CNN-DPC algorithm for hybrid precoding in millimeter-wave massive MIMO systems
Wireless Networks, ISSN: 1572-8196, Vol: 29, Issue: 6, Page: 2447-2456
2023
- 2Captures
Metric Options: Counts1 Year3 YearSelecting the 1-year or 3-year option will change the metrics count to percentiles, illustrating how an article or review compares to other articles or reviews within the selected time period in the same journal. Selecting the 1-year option compares the metrics against other articles/reviews that were also published in the same calendar year. Selecting the 3-year option compares the metrics against other articles/reviews that were also published in the same calendar year plus the two years prior.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Metrics Details
- Captures2
- Readers2
Article Description
The dynamic partially connected (DPC) structure can achieve the trade-off between hardware loss and precoding performance of millimeter-wave multi-input multi-ouput systems. Via convolutional neural network (CNN), a novel hybrid precoding approach is proposed for the DPC structure in this paper, namely CNN-DPC algorithm. Firstly, the Euler’s formula and identity matrix are used to construct a phase shift (PS) layer that handles diagonal constraints of the analog PS precoding matrix and constant modulus. Then, the state of the connection between the antennas the radio frequency (RF) chains is determined by the probability layer. On this basis, a lambda layer is established to output the vectorized hybrid precoding matrix, and a loss function is expressed as the minimization of the Euclidean distance between the optimal fully digital precoding matrix and the hybrid precoding matrix. Finally, after the CNN learns the mapping relationship between the hybrid precoding matrix and the channel characteristics, it can directly output the desired hybrid precoding matrix with the input of the channel matrix. The proposed CNN-DPC algorithm achieves higher energy efficiency and the spectral efficiency compared with the related algorithms is indicated in the simulations.
Bibliographic Details
Springer Science and Business Media LLC
Provide Feedback
Have ideas for a new metric? Would you like to see something else here?Let us know