1. 1 Performance Study of Congestion Price Based Adaptive Service Performance Study of Congestion Price Based Adaptive Service Xin Wang, Henning Schulzrinne Xin Wang, Henning Schulzrinne (Columbia university) (Columbia university)

2. 2 Outline Resource negotiation & RNAPResource negotiation & RNAP Pricing strategyPricing strategy User adaptationUser adaptation Simulation modelSimulation model Results and discussionResults and discussion

3. 3 Resource Negotiation & RNAP Assumption: network provides a choice of delivery services to userAssumption: network provides a choice of delivery services to user –e.g. diff-serv, int-serv, best-effort, with different levels of QoS –with a pricing structure (may be usage-sensitive) for each. RNAP: a protocol through which the user and network (or two network domains) negotiate network delivery services.RNAP: a protocol through which the user and network (or two network domains) negotiate network delivery services. –Network -> User: communicate availability of services; price quotations and accumulated charges –User -> Network: request/re-negotiate specific services for user flows. Underlying Mechanism: combine network pricing with traffic engineeringUnderlying Mechanism: combine network pricing with traffic engineering

4. 4 Resource Negotiation & RNAP, Cont’d Who can use RNAP?Who can use RNAP? –Adaptive applications: adapt sending rate, choice of network services –Non-adaptive applications: take fixed price, or absorb price change

5. 5 Centralized Architecture (RNAP-C) NRN S1 R1 NRN HRN Access Domain - B Access Domain - A Transit Domain Internal Router Edge Router Host RNAP Messages NRN HRN Network Resource Negotiator Host Resource Negotiator Intra domain messages Data

6. 6 S1 R1 HRN Access Domain - B Access Domain - A Transit Domain Internal Router Edge Router Host RNAP Messages HRN Host Resource Negotiator Data Distributed Architecture (RNAP-D)

7. 7 Resource Negotiation & RNAP, Cont’d Query Quotation Reserve Commit Quotation Reserve Commit Close Release Query: User enquires about available services, prices Quotation: Network specifies services supported, prices Reserve: User requests service(s) for flow(s) (Flow Id-Service-Price triplets) Commit: Network admits the service request at a specific price or denies it (Flow Id-Service-Status-Price) Periodic re-negotiation Close: tears down negotiation session Release: release the resources

8. 8 Pricing Strategy Current Internet:Current Internet: –Access rate dependent charge (AC) –Volume dependent charge (V) –AC + V AC-V –Usage based charging: time-based, volume-based Fixed pricingFixed pricing –Service class independent flat pricing –Service class sensitive priority pricing –Time dependent time of day pricing –Time-dependent service class sensitive priority pricing

9. 9 Pricing Strategy, Cont’d Congestion-based PricingCongestion-based Pricing –Usage charge: p u = f (service, demand, destination, time of day,...) c u (n) = p u x V (n) –Holding charge: P h i =  i x (p u i - p u i-1 ) c h (n) = p h x R(n) x  –Congestion charge: p c (n) = min [{p c (n-1) +  (D, S) x (D-S)/S,0 } +, p max ] c c (n) = p c (n) x V(n)

10. 10 Pricing Strategy, Cont’d A generic pricing structureA generic pricing structure –Cost = c ac (r ac ) + p (r ac ) (t-t m ) + +  i  n [p h i (n) r i (n)  + (p u i (n) + p c i (n)) v i (n)] (v i -v m i ) + : access ratec ac : access charge; r ac : access rate p (r ac ): unit time pricep (r ac ): unit time price i: class i; n: nth negotiation interval;i: class i; n: nth negotiation interval;  : negotiation period  : negotiation period t m : the minimum time without charge v m : the volume transferred free of chargev m : the volume transferred free of charge

11. 11 User Adaptation Based on perceived valueBased on perceived value Application adaptationApplication adaptation –Maximize total utility over the total cost –Constraint: budget, min QoS & max QoS

12. 12 CPA & FP CPA: congestion price based adaptive serviceCPA: congestion price based adaptive service FP: fixed price based serviceFP: fixed price based service

13. 13 User Adaptation, Cont’d An example utility functionAn example utility function –U (x) = U 0 + ω log (x / x m ) Optimal user demandOptimal user demand –Without budget constraint: x j = ω j / p j –With budget constraint: x j = (b x ω j / Σ l ω l ) / p j Affordable resource is distributed proportionally among applications of the system, based on the user’s preference and budget for each application.Affordable resource is distributed proportionally among applications of the system, based on the user’s preference and budget for each application.

14. 14 Simulation Model

15. 15 Simulation Model

16. 16 Simulation Model, Cont’d Parameters Set-upParameters Set-up –topology1: 48 users –topology 2: 360 users –user requests: 60 kb/s -- 160 kb/s –targeted reservation rate: 90% –price adjustment factor: σ = 0.06 –price update threshold: θ = 0.05 –negotiation period: 30 seconds –usage price: p u = 0.23 cents/kb/min

17. 17 Simulation Model, Cont’d Performance measuresPerformance measures –Bottleneck bandwidth utilization –User request blocking probability –Average and total user benefit –Network revenue –System price –User charge

18. 18 Design of the Experiments Performance comparison of CPA & FPPerformance comparison of CPA & FP Effect of system control parameters:Effect of system control parameters: – target reservation rate –price adjustment step –price adjustment threshold Effect of user demand elasticityEffect of user demand elasticity Effect of session multiplexingEffect of session multiplexing Effect when part of users adaptEffect when part of users adapt Session adaptation and adaptive reservationSession adaptation and adaptive reservation

19. 19 Performance Comparison of CPA and FP

20. 20 Bottleneck Utilization

21. 21 Request blocking probability

22. 22 Total network revenue ($/min)

23. 23 Total user benefit ($/min)

24. 24 Average user benefit ($/min)

25. 25 Price ($/kb/min)

26. 26 User bandwidth (kb/s)

27. 27 Average price ($/kb/min)

28. 28 Average user bandwidth (kb/s)

29. 29 Average user charge ($/min)

30. 30 Effect of target reservation rate

31. 31 Bottleneck utilization

32. 32 Request blocking probability

33. 33 Total user benefit

34. 34 Effect of Price Adjustment Step

35. 35 Bottleneck utilization

36. 36 Request blocking probability

37. 37 Effect of Price Adjustment Threshold

38. 38 Request blocking probability

39. 39 Effect of User Demand Elasticity

40. 40 Average user bandwidth

41. 41 Average user charge

42. 42 Effect of Session Multiplexing

43. 43 Request blocking probability

44. 44 Total user benefit

45. 45 Effect When Part of Users Adapt

46. 46 Bandwidth utilization

47. 47 Request blocking probability

48. 48 Session Adaptation & Adaptive Reservation

49. 49 Bandwidth utilization

50. 50 Blocking probability

51. 51 Conclusions CPA gain over FPCPA gain over FP –Network availability, revenue, perceived benefit –Congestion price as control is stable and effective Target reservation rate (utilization):Target reservation rate (utilization): –User benefit, with too high or too low utilization – Too low target rate, demand fluctuation is high – Too high target rate, high blocking rate

52. 52 Conclusions Effect of price scaling factor σEffect of price scaling factor σ – σ, blocking rate –Too large σ, under-utilization, large dynamics Effect of price adjustment threshold θEffect of price adjustment threshold θ –Too high, no meaningful adaptation –Too low, no big advantage

53. 53 Conclusions Demand elasticityDemand elasticity –Bandwidth sharing is proportional to its willingness to pay Portion of user adaptation results in overall system performance improvementPortion of user adaptation results in overall system performance improvement