Multi-Task Wavelength-Multiplexed Reservoir Computing Using a Silicon Microring Resonator

TL;DR

This work tackles the scalability of photonic reservoir computing by combining time-division multiplexing with wavelength-division multiplexing on a single silicon microring resonator. It numerically demonstrates three independent RC tasks—NARMA-10 time-series prediction, signal classification, and nonlinear wireless channel equalization—being solved in parallel across three resonant channels of an add-drop MRR, using 50 virtual nodes per task and ridge regression for readout. The TCMT-based physical model and RK4 simulations reveal that per-channel power and detuning critically shape performance, yet a coordinated parameter set can yield near-optimal results for all tasks, suggesting significant potential for multi-task on-chip photonic RC. Overall, the study highlights the viability of WDM-enabled multi-task reservoir computing on SOI platforms, offering a pathway to higher on-chip parallelism and more efficient photonic computing architectures.

Abstract

Among the promising advantages of photonic computing over conventional computing architectures is the potential to increase computing efficiency through massive parallelism by using the many degrees of freedom provided by photonics. Here, we numerically demonstrate the simultaneous use of time and frequency (equivalently wavelength) multiplexing to solve three independent tasks at the same time on the same photonic circuit. In particular, we consider a microring-based time-delay reservoir computing (TDRC) scheme that simultaneously solves three tasks: Time-series prediction, classification, and wireless channel equalization. The scheme relies on time-division multiplexing to avoid the necessity of multiple physical nonlinear nodes, while the tasks are parallelized using wavelength division multiplexing (WDM). The input data modulated on each optical channel is mapped to a higher dimensional space by the nonlinear dynamics of the silicon microring cavity. The carrier wavelength and input power assigned to each optical channel have a high influence on the performance of its respective task. When all tasks operate under the same wavelength/power conditions, our results show that the computing nature of each task is the deciding factor of the level of performance achievable. However, it is possible to achieve good performance for all tasks simultaneously by optimizing the parameters of each optical channel. The variety of applications covered by the tasks shows the versatility of the proposed photonic TDRC scheme. Overall, this work provides insight into the potential of WDM-based schemes for improving the computing capabilities of reservoir computing schemes.

Figures (7)

• Figure 1: Add-drop Microring resonator.
• Figure 2: Typical linear transmission response of an add-drop MRR: To the through port in green, to the drop port in orange.
• Figure 3: Proposed TDRC setup scheme solving three independent tasks in parallel through wavelength multiplexing.
• Figure 4: Frequency allocation used in this work.
• Figure 5: NMSE of the NARMA-10 task as a function of $\overline{P}_0$ and $\Delta\omega_0/2\pi$. A red circle marks the best performance.