Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
ES-HAS: An Edge- and SDN-Assisted Framework for
HTTP Adaptive Video Streaming
31st
ACM NOSSDAV 2021
October 1st
, 2021
rez...
Agenda
● Introduction
● State of the art
● Motivating example
● Proposed solution
● Evaluation setup
● Experimental result...
Introduction
3
● Video traffic has become the dominant traffic over the
Internet.
● It is expected to reach more than 82% of all Internet t...
● The adaptation process can be performed with different schemes:
○ Pure client-based:
■ The decision is based on the loca...
● The fundamental paradigm of modern networks to
address the limitations of conventional network architecture
like:
○ Comp...
● It is considered as a complementary technology to SDN
● NFV enables Virtual Network Functions (VNFs) to
○ run over an op...
State of the art
8
SABR: Network assisted content distribution for
adaptive bitrate video streaming
9
Bhat, D., Rizk, A., Zink, M. and Steinm...
Motivating example
10
Motivating example- Exchanged messages in SABR
11
● The number of DASH clients
● The number of exchanged messages to/from
...
Proposed solution
12
Proposed solution
13
1. Use Virtual reverse proxy servers (VRP) at the edge of network
2. VRPs play the role of a gateway ...
Exchanged messages in ES-HAS
14
The number of messages to/from the SDN
controller will decrease in ES-HAS
ES-HAS Architecture
15
● We leverage SDN, NFV, edge computing and propose our architecture in three layers
ES-HAS Architecture
16
RAM
17
SOM
ES-HAS Architecture
Server/Segment selection policy
18
Our server/segment policy is :
1. When the requested quality level exist in the cache s...
Evaluation setup
19
We evaluate the performance of ES-HAS compared to SABR and pure client-based
approaches on a large-scale cloud-based testb...
Experimental results
21
● We analyze the behavior of ES-HAS MILP Model by :
a. MILP model execution time
b. Different numbers of segment requests ...
● We analyze the Impact of different parameters on ES-HAS MILP model behavior by:
a. ACS : the average usage percentage of...
Requested quality levels vs. forwarded quality levels
24
Playback bitrate in different approaches:
25
Number of Stalls and Quality switch in different
approaches:
26
27
Conclusion and Future work
● This paper leverages the SDN and NFV paradigms to propose the ES-HAS framework
providing network assistance for HTTP ada...
Thank you for your attention
reza.farahani@aau.at | https://athena.itec.aau.at/
All rights reserved. ©2020
29
Upcoming SlideShare
Loading in …5
×

of

ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 1 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 2 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 3 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 4 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 5 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 6 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 7 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 8 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 9 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 10 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 11 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 12 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 13 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 14 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 15 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 16 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 17 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 18 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 19 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 20 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 21 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 22 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 23 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 24 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 25 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 26 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 27 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 28 ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming Slide 29
Upcoming SlideShare
What to Upload to SlideShare
Next
Download to read offline and view in fullscreen.

0 Likes

Share

Download to read offline

ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming

Download to read offline

Recently, HTTP Adaptive Streaming (HAS) has become the dominant video delivery technology over the Internet. In HAS, clients have full control over the media streaming and adaptation processes. Lack of coordination among the clients and lack of awareness of the network conditions may lead to sub-optimal user experience, and resource utilization in a pure client-based HAS adaptation scheme. Software-Defined Networking (SDN) has recently been considered to enhance the video streaming process. In this paper, we leverage the capability of SDN and Network Function Virtualization (NFV) to introduce an edge- and SDN-assisted video streaming framework called ES-HAS. We employ virtualized edge components to collect HAS clients’ requests and retrieve networking information in a time-slotted manner. These components then perform an optimization model in a time-slotted manner to efficiently serve clients’ requests by selecting an optimal cache server (with the shortest fetch time). In case of a cache miss, a client’s request is served (i) by an optimal replacement quality (only better quality levels with minimum deviation) from a cache server, or (ii) by the originally requested quality level from the origin server. This approach is validated through experiments on a large-scale testbed, and the performance of our framework is compared to pure client-based strategies and the SABR system [11]. Although SABR and ES-HAS show (almost) identical performance in the number of quality switches, ES-HAS outperforms SABR in terms of playback bitrate and the number of stalls by at least 70% and 40%, respectively.

