Rohmatillah, Mahdin and Hadi Suyono,, ST., MT., Ph.D and Rahmadwati,, ST., MT., Ph.D (2018) Design Of Deep Learning Based Method For Optimizing Mimo Communication. Magister thesis, Universitas Brawijaya.
Abstract
Sistem komunikasi Multiple Input Multiple Output (MIMO), sebuah sistem mengimplementasikan beberapa antena pada pemancar dan penerima, telah berkembang pesat untuk meningkatkan efektivitas komunikasi antar pengguna. Namun, pertukaran fenomena antara kinerja dan kompleksitas komputasi selalu menjadi yang terbesar dilema yang dialami oleh peneliti. Sebagai alternatif pemecahan masalah di atas, penelitian ini mengusulkan optimasi di kedua keragaman spasial dan multiplexing spasial Sistem komunikasi MIMO menggunakan model berbasis pembelajaran end-to-end, secara khusus menyesuaikan model autoencoder. Empat model diperkenalkan dalam tesis ini yang masing-masing membahas dua model masalah tentang tugas deteksi data dan tugas estimasi saluran yang belum ditangani dalam penelitian sebelumnya. Model yang diusulkan dievaluasi di salah satu yang paling umum gangguan saluran yang Rayleigh fading dengan tambahan Additive White Gaussian Noise (AWG). Hasilnya menunjukkan bahwa model berbasis pembelajaran mendalam ini untuk komunikasi MIMO sistem menghasilkan hasil yang sangat menjanjikan dengan mengungguli metode dasar (metode banyak digunakan dalam komunikasi MIMO konvensional). Dalam CSIR (Status Saluran) yang sempurna Informasi di sisi Penerima), model yang diusulkan mencapai BER hampir 10−5 di SNR 22,5 dB. Sementara dalam kasus estimasi saluran, model yang diusulkan dapat melebihi baseline kinerja bahkan dengan hanya mentransmisikan 2 pilot
English Abstract
Multiple Input Multiple Output (MIMO) communication system, a system implementing multiple antennas at the transmitter and receiver, has been developed rapidly in order to improve the effectiveness of communication among users. However, trade-off phenomenon between performance and computational complexity always become the hugest dilemma suffered by researchers. As an alternative solution to the aforementioned problem, this research proposes an optimization in both of spatial diversity and spatial multiplexing MIMO communication system using end-to-end learning based model, specifically, it adapts autoencoder model. Four models are introduced in this thesis which each two of them address a problem about data detection task and channel estimation task that has not been addressed in the previous research. The proposed models were evaluated in one of the most common channel impairment which is Rayleigh fading with additional Additive White Gaussian Noise (AWGN). The results show that these deep learning based models for MIMO communication system result in very promising results by outperforming the baseline methods (methods widely used in conventional MIMO communication). In perfect CSIR (Channel State Information in Receiver side) case, the proposed models achieve BER nearly 10−5 at SNR 22.5 dB. While in channel estimation case, the proposed models can exceed the baseline performance even by only transmitting 2 pilots
Other obstract
-
| Item Type: | Thesis (Magister) |
|---|---|
| Identification Number: | TES/621.382/FT/a/2018/041810249 |
| Subjects: | 600 Technology (Applied sciences) > 621 Applied physics > 621.3 Electrical, magnetic, optical, communications, computer engineering; electronics, lighting > 621.38 Electronics, communications engineering > 621.382 Communications engineering |
| Divisions: | S2/S3 > Magister Teknik Sipil, Fakultas Teknik |
| Depositing User: | Nur Cholis |
| Date Deposited: | 22 Aug 2022 04:32 |
| Last Modified: | 22 Aug 2022 04:32 |
| URI: | http://repository.ub.ac.id/id/eprint/193412 |
![[thumbnail of Mahdin Rohmatillah.pdf]](http://repository.ub.ac.id/style/images/fileicons/text.png) |
Text
Mahdin Rohmatillah.pdf Download (2MB) |
Actions (login required)
 |
View Item |