AI-Managed Cognitive Radio Digitizers

Abstract

Embedding Artificial Intelligence (AI) in integrated circuits is one of the technology pillars of the so-called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">digital transformation</i> . Nowadays, the vast majority of electronic devices benefits from digital signal processing to implement more and more functionalities, which can be further enhanced by the action of AI algorithms and artefacts. Moreover, as the analog/digital interfaces are moving closer and closer to the point where the information is either acquired or transmitted, the so-called AI-managed data converters are becoming key building blocks in an increasingly number of interconnected <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cyberphysical</i> systems–made up of both software and hardware components. Software Defined Radio (SDR) and Cognitive Radio (CR) systems intended for 5G/6G communications are good examples which can benefit from an early digitization managed by AI engines. <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">In this context, this paper presents an overview of circuits and systems techniques for AI-managed analog/digital interfaces with application in SDR/CR mobile telecom systems. Some design trends and challenges are discussed, going from new communications and computing paradigms for AIoT devices and networks, to digital-based/scaling-friendly analog circuit techniques for an efficient digitization. The state of the art on Analog-to-Digital Converters (ADCs) is surveyed, putting emphasis on highly-programmable Sigma-Delta Modulators (<inline-formula><tex-math notation="LaTeX">$\Sigma\Delta$</tex-math></inline-formula>Ms) as one of the best ADC candidates for SDR/CR transceivers. Some chip examples are shown to illustrate their potential application in AI-enhanced CR end-devices.