From the literature review analysis, it is evident that NYUSIM, METIS, FRFT and Machine learning techniques are better for channel modelling than other techniques. Moreover, these techniques showcase the most optimum performance for one or more parameters, and thus they must be used in combination for an effective channel modelling system.Milli-meter wave communication systems usually work towards improving the throughput of the system. Channel modelling plays a vital role in achieving this task. Modelling channels requires a lot of complex mathematical analysis, and this analysis changes with changes in traffic patterns, number of communicating nodes, actual channel type and many other real-time parameters. Due to these changes, a static channel model is usually insufficient for real- time use cases. Our problem statement is to integrate machine learning into channel modelling, so that the prepared channel model incorporates most of the real-time changes in network parameters.
A Review paper on Milli-Meter Wave Communications
01.12.2022
1092983 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
DSpace@MIT | 2003
|Milli Vanilli - Kurztest Opel Zafira
Kraftfahrwesen | 2008
|Messen+Testen: Milli-Kelvin am USB
British Library Online Contents | 2007