Intelligent and Autonomous Edge Slicing for IoT Systems
Bibliographic record
Abstract
Edge intelligence is rapidly emerging as a pivotal platform for supporting future IoT networks. The integration of artificial intelligence and machine learning (AI/ML) with edge computing furnishes a new era in which edge systems can learn environment dynamics and optimize resource autoscaling policies. However, the heterogeneity of IoT networks, characterized by diverse applications and requirements, necessitates edge systems with advanced intelligence to tailor resource autoscaling policies to specific environments. Despite ongoing research in edge intelligence, most studies have focused on a single environment or service type, thereby limiting their applicability to real-world scenarios with varied IoT services. To address this limitation, we propose the intelligent and autonomous edge slicing (IAES) system, a novel approach designed to recognize diverse IoT environments and implement per-slice resource allocation policies. IAES leverages deep reinforcement learning (DRL), namely, dueling double deep Q-networks (D3QN), to optimize resource autoscaling across distinct IoT environments, such as smart cities, eHealth, and smart factories. Additionally, IAES incorporates an intelligent environment classification component that utilizes joint traffic prediction and classification models. Several AI algorithms such as long short-term memory (LSTM), convolutional neural networks (CNN), and multilayer perceptron networks (MLP), are evaluated for their efficacy in predicting IoT environments. Simulation experiments demonstrate that the IAES system achieves a 50-60% reduction in system costs compared to both rule-based commercial autoscaling employed in Kubernetes systems and an intelligent prediction-based autoscaling algorithm.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".