taming wireless link fluctuations using data-driven sparse ...htk/...crouse...presentation.pdf ·...
TRANSCRIPT
![Page 1: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/1.jpg)
Taming Wireless Link Fluctuations by Predictive Queuing Using a Sparse-Coding Link-State Model
Stephen J. Tarsa, Marcus Comiter, Michael Crouse, Brad McDanel, HT Kung
1
ACM MobiHoc, June 25, 2015 Hangzhou, CN
![Page 2: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/2.jpg)
Summary & Results
• Swings in wireless signal quality paralyze higher-layer applications – browsers stall, media players skip, etc. -- up-to 80% of TCP connections at cell towers are stalled
• To predict signal quality, we actively measure links and use data-driven modeling to capture interactions between signals and their environment
• Compared to loss-rate, Markov-chain, and heuristic link modeling, sparse coding finds more stable predictive signatures by collapsing variations into a few states
Our data-driven model enables on-the-fly adaptation to a device’s wireless environment
We predict packet losses over wireless links in real time by applying sparse coding and support vector machines (SVMs)
• No static network stack, no matter how well-planned, can handle the variability of everyday wireless links, e.g. subway tunnels, offices with elevators, etc.
• Our system probes links and computes link-state predictions on-device; by holding packets likely to be lost, we boost TCP throughput up-to 4x for a 5% power overhead over commercial 802.11 and carrier networks
• SILQ (state-informed link-layer queuing) runs on general Linux and Android devices
![Page 3: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/3.jpg)
Motivating ScenarioData Collection & Link ModelingSystem Architecture & Results
![Page 4: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/4.jpg)
Everyday wireless networks struggle with fluctuating link quality, for example in subway tunnels, elevators, old buildings, hilly terrain, etc.
Wireless Packet Loss in Everyday Scenarios
![Page 5: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/5.jpg)
Wireless Packet Loss in Everyday Scenarios
Everyday wireless networks struggle with fluctuating link quality, for example in subway tunnels, elevators, old buildings, hilly terrain, etc.
![Page 6: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/6.jpg)
Wireless Packet Loss in Everyday Scenarios
Everyday wireless networks struggle with fluctuating link quality, for example in subway tunnels, elevators, old buildings, hilly terrain, etc.
![Page 7: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/7.jpg)
Wireless Packet Loss in Everyday Scenarios
Everyday wireless networks struggle with fluctuating link quality, for example in subway tunnels, elevators, old buildings, hilly terrain, etc.
![Page 8: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/8.jpg)
Wireless signals degrade due to line-of-sight occlusion, reflections off metal, attenuation through building materials, antenna nulls, etc.
Wireless Packet Loss in Everyday Scenarios
Subtle properties like device orientation and open/closed doors make coarse metrics like location insufficient to predict individual packet losses
Rural Signal Propagation
Indoor Signal Propagation
Urban Signal Propagation
![Page 9: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/9.jpg)
Not only is it difficult for carriers to ensure consistent signal strength, but just a few lost data packets can paralyze an application
Motivating Scenario – 3G Cellular Links on the Boston Subway
Throughput of a TCP File Transfer Over Boston Subway
A temporary dead-zone causes TCP
packets to be lost
The connection isstalled despite good
signal quality
By modeling and predicting temporary outages, we improve performance for higher-layer network applications by preempting data loss
5 min2.5 minHarvard Sq.
![Page 10: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/10.jpg)
Motivating ScenarioData Collection & Link ModelingSystem Architecture & Results
![Page 11: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/11.jpg)
Open-FieldNodes
Ground-Structure
Nodes
Experiments and Data Collection
To build a general link model, we collect data in three scenarios: 1) the Boston subway, 2) airborne links over rural farmland, ….
Forest Nodes
UAVNode
![Page 12: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/12.jpg)
Experiments and Data Collection
… and 3) an active indoor office environment capturing attenuation from building construction, fire-proof doors, an elevator, network
interference, etc.
