Bayesian Optimization for Microwave Devices Using Deep GP Spectral Surrogate Models

Abstract

In microwave design, Bayesian optimization (BO) techniques have been widely applied to the optimization of the frequency response of components and devices. The common approach in BO is to model and maximize an objective function over the design parameters, in order to find the optimal spectral response. Such an approach avoids the direct modeling of spectral responses, which is a challenging task for the typical data-efficient surrogate models used in BO. Simple objective functions may lead to a suboptimal solutions, while complicated objectives require more powerful and less data-efficient surrogate models. To resolve this issue, this article proposes to adopt a deep Gaussian process (DGP) to directly model all relevant S coefficients over the frequency and the design parameter ranges of interest. Subsequently, an objective probability distribution is retrieved from the DGP model and maximized using a BO scheme. The proposed approach is tested on two suitable microwave examples and compared to the standard BO approach. Results show increased accuracy in identifying the optimal frequency response for the given design parameters and the desired objective, while maintaining high data efficiency.

Modeling Electrically Long Interconnects Using Physics-Informed Delayed Gaussian Processes

“…However, this is often not the case when modeling high-speed interconnects, whose frequency response may be dynamic and oscillating. As an alternative, the use of deep Gaussian process (DGP) has been shown to be beneficial for the optimization of frequency responses [17], [18]. Although, DGPs come at the cost of high computational complexity and instability when dynamic functions are modeled.…”

On Accelerated Metaheuristic-Based Electromagnetic-Driven Design Optimization of Antenna Structures Using Response Features

“…Observe that the parameter ranges are broad: the average ratio of the upper and lower bounds is 2.5, 5.0, and 1.5 for Antennas I through III, respectively. In fact, the antenna structures employed in this work for verifying the proposed framework are challenging when compared to the verification case structures utilized for validating global simulation-driven design optimization algorithms reported in the literature [94,[105][106][107][108][109][110][111]. This pertains to both the number of the designable variables (six, ten, and eleven geometry parameters for Antenna I through III), as well as their ranges.…”

Modeling S-parameters of Interconnects using Periodic Gaussian Process Kernels

“…The wide-band S-parameters of such structures can exhibit a dynamic and oscillatory behavior. A potential solution for coping with this, is to adopt a type of GP with higher modeling power, like the Deep Gaussian Process (DGP) [6]. However, this significantly increases computational complexity and modeling time.…”

“…Furthermore, GPs have been successfully employed to optimize performance metrics of microwave devices, using Bayesian Learning [5], [6]. For a given DUT, they can rapidly identify the optimal values of performance metrics, which are modelled as a function of design variables.…”