Download Presentation (PowerPoint File) - IPAM

This Century Challenges:
Embedding the Internet
Deborah Estrin
UCLA Computer Science Department
[email protected]
http://lecs.cs.ucla.edu/estrin
1
Enabling Technologies
Embed numerous distributed
devices to monitor and interact
with physical world
Embedded
Network devices
to coordinate and perform
higher-level tasks
Networked
Exploit
collaborative
Sensing, action
Control system w/
Small form factor
Untethered nodes
Sensing
Tightly coupled to physical world
Exploit spatially and temporally dense, in situ, sensing and actuation
2
Embedded Networked Sensing Potential
Seismic Structure
response
Marine
Microorganisms
• Micro-sensors, onboard processing, and
wireless interfaces all
feasible at very small
scale
– can monitor
phenomena “up
close”
• Will enable spatially
and temporally dense
environmental
monitoring
• Embedded Networked
Sensing will reveal
previously
unobservable
phenomena
Contaminant
Transport
Ecosystems,
Biocomplexity
3
“The network is the sensor”
(Oakridge Natl Labs)
Requires robust distributed systems of thousands of
physically-embedded, often untethered, devices.
4
From Embedded Sensing to Embedded Control
•
•
•
•
Embedded in unattended “control systems”
– Different from traditional Internet, PDA, Mobility applications that
interface primarily and directly with human users
– More than control of the sensor network itself
Critical applications extend beyond sensing to control and actuation
– Transportation, Precision Agriculture, Medical monitoring and drug
delivery, Battlefied applications
Critical concerns extend beyond traditional networked systems
– Usability, Reliability, Safety
– Robust interacting systems under dynamic operating conditions
– Often mobile, uncontrolled environment,
– Not amenable to real-time human monitoring
Need systems architecture to manage interactions
– Current system development: one-off, incrementally tuned, stovepiped
– Serious repercussions for piecemeal uncoordinated design:
insufficient longevity, interoperability, safety, robustness,
scalability...
5
Macro
Centralized
(Shared Scientific
Instruments
(telescopes))
(Traditional Sensor
Systems)
Physical
Distributed
Micro
(Embedded Networked Sensing)
Virtual
(Internet)
6
New Design Themes
•
•
•
•
Long-lived systems that can be untethered and unattended
– Low-duty cycle operation with bounded latency
– Exploit redundancy and heterogeneous tiered systems
Leverage data processing inside the network
– Thousands or millions of operations per second can be done using energy
of sending a bit over 10 or 100 meters (Pottie00)
– Exploit computation near data to reduce communication
Self configuring systems that can be deployed ad hoc
– Un-modeled dynamics of physical world cause systems to operate in ad
hoc fashion
– Measure and adapt to unpredictable environment
– Exploit spatial diversity and density of sensor/actuator nodes
Achieve desired global behavior with adaptive localized algorithms
– Dynamic, messy (hard to model), environments preclude pre-configured
behavior
– Cant afford to extract dynamic state information needed for centralized
control or even Internet-style distributed control
7
Why cant we simply adapt Internet protocols and
“end to end” architecture?
• Internet routes data using IP Addresses in Packets and Lookup
tables in routers
– Humans get data by “naming data” to a search engine
– Many levels of indirection between name and IP address
– Works well for the Internet, and for support of Person-to-Person
communication
• Energy-constrained (un-tethered, small-form-factor),
unattended systems cant tolerate communication overhead of
indirection
• Embedded systems can’t rely on human intelligence, elasticity, to
compensate for system ambiguities
8
ENS Research Focus
•
Critical research needed in “systems”
– Component technology (sensors, low power devices, RF) is far ahead of our ability to
exploit
•
Must develop, distributed, in-network, autonomous event detection capabilities
– Adaptive Self-Organization to achieve reliable, long-lived, operation in dynamic,
resource-limited, harsh environment.
