Traffic modelling using Machine Learning
Pandey, Rohit (2024-11-13)
R. Pandey
13.11.2024
© 2024, Rohit Pandey. Tämä Kohde on tekijänoikeuden ja/tai lähioikeuksien suojaama. Voit käyttää Kohdetta käyttöösi sovellettavan tekijänoikeutta ja lähioikeuksia koskevan lainsäädännön sallimilla tavoilla. Muunlaista käyttöä varten tarvitset oikeudenhaltijoiden luvan.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202411136737
https://urn.fi/URN:NBN:fi:oulu-202411136737
Tiivistelmä
Within a few years, Artificial Intelligence (AI) and Machine Learning (ML) have become a central topic in all fields, including telecommunications. Artificial Intelligence and the revolution of Machine Learning have greatly influenced the modern world, and it can be used to find newer and faster ways to improve, for example, 6G and the speed of sending wireless information. With the help of machine learning and intelligent algorithms, we can develop faster and more powerful ways to send information and save energy simultaneously in traffic signaling. With Machine Learning we can optimize network resources and improve the security of data traffic and the performance of wireless networks.
By using intelligent algorithms, machine learning can identify patterns and trends that could be missed in traditional methods. This could also lead to more accurate predictions and efficient management of cellular traffic. The next-generation networks, such as 6G, will need high-speed data transmission.
Traditional traffic models often rely on linear assumptions and simplistic rules. These models struggle to capture the complex, non-linear relationships that are in real-world traffic behavior. Because of this, today's methods cannot handle such a large amount of data and complexity.
Machine Learning can increase energy efficiency by sending less unnecessary data and using cellular traffic more efficiently. This can make the telecommunication industry more sustainable, and use less energy and fewer resources.
This Thesis investigates the application of Machine Learning algorithms to wireless traffic modeling. The Thesis aims to enhance predictive accuracy and the usage of Machine Learning algorithms in processing large data. The goal is to improve Machine learning prediction accuracy of cellular traffic.
The growing data consumption creates challenges for network operators, such as increasing capacity, and the cost also increases.
By using intelligent algorithms, machine learning can identify patterns and trends that could be missed in traditional methods. This could also lead to more accurate predictions and efficient management of cellular traffic. The next-generation networks, such as 6G, will need high-speed data transmission.
Traditional traffic models often rely on linear assumptions and simplistic rules. These models struggle to capture the complex, non-linear relationships that are in real-world traffic behavior. Because of this, today's methods cannot handle such a large amount of data and complexity.
Machine Learning can increase energy efficiency by sending less unnecessary data and using cellular traffic more efficiently. This can make the telecommunication industry more sustainable, and use less energy and fewer resources.
This Thesis investigates the application of Machine Learning algorithms to wireless traffic modeling. The Thesis aims to enhance predictive accuracy and the usage of Machine Learning algorithms in processing large data. The goal is to improve Machine learning prediction accuracy of cellular traffic.
The growing data consumption creates challenges for network operators, such as increasing capacity, and the cost also increases.
Kokoelmat
- Avoin saatavuus [35294]