Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Circuit-centric Genetic Algorithm (CGA) for Analog and Radio-Frequency Circuit Optimization

Mingi Kwon, Yeonjun Lee, Ickhyun Song

TL;DR

This work addresses the challenge of efficiently optimizing RF receiver parameters in analog circuitry, where conventional optimization and deep learning approaches can be computationally intensive. It introduces the Circuit-centric Genetic Algorithm (CGA), which eschews crossover in favor of repeated mutations applied to the single best FoM-driven circuit across all component variables, yielding stable, progressive improvements. Empirical results on an LNA–mixer receiver layout demonstrate a ~30% FoM gain, with gains of about 13.13 dB, NF around 2.01 dB, and power near 0.011 W, validating CGA as a low-cost, adaptable alternative for transistor-level circuit optimization. The method is implemented in Python with LTspice automation, highlighting its practical impact for rapid, automated analog/RF design without the heavy computational burden of deep learning models.

Abstract

This paper presents an automated method for optimizing parameters in analog/high-frequency circuits, aiming to maximize performance parameters of a radio-frequency (RF) receiver. The design target includes a reduction of power consumption and noise figure and an increase in conversion gain. This study investigates the use of an artificial algorithm for the optimization of a receiver, illustrating how to fulfill the performance parameters with diverse circuit parameters. To overcome issues observed in the traditional Genetic Algorithm (GA), the concept of the Circuit-centric Genetic Algorithm (CGA) is proposed as a viable approach. The new method adopts an inference process that is simpler and computationally more efficient than the existing deep learning models. In addition, CGA offers significant advantages over manual design of finding optimal points and the conventional GA, mitigating the designer's workload while searching for superior optimum points.

Circuit-centric Genetic Algorithm (CGA) for Analog and Radio-Frequency Circuit Optimization

TL;DR

This work addresses the challenge of efficiently optimizing RF receiver parameters in analog circuitry, where conventional optimization and deep learning approaches can be computationally intensive. It introduces the Circuit-centric Genetic Algorithm (CGA), which eschews crossover in favor of repeated mutations applied to the single best FoM-driven circuit across all component variables, yielding stable, progressive improvements. Empirical results on an LNA–mixer receiver layout demonstrate a ~30% FoM gain, with gains of about 13.13 dB, NF around 2.01 dB, and power near 0.011 W, validating CGA as a low-cost, adaptable alternative for transistor-level circuit optimization. The method is implemented in Python with LTspice automation, highlighting its practical impact for rapid, automated analog/RF design without the heavy computational burden of deep learning models.

Abstract

This paper presents an automated method for optimizing parameters in analog/high-frequency circuits, aiming to maximize performance parameters of a radio-frequency (RF) receiver. The design target includes a reduction of power consumption and noise figure and an increase in conversion gain. This study investigates the use of an artificial algorithm for the optimization of a receiver, illustrating how to fulfill the performance parameters with diverse circuit parameters. To overcome issues observed in the traditional Genetic Algorithm (GA), the concept of the Circuit-centric Genetic Algorithm (CGA) is proposed as a viable approach. The new method adopts an inference process that is simpler and computationally more efficient than the existing deep learning models. In addition, CGA offers significant advantages over manual design of finding optimal points and the conventional GA, mitigating the designer's workload while searching for superior optimum points.
Paper Structure (16 sections, 2 equations, 6 figures, 3 tables, 1 algorithm)

This paper contains 16 sections, 2 equations, 6 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Receiver Design and Figure of Merit
  3. Genetic Algorithm Adaptation for Analog and Radio-frequency Circuit
  4. Genetic Algorithm
  5. Advantages of Genetic Algorithm
  6. Basic Principles of Genetic Algorithm
  7. The Challenges of Applying Genetic Algorithms in Circuit Design
  8. CGA : Circuit-Centric Genetic Algorithm
  9. CGA operation
  10. CGA’s distinct feature compared to GA
  11. Optimization Results and Discussion
  12. Results
  13. Discussion
  14. Merits
  15. Challenges
  16. ...and 1 more sections

Figures (6)

  • Figure 1: System configuration of an RF receiver (Rx) in which an antenna, an LNA, a down-conversion mixer, a voltage-controlled oscillator (VCO), and a low-pass filter are included. The frequencies of the input, the local oscillator (LO) signal, and the output are 2.4 GHz, 2.4 GHz, and 100 MHz, respectively.
  • Figure 2: Full schematic of RF receiver including an LNA and a single-balanced down -conversion mixer.
  • Figure 3: Genetic Algorithm flowchartr14
  • Figure 4: FoM of circuit designed with original GA algorithm
  • Figure 5: System configuration of an RF receiver (Rx) in which an antenna, an LNA, a down-conversion mixer, a voltage-controlled oscillator (VCO), and a low-pass filter are included. The frequencies of the input, the local oscillator (LO) signal, and the output are 2.4 GHz, 2.4 GHz, and 100 MHz, respectively.
  • ...and 1 more figures