Empowering ISAC Systems With Federated Learning: A Focus on Satellite and RIS-Enhanced Terrestrial Integrated Networks
Bibliographic record
Abstract
This paper presents a state-of-the-art analytical framework aimed to enhance spectral efficiency in satellite and terrestrial integrated networks (STINs), utilizing reconfigurable intelligent surface (RIS) within the realm of integrated sensing and communication (ISAC). Our methodology pivots on a pioneering federated deep reinforcement learning strategy that introduces new ground beyond conventional optimization techniques to tackle the intricate problem of non-convex resource allocation. The approach leverages federated learning to dynamically adapt to network changes, enabling efficient resource management and ensuring compliance with beamforming designs, multiple target signal-to-interference-plus-noise ratio thresholds, and RIS phase-shift requirements through an effective feedback loop. In particular, we propose a federated deep deterministic policy gradient (F-DDPG) algorithm across multi-agent systems that outperforms existing federated deep Q-network (F-DQN), centralized, and traditional DDPG and DQN methods. The empirical findings underscore the efficiency of the federated algorithms, which closely align with the performance of centralized models while markedly reducing execution time, thus achieving an optimal synergy between operational efficiency and system performance. Simulation results highlight the remarkable advantages of optimal RIS configurations, showcasing a performance increase of 54.2% over random RIS setups and a remarkable 76.8% enhancement compared to scenarios without RIS, underscoring the transformative impact of our federated learning approach. Additionally, our study evaluates the impact of channel estimation errors and interference, confirming the robustness of our approach and its potential to optimize ISAC-enabled STINs.
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".