The Network Function Virtualization (NFV) technologies are fundamental enablers to meet the objectives of 5G networks. In this work, we first introduce the architecture for dynamic deployment and composition of virtual functions proposed by the Superfluidity project. Then we consider a case study based on a typical 5G scenario. In particular, we detail the design and implementation of a Video Streaming service exploiting Mobile Edge Computing (MEC) functionalities. The analysis of the case study provide an assessment on what can be achieved with current technologies and gives a first confirmation of the validity of the proposed approach. Finally, we identify future directions of work towards the realization of a superfluid softwarized network.

1. Toward Superfluid Deployment of Virtual Functions:
Exploiting Mobile Edge Computing for Video Streaming
Stefano Salsano(1), Luca Chiaraviglio(1), Nicola Blefari-Melazzi(1), Carlos Parada(2),
Francisco Fontes(2), Rufael Mekuria(3), Dirk Griffioen(3)
(1)CNIT / Univ. of Rome Tor Vergata, Italy; (2) Altice Labs, Portugal; (3) Unified Streaming, Netherlands
Soft5 Workshop - First International Workshop on Softwarized Infrastructures for 5G
and Fog Computing, in conjunction with ITC 29
Genoa, Italy - 8th September, 2017
A super-fluid, cloud-native, converged edge system

2. Outline
• Superfluidity project: goals and architecture
• Mobile Edge Computing (MEC)
• Video Streaming with Late Transmuxing (LTM)
• Combined MEC/LTM Video streaming testbed
2

3. Superfluidity project
Superfluidity Goals
• Instantiate network functions and services on-the-fly
• Run them anywhere in the network (core, aggregation, edge), across
heterogeneous infrastructure environments (computing and networking), taking
advantage of specific hardware features, such as high performance accelerators,
when available
Superfluidity Approach
• Decomposition of network components and services into elementary and
reusable primitives (“Reusable Functional Blocks – RFBs”)
• Platform-independent abstractions, permitting reuse of network functions
across heterogeneous hardware platforms
3

4. The Superfluidity vision
4
Current NFV
technology
Granularity
Time scale
Superfluid
NFV
technology
Days, Hours Minutes Seconds Milliseconds
Big VMs
Small
components
Micro
operations • From VNF
Virtual Network Functions
to RFB
Reusable Functional Blocks
• Heterogeneous RFB execution
environments
- Hypervisors
- Modular routers
- Packet processors
…

5. Heterogeneous composition/execution environments
5
• Classical NFV environments (i.e. by ETSI NFV standards)
– VNFs are composed/orchestrated to realize Network Services
– VNFs can be decomposed in VNFC (VNF Components)
«Big»
VNF
«Big»
VNF
«Big»
VNF
«Big»
VNF
VNFC
VNFC
VNFC
VM
VM

6. Heterogeneous composition/execution environments
6
• Towards more «fine-grained» decomposition…
• Modular software routers (e.g. Click)
– Click elements are combined in configurations (Direct Acyclic Graphs)

7. Heterogeneous composition/execution environments
7
• Towards more «fine-grained» decomposition…
• XSFM-based (eXtended Finite State Machine) decomposition of
traffic forwarding / flow processing tasks, and HW support for
wire speed execution

8. The Superfluidity Architecture
8
RFB
#a
RFB
#b
RFB
#c
RFB
#n
(node-level) RDCL script
REE
RFB#2
(network-level) RDCL script
REE
Manager
REE User
REE
Resource
Entity
UM API
MR API
REE
User
UM API
REE
Resource
Entity
REE
Manager
(network-wide) REE
RFB Execution Environment
RFB#1
MR API(node-level) REE
RFB Execution Environment

9. (Towards) Common Abstractions
for Heterogeneous Environments
9
RFB Execution Environment(s) RFBs Description & Composition
Languages (RDCLs) and tools
• “Traditional” NFVI infrastructure
hypervisors with Full VMs
• Unikernel based virtualization
• Software modular routers
environments (e.g. Click)
• Radio processing SW modules
• Hardware packet processors
• ETSI VNF descriptors / NEMO
• MISTRAL – HEAT
• Docker Compose …
• Click configurations / SEFL /
Symnet
• PN (Process Networks), SDF
(Synchronous Data Flow)…
• XFSMs

