Efficient global optimization of multi-parameter network problems on wireless testbeds

Abstract

A large amount of research focuses on experimentally optimizing the performance of wireless solutions. Finding the optimal performance settings typically requires investigating all possible combinations of design parameters, while the number of required experiments increases exponentially for each considered design parameter. The aim of this paper is to analyze the applicability of global optimization techniques to reduce the optimization time of wireless experimentation. In particular, the paper applies the Efficient Global Optimization (EGO) algorithm implemented in the SUrrogate MOdeling (SUMO) toolbox inside a wireless testbed. Moreover, to cope with the unpredictable nature of wireless testbeds, the paper applies an experiment outlier detection which monitors outside interference and verifies the validity of conducted experiments. The proposed techniques are implemented and evaluated in a wireless testbed using a realistic wireless conferencing scenario. The performance gain and experimentation time of a SUMO optimized experiment is compared against an exhaustively searched experiment. In our proof of concept, it is shown that the proposed SUMO optimizer reaches 99.79% of the global optimum performance while requiring 8.67 times less experiments compared to the exhaustive search experiment.

Screening interacting factors in a wireless network testbed using locating arrays

“…Determining the levels of the factors screened by our method that maximize MOS while minimizing transmission exposure is the next step in experimentation. Validation by other methods, such as those used in SUMO [2], is of interest.…”

“…Transmission exposure calculates the electromagnetic energy absorbed by a human body due to uplink and downlink wireless transmissions [2].…”

“…The aim is to screen the measured responses of mean opinion score (MOS) [2] and the transmission exposure in a Wi-Fi audio broadcast, i.e., to identify the factors and low order interactions that influence these two measured responses.…”

“…The SUMO toolbox contains techniques for experiment generation, and the solution of such optimization problems. In [2], the toolbox was applied to a problem in a wireless network testbed using an exhaustive experiment. Necessarily, the number of factors was small.…”

Adaptive modeling and sampling methodologies for Internet of Things applications

“…The data-driven approximation (known as surrogate model, metamodel or response surface model) is then used for optimization, sensitivity analysis, design space exploration, or any other application relying heavily on evaluation. Several approximation methods have been successfully used in many applications over the years [1]- [5].…”