1 / 23

Using Tuángòu to Reduce IP Transit Costs

团购 ( tuángòu ) = group-buying. Using Tuángòu to Reduce IP Transit Costs. Rade Stanojevic (Joint work with Ignacio Castro and Sergey Gorinsky ) ‍‍ ACM CoNext 2011 Tokyo, Japan. Part 1: Tuángòu for IP transit . IP transit as a service. IP transit

annick
Télécharger la présentation

Using Tuángòu to Reduce IP Transit Costs

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. 团购 (tuángòu)= group-buying Using Tuángòuto Reduce IP Transit Costs RadeStanojevic (Joint work with Ignacio Castro and Sergey Gorinsky) ‍‍ ACM CoNext 2011 Tokyo, Japan

  2. Part 1: Tuángòufor IP transit CIPT: Using Tuángòu to Reduce IP Transit Costs

  3. IP transit as a service • IP transit • Lower tier ISPs customers of higher tier ISPs • Critical for global connectivity • Fee depends on traffic CIPT: Using Tuángòu to Reduce IP Transit Costs

  4. IP Transit costs • Affects almost every online entity • IP transit cost-reduction technologies • ISP peering • CDN • Multicast • P2P localization • Traffic shaping (P2P throttling) • The less traffic on transit links the lower the cost CIPT: Using Tuángòu to Reduce IP Transit Costs

  5. CIPT: Cooperative IP transit • Simple idea: • Exploit the IP transit market properties: • Price elasticity • 95th-percentile pricing purchase in group and share the costs CIPT: Using Tuángòu to Reduce IP Transit Costs

  6. IP transit billing: two key properties • Price elasticity • Peak based traffic metering: 95th-percentile pricing • Submodularity of the peak: • peak(f) + peak(g) ≥ peak(f+g) Voxelpricing Source=https://www.voxel.net/ip-services (as accessed on June 2011) CIPT: Using Tuángòu to Reduce IP Transit Costs

  7. CIPT as a cooperative game • How to share the benefits of cooperation? • Shapley value • ‘Fair’, exists and unique for any cooperative game • Individually rational (everyone better off in the coalition) • Hard to calculate exactly for large number of players • Monte-Carlo method for accurate estimation CIPT: Using Tuángòu to Reduce IP Transit Costs

  8. Part 2: Quantifying CIPT benefits CIPT: Using Tuángòu to Reduce IP Transit Costs

  9. From peering to transit traffic • ISP Transit traffic data: not available • ISP Peering traffic data: available at some IXPs • Peering traffic as a proxy for estimating transit traffic • Ttransit(t) = cTpeering(t) • Validation using 4 medium-sized (academic) ISPs CIPT: Using Tuángòu to Reduce IP Transit Costs

  10. Obtaining peering traffic data 1. Peering traffic data of 264 ISPs from 6 IXPs Collection of mrtg images Optical function/ character recognition 2. Transform images into numeric data on peering traffic CIPT: Using Tuángòu to Reduce IP Transit Costs

  11. Country-wide coalitions • Expected cost savings in the range of 8%-56% • ISP traffic volume distribution, peak-hour profile, nmb of transit providers, etc. • Per ISP savings from $1K to few $100K per year • Smallest ISPs save >90%, Largest ISPs save <10% • Breakdown • Around 1/3 of the savings come from the 95th-pct • The rest comes from the elastic pricing • Check the paper for details… CIPT: Using Tuángòu to Reduce IP Transit Costs

  12. CIPT coalition size: low of diminishing returns • Small (random) coalitions provide most of total attainable gains CIPT: Using Tuángòu to Reduce IP Transit Costs

  13. Beyond gains sharing • Organizational embodiment • Physical infrastructure • Performance/SLAs • Traffic confidentiality • Transit providers and strategic issues CIPT: Using Tuángòu to Reduce IP Transit Costs

  14. Open problems • CIPT coalition formation process? • Shapley value too implicit. Simpler metrics? • Tuángòu in other (price-elastic) domains? • IP transport • Wired/wireless access • Mobile voice/txt/data CIPT: Using Tuángòu to Reduce IP Transit Costs

  15. Conclusions • Team-buying has potential for cutting IP transit bill • Shapley value as a mechanism for cost sharing • Unique dataset of traffic data from 264 ISPs with heterogeneous sizes and temporal properties CIPT: Using Tuángòu to Reduce IP Transit Costs

  16. Backup slides CIPT: Using Tuángòu to Reduce IP Transit Costs

  17. Cooperative IP Transit (CIPT) • Tuángòu = team-buying coalitional arrangement for bulk buying of IP transit • CIPT gains Per-Mbps price reduction thanks to elastic pricing and peak-based (95th-pct) metering CIPT: Using Tuángòu to Reduce IP Transit Costs

  18. Price decay vs. traffic growth Per-Mbps transit price decline vs. interdomain traffic growth Source=https://www.telegeography CIPT: Using Tuángòu to Reduce IP Transit Costs

  19. Shapley value definition • Shapley value(i) • ISPi's expected marginal contribution if the players join the coalition one at a time, in a uniformly random order i’s marginal contribution N = number of players c(S)= cost of coalition S S(π,i) = set of players arrived in the system not later than i π = permutations of the set of players N CIPT: Using Tuángòu to Reduce IP Transit Costs

  20. Shapley value estimation • Monte Carlo method* • We estimate the Shapley value as the average cost contribution over set πkof K randomly sampled arrival orders. • Estimation accuracy • Kis the knob controlling the accuracy • We use K = 1000 to keep the error under 1% (*) D. Liben-Nowell, A. Sharp, T. Wexler, K. Woods, “Computing Shapley Value in Cooperative Supermodular Games”, Preprint, 2010. R. Stanojevic, N. Laoutaris, P. Rodriguez, “On Economic Heavy Hitters: Shapley Value Analysis of the 95th-Percentile Pricing”, Proc. of ACM IMC 2010. CIPT: Using Tuángòu to Reduce IP Transit Costs

  21. Peering-transit traffic similarity • Peering = 35-40% of the total traffic. • Peering and transit follow very similar patterns. CIPT: Using Tuángòu to Reduce IP Transit Costs

  22. Aggregate CIPT gains • Absolute aggregate CIPT gains grow with IXP size (in terms of billed traffic) • Relative aggregate CIPT gains decrease with IXP size CIPT: Using Tuángòu to Reduce IP Transit Costs

  23. Per-partner CIPT gains • Absolute individual CIPT gains grow with ISP size • Relative individual CIPT gains decrease with ISP size There are large gains for all CIPT members CIPT: Using Tuángòu to Reduce IP Transit Costs

More Related