Causal CSI-Based Trajectory Design and Power Allocation for UAV-Enabled Wireless Networks Under Average Rate Constraints: A Constrained Reinforcement Learning Approach
Bibliographic record
Abstract
With their flexible deployment and cost-effectiveness, unmanned aerial vehicles (UAVs) are unlocking possibilities for connectivity and services in future wireless networks. The mobility of UAVs can be leveraged through trajectory design to satisfy the stringent rate requirement of users. Most existing works on UAV trajectory design focus on scenarios where noncausal channel state information (CSI) is available to the UAV in advance. In this article, we investigate the trajectory design and power allocation based on causal CSI to maximize the sum-rate under the constraint on average rate per user. Since the constraint on average rate must be met over an extended period, we formulate a constrained Markov decision process problem and solve it by adopting the Lagrangian relaxation technique. Thereby, we propose a model-free reinforcement learning algorithm, where the real-time signal strength measured by the UAV along its current location is used to design the trajectory and allocate power optimally. To further improve the efficiency of the learning algorithm, we introduce the water-filling algorithm and the idea of action elimination, by which the size of state/action spaces is reduced. For real-world applications, we provide an online fine-tuning algorithm for real-time policy adjustments to mitigate environmental changes and/or model inaccuracies. Simulation results show that the proposed algorithm outperforms benchmark methods and satisfies the constraint on average rate per user upon convergence.
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 | 0.001 |
| 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".