AI Technologies for Tactical Edge Networks

Page
1

AI Technologies for

Tactical Edge Networks

Karen Zita Haigh

Raytheon BBN Technologies

May 2011

Page
2

What is AI?

The Odd Paradox

Practical AI successes … were soon assimilated into whatever
application domain they were found to be useful in, and became silent
partners …, which left AI researchers to deal only with the failures.”
[McCorduck, 2004]

Karen Zita Haigh

Artificial
Intelligence

Mathematics

Economics

Psychology

Control Theory

Natural
Language
Processing

Speech
Recognition

Machine Vision

Robotics

Page
3

Joe Mitola’s OOPDAL Loop
















Joseph Mitola III,
Cognitive Radio: An Integrated Agent Architecture for Software
Defined Radio
, Phd Thesis, Royal Institute of Technology (KTH), 2000

Karen Zita Haigh

Page
4

Joe Mitola’s OOPDAL Loop (2)

Karen Zita Haigh

Orient

Plan

Act

Observe

Decide

Learn

Collect

Validate

Assess situation

Infer Intent

Impact Analysis

Select Goals

Generate Plans

Schedule

Select Plan

Allocate Resources

Implement

Update
Models

Page
5

Roles for AI in Networking

•
Cyber Security

•
Network Configuration
(which modules to use)

•
Network Control (which
parameter settings to
use)

•
Policy Management

•
Traffic Analysis

•
Performance Analysis

•
Sensor fusion /
situation assessment

•
Planning

•
Coordination

•
Optimization

•
Constraint reasoning

•
Learning (Modelling)

–
Complex Domain

–
Dynamic Domain


Unpredictable by
Experts

AI enables real
-
time, context
-
aware adaptivity

Page
6

MANET Characteristics

What AI is good at

•
Dynamic

•
Diverse

•
Massive Scale

•
Complex Parameter
Interactions

•
Partially
-
observable
feedback

•
Complex Access Policies

•
Multi
-
objective
performance requirements


Main challenges for AI

•
Ambiguous feedback

•
High
-
latency feedback

•
Resource Constrained

•
Heterogeneous
Intercommunication

Karen Zita Haigh

Cross
-
Layer Optimization on Steroids

Page
7

Knowledge Engineering

•
Captures knowledge so that a computer system
can solve complex problems, e.g.

–
models of physics and signal propagation, constraints
on the system, analysis of interactions, and rules of
thumb (e.g., about how to configure the system).

•
A formal ontology may help a cognitive system
reason about how and when capabilities are
interchangeable

•
Knowledge bases can help optimize the network

–
e.g. By biasing a learning algorithm

–
e.g. By constraining a planner

Karen Zita Haigh

Page
8

Planning and Scheduling

•
Organizes tasks to meet performance objectives
under resource constraints

–
Multi
-
agent planning, dynamic programming, constraint
satisfaction, and distributed or combinatorial
optimization algorithms

•
Planning and scheduling techniques in networks
can decide what content to move, where, when,
and how

–
Prefetch

/
prepush

data

–
Power
-
aware computing

–
Node activity and task scheduling

–
Network management

–
Server placement; when to handle queries

Karen Zita Haigh

Page
9

Multi
-
Agent Systems

•
Traditional MAS approaches fail in MANET
because they assume that communications are (a)
infinite and (b) always available

•
Biologically
-
inspired approaches have done better.

•
Demonstrated Applications:

–
Routing:
AntHocNet

uses both proactive and reactive
schemes to update the routing tables, and outperforms
AODV.

–
Network connectivity

–
Dynamic load balancing

–
Service placement

Karen Zita Haigh

Page
10

Machine Learning

•
ML improves the performance of a system by
observing the environment and updating models

–
the learner must generalize so that the learned model is
useful for new (previously unseen) situations.

–
Artificial neural networks
, support vector machines,
clustering, explanation
-
based learning, induction,
reinforcement learning
,
genetic algorithms
, nearest
neighbour methods, and case
-
based learning.

•
Demonstrated Applications

–
Routing

–
Energy management

–
Node mobility

–
Parameter interaction

Karen Zita Haigh

Page
11

Concrete Example: ML in ADROIT

•
Adaptive Dynamic Radio Open
-
source Intelligent
Team (ADROIT)

•
Create cognitive radio teams that

–
Recognize that the situation has changed

–
Anticipates changes in networking needs

–
Adapts the network, in real
-
time, for improved
performance

•
Real
-
time composability of the stack

•
Real
-
time control of parameters

•
On one node and across the network

Page
12

ADROIT’s Experimental Testbed

Maximize %
of shared
map of the
environment

Page
13

Experimental Results

Training Run:

•
In first run nodes learn
about environment

•
Train neural nets with
(Conditions,Strategy)

Performance

tuples

–
Every 5s, measure and
record progress, conditions,
& strategy

–
Observations are local, so
each node learns different
model!

