Assisting Delay and Bandwidth Sensitive Applications in a Self-Driving Network

Madanapalli, Sharat Chandra; Gharakheili, Hassan Habibi; Sivaraman, Vijay

doi:10.1145/3341216.3342215

Cited by 8 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This might affect users' experience, especially in gaming. However, a ping rate from 20 to 100 ms will still get to enjoy the gameplay, but might not give maximum performance for games where timing is everything [19].…”

Section: Results and Analysismentioning

confidence: 99%

Securing Network Using Raspberry Pi by Implementing VPN, Pi-Hole, and IPS (VPiSec)

Taib¹

2020

IJATCSE

View full text Add to dashboard Cite

Every device on earth these days is associated with the Internet which brings humans an advancement of communication. Nonetheless, this technology discloses the user to the security threat. Barely users are sensitive that their data are being monitored by Internet Service Providers (ISPs) and other third-party companies. Furthermore, every webpage they visit, each information they fill in the search box are being monitored by a third-party company that wanted to know the user's interest and then will pop up advertisement which related to the user's interest. This turns into the issue when the third party has all the sensitive information and misuses it in unethical manners. Thus, it is the reason why a device that can protect the user is needed. A device with a capability to conceal the user's Internet Protocol (IP) and protect the user from any tracker and advertisement from the internet is proposed in this project. Hiding the user's IP address can be done by masking it with the OpenVPN server that is deployed in another country than making it safe for the user from being tracked by an attacker. Besides, blocking any Domain Name System (DNS) request for known tracking and advertising domain is achieved by using the Pi-Hole project that is being maintained by the online community. Along with that, the implementation of OSSEC IPS inside the Raspberry Pi has successfully prevented the brute force attack from inside the network to provide additional protection. The device with these integrated features is called VPiSec. Then, the network performance in terms of speed during the uploading and downloading before and after applying VPiSec is evaluated to see whether it is degraded. The findings show that there is no significant difference in terms of uploading and downloading speed without and with the application of WPiSec. Thus, users gained secure network activities while enjoying a smooth network performance.

show abstract

Section: Results and Analysismentioning

confidence: 99%

Securing Network Using Raspberry Pi by Implementing VPN, Pi-Hole, and IPS (VPiSec)

Taib¹

2020

IJATCSE

View full text Add to dashboard Cite

show abstract

“…An Autonomic Management System (AMS) proposal for automated intent realization. Currently, there is no accepted framework yet, and most of the literature focuses on specific elements of a self-driving network, for instance Jacobs [82] focuses on the intent refinement to translate intents expressed in natural languages; Madanapalli [87] explores quality of experience by detecting deteriorated states and applying corrective actions; Zerwas [88] proposes self-driving network benchmarks; and Pasandi [89] proposes a self-driving approach for the design and evaluation of network protocols.…”

Section: Ourmentioning

confidence: 99%

Towards a Self-Driving Management System for the Automated Realization of Intents

Dzeparoska¹,

Beigi-Mohammadi

Tizghadam

et al. 2021

IEEE Access

View full text Add to dashboard Cite

“…In terms of QoE, our work complements and builds upon existing literature by developing a method to detect buffer stalls by tracking the buffer health of live video streams in real-time. The QoE metrics obtained from our system can be further used to augment: routing optimization systems like [20], or an adaptive scheduling systems like [21]. Our design choices primarily aim at scalability and ease of deployment by identifying inexpensive traffic attributes (to compute), and building machine learning models that are "general" (work across providers) and "simple" (lower-memory footprint, and ease of training and deployment).…”

Section: Related Workmentioning

confidence: 99%

Modeling Live Video Streaming: Real-Time Classification, QoE Inference, and Field Evaluation

Madanapalli¹,

Mathai²,

Gharakheili³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Social media, professional sports, and video games are driving rapid growth in live video streaming, on platforms such as Twitch and YouTube Live. Live streaming experience is very susceptible to short-time-scale network congestion since client playback buffers are often no more than a few seconds. Unfortunately, identifying such streams and measuring their QoE for network management is challenging, since content providers largely use the same delivery infrastructure for live and videoon-demand (VoD) streaming, and packet inspection techniques (including SNI/DNS query monitoring) cannot always distinguish between the two.In this paper, we design, build, and deploy ReCLive: a machine learning method for live video detection and QoE measurement based on network-level behavioral characteristics. Our contributions are four-fold: (1) We analyze about 23,000 video streams from Twitch and YouTube, and identify key features in their traffic profile that differentiate live and on-demand streaming. We release our traffic traces as open data to the public; (2) We develop an LSTM-based binary classifier model that distinguishes live from on-demand streams in real-time with over 95% accuracy across providers; (3) We develop a method that estimates QoE metrics of live streaming flows in terms of resolution and buffer stall events with overall accuracies of 93% and 90%, respectively; and (4) Finally, we prototype our solution, train it in the lab, and deploy it in a live ISP network serving more than 7,000 subscribers. Measurements from the field show that 99.8% of Twitch videos are streamed live, while this measure is only 2.3% for YouTube. Further, during peak hours as many as 15% of live video streams are played at low-definition resolution and about 7% of them experience a buffer stall. Our method provides ISPs with fine-grained visibility into live video streams, enabling them to measure and improve user experience.

show abstract

Assisting Delay and Bandwidth Sensitive Applications in a Self-Driving Network

Cited by 8 publications

References 12 publications

Securing Network Using Raspberry Pi by Implementing VPN, Pi-Hole, and IPS (VPiSec)

Securing Network Using Raspberry Pi by Implementing VPN, Pi-Hole, and IPS (VPiSec)

Towards a Self-Driving Management System for the Automated Realization of Intents

Modeling Live Video Streaming: Real-Time Classification, QoE Inference, and Field Evaluation

Contact Info

Product

Resources

About