self-tuning wireless network power management

27
Self-Tuning Wireless Network Power Management CSC 547 - Fall 2013, University of Arizona Sumin Byeon

Upload: sumin-byeon

Post on 29-Jun-2015

197 views

Category:

Technology


1 download

DESCRIPTION

Explores strategies to design and implement an intelligent power management module that adapts to the usage pattern and the characteristics of the network interface card. Anand, Manish, Edmund B. Nightingale, and Jason Flinn. "Self-Tuning Wireless Network Power Management." Wireless Networks 11.4 (2005): 451-69. Print.

TRANSCRIPT

Page 1: Self-Tuning Wireless Network Power Management

Self-Tuning Wireless Network Power

Management

CSC 547 - Fall 2013, University of ArizonaSumin Byeon

Page 2: Self-Tuning Wireless Network Power Management

Problems

• Wireless card shortens battery life

• Obvious solution: turn it off!

• Power management can degrade performance

• Critical for latency sensitive applications

• No one-fits-to-all solution

Page 3: Self-Tuning Wireless Network Power Management

Previous Work

• Power Saving Mode (PSM) in 802.11

• Will refer this as “PSM-static”

• Does not adapt to power characteristics of the network and mobile devices

• Does not adapt to usage patterns

Page 4: Self-Tuning Wireless Network Power Management

Solution

• Self-tuning power management module that adapts to

• Usage patterns

• Network interface characteristics

• System (i.e., hardware)

Page 5: Self-Tuning Wireless Network Power Management

Design Principles

• Know application intent

• Be proactive

• Respect the critical path

• Embrace the performance/energy tradeoff

• Adapt to the operating environment

Page 6: Self-Tuning Wireless Network Power Management

Know Application Intent

• Not knowing intent of applications - Leads to either too conservative or too extravagant power management

• Allow applications to disclose “hints” - STPM can work more efficiently

Page 7: Self-Tuning Wireless Network Power Management

Be Proactive

• Reactive strategy - Cost of transition between modes must be low

• Transition time 200-600ms; exceeds perception threshold (50-200ms)

• STPM performs cost-benefit analysis based on hints

• Not always possible

Page 8: Self-Tuning Wireless Network Power Management

Respect the Critical Path

• Perception threshold - generally 50-200ms

• Foreground transfer - latency sensitive, interactive, synchronous

• Background transfer - latency tolerable, asynchronous

Page 9: Self-Tuning Wireless Network Power Management

Performance-Energy Tradeoff

• Inherent tradeoff between performance and energy conservation

• Static threshold won’t work

• STPM provides mechanism to adjust priorities

• Is performance your priority? Or energy conservation?

Page 10: Self-Tuning Wireless Network Power Management

Adapt to Environment

• Global optimization

• Excessive power saving on network interface may lead to inefficient energy usage on other components

• Consider base power usage

Page 11: Self-Tuning Wireless Network Power Management

Implementation

• Implemented as Linux kernel module

• Inputs:

• Base power and current tradeoff between energy conservation and performance

• Device-specific power usage characteristics and transition costs

Page 12: Self-Tuning Wireless Network Power Management

API

Page 13: Self-Tuning Wireless Network Power Management

Power Cost Analysis

1. Base power

2. Power usage for each mode

3. Translation cost between modes

4. Power usage for data transfer in each mode

Page 14: Self-Tuning Wireless Network Power Management

Algorithm

• Assume network card only supports two modes: CAM and PSM

Page 15: Self-Tuning Wireless Network Power Management

Transition to CAM

• Delay tolerance is less than the maximum latency of PSM (i.e., beacon interval)

• Forthcoming transfer will be large enough

• Forthcoming transfer will be large enough, and STPM expects that there will be enough subsequent short transfers

Page 16: Self-Tuning Wireless Network Power Management

Transition to PSM

• No transfers in progress

• No application specified delay tolerance

• Network card will be idle long enough

Page 17: Self-Tuning Wireless Network Power Management

General Model

• Some network cards support more than two modes

• Number of possible strategies proportional to square of number of modes

• Calculates the lowest cost policy that transitions to each mode

• Calculates the lowest cost hybrid policies then make a further transition at some later time

Page 18: Self-Tuning Wireless Network Power Management

Evaluation

• Question: How much did STPM improve the power efficiency? What was the impact on the performance?

Page 19: Self-Tuning Wireless Network Power Management

Experiments

• Coda (distributed file system)

• NFS (Network File System)

• Xmms (audio streaming)

• Thin client using remote X

Page 20: Self-Tuning Wireless Network Power Management

Coda

Page 21: Self-Tuning Wireless Network Power Management

NFS

Page 22: Self-Tuning Wireless Network Power Management

Xmms

Page 23: Self-Tuning Wireless Network Power Management

Remote X

Page 24: Self-Tuning Wireless Network Power Management

Effect of Think Time

Page 25: Self-Tuning Wireless Network Power Management

Potential Weakness

• In their experiments, they made modifications on applications to emit hints

• Unrealistic to modify every single application in the world

• How would have STPM behaved if applications were not modified? (i.e., no hints)

Page 26: Self-Tuning Wireless Network Power Management

Conclusion

• Power management may degrade performance, and even increase total energy consumption

• Power management must be tuned to reflect application intent and characteristics of network interface card

• Can’t expect users to manually tune power management algorithm

Page 27: Self-Tuning Wireless Network Power Management

Conclusion (cont.)

• Results show that STPM improves both performance and energy conservation

• Future work: adapt STPM to other network cards and different system components (e.g., disks)