The Economics of Transit and Peering Interconnections in the Internet Amogh Dhamdhere (CAIDA/UCSD)...

The Economics of Transit and Peering Interconnections in the

InternetAmogh Dhamdhere (CAIDA/UCSD)

[email protected]

Constantine Dovrolis (Georgia Tech)Pierre Francois (Univ. catholique de Louvain)

Kc Claffy (CAIDA)

04/18/23 1

mailto:[email protected]

Outline

• Motivation

• ITER: A computational model of interdomain interconnection

• Modeling the transition from the “old” to the “new” Internet

• Modeling complex interdomain relationships: value-based peering

• Ongoing Work

04/18/23 The Economics of Transit and Peering Interconnections 2

[CoNEXT 2010, to appear]

[ITC 2010, NANOG 49]

[NSF NETSE grant, 2010-2013]

The Internet Ecosystem

• >30,000 autonomous networks independently operated and managed

• The “Internet Ecosystem”– Different types of networks– Interact with each other and with “environment”

• Network interactions– Localized, in the form of bilateral contracts– Competitive (customer-provider), symbiotic (peering)

• Distributed optimizations by each network

04/18/23 3The Economics of Transit and Peering Interconnections

High Level Questions

• How does the Internet ecosystem evolve?

• What is the Internet heading towards?– Topology– Economics– Performance

• Which interconnection strategies of networks optimize their profits, costs and performance?

• How do these strategies affect the global Internet?


Economics of the Internet Ecosystem


Source: Cisco

Source: Arbor Networks

Source: William Norton

Source: IAB

Economics of the Internet Ecosystem

How do we make sense of all this?


Economically-principled models

• Objective: understand the structure and dynamics of the Internet ecosystem from an economic perspective

• Capture interactions between network business relations, internetwork topology, routing policies, and resulting interdomain traffic flow

• Create a scientific basis for modeling Internet interconnection and dynamics based on empirical data


Previous Work

• “Descriptive”– Match graph properties

e.g. degree distribution

• Homogeneity– Nodes and links all the

same

• Game theoretic, analytical– Restrictive assumptions

• Little relation to real-world data

04/18/23 8

• “Bottom-up”– Model the actions of

individual networks

• Heterogeneity– Networks with different

incentives, link types

• Computational– As much realism as

possible

• Parameterize/validate using real data

The Economics of Transit and Peering Interconnections

Outline

• Motivation




• Ongoing Work


The ITER Model

Agent-based computational model to answer “what-if” questions about Internet evolution

Inputs: According to the best available data… Network types based on business function Peer/provider selection methods Geographical constraints Pricing/cost parameters Interdomain traffic matrix

Output: Equilibrium internetwork topology, traffic flow, per-network fitness

1004/18/23 The Economics of Transit and Peering Interconnections

The ITER approach

11

InterdomainTM

Traffic flow

Interdomain topology

Per-ASfitness

Cost/priceparameters

Routing

Providerselection

Peer selection

Compute equilibrium: no network has the incentive to change its providers/peers

Measure topological and economic properties of equilibrium e.g., path lengths, which providers are profitable, who peers with whom


Why Study Equilibria?

• The Internet is never at equilibrium, right?– Networks come and go, traffic patterns change,

pricing/cost structures change, etc….

• Studying equilibria tells us what’s the best that networks could do under certain traffic/economic conditions, and what that means for the Internet as a whole

• If those conditions change, we need to re-compute equilibria


ITER: Network Types

• Enterprise Customers (EC)– Stub networks at the edge, e.g. Georgia Tech

• Transit Providers– Provide Internet transit– Regional in scope (STP), e.g. Comcast– “Tier-1” or global (LTP), e.g., AT&T

• Content Providers (CP)– Major sources of content, e.g. Google


ITER: Provider and Peer Selection

• Provider selection– Choose providers based on customer cone size– Good measure of the “size” of a provider– Used by commercial products, e.g., Renesys

• Peer selection strategies– Peer based on total traffic handled– Approximates the “equality” of two ISPs


ITER: Economics, Routing and Traffic Matrix

• Realistic transit, peering and operational costs– Transit prices based on data from NANOG

• BGP-like routing policies– No-valley, prefer customer, prefer peer routing policy

