The concept of cognitive radio (CR) focuses on devices that can sense their environment, adapt configuration parameters, and\r\nlearn from past behaviors. Architectures tend towards simplified decision-making algorithms inspired by human cognition.\r\nInitial works defined cognitive engines (CEs) founded on heuristics, such as genetic algorithms (GAs), and case-based reasoning\r\n(CBR) experiential learning algorithms. This hybrid architecture enables both long-term learning, faster decisions based on past\r\nexperience, and capability to still adapt to new environments. This paper details an autonomous implementation of a hybrid\r\nCBR-GA CE architecture on a universal serial radio peripheral (USRP) software-defined radio focused on link adaptation. Details\r\ninclude overall process flow, case base structure/retrieval method, estimation approach within the GA, and hardware-software\r\nlessons learned. Unique solutions to realizing the concept include mechanisms for combining vector distance and past fitness\r\ninto an aggregate quantification of similarity. Over-the-air performance under several interference conditions is measured using\r\nsignal-to-noise ratio, packet error rate, spectral efficiency, and throughput as observable metrics. Results indicate that the CE is\r\nsuccessfully able to autonomously change transmit power, modulation/coding, and packet size to maintain the link while a noncognitive\r\napproach loses connectivity. Solutions to existing shortcomings are proposed for improving case-base searching and\r\nperformance estimation methods.
Loading....