10. Working prototype
RDCL 3D: RFB Description and Composition Language Design Deploy and Direct
10
This is a regular
VM (XEN HVM)
These are 3 Unikernel
VMs
(ClickOS)

11. Outline
• Superfluidity project: goals and architecture
• Mobile Edge Computing (MEC)
• Video Streaming with Late Transmuxing (LTM)
• Combined MEC/LTM Video streaming testbed
11

12. Mobile Edge Computing (MEC) Basics
12
Datacenter
Core
Central Office
Central Office
Customer

13. Mobile Edge Computing (MEC) Model
13
MEC Platform
Dedicated/Specific
Hardware
Dedicated/Specific
Hardware
COTS Hardware
Base Band
Unit B (BBU)
Base Band
Unit A (BBU)
Remote Radio
Head A (RRH)
Remote Radio
Head B (RRH)
CPRI
CPRI
(fixed)
Central
Office
DC
API API API API API
MEC-App MEC-App MEC-App
MEC-App MEC-App MEC-App
Core DC

14. Mobile Edge Computing (MEC) Architecture
14
User Traffic Forwarding
eNB/BBU
User Traffic Forwarding
CORE
(EPC)
MEC TOF
GTP-U
Encap
S/DNAT
Traffic
Filter
(UL)
Router
Traffic
Filter
(DL)
GTP-U
Encap
MEC Host
ME Service
(TOF)
ME Service
(RNIS)
ME Service
(LOC)
ME Service
(DNS)
ME App C
(e.g. Video
Streaming)
ME App B
(e.g. Augmented
Reality)
ME App A
(e.g. IoT)
GTP-U
Decap
GTP-U
Decap
NFVI
User Traffic Forwarding
UserTrafficForwarding
API
(LOC)
API
(DNS)
API
(NIS
API
(TOF)
MEPlatform(BUS)
Applications and Services (AS)
Data Plane Forwarding (DPF)
MEC System level
ME Orchestrator
Virtualized Infrastructure Management
(VIM)
Platform Manager
ME App A
Manager
ME App B
Manager
ME App C
Manager
Rep
MEC Edge level
Management and Orchestration (MO)

15. Network scenario: sharing the HW infrastructure
15
RRHs
RRHs
RRHs
ADSL
Cable
Fiber
Fixed Networks
vDSLAM/vOLT/vCTMS BBUBBU BBU
µDC-PoP
Edge Computing (MEC) Platform

16. Service Example: Local Offloading of Video Streaming
(with Late Transmuxing)
16
Core DC
MEC Host
Data Plane Data Plane
Traffic
Offloading
Function
BBURRH

17. Outline
• Superfluidity project: goals and architecture
• Mobile Edge Computing (MEC)
• Video Streaming with Late Transmuxing (LTM)
• Combined MEC/LTM Video streaming testbed
17

18. Basic Video Streaming deployment
18
JIT
PACKAGER
MPEG-DASH,
HLS, HSS, HSD
CDN
MPEG-DASH,
HLS, HSS, HSD
Media Storage
or Live Encoder
Origin ServerCDN
Proxy Cache
End-user
Devices

19. Late TransMuxing
19
1. Unified Origin: one ingest format, various output formats
2. Contribution: split and move to the edge
3. How? Use an intermediate optimal media exchange format between core and
edge, cache this format

20. Late Transmuxing Prototype
RFB based deployment
20
Video
Content
Storage
Nginx
Byte
Range
Cache
Nginx
CDN
Cache
Proxy
Back endEdge end
Manifest
Generation
Apache
Origin
Transmux
App
Manifest
Generation
Apache
Edge
Transmux
App
Multi
bit-rate
Encoder
Front end
Player
page

21. Outline
• Superfluidity project: goals and architecture
• Mobile Edge Computing (MEC)
• Video Streaming with Late Transmuxing (LTM)
• Combined MEC/LTM Video streaming testbed
21

22. Prototype architecture
22

23. UE (Bob)
MEC/Video Streaming Demo
User Traffic Forwarding
eNB/BBU
User Traffic Forwarding
Server
MEC TOF
GTP-U
Encap
S/DNAT
Traffic
Filter
(UL)
Router
Traffic
Filter
(DL)
GTP-U
Encap
GTP-U
Decap
GTP-U
Decap
Data Plane Forwarding
MEC Host
NFVI
User Traffic Forwarding
UserTrafficForwarding
Applications and Services
• The LTM server in the core is initially contacted
CORE
(EPC)
UO
LTM
UO
Storage

