Skip to content
Preprint

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

Sep 2026 · 0 citations · 20 references
Computer Science

TL;DR

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.

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.

View source

Similar papers

Preprint Nov 2026

Drift-Resilient Predictive Interference Management: Online Adaptation of an Extreme-Value Predictor

Predictive interference management supports ultra-reliable low-latency communication (URLLC) by allocating finite-blocklength resources against a high conditional quantile of next-slot interference. Building on an extreme-value-theory/kernel-density-estimation (EVT/KDE) predictor with quantile-defined interference stat...

Aamir Mahmood, Fateme Salehi, N. H. Mahmood et al. · 0 citations
Open access Oct 2026

Where 5G Throughput Prediction Actually Fails: A Transition-Aware, Leakage-Audited Evaluation on Real Drive-Test Traces

Machine-learning models that predict short-horizon cellular throughput underpin adaptive video streaming, cloud gaming, and edge orchestration. On the widely used Raca et al. 5G drive-test dataset, such models can report low error. We show that, on this dataset, these headline numbers can be optimistic and, more import...

Najem N. Sirhan, Riyad Alrousan, Sami Serhan et al. · 0 citations
Open access Oct 2026

Proactive Cloud Elasticity via XGBoost Predictive Scaling

Cloud-native systems commonly scale resources reactively, adjusting capacity only after a monitored metric such as CPU utilisation or request rate crosses a threshold. This creates a structural lag between demand onset and capacity availability. This paper proposes a proactive elasticity framework that uses XGBoost to...

Venkata Velavarthipati · 0 citations
#artificial intelligence Conference Open access Sep 2026

Leakage-Safe and Scheduler-Aware Machine Learning for Grid Job Runtime Prediction

The results show that random-split evaluation overestimates performance, categorical-native boosting improves temporal generalization, and long-job underestimation remains a scheduler-relevant challenge.

Ashfaq Ali Shafin, Khandaker Mamun Ahmed · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.