Inference-Aware State Reconstruction for Industrial Metaverse under Synchronous/Asynchronous Short-Packet Transmission

TL;DR

This paper develops an inference-based approach for real-time state reconstruction in industrial metaverse systems, leveraging spatial-temporal correlations to significantly reduce mean squared error under short-packet wireless transmission.

Contribution

It introduces a novel inference framework considering both synchronous and asynchronous transmission modes, with analytical thresholds and optimization strategies for improved accuracy.

Findings

Inference reduces MSE by over 50% compared to no inference.

Positive correlation between MSE and BLEP in synchronous mode.

Negative correlation between MSE and BLEP in asynchronous mode under certain conditions.

Abstract

We consider a real-time state reconstruction system for industrial metaverse. The time-varying physical process states in real space are captured by multiple sensors via wireless links, and then reconstructed in virtual space. In this paper, we use the spatial-temporal correlation of the sensor data of interest to infer the real-time data of the target sensor to reduce the mean squared error (MSE) of reconstruction for industrial metaverse under short-packet transmission (SPT). Both synchronous and asynchronous transmission modes for multiple sensors are considered. It is proved that the average MSE of reconstruction and average block error probability (BLEP) have a positive correlation under inference with synchronous transmission scheme, and they have a negative correlation in some conditions under inference with asynchronous transmission scheme. Also, it is proved that the average MSE of reconstruction with inference can be significantly lower than that without inference, even under weak mean squared spatial correlation (MSSC). In addition, closed-form MSSC thresholds are derived for the superiority regions of the inference with synchronous transmission and inference with asynchronous transmission schemes, respectively. Adaptations of blocklength and time shift of asynchronous transmission are conducted to minimize the average MSE of reconstruction. Simulation results show that the two schemes significantly outperform the no inference case, with an average MSE reduction of more than 50%.