MILAAP: Mobile Link Allocation via Attention-based Prediction

2025-06-24

AI Summary

In channel-hopping (CH) wireless networks, node mobility and dynamic interference lead to high state-sharing overhead and degraded throughput. To address this, we propose a distributed link scheduling method that eliminates the need for global state exchange. Our approach introduces an end-to-end prediction framework based on multi-head self-attention, jointly modeling temporal spectral patterns and spatial dependencies solely from local, passive observations—enabling both channel occupancy prediction and node trajectory inference. By avoiding explicit inter-node communication, the method incurs zero signaling overhead and supports zero-shot generalization across hopping periods. Experimental results demonstrate near-perfect (≈100%) channel state prediction accuracy across diverse mobility scenarios, yielding substantial improvements in throughput efficiency and scheduling scalability.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Distributed Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Channel hopping (CS) communication systems must adapt to interference changes in the wireless network and to node mobility for maintaining throughput efficiency. Optimal scheduling requires up-to-date network state information (i.e., of channel occupancy) to select non-overlapping channels for links in interference regions. However, state sharing among nodes introduces significant communication overhead, especially as network size or node mobility scale, thereby decreasing throughput efficiency of already capacity-limited networks. In this paper, we eschew state sharing while adapting the CS schedule based on a learning-based channel occupancy prediction. We propose the MiLAAP attention-based prediction framework for machine learning models of spectral, spatial, and temporal dependencies among network nodes. MiLAAP uses a self-attention mechanism that lets each node capture the temporospectral CS pattern in its interference region and accordingly predict the channel occupancy state within that region. Notably, the prediction relies only on locally and passively observed channel activities, and thus introduces no communication overhead. To deal with node mobility, MiLAAP also uses a multi-head self-attention mechanism that lets each node locally capture the spatiotemporal dependencies on other network nodes that can interfere with it and accordingly predict the motion trajectory of those nodes. Detecting nodes that enter or move outside the interference region is used to further improve the prediction accuracy of channel occupancy. We show that for dynamic networks that use local CS sequences to support relatively long-lived flow traffics, the channel state prediction accuracy of MiLAAP is remarkably ~100% across different node mobility patterns and it achieves zero-shot generalizability across different periods of CS sequences.

Problem

• Adapts channel hopping to interference and mobility changes
• Predicts channel occupancy without state sharing overhead
• Uses attention-based learning for spectral and spatial dependencies

Innovation

• Attention-based channel occupancy prediction
• Self-attention for spectral-temporal dependencies
• Multi-head attention for mobility tracking