24. MEC Host
NFVI
User Traffic Forwarding
Applications and Services
UserTrafficForwarding
UE (Bob)
MEC/Video Streaming Demo
User Traffic Forwarding
eNB/BBU
User Traffic Forwarding
Server
MEC TOF
GTP-U
Encap
S/DNAT
Traffic
Filter
(UL)
Router
Traffic
Filter
(DL)
GTP-U
Encap
GTP-U
Decap
GTP-U
Decap
Data Plane Forwarding
Unified
Origin
LTM
• The Management and Orchestration (MANO) layer instantiates the LTM
application in the edge (so far, MANO is just a manual script execution)
CORE
(EPC)
UO
LTM
UO
Storage
MEC Management
and Orchestrator

25. MEC Host
Unified
Origin
LTM
NFVI
User Traffic Forwarding
Applications and Services
UserTrafficForwarding
UE (Bob)
MEC/Video Streaming Demo
User Traffic Forwarding
eNB/BBU
User Traffic Forwarding
Server
MEC TOF
GTP-U
Encap
S/DNAT
Traffic
Filter
(UL)
Router
Traffic
Filter
(DL)
GTP-U
Encap
GTP-U
Decap
GTP-U
Decap
Data Plane Forwarding
• After the LTM instantiation is fully operational, the MANO layer
configures the TOF in order to redirect the video request to the new LTM
CORE
(EPC)
UO
LTM
UO
Storage
MEC Management
and Orchestrator

26. MEC Host
Unified
Origin
LTM
NFVI
User Traffic Forwarding
Applications and Services
UserTrafficForwarding
UE (Bob)
MEC/Video Streaming Demo
User Traffic Forwarding
eNB/BBU
User Traffic Forwarding
Server
MEC TOF
GTP-U
Encap
S/DNAT
Traffic
Filter
(UL)
Router
Traffic
Filter
(DL)
GTP-U
Encap
GTP-U
Decap
GTP-U
Decap
Data Plane Forwarding
• The subscriber will, transparently, start getting the video service from
the edge LTM, which in turn accesses the central storage for contents
CORE
(EPC)
UO
LTM
UO
Storage

27. Testbed Results
27

28. Testbed Results
Deployment time of Edge Video Streaming components
28

29. Thank you. Questions?
Contacts
Stefano Salsano
University of Rome Tor Vergata / CNIT
stefano.salsano@uniroma2.it
http://superfluidity.eu/
The work presented here only covers a subset of the work performed in the project
29

30. References
• SUPERFLUIDITY project Home Page http://superfluidity.eu/
• G. Bianchi, et al. “Superfluidity: a flexible functional architecture for 5G networks”, Transactions on
Emerging Telecommunications Technologies 27, no. 9, Sep 2016
• S. Salsano, L. Chiaraviglio, N. Blefari-Melazzi, C. Parada, F. Fontes, R. Mekuria, D. Griffioen,
“Toward Superfluid Deployment of Virtual Functions: Exploiting Mobile Edge Computing for Video
Streaming”, Soft5 Workshop, 1st International Workshop on Softwarized Infrastructures for 5G and
Fog Computing, in conjunction with 29th ITC conference, Genoa, Italy, 8th September 2017
• S. Salsano, F. Lombardo, C. Pisa, P. Greto, N. Blefari-Melazzi,
“RDCL 3D, a Model Agnostic Web Framework for the Design and Composition of NFV Services”,
submitted paper, https://arxiv.org/abs/1702.08242
• L. Chiaraviglio, L. Amorosi, S. Cartolano, N. Blefari-Melazzi, P. Dell’Olmo, M. Shojafar, S. Salsano,
“Optimal Superfluid Management of 5G Networks”,
3rd IEEE Conference on Network Softwarization, NetSoft 2017, 3-7 July 2017, Bologna, Italy
30

31. The SUPERFLUIDITY project has received funding from the European Union’s Horizon
2020 research and innovation programme under grant agreement No.671566
(Research and Innovation Action).
The information given is the author’s view and does not necessarily represent the view
of the European Commission (EC). No liability is accepted for any use that may be
made of the information contained.
31