Power Amplifier and Digital Pre-Distortion Design with MATLAB
|Start Time||End Time|
|29 Nov 2023, 4:30 AM EST||29 Nov 2023, 5:30 AM EST|
|29 Nov 2023, 9:00 AM EST||29 Nov 2023, 10:00 AM EST|
|29 Nov 2023, 2:00 PM EST||29 Nov 2023, 3:00 PM EST|
In this webinar, you will learn about digital predistortion (DPD) in modern terrestrial and satellite communications systems. We start by showing how to characterize the response of a power amplifier (PA) according to its nonlinearity order and its memory depth. We then show how you can design DPD systems using a variety of techniques. These techniques include a nonlinear memory polynomial, a neural network that has been trained offline, and a neural network with online training. Learn how the AI-based DPD achieves better adjacent channel power ratio (ACPR) performance than the traditional memory polynomial DPD.
- Characterizing a PA with an NI Vector Signal Transceiver (VST) that transmits and receives a MATLAB-generated stimulus signal that has been passed through the PA.
- Designing a DPD based on a memory polynomial that can significantly reduce ACPR.
- Designing and simulating a neural network DPD that can outperform the ACPR reduction of the memory polynomial DPD.
- Developing a neural network DPD that periodically trains while in operation, thus compensating for temperature-based changes in PA behavior.
Please allow approximately 45 minutes to attend the presentation and Q&A session. We will be recording this webinar, so if you can't make it for the live broadcast, register and we will send you a link to watch it on-demand.
About the Presenters
Mike McLernon is an advocate for communications and software-defined radio products at MathWorks. Since joining MathWorks in 2001, he has overseen the development of numerous PHY layer capabilities in Communications Toolbox, and of connectivity to multiple SDR hardware platforms. He has worked in the communications field for over 30 years, in both the satellite and wireless industries. Mike received his BSEE from the University of Virginia and his MEEE from Rensselaer Polytechnic Institute.
ETHEM MUTLU SÖZER is a principal software engineer at MathWorks Inc. in Natick, MA. He specializes in software development for signal processing and communications toolboxes in the fields of SDR support, receiver algorithms, and AI for wireless. Previously he was a research engineer at Massachusetts Institute of Technology, where he developed underwater acoustic communication hardware and software platforms. He has bachelor’s and master’s degrees from Middle East Technical University, and a Ph.D. from Northeastern University.
You are already signed in to your MathWorks Account. Please press the "Submit" button to complete the process.