Hierarchical JEPA Meets Predictive Remote Control in Beyond 5G Networks

TL;DR

This paper introduces H-JEPA, a hierarchical predictive architecture that encodes device states into low-dimensional embeddings for scalable, efficient remote control in beyond 5G wireless networks, supporting more devices with limited bandwidth.

Contribution

The paper presents a novel hierarchical embedding-based predictive control architecture that improves scalability and communication efficiency in wireless networked control systems.

Findings

Supports up to 42.83% more devices under bandwidth constraints

Enables long-term prediction stability and fine-grained control

Reduces need for state reconstruction in control actions

Abstract

In wireless networked control systems, ensuring timely and reliable state updates from distributed devices to remote controllers is essential for robust control performance. However, when multiple devices transmit high-dimensional states (e.g., images or video frames) over bandwidth-limited wireless networks, a critical trade-off emerges between communication efficiency and control performance. To address this challenge, we propose a Hierarchical Joint-Embedding Predictive Architecture (H-JEPA) for scalable predictive control. Instead of transmitting states, device observations are encoded into low-dimensional embeddings that preserve essential dynamics. The proposed architecture employs a three-level hierarchical prediction, with high-level, medium-level, and low-level predictors operating across different temporal resolutions, to achieve long-term prediction stability, intermediate interpolation, and fine-grained refinement, respectively. Control actions are derived within the embedding space, removing the need for state reconstruction. Simulation results on inverted cart-pole systems demonstrate that H-JEPA enables up to 42.83 % more devices to be supported under limited wireless capacity without compromising control performance.