Latency Aware VNF Deployment at Edge Devices for IoT Services: An Artificial Neural Network Based Approach
Bibliographic record
Abstract
Virtual Network Functions (VNFs) placed at the edge devices in the vicinity of users improve response time, avoid redundant utilization of core network, and reduce user-to-VNF end to end latency to a great extent, while leveraging the Internet of Things (IoT) services in Network functions virtualization (NFV) context. Different approaches for VNF placement have been proposed, however, the main concern has been to minimize resource utilization as much as possible by reducing the required number of servers to run a chain of VNFs to provide a specific service, without considering network conditions, for example, latency. In this paper, we implement the optimal edge VNF placement problem as an Integer Linear Programming model that guarantees the minimum end to end latency, while ensuring Quality of Service by not overstepping beyond an acceptable limit of latency violation. Latency beyond such limits can be the cause of disruption and degradation of performance for time-sensitive IoT services. The time complexity of the existing optimal edge VNF placement algorithm being NP-hard, we further propose a VNF placement strategy using Artificial Neural Network (ANN) trained by the assignment solutions generated from the Integer Linear Programming (ILP) model of the optimal edge VNF placement method for smaller instances of VNFs. This approach solves the VNF assignment problem at edge devices for a larger number of VNFs, while reducing the time complexity to be linear and providing similar results as the ILP model in terms of latency. This research work can be considered as a pioneering mark for IoT virtual service orchestration systems by embedding intelligence that can scale down the massive fabrication costs of IoT endpoints (e.g., sensors, actuators) required to be equipped with high processing power to enable ultra-low response time for users.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".