• Traffic matrix– Heavy-tailed content popularity and consumption by sinks

– client-server traffic: from CPs to ECs

– peer-to-peer traffic: between ECs


Computing Equilibrium

• Situation where no network has the incentive to change its connectivity

• Too complex to find analytically: Solve computationally

• Computation– Proceeds iteratively, networks “play” in sequence– Compute routing, traffic flow, AS fitness– Repeat until no player has incentive to move


Properties of the equilibrium

• Is equilibrium always reached?– Yes, in most cases

• Is the equilibrium unique?– No, can depend on playing sequence

• Multiple runs with different playing sequence– Per-network properties vary widely across runs– Macroscopic properties show low variability


Outline

• Motivation




• Ongoing Work


[CoNEXT 2010, to appear]

Recent Trends: Arbor Networks Study

• The Old Internet (late 90s – 2007)

• Content providers generated small fraction of total traffic

• Content providers were mostly local

• Peering was restrictive

• The New Internet (2007 onwards)

• Content providers generate large fraction of total traffic

• Content providers are present everywhere

• Peering is more open

“Internet Interdomain Traffic”, Labovitz et al., Sigcomm 2010


Plugging into ITER

• Simulate two instances of ITER: “Old” and “New” Internet

• Change three parameters– Fraction of traffic sourced by CPs– Geographical spread of CPs– Peering openness

• Compute equilibria for these two instances– Compare topological, economic properties


ITER Sims: End-to-end Paths

• End-to-end paths weighted by traffic are shorter in the “new Internet”


ITER Sims: Traffic Transiting Transit Providers

• Traffic bypasses transit providers

• More traffic flows directly on peering links

• Implication: Transit providers lose money!

• Content providers get richer


ITER Sims: Peering in the New Internet

• Transit providers need to peer strategically in the “new” Internet

• Peering with large Content Providers benefits transit providers in the new Internet

• Try to attract traffic by peering with CPs


Outline

• Motivation




• Ongoing Work


[ITC 2010, NANOG 49]

Complex Interdomain Relationships

• So far, we considered customer-provider and settlement-free peering links

• Customer-provider: customer pays provider

• Settlement-free peering: No payments

• A whole spectrum of relationships somewhere in between – paid peering

• “To peer or not to peer?” “To peer or not to peer, at what price?”


To Peer or Not to Peer, at What Price?

26

AA BB

Should I peer with B? make

Should it be settlement-free or

paid-peering?What price would B be

willing to offer (or accept) ?

???


Value Based Peering

Price based on the “value” of the link

For a network, define the notion of “fitness” f = revenue – interconnect costs – backhaul cost

Value of the link is the difference in fitness with and without the link

V = fwith - fwithout

Revenue and costs could change on peering/depeering


What Affects Peering Value?

• Interconnect cost changes: Avoid a transit provider

• Backhaul cost changes: Peering link changes how traffic is routed in a network

• Revenue changes: Attract/lose traffic due to new peering link

28

AA BB

TT

$$$

$$$ $$$


The Fair Peering Price

An oracle knows VA

and VB

Oracle must decide the price for peering

Fair price is (VA-V

B)/2

29

The fair price equalizes the benefit that A and B see from the link

AA BB

VA VB

(VA-VB)/2


Why Peer at the Fair Price? Peering with the fair price is optimal

Both networks see better fitness by peering at the fair price

Peering with the fair price is stable No network has the incentive to unilaterally depeer the

other network Unique Nash Equilibrium

Optimal and stable as long as VA+V

B > 0

Either VA or VB can be negative, as long as total is positive For cost-benefit peering, both VA and VB must be positive


Some Hard Questions..

Value-based peering is fair, optimal and stable. But is there an incentive to be fair?

How do networks estimate peering value?

What if networks lie about peering value?

What happens if everyone uses value-based peering?


ITER Results: Value-based Peering

Higher density of peering links with value-based peering Shorter end-to-end paths Links that are not allowed with traffic-ratio or cost-

benefit peering are possible with value-based peering

Payment direction: Content providers end up paying large transit providers, get paid by smaller transit providers This could be happening already!


Outline

• Motivation




• Ongoing Work


[NSF NETSE grant, Aug 2010-2013]

Ongoing Work

• Strategy selection by ISPs– Model how networks dynamically change their

provider/peer selection strategies– What is the best possible strategy for different

network types?

• Managing the cost of network traffic– Model traffic related-costs for ISPs– Support peering decisions, capacity upgrades,

differential pricing models


[A. Lodhi, A. Dhamdhere, C. Dovrolis]

[M. Motiwala, A. Dhamdhere, N. Feamster, A. Lakhina]

Avoiding “garbage-in, garbage-out”

• Models are only as good as the data you provide as input

• How do we get the best possible data to parameterize ITER-like models?

