Maintaining%20Performance%20while%20Saving%20Energy%20on%20Wireless%20LANs

1
Maintaining Performance while Saving Energy on
Wireless LANs

• Ronny Krashinsky
• 6.929 Term Project
• 12-7-2001

2
Motivation

• Mobile devices limited by battery weight and
  lifetime
• Wireless network access consumes a lot of energy
• Want to disable the network interface card
  whenever its not in use
• Basic problem data may arrive from the network
  at any time
• Focus of this work a mobile client communicating
  with a wired base-station to perform
  request/response traffic (e.g. web browsing)
• Not focusing on ad hoc networks, mobile servers,
  real-time communication (voice)
• Not relying on high-level knowledge of
  application state

3
802.11 Power-Saving Mode Overview(For
Infrastructure Networks)

• Network Interface Card power consumption
• Cisco Aironet 1.7W Tx, 1.2W Rx, 1.1W Idle, 50mW
  Sleep
• Basic idea sleep to save energy, periodically
  wakeup to check for pending data
• Clients go to sleep after sending or receiving
  data
• Base-station buffers received data while client
  is asleep
• Base-station sends out beacons every 100ms
  indicating whether or not the Client has pending
  data
• Client wakes up to listen to beacon, then polls
  Base-station to receive data (ListenInterval can
  be less than BeaconPeriod)
• Client can wake up to send data at any time

4
Talk Outline

• Measured performance of TCP over 802.11 PSM (its
  not good)
• Trace analysis for characteristics of client HTTP
  traffic (how to save energy)
• Proposed enhancements to 802.11 PSM to improve
  performance and minimize energy
• Simulation of web browsing traffic over existing
  802.11 PSM and alternatives

5
Request/Response Over TCP Over 802.11
RTT delta
6
Request/Response Performance Test

• Client
• Compaq iPAQ with Enterasys Networks RoamAbout
  802.11 NIC
• Servers
• Methodology
• repeat tests five times, alternating between PSM
  on and off, use mean

for (N various sizes) start timer for
(several iterations) TCP connect to server
send request receive N bytes close
connection stop timer
RTT Bandwidth
LCS 5ms 10Mbps
Berkeley 80ms 10Mbps
Home (DSL) 50ms 70Kbps
7
802.11 PSM Measured Performance
8
802.11 PSM Measured Slowdown

• Conclusion 802.11 PSM is too coarse-grain to
  maintain network performance

9
Client Network Usage

• Analyzed UC Berkeley Home-IP (modem) HTTP Traces
• client ID, request time, response start time,
  response end time
• Classified client state as wait, idle, receive
• Discarded incomplete transactions (no timestamp)
• Ignored receive and idle times longer than 1000s

10
Client Network Usage Characteristics

• Most wait time and idle time is spent in a few
  number of long latency events
• These events will therefore account for most of
  the sleep energy

• Conclusion 802.11 PSM is too fine-grain to
  reduce energy effectively

11
Proposed Solution StayAlive and
ListenInterval-Backoff
request
PSM basic
12
Latency and Energy Comparison
Latency (vs. No PSM) Latency (vs. No PSM) Latency (vs. No PSM) Energy (vs. PSM basic) Energy (vs. PSM basic)
Short Medium Long active (awake) listening to beacons
PSM basic Increased by up to 100ms Increased by up to 100ms Increased by up to 100ms
StayAlive Unchanged Increased by up to 100ms Increased by up to 100ms Increased Unchanged
ListenInterval-Backoff (2x) Increased by up to 2x Increased by up to 2x Increased by up to 0.9s Unchanged Decreased
20 delay Unchanged Increased by up to 20 Increased by up to 0.9s Increased Decreased
13
Client Web Browsing Simulation

• Modeled 802.11 PSM using ns-2
• Did not model detailed MAC protocol no channel
  contention, no node movement, no packet losses
• Modified Link C code to support sleep mode and
  send alerts to OTcl , control and beaconing in
  OTcl
• Modeled HTTP traffic using empirical model
• Based on study by Bruce Mah
• Limited Think Time to 1000s
• Added Server Response Time based on wait time
  from UCB Home-IP traces (less 100ms to account
  for network delays).
• Updated to use FullTcp
• Client ? BaseStation 0.1ms, 5Mbps
• BaseStation ? Server 20ms, 10Mbps
• Energy 1W while active, 50mW while sleeping, 5mJ
  per listened-to beacon (1W?5ms)

14
Performance Results
15
Performance and Energy Results
energy per page (PSM off 54 J)
slowdown (vs. PSM off)
PSM basic
StayAlive
LI-Backoff 2x
Max delay
16
Conclusions

• Existing 802.11 PSM causes RTTs to be rounded up
  to the nearest 100ms
• This adversely affects short TCP connections
  which are limited by the RTT
• A viable solution is to stay awake for a short
  period of time after sending a request
• When using 802.11 PSM, almost all energy
  consumption is due to sleep power and listening
  to beacons
• ListenInterval-Backoff can reduce the listen
  energy
• Longer sleep intervals have the potential to
  enable deeper sleep modes

17
(No Transcript)
18
(backup slides)
19
Simulation vs. Measured
20
Actual Values Used in HTTP Simulation
21
(No Transcript)
22
Intersil PRISM Radio Chip Set
Current (mA) WakeupTime (ms)
Tx 488
Rx 287
PSM 1 190 1
PSM 2 70 25
PSM 3 60 2000
PSM 4 30 5000