RESUMEN
In an era dominated by Internet of Things (IoT) devices, software-as-a-service (SaaS) platforms, and rapid advances in cloud and edge computing, the demand for efficient and lightweight models suitable for resource-constrained devices such as data processing units (DPUs) has surged. Traditional deep learning models, such as convolutional neural networks (CNNs), pose significant computational and memory challenges, limiting their use in resource-constrained environments. Echo State Networks (ESNs), based on reservoir computing principles, offer a promising alternative with reduced computational complexity and shorter training times. This study explores the applicability of ESN-based architectures in image classification and weather forecasting tasks, using benchmarks such as the MNIST, FashionMnist, and CloudCast datasets. Through comprehensive evaluations, the Multi-Reservoir ESN (MRESN) architecture emerges as a standout performer, demonstrating its potential for deployment on DPUs or home stations. In exploiting the dynamic adaptability of MRESN to changing input signals, such as weather forecasts, continuous on-device training becomes feasible, eliminating the need for static pre-trained models. Our results highlight the importance of lightweight models such as MRESN in cloud and edge computing applications where efficiency and sustainability are paramount. This study contributes to the advancement of efficient computing practices by providing novel insights into the performance and versatility of MRESN architectures. By facilitating the adoption of lightweight models in resource-constrained environments, our research provides a viable alternative for improved efficiency and scalability in modern computing paradigms.
RESUMEN
The performance and potential of a W-band radio-over-fiber link is analyzed, including a characterization of the wireless channel. The presented setup focuses on minimizing complexity in the radio frequency domain, using a passive radio frequency transmitter and a Schottky diode based envelope detector. Performance is experimentally validated with carriers at 75-87GHz over wireless distances of 30-70m. Finally the necessity for and impact of bend insensitive fiber for on-site installation are discussed and experimentally investigated.
RESUMEN
Optical threshold functions are a basic building block for all-optical signal processing, and this paper investigates a threshold function design reliant on a single active element. An optical threshold function based on nonlinear polarization rotation in a single semiconductor optical amplifier is proposed. It functions due to an induced modification of the birefringence of a semiconductor optical amplifier caused by an externally injected optical control signal. It is shown that switching from both the TE to the TM mode and vice versa is possible. The measured results are supported by simulation results based on the SOA rate equations.
RESUMEN
We experimentally demonstrate an optical node with time-space-and- wavelength domain contention resolution, deflection and dropping capability. The node is composed of an optical buffer based on an optical crossconnect and a wavelength converter. Although the experimental results are shown at 10 Gbit/s the bitrate can be increased substantially. Bit-error rate measurements are shown, sustaining only 3.5 dB power penalty after 10mus of optical buffering and agile wavelength conversion over 18nm span.