Reinforcement Learning-based User-centric Handover Decision-making in 5G Vehicular Networks
Bibliographic record
Abstract
The advancement of 5G technologies and Vehicular Networks open a new paradigm for Intelligent Transportation Systems (ITS) in safety and infotainment services in urban and highway scenarios. Connected vehicles are vital for enabling massive data sharing and supporting such services. Consequently, a stable connection is compulsory to transmit data across the network successfully. The new 5G technology introduces more bandwidth, stability, and reliability, but it faces a low communication range, suffering from more frequent handovers and connection drops. The shift from the base station-centric view to the user-centric view helps to cope with the smaller communication range and ultra-density of 5G networks. In this thesis, we propose a series of strategies to improve connection stability through efficient handover decision-making. First, a modified probabilistic approach, M-FiVH, aimed at reducing 5G handovers and enhancing network stability. Later, an adaptive learning approach employed Connectivity-oriented SARSA Reinforcement Learning (CO-SRL) for user-centric Virtual Cell (VC) management to enable efficient handover (HO) decisions. Following that, a user-centric Factor-distinct SARSA Reinforcement Learning (FD-SRL) approach combines time series data-oriented LSTM and adaptive SRL for VC and HO management by considering both historical and real-time data. The random direction of vehicular movement, high mobility, network load, uncertain road traffic situation, and signal strength from cellular transmission towers vary from time to time and cannot always be predicted. Our proposed approaches maintain stable connections by reducing the number of HOs by selecting the appropriate size of VCs and HO management. A series of improvements demonstrated through realistic simulations showed that M-FiVH, CO-SRL, and FD-SRL were successful in reducing the number of HOs and the average cumulative HO time. We provide an analysis and comparison of several approaches and demonstrate our proposed approaches perform better in terms of network connectivity.
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 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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".