ANFIS-based rate compatible punctured Turbo code for fixed broadband wireless access networks

This paper investigates the application of adaptive neuro-fuzzy inference system-based rate compatible punctured turbo code to compensate for inter-cell interference and rain attenuation and then to effectively improve the system performance on fixed broadband wireless access system. Fixed broadband wireless access systems, for instance the local multipoint distribution service (LMDS), provide wireless multimedia services to several fixed terminal stations and offer various advantages over the wired networks services, for example the low cost and the flexibility for the deployment of the system compared to the deployment of DSL and cables ones. LMDS system is a two-way digital cellular system operating at 10-60 GHz. Operating at such high frequency band, rain attenuation and inter cell interference are two significant influential factors of the system performance. In order to combat the impacts of rain fading and of intercell interference on LMDS networks, we propose a new criterion for the choice of the puncturing patterns, in which rain rate and the cross polarization discrimination (XPD) are put into fuzzy inference system and the output is referred to as quality of channel. In accordance with the system situation, the channel quality will be adopted to determine the puncturing pattern, and then to reduce redundant bits as well as improving the bandwidth efficiency. Simulation results indicate that the bit error rate of two schemes are equally well; moreover, the proposed scheme indeed has improved the bandwidth efficiency of the without punctured turbo code scheme for LMDS network.