Related Books

Free with a 30 day trial from Scribd

See all
  • Be the first to like this

ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming

  1. 1. ES-HAS: An Edge- and SDN-Assisted Framework for HTTP Adaptive Video Streaming 31st ACM NOSSDAV 2021 October 1st , 2021 reza.farahani@aau.at | https://athena.itec.aau.at/ Reza Farahani, Farzad Tashtarian, Alireza Erfanian, Christian Timmerer, Mohammad Ghanbari, Hermann Hellwagner
  2. 2. Agenda ● Introduction ● State of the art ● Motivating example ● Proposed solution ● Evaluation setup ● Experimental results ● Conclusion and Future work
  3. 3. Introduction 3
  4. 4. ● Video traffic has become the dominant traffic over the Internet. ● It is expected to reach more than 82% of all Internet traffic in 2021 [1]. ● HTTP adaptive streaming (HAS) has been considered as the de-facto video delivery technology over the Internet. Introduction- Video Streaming 4 [1] Cisco. Global - 2021 Forecast Highlights. https://www.cisco.com/c/dam/m/en_us/solutions/service-provider/vni-forecast-highlights/pdf/Global_2021_Forecast_Highlights.pddf
  5. 5. ● The adaptation process can be performed with different schemes: ○ Pure client-based: ■ The decision is based on the local parameters, e.g., ● buffer status ● estimated available bandwidth ■ Insufficient information about the network ● It can lead to a suboptimal adaptation decision ○ Network-assisted: ■ The decision is performed via a centralized network component with a global view of the entire network topology. ■ can be more beneficial for the users’ QoE ● Fundamental paradigms of modern networks, i.e., SDN, NFV, edge computing have been used in modern network-assisted frameworks Introduction- Network-assisted video streaming 5
  6. 6. ● The fundamental paradigm of modern networks to address the limitations of conventional network architecture like: ○ Complex Network Devices ○ Management Overhead ○ Limited Scalability ● The control plane (forwarding decision) is decoupled from the data plane (acts on the forwarding decision) ○ Centralized Network Controller ○ Standard communication Interface (OpenFlow), ○ Programmable Open APIs Introduction-Software-Defined Networking (SDN) 6
  7. 7. ● It is considered as a complementary technology to SDN ● NFV enables Virtual Network Functions (VNFs) to ○ run over an open hardware platform ○ Reduce OpEx, CapEx ○ Accelerate innovations Introduction-Network Function Virtualization (NFV) 7 Router Switch Load Balancer (LB) Firewall Virtualization Layer VRouter VFirewall VSwitch VLB VNF VNF VNF VNF
  8. 8. State of the art 8
  9. 9. SABR: Network assisted content distribution for adaptive bitrate video streaming 9 Bhat, D., Rizk, A., Zink, M. and Steinmetz, R., 2017, June. Network assisted content distribution for adaptive bitrate video streaming. In Proceedings of the 8th ACM on Multimedia Systems Conference (pp. 62-75).
  10. 10. Motivating example 10
  11. 11. Motivating example- Exchanged messages in SABR 11 ● The number of DASH clients ● The number of exchanged messages to/from the SDN controller ● System efficiency
  12. 12. Proposed solution 12
  13. 13. Proposed solution 13 1. Use Virtual reverse proxy servers (VRP) at the edge of network 2. VRPs play the role of a gateway for the client to the network and vice versa 3. DASH clients send requests to the VRP for the desired segments’ qualities, and the VRP collects these received requests in each time slot 4. The VRP requests the cache map and network status information from the SDN controller for all collected requests 5. The VRP determine the optimal cache servers for the gathered clients’ requests.
  14. 14. Exchanged messages in ES-HAS 14 The number of messages to/from the SDN controller will decrease in ES-HAS
  15. 15. ES-HAS Architecture 15 ● We leverage SDN, NFV, edge computing and propose our architecture in three layers
  16. 16. ES-HAS Architecture 16 RAM
  17. 17. 17 SOM ES-HAS Architecture
  18. 18. Server/Segment selection policy 18 Our server/segment policy is : 1. When the requested quality level exist in the cache servers (Cache hit) ○ find the cache server with minimum fetch time 2. When the requested quality level is not available in any cache server (Cache miss) ○ serve client with replacement quality from a cache server with minimum fetch time ○ fetch the original requested quality from the origin server We propose a MILP optimization model to find the optimal solution by :
  19. 19. Evaluation setup 19
  20. 20. We evaluate the performance of ES-HAS compared to SABR and pure client-based approaches on a large-scale cloud-based testbed. ○ Sixty clients (AStream DASH Player) ○ Four cache servers (60% of the videos’ segment) and an Origin server (Apache web server) ○ Five OpenFlow switches (Ubuntu 18.04 LTS inside Xen virtual machines) ○ An SDN controller (dockerized Floodlight) ○ Two VRP servers (Python, and Pulp with CBC solver) ○ A video Dataset including: ■ ten video sequences (BBB with 150 segments) ■ 2, 4, 6 segments ■ five representations ({0.89, .260, .790, 2.4, 4.2} Mbps) ○ Two ABR algorithms (Squad, and BOLA) ○ MongoDB for cache-map transaction ○ Different Network paths with various bandwidth ○ Bandwidth monitoring (Floodlight Restful API) ○ LRU cache replacement policy Testbed 20
  21. 21. Experimental results 21
  22. 22. ● We analyze the behavior of ES-HAS MILP Model by : a. MILP model execution time b. Different numbers of segment requests and cache servers c. Different video segment duration Evaluation of the ES-HAS MILP Model 22
  23. 23. ● We analyze the Impact of different parameters on ES-HAS MILP model behavior by: a. ACS : the average usage percentage of cache servers with the shortest fetch time b. AMD: the average (for different accepted max-deviation value) of the maximum deviation between requested quality and forwarded quality c. AQB: the average of the video quality bitrate for all received segments in Mbps Evaluation of the ES-HAS MILP Model 23
  24. 24. Requested quality levels vs. forwarded quality levels 24
  25. 25. Playback bitrate in different approaches: 25
  26. 26. Number of Stalls and Quality switch in different approaches: 26
  27. 27. 27 Conclusion and Future work
  28. 28. ● This paper leverages the SDN and NFV paradigms to propose the ES-HAS framework providing network assistance for HTTP adaptive video streaming ● We introduce components named VRPs at the edge of the network that employs a novel server/segment policy. ● We implement the proposed framework and its modules on a cloud-based large-scale testbed consisting of 60 clients and conducts experiments in different scenarios ● ES-HAS outperforms state-of-the-art approach in terms of playback bitrate and the number of stalls by at least 70% and 40%, respectively. ● Edge caching, Edge collaboration, extending proposed MILP model, and utilizing learning-based approach are possible future work directions. Ongoing and Future Work All rights reserved. ©2020 28
  29. 29. Thank you for your attention reza.farahani@aau.at | https://athena.itec.aau.at/ All rights reserved. ©2020 29