Real
-
time learning run:

•
In second run, nodes adapt
behaviour to perform
better.

•
Adapt each minute by
changing strategy
according to current
conditions


Real
-
time cognitive control of a

real
-
world wireless network

Page
14

Observations from Learning

•
Selected configurations explainable but not
predictable

–
Farthest
-
refraining was usually better

•
congestion, not loss dominated

–
Unicast/Multicast was far more complex

•
close: unicast wins (high data rates)

•
medium: multicast wins (sharing gain)

•
far: unicast wins (reliability)

14

System performed better with learning

Page
15

Biggest remaining challenges

•
Social engineering

–
the human
-
to
-
human interaction of the AI
community differs dramatically from that of the
networking community

•
Software architecture

–
Network architectures are traditionally tightly
coupled; we need to provide hooks

May 2011

Karen Zita Haigh

Module 1

Module 2

Module 2

Module 1

Broker

Page
16

SOFTWARE ARCHITECTURE

Karen Zita Haigh

May 2011

Page
17

A Need for Restructuring

•
SDR gives opportunity to create
highly
-
adaptable systems, BUT

–
They usually require network experts to
exploit the capabilities!

–
They usually rely on module APIs that are
carefully designed to expose each
parameter separately.

•
This approach is not maintainable

–
e.g. as protocols are redesigned or new
parameters are exposed.

•
This approach is not amenable to
real
-
time cognitive control

–
Hard to upgrade

–
Conflicts between module & AI

Module 1

Module 2

Page
18

A Need for Restructuring

•
We need one consistent, generic, interface

for all modules to expose their parameters

and dependencies.

Module 2

Module 1

Page
19

A Generic Network Architecture

exposeParameter(
parameter_name
,
parameter_properties
)

setValue(
parameter_handle
,
parameter_value
)

getValue(
parameter_handle

)

Broker


-
Assigns
handles

-
Provides
directory
services

-
Sets up event
monitors

-
Pass through
get/set

Cognitive Control

Command Line
Interface

Network Management

Network Stack

Network Module

Network Module

Registering
Modules

Re/Setting
Modules

Observing
Params

Registering
Modules &
Parameters

Re/Setting
Modules

Observing
Params

Applications / QoS

Page
20

20

Benefits of a Generic Architecture

•
It supports network architecture design &
maintenance

–
Solves the
n
х
m

problem (upgrades or
replacements of network modules)

•
It doesn’t restrict the form of cognition

–
Open to just about any form of cognition you
can imagine

–
Supports
multiple
forms of cognition on each
node

–
Supports
different

forms across nodes

•
It doesn’t
mandate

cognition

Page
21

SOCIAL ENGINEERING

Karen Zita Haigh

May 2011

Page
22

Cultural Issues: But why?

•
Benefits and scope of
cross
-
layer design:

–
More than 2 layers!

–
More than 2
-
3
parameters per layer



Drill
-
down walkthroughs
highlighted benefits to
networking folks;
explained restrictions to
AI folks


Simulation results for
specific scenarios
demonstrated the power

•
Traditional network
design includes
adaptation

–
But this works against
cognition: it is hard to
manage
global

scope

–
AI people want to
control everything

–
But network module
may be better at doing
something focussed



Design must include
constraining

how a
protocol adapts

Page
23

Cultural Issues: But how?

•
Reliance on centralized
Broker:

–
Networking folks don’t
like the single bottleneck


Design must have fail
-
safe default operation

•
Asynchrony and
Threading:

–
AI people tend to like
blocking calls.

•
e.g. to ensure that
everything is consistent

–
Networking folks outright
rejected it.


Design must include
reporting and alerting

Page
24

Cultural Issues: But it’ll break!?!

•
Relinquishing control
outside the stack:

–
Outside controller
making decisions scares
networking folks

–
AI folks say “give me
everything & I’ll solve
your problem”



Architecture includes
“failsafe” mechanisms to
limit both sides


•
Heterogeneous and
non
-
interoperable

nodes

–
Networks usually have
homogeneous
configurations to
maintain
communications

–
AI likes heterogeneity
because of the benefit

•
But always assumes safe
communications!



“Orderwire” bootstrap
channel as backup

Page
25

Cultural Issues: New horizons?

•
Capability Boundaries

–
Traditional Networking has very clear boundary
between “network” and “application”

–
Generic architecture blurs that boundary

•
AI folks like the benefit

•
Networking folks have concerns about complexity


Removing this conceptual restriction will
result in interesting and significant new
ideas.


Page
26

Conclusion

•
AI techniques are ready to be
challenged with this complex real
-
world
domain, just as Networking
requirements are reaching the limits of
what can be done without AI.


•
To demonstrate the power of cognitive
networking, both AI folks & Networking
folks need to recognize and adapt