Priority-Aware Deployment of Autoscaling Service Function Chains Based on Deep Reinforcement Learning
Bibliographic record
Abstract
Communication networks are being restructured by means of network function virtualization (NFV) and service-based architecture (SBA) to embrace greater flexibility, agility, programmability and efficiency. The deployment of service function chains (SFCs) to flexibly offer diverse network services is considered essential in NFV-based networks. Beyond the fifth-generation (5G) and sixth-generation (6G) eras, SFC deployment should be capable of satisfying various quality of service (QoS) requirements, coping with dynamic network states and traffic, handling urgent business in a timely manner, and avoiding resource congestion, all of which present significant scheduling challenges. In this paper, we propose a priority-aware deployment framework for autoscaling and multi-objective SFCs, which mainly includes 2 parts. First, to guarantee the diverse QoS requirements (e.g., latency and request acceptance rate) of various network services, a multi-objective SFC deployment scheme is established to optimize the service latency, deployment cost and service acceptance rate. Second, a deep reinforcement learning (DRL) algorithm, named the autoscaling and priority-aware SFC deployment algorithm (APSD), is further designed to solve the multi-objective optimization problem, which is NP hard. In APSD, we first prioritize requests with varying real-time characteristics to ensure that urgent services can be processed in a timely manner; based on the resiliency characteristics of virtual network functions (VNFs), we propose a hybrid scaling strategy to scale VNFs both horizontally and vertically to respond to changes in service requests and workload. We report comprehensive experiments carried out to assess the effectiveness of the proposed SFC deployment framework and demonstrate its advantages over its counterparts. Thus, we show that APSD is time efficient in solving the multi-objective optimization problem and that the obtained strategy always consumes the least resources (e.g., central processing unit (CPU) and memory resources) and surpasses two baseline algorithms with a 29.5% and 12.36% lower latency on average.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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 | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".