– Collaborative, multi-modal, processing and active database techniques
– Primitives for programming aggregates to create an autonomous, adaptive,
monitoring capability across 1000s of nodes
– Sensor coordinated actuation will enable truly self-configuring and reconfiguring
systems by allowing for adaptation in physical space
– Safety, Predictability, Usability, particularly as we embed sophisticated behaviors
in previously-”simple” objects.
•
Strive toward an Architecture and associated principles by building working systems,
studying them, iterating
– Analogous to TCP/IP stack, soft state, fate sharing, and eventually, self-similarity,
congestion control…
– What is our stack, metrics, system taxonomy…
9
Sample Layered Architecture
User Queries, External Database
Application processing, Distributed
query processing, QOT tradeoffs
Data dissemination, aggregation,
storage, caching
Routing
Self-configuring network topology
MAC, Time, Location
Phy: comm, sensing, actuation, SP
10
Metrics
• Efficiency
– System lifetime/System resources
• Resolution/Fidelity
– Detection/Identification
• Latency
– Response time
• Robustness
– To variable system and input state]
– Security to malicious or buggy nodes
• Scalability
– Over space and time
11
Systems Taxonomy: Dimensions
•
•
•
•
Spatial and Temporal Scale
– Sampling interval
– Extent
– Density (of sensors relative to stimulus)
Variability
– Ad hoc vs. engineered system structure
– System task variability
– Mobility (variability in space)
Autonomy
– Multiple sensor modalities
– Computational model complexity
Resource constrained
– Energy, BW
– Storage, Computation
12
Traffic/Load/Event Models: Dimensions
• Frequency (spatial, temporal)
– Commonality of events in time and space
• Locality (spatial, temporal)
– Dispersed vs. clustered/patterned
• Mobility
– Rate and pattern
13
Constructs for in network processing
• Nodes pull, push, and store named data (using tuple space) to create
efficient processing points in the network
– e.g. duplicate suppression, aggregation, correlation
• Nested queries reduce overhead relative to “edge processing”
• Complex queries support
collaborative signal
processing
– propagate function
describing desired
locations/nodes/data
(e.g. ellipse for tracking)
• Interesting analogs to emerging
peer-to-peer architectures
14
Directed Diffusion
•
Basic idea
– name data (not nodes) with externally relevant attributes
• Data type, time, location of node, SNR, etc
– diffuse requests and responses across network using application
driven routing (e.g., geo sensitive or not)
– optimize path with gradient-based feedback
– support in-network aggregation and processing
•
Data sources publish data, Data clients subscribe to data
– However, all nodes may play both roles
• A node that aggregates/combines/processes incoming sensor
node data becomes a source of new data
• A sensor node that only publishes when a combination of
conditions arise, is a client for the triggering event data
– True peer to peer system
•
Implemented defines namespace and simple matching rules in the form
of filters
– Linux (32 bit proc) and TinyOS (8 bit proc) implementations
15
Of more interest than simple Aggregation are
Nested Queries
(Source: Heidemann et. al.)
flat
Use application-level
information to scope
and process data.
nested
audio
light
sensors
user
16
• Nested queries greatly improve
event delivery rate
• Specific results depend on
experiment
– placement
– limited quality MAC
• General result: app-level info
needed in sensor nets; diffusion
is good platform
events successfully received (%)
Nested Query Evaluation
(A real experiment w/sub-optimal hardware)
nested
80
60
40
flat
20
1
2
3
4
number of light sensors
17
Sub-optimal aggregation tree constructions
(From Krishnamachari et.al.)
• On a general graph if k nodes are sources and one is a
sink, the aggregation tree that minimizes the number of
transmissions is the minimum Steiner tree. NP-complete
• Center at Nearest Source (CNSDC): All sources send
through source nearest to the sink.
• Shortest Path Tree (SPTDC): Merge paths.
• Greedy Incremental Tree (GITDC): Start with path from
sink to nearest source. Successively add next nearest
source to the existing tree.
• AC: Distinct paths from each source to sink.
18
Source placement: event-radius model
(From Krishnamachari et.al.)
19
Comparison of energy costs
(From Krishnamachari et.al.)