2nd Floor
Start/Finish
Fire-Proof Doors
Access Point
Elevator1st FloorGround Floor
Basement
Access Point Environment
Fire-Proof Doors
2nd Floor Elevator
![Page 13: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/13.jpg)
A Sparse-Coding Link Model
Wireless link models in the literature use physical simulations or data-driven statistics – we take the latter approach and use clustering to
reduce state space/training data requirements
Environment Knowledge
Training Data
Physical simulations
• Two-Ray Interference• Geometric Occlusion• Distance Attenuation
Statistical models
• Loss-Rate• Markov-Chain burst
models
Link Modeling Techniques
Location-Based Stats Models
• Wi-Fi SLAM• Location-Specific
Markov Burst Models
![Page 14: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/14.jpg)
Measurement Data and Predictive Model
We measure links by sending small UDP probes and recording successful receptions. Signatures that precede upcoming gaps predict transmissions
that are likely to fail
Wireless ChannelUser
Device
Phone, Laptop, IoT Device
802.11 Router,3G Cell Tower
1 1 1 1 1 1 0 1 0 1 1 1 0 1 1 0 0 0 0 0 1 1 1 1 1 1 0 1 1 1 1 0Packet Receptions:
OutagePredictive Signature
BaseStation
![Page 15: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/15.jpg)
A Sparse-Coding Link Model
00 01
10 11
01
10 11
00
# Transitions grows exponentially
with temporal scale
Common states (e.g. identified by clustering) change across networks
and environments
+
Burst On-to-Off Queuing
Finite-State-MachinePacket Loss Models
Clustered/Reduced-State FSM
Sparse Coding Link Model
Sparse coding finds a universal dictionary of
features that combine to express diverse link states
A key limitation of data-driven models is the complexity and volume of training data required to capture all possible link states
![Page 16: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/16.jpg)
A Sparse-Coding Link ModelLink primitives discovered by sparse coding reflect canonical patterns that describe link transitions, temporary outages, and network effects
like queuing
UAV Ground-Structure
UAV Field Indoor Office Subway
Link-State Primitives By Environment
![Page 17: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/17.jpg)
Motivating ScenarioData Collection & Link ModelingSystem Architecture & Results
![Page 18: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/18.jpg)
State-Informed Link-Layer Queuing (SILQ) Architecture
Online, our system probes links, matches measurements to canonical primitives, and predicts 100ms outages – we then hold packet
transmissions that are likely to fail
Queue
Link Model
State Predictions
Network Application
Wireless Channel
SILQ End-Pointe.g. Wi-Fi Router
User Device
Base Station
![Page 19: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/19.jpg)
For TCP, SILQ causes connections to wake up quickly after outages, boosting 3G throughput on the Boston subway by up-to 4x
Motivating Scenario – 3G Cellular Links on the Boston Subway
Dead-zones are pre-dicted, data packets
held, and loss avoided
The connection wakes up quickly when the link is
physically restored
SILQ + Linux TCPPredicted Link State:
Off On
6 minHarvard Sq.Charles/MGH
Outbound
Throughput of a TCP File Transfer Over Boston Subway
5 min
Harvard Sq. Charles/MGH
Inbound
![Page 20: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/20.jpg)
1 min 3 min2 min
1 min 3 min2 min
SILQ Performance
In an indoor office, SILQ improves Wi-Fi throughput by 2x, preventing connections from dying in an elevator or when passing through fire-
proof doors
Dead-zone caused by fire-proof doors
Interruptions caused by elevator ride
Linux TCP
SILQ + Linux TCP
a.
b.Predicted Link State:
Off On
![Page 21: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/21.jpg)
SILQ Performance Summary
SILQ’s gains are largest in the harshest environments where links fluctuate most
Environment Network Type Throughput Gain
Reduction in Perf. Variation
MBTA Red Line 3G Cellular 4x --Indoor Office 802.11 (Wi-Fi) 2x 3xRural with Nearby Ground Structures
802.11 (Wi-Fi) 1.2x --
Rural Open-Field 802.11 (Wi-Fi) 1.0x 4x
![Page 22: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/22.jpg)
Reducing SILQ OverheadsSparse-coded prediction statistics are more resilient to low-energy, less-
frequent probing than heuristic and rate-based predictors
Sparse CodingHeuristic Loss Rate Threshold
Max. Possible Data Rate (After Probe Overhead)
779 kbps 845 kbps 992 kbps 995 kbps
Effect of Increasing SILQ Probe Interval on TCP Throughput
![Page 23: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/23.jpg)
SILQ Performance Summary
SILQ’s power overhead is 4% above a data connection – only 1% energy is spent computing link predictions, with the rest spent servicing probes
Power Consumption for HTC One (M8) Smartphone
![Page 24: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/24.jpg)
SILQ Current Status
SILQ scales to 20 Mbps, runs on Linux and Android devices, and has been deployed on commercial 802.11 (Wi-Fi) and 3G cellular networks
![Page 25: Taming Wireless Link Fluctuations Using Data-Driven Sparse ...htk/...crouse...presentation.pdf · everyday wireless links, e.g. subway tunnels, offices with elevators, etc. • Our](https://reader033.vdocuments.mx/reader033/viewer/2022060512/5f2abbdf26557b5f900df9c9/html5/thumbnails/25.jpg)
Conclusion
Data-driven learning is key to addressing difficult networking scenarios
Sparse coding improves over other link models by finding a state model that is tolerant to measurement variation
A learning pipeline based on offline big-data clustering and onlineprediction offers the design flexibility necessary for mobile devices
• Machine Learning is quickly becoming successful in wireless, e.g. SIGCOMM best-paper by Keith Winstein, other MobiHoc talks
• Link variability is a hugely important, interesting problem, Verizon: “top-3 technical problem”, Intel: “single greatest challenge for 5G”, Akamai: top priority in 2015
• Unlike prior models, canonical features port across diverse networks and scenarios• Only a small number of statistics need to be tuned in feature space
• Expensive unsupervised learning to find structure in big data can be performed in datacenters, with lighter supervised SVM predictors tuned to small data on device
• Sacrificing some bandwidth for state measurement pays off many times over