Machine-Learning-Assisted Transmission Power Control for LoRaWAN Considering Environments With High Signal- to -Noise Variation
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
To achieve an adequate tradeoff between range and energy efficiency, LoRaWAN End Nodes (ENs) choose their transmission parameters using an Adaptive Data Rate (ADR) scheme based on the maximum value of previous Signal-to-Noise ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SNR</i> ) values. However, the ADR only performs well in favorable channel conditions. In fact, if the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SNR</i> exhibits high variability, these parameters could be inefficiently set and may negatively affect the Packet Delivery Rate (PDR). Therefore, a link margin could be overestimated to improve the PDR by the ADR algorithm, which may, however, waste the EN’s energy. This paper proposes a novel ADR that does not rely on the past <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SNR</i> values. Still, our proposed design directly predicts the current <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SNR</i> and transmission parameters using Machine Learning. Specifically, the underlying Machine Learning models were trained using in-field measurements for six months in Medellín, Colombia, including different environmental variables and their effects on the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SNR</i> . Our ADR scheme improved energy consumption by 47.1% with a PDR of 99% and reduced collisions in dense networks up to 9.5% compared with the ADR scheme. Furthermore, we show that our proposed design outperforms some enhanced versions of the ADR scheme proposed in the literature in both energy consumption and collision rate. Finally, our proposed framework enables simple implementation since it runs directly in the ENs, improving the response time compared with the traditional ADR scheme.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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