Recently, HTTP Adaptive Streaming (HAS) has become the dominant video delivery technology over the Internet. In HAS, clients have full control over the media streaming and adaptation processes. Lack of coordination among the clients and lack of awareness of the network conditions may lead to sub-optimal user experience, and resource utilization in a pure client-based HAS adaptation scheme. Software-Defined Networking (SDN) has recently been considered to enhance the video streaming process. In this paper, we leverage the capability of SDN and Network Function Virtualization (NFV) to introduce an edge- and SDN-assisted video streaming framework called ES-HAS. We employ virtualized edge components to collect HAS clients’ requests and retrieve networking information in a time-slotted manner. These components then perform an optimization model in a time-slotted manner to efficiently serve clients’ requests by selecting an optimal cache server (with the shortest fetch time). In case of a cache miss, a client’s request is served (i) by an optimal replacement quality (only better quality levels with minimum deviation) from a cache server, or (ii) by the originally requested quality level from the origin server. This approach is validated through experiments on a large-scale testbed, and the performance of our framework is compared to pure client-based strategies and the SABR system [11]. Although SABR and ES-HAS show (almost) identical performance in the number of quality switches, ES-HAS outperforms SABR in terms of playback bitrate and the number of stalls by at least 70% and 40%, respectively.

Views

Total views

600

On Slideshare

0

From embeds

0

Number of embeds

540

Actions

Downloads

1

Shares

0

Comments

0

Likes

0

×