• What data do we need?– Interdomain traffic patterns– Peering policies– Geographical presence of networks– Cost/pricing structures


Measuring Interdomain Traffic

• We don’t really know how much traffic each pair of networks exchanges!

• Measure qualitative properties of the interdomain TM from different vantage points


GT GT

A A B B

Internet

Internet

Netflow


• We don’t really know how much traffic each pair of networks exchanges!

• Measure qualitative properties of the interdomain TM from different vantage points


C C A A

B B

ISP ISPNetflow


• We need data from as many vantage points as possible!

• Currently working with GEANT, SWITCH, Georgia Tech

• Let us know if you can help!


C C A A

B B

ISP ISPNetflow

Summary

• We need realistic, economically-principled models to make sense of the Internet ecosystem

• We developed ITER, a computational model of interdomain interconnection

• We are working on better parameterization and validation using real-world measurements

• We need your help and feedback!


[email protected]

www.caida.org/~amogh


mailto:[email protected]

References

• “The Internet is Flat: Modeling the Transition from a Transit Hierarchy to a Peering Mesh”– A. Dhamdhere, C. Dovrolis [CoNEXT 2010]

• “A Value-based Framework for Internet Peering Agreements”– A. Dhamdhere, C. Dovrolis, P. Francois [ITC 2010]

• “The Economics of Transit and Peering Interconnections in the Internet”– C. Dovrolis, K. Claffy, A. Dhamdhere [NSF NETSE 2010-2013]


Backup slides


Network actions

• Networks perform their actions sequentially

• Can observe the actions of previous networks– And the effects of those actions on traffic flow and

economics

• Network actions in each move– Pick set of preferred providers– Evaluate each existing peering link– Try to create new peering links


Three Factors

• Fraction of traffic sourced by CPs

• Geographical presence of CPs

• Peering openness• All three factors need to

change to see the differences between the “old” and “new” Internet


Peering Requirements

Laundry list of conditions that networks specify as requirements for (settlement-free) peering Traffic ratios, minimum traffic, backbone capacity,

geographical spread …

Heuristics to find networks for which it makes sense to exchange traffic for “free” But when it comes to paid peering.. What is the right price? Who should pay whom?

Are these heuristics always applicable? Mutually beneficial peering links may not be formed


Peering Uncertainty – Current Peers

46

AA BB

Why is B still a settlement-free peer?

Does B benefit more than me? make Should I demand

payment? Should I depeer?


Negative Peering Value

47

A A B B

fA: $50k $60k fB: $100k $95k

VB=-$5kVA=$10k

$7.5k

$52.5k $102.5k


Modeling the Internet Ecosystem

• Networks select providers and peers to optimize an objective function• E.g., Profit, performance…

• What are the effects of provider and peer selection strategies on the involved networks?

• What are the global, long-term effects of these strategies on the whole Internet?• Topology, traffic flow, economics, performance (path lengths)

• E.g., Can we predict what would happen if (fair) paid-peering becomes the common case?


Measuring Peering Value

How do A and B measure VA and VB?

With Peering trials: Collect: netflow, routing data Know: topology, costs, transit providers

With peering trials, A and B can measure their own value for the peering link (VA and VB) reasonably well

Hard for A to accurately measure VB (and vice versa)


Hiding peering value

Assume true VA+ V

B > 0 and V

B> V

A

A should get paid (VB - V

A )/2

If A estimates VB correctly, and claims its peering value is VL, where VL << VA

B is willing to pay more: (VB - V

L )/2

If A doesn’t estimate VB correctly, and VL+ V

B < 0, the

peering link is not feasible! A loses out on any payment

Does the risk of losing out on payment create an incentive to disclose the true peering value?


Peering Policies

• What peering policies do networks use? How does this depend on network type?

• Do they peer at IXPs? How many IXPs are they present at?

• PeeringDB: Public database where ISPs volunteer information about business type, traffic volumes, peering policies

• Collecting peeringDB snapshots periodically • Goal is to study how peering policies evolve


peeringDB


The Economics of Transit and Peering Interconnections in the Internet Amogh Dhamdhere (CAIDA/UCSD)...

Documents

Transcript of The Economics of Transit and Peering Interconnections in the Internet Amogh Dhamdhere (CAIDA/UCSD)...