Integrating Deep Learning Models into Stochastic Network Calculus for Enhanced Channel State Prediction in Underwater Acoustic Networks.
Saved in:
| Title: | Integrating Deep Learning Models into Stochastic Network Calculus for Enhanced Channel State Prediction in Underwater Acoustic Networks. |
|---|---|
| Authors: | Saravanan, M.1 (AUTHOR) saravanan.be88@gmail.com, Sukumaran, Rajeev1 (AUTHOR) raajeev.bce@gmail.com |
| Source: | Wireless Personal Communications. Feb2025, Vol. 140 Issue 3/4, p1085-1118. 34p. |
| Subjects: | Stochastic learning models, Underwater acoustic communication, Telecommunication, Marine communication, Wireless communications |
| Abstract: | The unpredictable environmental conditions create significant challenges for data transmission in underwater acoustic communication systems. Stochastic Network Calculus (SNC) provides a strong framework for analyzing and optimizing these networks, but traditional models struggle with predictive accuracy in rapidly changing environments. This paper presents an innovative approach by integrating deep learning models with SNC to enhance channel state prediction and improve network performance. The Deep Learning model used to predict future channel states and allowing proactive adjustments to the SNC model. The results show a 10% reduction in expected delay and an 18% reduction in backlog compared to traditional models. The method also enhances throughput and transmission efficiency by adjusting network parameters based on predictions. This integration fosters resilience to dynamic underwater environments affected by temperature, salinity changes and emphasizing the importance of optimizing underwater acoustic communication for marine exploration for environmental monitoring applications. [ABSTRACT FROM AUTHOR] |
| Copyright of Wireless Personal Communications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | The unpredictable environmental conditions create significant challenges for data transmission in underwater acoustic communication systems. Stochastic Network Calculus (SNC) provides a strong framework for analyzing and optimizing these networks, but traditional models struggle with predictive accuracy in rapidly changing environments. This paper presents an innovative approach by integrating deep learning models with SNC to enhance channel state prediction and improve network performance. The Deep Learning model used to predict future channel states and allowing proactive adjustments to the SNC model. The results show a 10% reduction in expected delay and an 18% reduction in backlog compared to traditional models. The method also enhances throughput and transmission efficiency by adjusting network parameters based on predictions. This integration fosters resilience to dynamic underwater environments affected by temperature, salinity changes and emphasizing the importance of optimizing underwater acoustic communication for marine exploration for environmental monitoring applications. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 09296212 |
| DOI: | 10.1007/s11277-025-11759-7 |
