Using a GA in Intelligent Software Defined Radio
A piece of research completed in conjunction with the De Montfort University in 2013 demonstrated how the Genetic Algorithm Framework (GAF) could be used with a Software Defined Radio (SDR) system, to provide automatic frequency control (AFC).
The aim of AFC is to ensure that a radio system stays tuned to the desired frequency in conditions where the frequency is subject to change. The research demonstrated that a genetic algorithm (GA) can perform this task. In addition, the research showed how the GA can also handle very large changes in frequency such as the doppler shift that can be experienced with satellite communications, and the channel hopping nature of Cognitive Radio systems.
The research report can be found here... File:Report.pdf
A summary of the activity is described below.
Software Defined Radio
Software Defined Radio (SDR) is a radio system that uses software in place of components that were traditionally implemented in hardware. With the increase in power of computer systems and digital electronics, it is now possible to present a large amount of the radio spectrum to computer software for processing. This processing effectively replaces traditional radio receiver hardware technologies.
SDR Radio Controller
The basic aim is for the GA to find the desired signal within the frequency spectrum, tune the radio system to that signal and then remain ‘locked’ to that signal irrespective of any frequency changes large or small.
Within the research, the signal being tuned was a 620Hz bandwidth Radio Teletype (RTTY) transmission from the German Meteorological service known as DDK.
A wide bandwidth radio frequency signal was passed from an RFSpace SDR IQ radio receiver to the computer for tuning, filtering and demodulation by SDR Sharp software (SDR#). In order to provide the deeper integration required to utilise a GA for radio control, software, referred to as the ’GA Controller’, was developed and incorporated into the radio system. The GA Controller is responsible for integrating the SDR# software with the GAF.
The GA Controller was developed as a ’Plug In’ to the open source SDR# software and utilises the Genetic Algorithm Framework (GAF) to provide the GA based control.
Scope and Diversity Plots
The GA Controller includes a small Graphical User Interface (shown here) that allows the properties of the Genetic Operators of the GAF to be changed. With the genetic operators supplied in the GAF having thread safe parameters, the GUI can be used to change the operator parameters whilst the GA is running. This dynamic control of the GA was monitored using the GAF events to identify such things as general accuracy, error rate and diversity. Being able to monitor the error rate and diversity graphically, proved to be an extremely useful facility in determining the configuration for the GA and the respective operators.