Energy-Efficient Deep Reinforcement Learning Assisted Resource Allocation for 5G-RAN Slicing
Bibliographic record
Abstract
One of the pillars of the 5G architecture is network slicing, in which hardware, radio, and power resources are virtualized as a logical network taking into account the requirements of diverse applications. While ensuring performance isolation among different slices, resource allocation in 5G Radio Access Networks (RANs) is associated with different challenges due to network dynamics and the different applications’ requirements. In this paper, we have considered the allocation of power and radio resources to rate-based as well as resource-based users. We propose an energy-efficient deep reinforcement learning-assisted resource allocation (EE-DRL-RA) method for RAN slicing in 5G networks. The main idea of the proposed method is to exploit a collaborative learning framework that includes deep reinforcement learning (DRL) and deep learning (DL) to decide on resource allocation in the RAN. Specifically, we use DL for decision-making on resource allocation on a large time-scale and DRL for decision-making on resource allocation on a small time-scale. The asynchronous advantage actor-critic (A3C) and the stacked and bidirectional long-short-term-memory (SBiLSTM) network are used as DRL and supervised DL methods, respectively. Furthermore, we determine the optimal power and resource blocks (RBs) for rate-based users by formulating the energy-efficient power allocation (EE-PA) problem as a non-convex optimization problem and solve it by an efficient iterative algorithm. Our proposed approach is unique in that it simultaneously allocates power and RBs while ensuring slice isolation with low computational and time complexity. Simulation results show that EE-DRL-RA yields better performance compared to a state-of-the-art published method in terms of convergence speed, computational complexity, energy efficiency, and the number of accepted users as well as the degree of inter-slice isolation.
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) | 0.002 | 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".