WMuNeP05

Performance Analysis of the Intertwined Effects between Network Layers for 802.11g Transmissions: 

Performance Analysis of the Intertwined Effects between Network Layers for 802.11g Transmissions Wireless Multimedia Networking and Performance Modeling (WMuNeP) Montreal, Canada, October 2005 Jon Gretarsson, Feng Li, Mingzhe Li, Ashish Samant, Huahui Wu, Mark Claypool and Robert Kinicki WPI Computer Science Department Worcester, MA, 01609 USA Presenter - Bob Kinicki

Outline: 

Outline Motivation Previous Work Analytic Models Measurement Studies Experiments Tools and Setup Experimental Design Results and Analysis Conclusions and Future Work

Motivation: 

Motivation Previous research has studied WLAN performance through analytic modeling, simulation and measurement. However, the conclusions drawn have not always been precise and the results have focused on one protocol layer (primarily the data link layer). Important Question: Is Quality of Service (QoS) a realistic goal over WLAN’s? We are interested in “refining” how one application running over a Wireless LAN (WLAN) can impact another application. The interaction between protocol layers can yield results that can significantly impact performance when multiple applications run over a WLAN.

Outline: 

Outline Motivation Previous Work Analytic Models Measurement Studies Experiments Tools and Setup Experimental Design Results and Analysis Conclusions and Future Work

Analytic Models of 802.11: 

Analytic Models of 802.11 [Cali et al. 98] “IEEE 802.11 Wireless LAN: Capacity Analysis and Protocol Enhancement” Models early 802.11, i.e., no dynamic rate adaptation. Models the “ideal” channel: no transmission errors, no hidden terminals. [Bianchi 2000] “Performance Analysis of the IEEE 802.11 Distributed Coordination Function” Uses the same assumptions as Cali, but emphasizes the “saturation” throughput such that the transmission queue of each wireless node is never empty. [Heuss et al 03] “Performance Anomaly of 802.11b” Employs analytic equations based on simplified version of Bianchi including no multiple collisions (no retries) and hosts alternate transmissions. Focuses on dynamic rate adaptation effect. Conclusion: A single slow wireless node brings all wireless nodes down to its throughput level. Simulate and measure, but measurement uses only upstream UDP and TCP. Note: TCP results do not match very well.

Generic WLAN with AP: 

Generic WLAN with AP Server Access Point Client Client queue Downstream Upstream

Measurement Studies of 802.11: 

Measurement Studies of 802.11 [Pilosof et al. 03] “Understanding TCP fairness over Wireless LAN” Predominantly simulation, but includes one set of measurement results to show that TCP upstream dominates over TCP downstream with background UDP traffic that makes buffers available at the AP the critical resource. [Aguayo et al. 04] “Link-level Measurements from an 802.11b Mesh Network” Perform early morning measurements of Roofnet where there is one sender at a time. Conclude there is not a strong correlation with link distance and SNR with link level loss rates and that an important cause of intermediate loss rates is multi-path fading.

Measurement Studies of 802.11: 

Measurement Studies of 802.11 [ [Bai and Williamson 04] “The Effects of Mobility on Wireless Media Streaming Performance” Create their own AP device to vary queue size. Downstream measurements of UDP videos show WLAN supports easily two fixed clients receiving 1Mbps video clips with AP queue < 30 buffers. When one client becomes mobile, it goes through “bad” locations and frames get discarded, rate adaptation moves to 1 Mbps, AP queue backlogs and overflows!! When one client fixed and one client mobile, mobile client kills performance of fixed client because the MAC-layer queue fills with frames from poorly-connected client. The AP queue is the bottleneck. [Yarvis et al. 05] “Characteristics of 802.11 Wireless Networks” Consider: transmission rate, transmission power, node location, house type. Conduct measurements in three homes with link layer retransmissions disabled. Discover: wireless performance can be quite asymmetric, node placement can be a key factor, no correlation with physical distance.

Outline: 

Outline Motivation Previous Work Analytic Models Measurement Studies Experiments Tools and Setup Experimental Design Results and Analysis Conclusions and Future Work

Tools & Experimental Setup: 

Tools & Experimental Setup Wireless Signal Strength Good Location: >= -70dBm Bad Location: <= - 75dBm

Experiments: 

Experiments Streaming Video Characteristics Length : 2 minutes Encoding bit rate: 5Mbps Resolution: 352 x 288 Frame Rate : 24 fps

Experimental Design: 

Experimental Design The two laptops are positioned in “exactly” the same location with the same physical orientation and at locations known for little wireless traffic. All experiments were conducted at night to minimize motion (from people). Although the videos stream for two minutes, our analysis uses data between the 50-100 second interval. Each experiment was repeated three times.