20
Opportunism always pays;
Greed pays only when things get very crowded
(From Intanagowiwat et.al. ns-2 more detailed simulations)
Self-Organization with Localized Algorithms
• Self-configuration and reconfiguration essential to lifetime of unattended
systems in dynamic, constrained energy, environment
– Too many devices for manual configuration
– Environmental conditions are unpredictable
• Example applications:
– Efficient, multi-hop topology formation: node measures
neighborhood to determine participation, duty cycle, and/or power
level
– Beacon placement: candidate beacon measures potential reduction
in localization error
• Requires large solution space; not seeking unique optimal
• Investigating applicability, convergence, role of selective global
information
22
Adaptive Topology Schemes
• SPAN
Benjie Chen, Kyle Jamieson, Robert Morris, Hari
Balakrishnan, MIT,
http://www.pdos.lcs.mit.edu/papers/span:wireless01
– Goal: preserve fairness and capacity while providing energy
savings (minimize number of coordinators while still preserving
network capacity).
– Mechanism: elects coordinators to create backbone topology.
– Limitation: Depends on ad-hoc routing protocol to get list of
neighbors and connectivity matrix between them.
• ASCENT
Alberto Cerpa and Deborah Estrin, UCLA,
http://lecs.cs.ucla.edu/~cerpa/ASCENT-final-infocompdf1.3.pdf
– Goal: exploit the redundancy in the system (high density) to save
energy while providing a topology that adapts to the application
needs
– Mechanism: empirical adaptation. Each node assesses its
connectivity and adapts participation in multi-hop topology based
on the measured operating region.
– Limitation
23
Performance Results
(From Chen et. al. simulations)
24
Performance Results
(From Cerpa, Simulations and Implementation)
Energy Savings (normalized to the Active case, all nodes turn on) as a function of density.
ASCENT provides significant amount of energy savings, up to a factor of 5.5 for high
density scenarios.
25
Programming Paradigm
• How do we task a 1000+ node dynamic sensor network to
conduct complex, long-lived queries and tasks ??
• Map isotherms and other “contours”, gradients, regions
– Record images wherever acoustic signatures
indicate significantly above-average species activity,
and return with data on soil and air temperature and
chemistry in vicinity of activity.
– Mobilize robotic sample collector to region where soil
chemistry and air chemistry have followed a
particular temporal pattern and where the region
presents different data than neighboring regions.
• Pattern identification: how much can and should we do in
a distributed manner?
26
Towards a Unified Framework for ENS
•
General theory of massively distributed systems that interface
with the physical world
– low power/untethered systems, scaling, heterogeneity,
unattended operation, adaptation to varying environments
•
Programming the Collective
– What local behaviors will result in global tasks
– Programming model for instantiating local behavior and
adaptation
– Abstractions and interfaces that do not preclude efficiency
•
Large-scale experiments to challenge assumptions behind
heuristics
– Measurement tools
– Data sets
27
Pulling it all together
CENS Core Research
Collaborative
Signal
Processing and
Active
Databases
Sensor
Coordinated
Actuation
Adaptive
Self-Configuration
Environmental
Microsensors
Academic Disciplines
Networking
Communications
Signal Processing
Databases
Embedded Systems
Controls
Optimization
…
Biology
Geology
Biochemistry
Structural Engineering
Education
Environmental Engineering
28
Follow up
•
•
•
•
Embedded Everywhere: A Research Agenda for Networked Systems
of Embedded Computers, Computer Science and Telecommunications
Board, National Research Council - Washington, D.C.,
http://www.cstb.org/
DARPA Programs
• http://dtsn.darpa.mil/ixo/sensit.asp
• http://www.darpa.mil/ito/research/nest/
Related projects at UCLA and USC-ISI
• http://cens.ucla.edu
• http://lecs.cs.ucla.edu
• http://www.isi.edu/scadds
Many other emerging, active research programs
• UCB: Culler, Hellersein, BWRC, Sensorwebs, CITRIS
• MIT: Chandrakasan, Balakrishnan
• Cornell: Gherke, Wicker
• Univ Washington: Boriello
• UCSD: Cal-IT2
29