Closing the Loop: Continuous Measurement-Driven Refinement of Offloading Predictions

2026-09-24

AI Summary

This study addresses the problem of performance prediction model drift caused by dynamic environmental changes in vehicular edge computing. We propose a measurement-driven, closed-loop online calibration framework that leverages real-time execution data to continuously refine a lightweight multi-head neural network via a runtime incremental update mechanism. This approach implicitly captures non-Gaussian distributional characteristics while ensuring model stability, thereby enabling accurate prediction of absolute performance metrics. Experimental results demonstrate that the proposed system significantly mitigates prediction drift, enhances the accuracy of key indicators such as round-trip time (RTT), and improves robustness under heterogeneous latency conditions. Nevertheless, residual limitations persist in extreme scenarios.

Abstract

Modern vehicles increasingly offload computation- ally intensive perception and decision functions to backend servers, requiring accurate predictions of absolute performance metrics such as Round-Trip Time (RTT), processing time, and utilization. In practice, strong temporal variability, heterogeneous backend hardware, and multimodal latency regimes cause offline- trained predictors to drift, creating a reliability gap for latency- sensitive functions. We address this gap with an operational, measurement-driven closed loop that continuously recalibrates absolute-value predictors during runtime. The system aligns real execution measurements with predicted values and performs incremental online updates of a lightweight multi-head neural network while preserving model stability. The model implicitly learns the broad, non-Gaussian spread of input metrics, and a sigma-based error analysis in our evaluation characterizes resid- ual variability under dynamic conditions. Experiments across two Kubernetes clusters show that continuous measurement- driven refinement reduces prediction drift, improves accuracy for RTT, processing time, and utilization, and stabilizes prediction behavior across heterogeneous latency regimes. However, the broad and multimodal distribution of input metrics imposes fundamental limits on absolute-value prediction, with residual errors frequently exceeding configured thresholds. Overall, online calibration proves feasible and necessary for robust computation offloading in dynamic vehicular edge environments, while high- lighting the need for future mechanisms that address extreme latency regimes and high-variance operating conditions.

Problem

• computation offloading
• prediction drift
• vehicular edge computing
• latency prediction
• model recalibration

Innovation

• Computation Offloading
• Online Calibration
• Closed-loop Prediction
• Multi-head Neural Network
• Vehicular Edge Computing