Accesso libero

Interface Selection and Optimization of Weights using Artificial Neural Network in Heterogeneous Wireless Environment

Monika Rani

Monika Rani

IKG Punjab Technical UniversityKapurthala, India
Cerca questo autore su
Sciendo|Google Scholar
Rani, Monika
 e 
Kiran Ahuja

Kiran Ahuja

Department of Electronics & Communication Engineering, DAV Institute of Engineering & Technology, Jalandhar, IKG Punjab Technical UniversityIndia
Cerca questo autore su
Sciendo|Google Scholar
Ahuja, Kiran
  
15 dic 2023
Interface Selection and Optimization of Weights using Artificial Neural Network in Heterogeneous Wireless Environment's Cover Image
INFORMAZIONI SU QUESTO ARTICOLO
Articolo precedente
Articolo Successivo
Cita
Scarica la copertina
Categoria dell'articolo: Article
Pubblicato online: 15 dic 2023
Ricevuto: 31 mag 2023
DOI: https://doi.org/10.2478/ijssis-2023-0016
Parole chiave
© 2023 Monika Rani et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1:

General structure of backpropagation.
General structure of backpropagation.

Figure 2:

Hierarchy of the system.
Hierarchy of the system.

Figure 3:

Weights for video application.
Weights for video application.

Figure 4:

Weights for audio application.
Weights for audio application.

Figure 5:

Weights for web browsing application.
Weights for web browsing application.

Figure 6:

Weights for data transfer application.
Weights for data transfer application.

Figure 7:

Network outputs for video application.
Network outputs for video application.

Figure 8:

Network outputs for audio application.
Network outputs for audio application.

Figure 9:

Network outputs for web browsing application.
Network outputs for web browsing application.

Figure 10:

Network outputs for data application.
Network outputs for data application.

Figure 11:

% Throughput for all networks.
% Throughput for all networks.

Figure 12:

Comparison with existing algorithm.
Comparison with existing algorithm.

Normalized weights for different applications

Application DS L BW PLR Jitter Total
Video 0.3101 0.1661 0.2912 0.0519 0.1808 1
Audio 0.4427 0.2843 0.1127 0.0639 0.0964 1
Data transfer 0.5232 0.1924 0.1331 0.1152 0.0361 1
Web browsing 0.3686 0.3743 0.1242 0.0868 0.0461 1

Throughput of networks

Network Obtained output (normalized values)/s Delivered output (normalized values)/s % Throughput
3G 0.8817 0.9524 92.58
WLAN 0.896 0.966 92.75
4G 0.9243 0.955 96.79
5G 0.9182 0.988 92.94

Parameters of different networks [24, 25]

Networks Network download speed (Mbps) Latency (ms) Bandwidth PLR (%) Jitter (ms) Target output (maximum download speed) Mbps
3G 144 kbps–2 Mbps 30–200 0.1 Mbps–3 Mbps 2–10 10–30 3–7.2
WLAN 1 Mbps–8 Mbps 80–300 2 Mbps–10 Mbps 4–15 30–80 450–600
4G 15 Mbps–90 Mbps 20–150 200 Mbps–1 Gbps 4–20 15–40 20–200
5G 150 Mbps–10 Gbps 1–10 1 Gbps–10 Gbps 0–10 10–20 1000–10,000

Mean square error of available networks

Network Mean Square Error
3G 0.005272
WLAN 0.00499
4G 0.004527
5G 0.008507
Lingua:
Inglese
Frequenza di pubblicazione:
1 volte all'anno
Argomenti della rivista:
Ingegneria, Introduzioni e rassegna, Ingegneria, altro
Feed RSS della rivista