Risk-Budgeted Online Scheduling for Continuous Edge Inference over Evolving Time Horizons

TL;DR

This paper introduces AEGIS, a risk-aware online scheduling framework for continuous edge inference that balances latency, stability, and resource constraints using prediction and dynamic risk management.

Contribution

It proposes a novel risk-budgeted scheduling approach with LSTM-based prediction and an asynchronous algorithm, addressing long-term stability in edge inference.

Findings

AEGIS improves the timely inference ratio.

It reduces average violation risk and burst length.

Achieves a better delay--risk--convergence trade-off.

Abstract

Continuous edge inference necessitates not merely low per-timeslot latency, but sustained timeliness guarantees in the presence of time-varying channels, fluctuating edge workloads, and coupled bandwidth-computing resource constraints. Existing studies predominantly optimize instantaneous delay or per-timeslot utility, while largely overlooking the regulation of cross-time deadline violation dynamics in continuous services. To address this, we propose AEGIS, a prediction-empowered risk-budgeted online scheduling framework for continuous edge inference. AEGIS models deadline-violation tendency as an updatable cross-time control state through dynamic user-level risk budgets, so that online scheduling accounts for both instantaneous efficiency and long-term service stability. To support proactive decision making, AEGIS leverages LSTM-based short-term state prediction to construct a smooth deadline-violation risk surrogate, and formulates the resulting time-wise resource competition as a potential-aligned game under coupled feasibility constraints. An asynchronous online algorithm is then developed with finite-step convergence. Experiments demonstrate that AEGIS improves the timely inference ratio, reduces average violation risk and violation burst length, and achieves a favorable delay--risk--convergence trade-off over representative baselines.