VNFs which could interrupt network services.

Single and Multi-Domain Adaptive Allocation Algorithms for VNF Forwarding Graph Embedding

/pdf/application-specific-slicing-for-mvno-through-software-2xsdroqn6a.pdf

Application Specific Slicing for MVNO through Software-Defined Data Plane Enhancing SDN

Application identification is beneficial for malware detection, content cache, application-specific QoS, traffic control, etc. The existing identification methods using machine learning are usually limited to identification of protocols, not applications, and hard to adapt to the emergence of new applications. We have been proposing a new method for adaptive application identification with machine learning where we create training dataset in real-time by tagging traffic with application process names from a small number of modified smartphones and identify the unknown flow using the classifier trained by the training data. Our previous research [1] achieves more than 80% of accuracy in application identification when not using DPI (Deep Packet Inspection). In this paper, we propose an extension to the previous method using DPI and on-line machine learning with pre-classification of traffic based on ports to improve the inference accuracy. The evaluation shows that our method can identify more than 92% of traffic accurately using DPI when learning period is 5 days, and achieves up to 93% of accuracy at best for general traffic. When limited to HTTP, the accuracy becomes 96%. This result shows that we can build a system identifying more than 92% of the applications adaptively in relatively short training period, e.g., 5 days of training, even when new applications emerge. We envision that our proposed system eventually enables application specific traffic engineering as well as application specific network function execution within the network.

Adaptive mobile application identification through in-network machine learning

The benefits of Mobile/Multi-access Edge Computing (MEC) are often discussed for reducing the latency and offloading intense computation for data processing of emerging applications on the user equipment (UE), such as Aug-mented/Virtual Reality (AR/VR), connected car, content delivery, etc., onto edge cloud. On the other hand, the performance of UE is rapidly improving with abundant resources for enabling local data processing. In this paper, we rethink the benefits of MEC by first arguing these benefits are myths, that is, the advancement of UE may defeat the often-assumed benefits of MEC, i.e., offloading computation and reducing latency, and then demystify the myths by carefully summarizing the latency and computational requirements of the existing applications possibly benefiting from MEC by surveying several tens of publications while examining the recent UEs performance improvement. We also attempt to undercover new benefits of MEC. In the light of these observations, we conclude that MEC is not necessarily just required for low-latency and computationally intensive applications, but also brings benefits from the four additional perspectives: (1) Data Scalability, (2) Application Scalability, (3) Intent-driven Networking, (4) Partial offloading of the network functions.

Demystifying Myths of MEC: Rethinking and Exploring Benefits of Multi-Access/Mobile Edge Computing

SUMMARY In this paper, we apply the concept of software-defined data plane to defining new services for Mobile Virtual Network Operators (MVNOs). Although there are a large number of MVNOs proliferating all over the world and most of them provide low bandwidth at low price, we propose a new business model for MVNOs and empower them with capability of tailoring fine-grained subscription plans that can meet users’ demands. For example, abundant bandwidth can be allocated for some specific applications, while the rest of the applications are limited to low bandwidth. For this purpose, we have recently proposed the concept of application and/or device specific slicing that classifies application and/or device specific traffic into slices and applies fine-grained quality of services (QoS), introducing various applications of our proposed system [9]. This paper reports the prototype implementation of such proposal in the real MVNO connecting customized smartphones so that we can identify applications from the given traffic with 100% accuracy. In addition, we propose a new method of identifying applications from the traffi co f unmodified smartphones by machine learning using the training data collected from the customized smartphones. We show that a simple machine learning technique such as random forest achives about 80% of accuracy in applicaton identification.

INVITED PAPER Special Section on Network Systems for Virtualized Environment Application Specific Slicing for MVNO through Software-Defined Data Plane Enhancing SDN

With the proliferation of traffic encryption, the need for application identification of given encrypted traffic using machine learning is growing for application-specific traffic management. However, there is not much research on the negative impact of classification delay and misclassification. In particular, an application generating bursty traffic such as video streaming causes congestion during the classification, which degrades QoE due to a considerable classification delay. In this paper, we propose a new mechanism called Progressive Slicing, which adaptively assigns the flow to multiple slices according to the state of the classifications. This new classification mechanism mitigates the classification delay by progressively isolating flows into the slices in the course of the classifications. In addition, multiple stages of classifications improve accuracy and enable more flexible application slicing based on the confidence scores. We evaluate the proposed method on multiple user scenarios on Android VMs. We show that this method improves search response time on Twitter by 35% compared to the slicing with a single classification even when the traffic of video applications coexists.

Takamitsu Iwai

Papers

Application Specific Slicing for MVNO through Software-Defined Data Plane Enhancing SDN

Adaptive mobile application identification through in-network machine learning

Demystifying Myths of MEC: Rethinking and Exploring Benefits of Multi-Access/Mobile Edge Computing

INVITED PAPER Special Section on Network Systems for Virtualized Environment Application Specific Slicing for MVNO through Software-Defined Data Plane Enhancing SDN

Progressive Slicing for Application Identification in Application-Specific Network Slicing