FLAIR: QoS-Aware Scheduling and Workload Placement in Fog-Enabled Smart Manufacturing Warehouses
Bibliographic record
Abstract
Smart manufacturing environments rely on timely detection of critical events to preserve operational safety and efficiency. Fog computing offers a promising alternative to cloud-based systems by processing image and video data from IoT devices and sensors on fog nodes located near the data sources, or the edge, enabling faster and more efficient detection of anomalies within the manufacturing warehouse. These fog nodes are heterogeneous, meaning they handle a wide variety of dynamic and diverse workloads. However, they remain resource-constrained and highly sensitive to the variability of these workloads. This paper presents FLAIR (Fog Layer Architecture with Intelligent Routing), a fog-native workload placement framework designed to meet strict latency-based Quality of Service (QoS) requirements for real-time classification tasks. FLAIR combines three key components: (1) a predictive data-driven Response Time Model (RTM) trained using AutoML; (2) a Digital Twin mechanism that simulates co-location scenarios to estimate resource utilization; and (3) a lightweight, threshold-based placement algorithm that selects a feasible node when a new critical workload arrives. Experimental evaluations show that FLAIR consistently outperforms traditional Queuing Network Models (QNM), especially in heterogeneous deployments, reducing mean absolute percentage error (MAPE) from 39.56% to 6.43% and avoiding incorrect placement decisions that violate QoS constraints. These results underscore FLAIR’s effectiveness in supporting latency-critical classification tasks in a heterogeneous fog infrastructure within a smart manufacturing warehouse environment.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".