Preamble Selection Probability Optimization in RACH: A Multi-Armed Bandits Approach
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The use of cellular networks for massive machine-type communications (mMTC), is an attractive solution due to the availability of existing infrastructure. However, the sheer number of user equipments (UEs) creates congestion and overloading challenges on the random access channel (RACH). To address this, we develop a multi-armed bandit (MAB)-based reinforcement learning (RL) approach that learns optimal preamble selection strategies without requiring the base station (BS) to know the number of UEs in the network. We first model a two-priority RACH that captures the behavior of UEs through access patterns observed at the BS. This enables us to design a non-uniform preamble selection scheme and formulate an optimization problem that seeks the best preamble selection probabilities to maximize high-priority UE success while constraining low-priority access. Our proposed RL framework uses a discretized and compressed the action space (AS) to improve scalability, and uses cross-entropy methods to efficiently update the MAB solution. In addition, we present a compact AS (CAS) approach that leverages a lookup table of pre-optimized preamble selection probabilities across different network loads. This not only reduces the AS further but also enables implicit network load estimation. Numerical experiments show that the proposed method offers higher throughput for high priority UEs compared to the uniform preamble selection scheme, as well as an access class barring scheme, while maintaining a minimum throughput for low priority UEs.
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.
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 | 0.001 | 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 | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 it