Consistency Test: 

Consistency Test Figure 2: Wireless Signal Strength and Channel Capacity for Three Separate Runs dynamic rate adaptation

Outline: 

Outline Motivation Previous Work Analytic Models Measurement Studies Experiments Tools and Setup Experimental Design Results and Analysis Conclusions and Future Work

A Single TCP Download: 

A Single TCP Download Average throughput 18.8 Mbps

802.11 Performance Anomaly: 

802.11 Performance Anomaly A: 9.3 Mbps B: 9.6 Mbps A: 2.8 Mbps B: 2.1 Mbps

TCP Download Channel Capacities: 

TCP Download Channel Capacities Figure 5: Channel Capacity Impacted by Location

Bad UDP Stream: 

Bad UDP Stream Figure 6: Throughput Impacted by Location and Application A: 2.8 Mbps B: 2.1 Mbps A: 0.3 Mbps B: 2.5 Mbps UDP stream kills TCP download!!

Frame Retries and Packet Loss: 

Frame Retries and Packet Loss Figure 7: Wireless Layer Retry Fraction Figure 8: UDP Ping Loss Fraction A: 0.05 B: 0.2 AP queue causes high packet loss

Round Trip Times: 

Round Trip Times large UDP RTT’s

Round Trip Times: 

Round Trip Times TCP does not fill the AP Queue.

Good Streaming: 

Good Streaming

Bad Streaming: 

Bad Streaming TCP streaming adjusts to bad location

Single Bad Streams: 

Single Bad Streams

Conclusions and Future Work: 

Conclusions and Future Work Application behavior impacts WLAN performance of concurrent applications. The choice of Transport Protocol impacts performance over a WLAN. Just modeling the data link channel misses interwined effects of the AP network layer queuing. We need to get ‘inside’ the AP to understand the queuing in both the upstream and downstream direction. Is there a way for streaming application to get “hints” about the wireless data link layer?

Performance Analysis of the Intertwined Effects between Network Layers for 802.11g Transmissions: 

Performance Analysis of the Intertwined Effects between Network Layers for 802.11g Transmissions Wireless Multimedia Networking and Performance Modeling (WMuNeP) Montreal, Canada, October 2005 Jon Gretarsson, Feng Li, Mingzhe Li, Ashish Samant, Huahui Wu, Mark Claypool and Robert Kinicki WPI Computer Science Department Worcester, Massachusetts 01609 rek@cs.wpi.edu Thank You!

Random Observations from MSWiM(Modeling and Simulation of Wireless Mobile systems): 

Random Observations from MSWiM (Modeling and Simulation of Wireless Mobile systems) and WMuNeP Workshop (Wireless Multimedia Networking Performance Modeling)

Keynote on Wireless Sensor Networks: 

Keynote on Wireless Sensor Networks Big Issues Spatio-Temporal correlation in WSN’s Connectivity (fading issues) Asymmetric links Energy consumption Cost reduction What to do with terabytes of information?

Thoughts/Observations: 

Thoughts/Observations Many researchers trying to use ns-2 to simulate wireless networks. “Cross-Layer Interactions” was a common buzz phrase. One paper talked about slow versus fast fading.

Wireless Mesh Networking Panel: 

Wireless Mesh Networking Panel The panel was a good mix of industry versus academic voices. Items that came up: PAN (Personal Area Networks) to WAN linkages, Wireless DSL, WAN repeater for fixed wireless, solar battery powered sensor networks (AP power saving using protocols). The Big Debate “ Will we really have QoS for WLAN’s in five years?” Academics – Yes! Industry – No Way! The real undercurrent – will 802.11e succeed?

More Random Observations: 

More Random Observations 802.11e is good fodder for analytic modeling crowd. {my opinion – there is no sense of reality here} New idea is MIMO Multiple Input Multiple Output WLANS (e.g. two radios). A counterexample paper was presented to show that congestion control with TCP in wireless will not be workable. They mentioned “neighborhood RED” [Gerla 03].

Multimedia: 

Multimedia Real-time Transport Protocol for Image Based Rendering Ambitious, ISP (Interactive Streaming Protocol) deals with VBR and uses ACK-based solution to adapt sending speed to packet loss rate. “Tradeoffs in Bit-Rate Allocation for Wireless Video Streaming” They connected video distortion to low-level fading. They modeled distortion using SSIM (structural similarity) and spoke of perceptual distortion model. The emphasis in this treatment was analysis using equations.

WMuNeP: 

WMuNeP Several analytic modeling based papers. SCTP (Stream Control Transmission Protocol) discussed in terms of multi-homing for mobile systems. One paper using linear programming to find optimal encoding parameters for audio MPEG-4 over wireless. One paper on experimental measurements of secure AODV with people in a soccer field. {This paper referred to a gray area that is similar to our “edge” area in Weather Forecasting paper.}