Slice Reconfiguration based on Demand Prediction with Dueling Deep Reinforcement Learning
Bibliographic record
Abstract
Network slicing is capable of satisfying differentiated service demands of vertical industries by tailoring a common infrastructure to multiple logical networks which are isolated. Considering that the dynamic of service demands makes it difficult to maintain high quality of user experience and high revenue of tenants, slice reconfiguration is necessary to avoid performance degradation. Hence, this paper proposes an optimal and fast slice reconfiguration (OFSR) solution by leveraging advanced deep reinforcement Learning. To deal with the uncertain changes in resources requirement, a demand prediction model based on Markov renewal process is introduced in decision-making. Taking into account the operation costs of reconfiguring diversified slices and the constraints of available resources, the proposed OFSR scheme aims at obtaining high long-term revenue with low operation cost. Given that the convergence of the conventional reinforcement learning approach is slow to learn the optimal reconfiguration policy for different classes of slices, deep dueling neural network combined with Q-learning is applied to improve the speed of convergence. Simulation results validate that the proposed framework is effective in achieving long-term revenue for tenants and the dueling deep Q-learning approach performs better than other current approaches.
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 | 0.000 |
| 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".