Cognitve ranging

Cognitive Engine Design

By,Anusree A(208114016)

Tomin Francis(208114017)Samuel Cherukutty

C(208114018)

What we'll be seeing...

Introduction Functions of a typical Cognitive engine AI techniques in Congitive Engine Design Performance Measurements of Cognitive Engine Cognitive Engine Modules Cognitive Learning Cycle Cognitive Paradigms Comparison of Algorithms

Introduction

SDR + AI = CGR Cognitive Engine provides the

'AI' part of the CGR The abilities or performances

of CGR are determined by the

algorithms implemented in the Cognitive engine

Cognitive Engine

Cognitive engine decision making process is highly dependant upon parameters Radio transmission parameters Environmental measurements Performance Objectives

How can these parameters be related to radio objectives analytically? Engine must understand how parameters affect the environment Multiple parameters must be related to multiple objectives

Performance Parameters

Responsiveness Measure of how fast the system responds to the variations in

surroundings Complexity

Complexity of the algorithm determined by the number of LUT's that will be used

Its a direct factor in determining the cost of the CGR system Security

Measure of the security of the data transmission channel Robustness

Measure of CE's performance in harsh and difficult environments Stability

Measure of variation in design parameters with the changing environment

AI Techniques implemented in CE

Genetic Algorithm(Ontology Based) Artificial Neural Networks (ANNs) Case-based Systems (CBSs) Metaheuristic Algorithms Hidden Markov Models (HMMs) Rule-based Systems (RBSs)

Cognitive Engine Modules

Sensing Module provides radio environment sensing results

REM(Radio Environment Maps) provides a snapshot of the radio scenario through time

Main Controller decides which algorithm to use

Case and Knowledge Reasoner provides coarse solution, starting point for the Multi-

objective Optimizer Multi-objective Optimizer

further refines the solution obtained by the CBR

Typical Design

Radio TX Channel Statistics

Cognitive Engine

Radio RX

“Meters” “Old KnobsSettings”

“Old KnobsSettings”

Software DefinedRadio Parameters“Knobs and Meters”

“Optimized Solution”

“New Settings” “New Settings”

CR reads the meters and turns the knobs.

Knobs– Transmit

power– Modulation– Coding– Symbol rate– Spectrum

shaping– Spreading– Antenna

Beamforming– Etc.

Meters– Bit error rate

(BER)– Frame error rate

(FER)– Signal power– Battery life– Computational

resources– Etc.

Two-Loop Cognition Cycle– Inner loop: Learning– Outer loop: Recognition and Adaptation

Environment awareness and evolving knowledge lead to optimal radio reconfiguration

Cognitive Radio Paradigms

Underlay Cognitive radios constrained to cause minimal interference to

noncognitive radios Interweave

Cognitive radios find and exploit spectral holes avoiding interference with noncognitive radios

Overlay Cognitive radios overhear and enhance noncognitive radio

transmissions

Knowledgeand

Complexity

Underlay Systems

Cognitive radios determined by their interference in transmission to noncognitive nodes Transmit if interference below a given threshold

The interference constraint may be met Via wideband signalling to maintain interference below the

noise floor (spread spectrum or UWB) Via multiple antennas and beamforming

NCR

IP

NCRCR CR

Underlay Challenges

Measurement challenges Measuring interference at primary receiver Measuring direction of primary node for beamsteering

Policy challenges Underlays typically coexist with licensed users Licensed users paid $$$ for their spectrum

Licensed users don’t want underlays Insist on very stringent interference constraints Severely limits underlay capabilities and applications

Interweave Systems Measurements indicate that even crowded spectrum is

not used across all time, space, and frequencies Original motivation for “cognitive” radios (Mitola’00)

These holes can be used for communication Interweave CRs periodically monitor spectrum for holes Hole location must be agreed upon between TX and RX Hole is then used for opportunistic communication with minimal

interference to noncognitive users

Interweave Challenges

Spectral hole locations change dynamically Need wideband agile receivers with fast sensing

Compresses sensing can play a role here Spectrum must be sensed periodically TX and RX must coordinate to find common holes Hard to guarantee bandwidth

Detecting and avoiding active users is challenging Fading and shadowing cause false hole detection Random interference can lead to false active user detection

Policy challenges Licensed users hate interweave even more than underlay

Overlay Systems

Cognitive user has knowledge of other user’s message and/or encoding strategy

Used to help noncognitive transmission Used to presubtract noncognitive interference

RX1

RX2NCR

CR

Algorithms:Genetic Algorithm

Biologically inspired optimization method based on Genetics and Natural Selection

Robust problem solving method by starting out with a set of random answers and gradually defining them

Solves Problems heuristically and loops through iterations which finally converges to the desired solution

Rondeau and Raiser from VirginiaTech designed first cognitive engine with genetic algorithm

Advantages of Genetic Algorithm

Problems With Genetic AlgorithmProblems With Genetic Algorithm

Convergence of Genetic Algorithm is not good Algorithm doesnt scale well with complexity Operation on dynamic data set is difficult

Comparison of Different AI techniques

To Conclude:

Cognitive Engine is the vital part of a cognitive radio. There are basically 5 modules to be designed for a cognitive

engine The hardware and software should be so chosen to fit the

design of cognitive radio into any of the three paradigm

References:

Cognitive Engine Design for Cognitive Radio By Salma BOURBIA, Madiha ACHOURI, Khaled GRATI, Daniel LE GUENNEC,

Adel GHAZEL Design and implementation of a cognitive engine functional

architecture ByDONG Xu, LI Ying & WEI ShengQun

Cognitive Radio Engine Design for Link Adaptation by Haris I. Volos

Tactical Wireless Communications and Networks: Design Concepts and Challenges By George F. Elmasry