Reservoir Computing-Based Detection for Molecular Communications

TL;DR

This paper introduces a low-complexity Reservoir Computing detector for diffusion-based Molecular Communication, effectively handling severe ISI in dynamic environments with minimal training and computational resources.

Contribution

It proposes a novel RC-based detection method that captures ISI dynamics without explicit channel modeling, outperforming classical and complex ML detectors with fewer parameters.

Findings

RC detector outperforms classical detectors in severe ISI conditions

Achieves higher accuracy than LSTM, CNN, MLP in simulations

Requires significantly fewer trainable parameters and low latency inference

Abstract

Diffusion-based Molecular Communication (MC) is inherently challenged by severe inter-symbol interference (ISI). This is significantly amplified in mobile scenarios, where the channel impulse response (CIR) becomes time-varying and stochastic. Obtaining accurate Channel State Information (CSI) for traditional model-based detection is intractable in such dynamic environments. While deep learning (DL) offers adaptability, its complexity is unsuitable for resource-constrained micro/nanodevices. This paper proposes a low-complexity Reservoir Computing (RC) based detector. The RC architecture utilizes a fixed, recurrent non-linear reservoir to project the time-varying received signal into a high-dimensional state space. This effectively transforms the complex temporal detection problem into a simple linear classification task, capturing ISI dynamics without explicit channel modeling or complex retraining. Evaluated in a realistic 3D mobile MC simulation environment (Smoldyn), our RC detector significantly outperforms classical detectors and achieves superior performance compared to complex ML methods (LSTM, CNN, MLP) under severe ISI. Importantly, RC achieves this with significantly fewer trainable parameters (e.g., 300 vs. up to 264k for MLP) and ultra-low latency inference (approx. 1 $\mu$s per symbol).