Exploring Dynamic Sparse Memory Effect Under Varying Transmission States for Digital Predistortion of RF Power Amplifiers
Bibliographic record
Abstract
In wideband wireless communication systems, it is particularly crucial to compensate for the memory effect of radio frequency power amplifiers (RFPAs) to ensure optimal system performance. In this work, the representation of the memory effect of RFPAs is comprehensively reviewed first. The concept of the sparse memory effect (SME) of RFPAs is introduced, emphasizing that only a minimal amount of key memory information can achieve excellent performance. According to the SME concept, we further explore the mechanism of the dynamic SME (DSME), which indicates that the characteristics of the SME change with varying transmission states. Through both theoretical analysis and extensive experiments, the DSME of RFPAs is validated, providing compelling evidence for its reasonability. Moreover, the generalization of the DSME is explored to guide predistorter tap selection under unseen transmission states. Second, a novel universal dynamic sparse delay taps switch digital predistortion (DSDTS-DPD) framework is proposed to tackle the nonlinearity of RFPAs under varying transmission states. This model-agnostic architecture, which is implemented by dynamic states mapping module and dynamic delay switching module, is utilized to dynamically capture the memory information, with a minimum number of delay taps. Finally, experimental results further demonstrate the DSME compensation mechanism, as validated with a generalized memory polynomial (GMP) model, provides a superior solution for characterizing the RFPA memory effect than conventional compensation methods, in terms of both modeling accuracy and linearization performance. It also seamlessly integrates with existing dynamic digital predistortion (DPD) neural network models, highlighting robust structure adaptability of the proposed framework to dynamic operational conditions.
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) | 0.000 | 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 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".