Optimising Cellular Wireless Networks using Evolutionary Computing

1
Optimising Cellular Wireless Networks using
Evolutionary Computing
Martin Klepal

• Centre for Adaptive Wireless Systems

22nd June 2005
2

• Adaptive Radio Resource Management for GSM
• Large Scale WLAN Design and Optimisation

(Ken Murray, Dirk Pesch)
(Martin Klepal, Alan Mc Gibney)
3
Adaptive Radio Resource Management for GSM
Objective
Increase network capacity in GSM using an
adaptive radio resource management system.
GSM networks employ fixed channel allocation
model (FCA) to assign frequencies to base
stations
The traffic evolution between cells is different
Busy periods occur at different times
Resources at quiet cells are wasted
With the introduction of 2.5G services such as
GPRS and EDGE, a more flexible method of resource
management is required to maximize system
resources.
4
Proposed Solution
Adaptive Radio Resource Management for GSM
Using Evolutionary computing techniques, we
propose an Adaptive Radio Resource Management
System
5
Results and Conclusion
Adaptive Radio Resource Management for GSM
Simulation has shown resource gains of up to 21
when compared with current FCA frequency
assignment schemes
The proposed approach has a non-invasive
implementation within Operation Maintenance
Centers of existing GSM network.
6
Large Scale WLAN Design and Optimisation
Martin Klepal, Alan Mc Gibney
7
Large Scale WLAN Design and Optimisation
Motivation
8
Outline
Large Scale WLAN Design and Optimisation

• Site Description
• Signal Coverage and Channel Throughput Prediction
• AP Placement Pre-processing Optimisation
• Current Implementation
• Result Scalability
• Future Research

9
Site Description
Large Scale WLAN Design and Optimisation
Part of CIT Campus
Multi-Storey Building
10
Large Scale WLAN Design and Optimisation
Signal Coverage Prediction
11
Throughput Prediction
Large Scale WLAN Design and Optimisation
12
Selection of Candidate AP
Large Scale WLAN Design and Optimisation
Candidate Access Point positions forming an
undirected graph that can be traversed during the
optimisation
13
Fitness Function
Large Scale WLAN Design and Optimisation
The objective of the optimisation is to minimise
the Fitness Function that evaluates if the
suggested design of the network satisfies user
demands by maximizing throughput with a minimum
number of APs and other constraints.
Elements of the Fitness Function
D User Demand Satisfaction A Number of Access
Points R Restricted Area B Solution
Balance wi Waiting Factors
14
Optimisation Technique
Large Scale WLAN Design and Optimisation
Evolution Strategies
Initialise
Objective Function Evolutionary
Operators Site-Specific Knowledge
Selection
Parents(µ)
Survival of the fittest
Self-adaptation
Population
Mutation(s)
FF
Offspring (?)
Terminate
15
Implementation
Large Scale WLAN Design and Optimisation
16
Results
Large Scale WLAN Design and Optimisation
100 Coverage with a minimum number of AP
Initial results of the optimisation technique
implemented are stable because the same solution
is suggested after each run on the same
environment.
17
Scalability
Large Scale WLAN Design and Optimisation

• Segmentation

• Voronoi Graph

• Crystals of Variable Size

• Backtracking Algorithm

18
Ongoing Future Research
Large Scale WLAN Design and Optimisation

• Overcome the problem of scalability using
  Segmentation Backtracking Algorithm
• 3D Implementation
• Large scale measurement and analysis of a
  deployed solution

19
Conclusion
Large Scale WLAN Design and Optimisation

• Adaptive Radio Resource Management System for GSM
• shows resource gains of up to 21 when compared
  with current FCA frequency assignment schemes
• Large Scale WLAN Design and Optimisation
• aims to developed a computer aided automatic
  design tool that will provide an optimum WLAN
  design with minimum number of APs providing
  required signal coverage and network capacity.

20

• Thank you for your attention!