Max-Min Throughput in RSMA-Aided SWIPT for Sustainable Internet of Underground Things: A Deep Reinforcement Learning Approach
Organizations: K. Lin and M.-S. Alouini are with the Division of Computer, Electrical and Mathematical Sciences and Engineering, King Abdullah University of Science and Technology, Thuwal 23955, Saudi Arabia.
Abstract
Unmanned aerial vehicle (UAV)-enabled wireless-powered underground sensor networks (WPUSNs) allow underground devices (UDs) to harvest radio-frequency energy from a UAV via wireless energy transfer (WET) techniques, enabling sustainable Internet of underground things (IoUT) applications. This paper integrates rate-splitting multiple access (RSMA)-aided simultaneous wireless information and power transfer (SWIPT) into UAV-enabled WPUSNs to deliver information and energy to UDs. Within this framework, we investigate a max-min fairness problem that jointly optimizes the UAV transmit power, power allocation and message splitting, power-splitting ratios, and time allocation, aiming to maximize the minimum uplink throughput across UDs subject to per-UD downlink throughput requirements and a UAV energy-consumption constraint. To address this non-convex problem under dynamic underground environments, we develop an off-policy deep reinforcement learning approach based on the primal-dual truncated quantile critics (PD-TQC), where a TQC-based reward critic evaluates the fairness objective, cost critics estimate constraint costs, and an actor learns the resource-control policy with adaptive dual-variable updates. Simulations using in-situ soil volumetric water content measurements from a center-pivot irrigation farm demonstrate that PD-TQC achieves the highest annual average minimum uplink throughput compared with four benchmarks while satisfying the per-frame constraints in over 96% of the evaluated frames, and that this throughput advantage is preserved under different Rician factors, numbers of UDs, and downlink throughput thresholds.
Figures & tables
| Parameters | Values |
| Operating Scenario [ 14 , 32 , 13 , 9 ] | |
| Number of UDs ( ) | |
| Number of UAV antennas ( ) | |
| Deployment radius ( ) | m |
| UAV altitude ( ) | m |
| Frame duration ( ) | s |
| Approach | Minimum uplink throughput (kbps) | Minimum downlink throughput (kbps) | Downlink throughput constraint satisfaction | UAV residual-energy constraint satisfaction |
| Greedy | 21.58 | 19.81 | 53.97% | 93.42% |
| PPO | 38.41 | 22.86 | 99.81% | 99.71% |
| SAC | 42.86 | 26.06 | 92.77% | 99.61% |
| PD-TQC (SDMA) | 43.32 | 21.08 | 85.91% | 99.45% |
| PD-TQC | 45.05 | 23.54 | 96.99% | 99.72% |
| Approach | Offline training phase | Online inference phase | ||||
| Trainable parameters | Training time per epoch (s) | Training time to convergence (h) | Deployed parameters | Floating-point operations per decision ( ) | Latency per decision (ms) | |
| Greedy | – | – | – | – | – | 1176.66 |
| PPO | 156,201 | 1.94 | 0.32 | 155,944 | 0.307 | 0.52 |
| SAC | 1,117,486 | 9.98 | 2.77 | 155,944 | 0.307 | 0.78 |
| PD-TQC (SDMA) | 1,622,302 | 10.69 | 1.48 | 153,888 | 0.303 | 0.86 |
| PD-TQC | 1,697,062 | 11.20 | 2.49 | 159,528 | 0.314 | 0.88 |
Wireless Communications
Wireless communications studies how information is sent over radio links and how networks manage signals, spectrum, and resources reliably.
See all 432 papers