View source for Samsung electronics co., ltd. (20240205107). ML BASED FAIR FLOW CONTROL MECHANISM FOR TCP IN CORE NETWORK simplified abstract

=ML BASED FAIR FLOW CONTROL MECHANISM FOR TCP IN CORE NETWORK=


==Organization Name==

[[:Category:samsung electronics co., ltd.|samsung electronics co., ltd.]]


[[Category:samsung electronics co., ltd.]]

==Inventor(s)==

[[:Category:Vasanth Kanakaraj of Bangalore (IN)|Vasanth Kanakaraj of Bangalore (IN)]][[Category:Vasanth Kanakaraj of Bangalore (IN)]]

[[:Category:Shreyanshu Agarwal of Bangalore (IN)|Shreyanshu Agarwal of Bangalore (IN)]][[Category:Shreyanshu Agarwal of Bangalore (IN)]]

[[:Category:Issaac Kommineni of Bangalore (IN)|Issaac Kommineni of Bangalore (IN)]][[Category:Issaac Kommineni of Bangalore (IN)]]

[[:Category:Vishal Murgai of Bangalore (IN)|Vishal Murgai of Bangalore (IN)]][[Category:Vishal Murgai of Bangalore (IN)]]

[[:Category:Anish Nediyanchath of Bangalore (IN)|Anish Nediyanchath of Bangalore (IN)]][[Category:Anish Nediyanchath of Bangalore (IN)]]

[[:Category:Gaurav Jha of Bangalore (IN)|Gaurav Jha of Bangalore (IN)]][[Category:Gaurav Jha of Bangalore (IN)]]

[[:Category:Naveen Kumar Srinivasa Naidu of Bangalore (IN)|Naveen Kumar Srinivasa Naidu of Bangalore (IN)]][[Category:Naveen Kumar Srinivasa Naidu of Bangalore (IN)]]

[[:Category:Sukhdeep Singh of Bangalore (IN)|Sukhdeep Singh of Bangalore (IN)]][[Category:Sukhdeep Singh of Bangalore (IN)]]

==ML BASED FAIR FLOW CONTROL MECHANISM FOR TCP IN CORE NETWORK - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240205107 titled 'ML BASED FAIR FLOW CONTROL MECHANISM FOR TCP IN CORE NETWORK

The patent application describes a method for congestion control and reducing latency in a core network using a control plane gateway.

* Monitoring key performance indicators (KPIs) of user plane gateways in the core network.
* Predicting optimal window sizes for each user plane gateway using a machine learning model based on KPI values.
* Transmitting the optimal window sizes to the respective user plane gateways.

Potential Applications:
- Telecommunication networks
- Data centers
- Internet service providers

Problems Solved:
- Congestion control in core networks
- Reduction of data latency
- Optimization of network performance

Benefits:
- Improved network efficiency
- Enhanced user experience
- Cost savings for network operators

Commercial Applications:
Title: "Optimized Congestion Control Solution for Core Networks"
This technology can be used by telecommunications companies to improve the performance of their networks, leading to better service for customers and potentially attracting more subscribers. It can also be utilized by data centers and internet service providers to optimize data transmission and reduce latency.

Prior Art:
Prior research in the field of network optimization and congestion control algorithms can provide valuable insights into similar approaches and technologies.

Frequently Updated Research:
Stay updated on advancements in machine learning algorithms for network optimization and congestion control to enhance the efficiency and effectiveness of the proposed method.

Questions about the technology:
1. How does the machine learning model predict optimal window sizes for user plane gateways?
- The machine learning model analyzes the monitored KPI values to determine the optimal window size for each gateway based on historical data and patterns.

2. What are the potential challenges in implementing this congestion control method in a real-world network environment?
- Some challenges may include integration with existing network infrastructure, scalability issues, and ensuring compatibility with different types of user plane gateways.


==Original Abstract Submitted==

a method of providing congestion control and reducing latency of data incoming to a core network, the method performed by a control plane gateway, includes: monitoring values of key performance indicators (kpis) associated with a plurality of user plane gateways in the core network; predicting, using a machine learning (ml) model, an optimal window size respectively for each of the plurality of user plane gateways, based on the monitored values of the kpis; and transmitting the optimal window size to the respective user plane gateway in the plurality of user plane gateways.



[[Category:H04L41/5009]]
[[Category:H04L41/16]]
[[Category:H04W28/08]]
[[Category:CPC_H04L41/5009]]