17956035. SYSTEM FOR MACHINE LEARNING (ML) BASED NETWORK RESILIENCE AND STEERING simplified abstract (Mellanox Technologies, Ltd.)

SYSTEM FOR MACHINE LEARNING (ML) BASED NETWORK RESILIENCE AND STEERING

Organization Name

Mellanox Technologies, Ltd.

Inventor(s)

Ioannis (Giannis) Patronas of Piraeus (GR)

Tamar Viclizki Cohen of Herzliya (IL)

Vadim Gechman of Kibbutz Hulda (IL)

Dimitrios Syrivelis of Volos (GR)

Paraskevas Bakopoulos of Ilion (GR)

Nikolaos Argyris of Zografou (GR)

Elad Mentovich of Tel Aviv (IL)

SYSTEM FOR MACHINE LEARNING (ML) BASED NETWORK RESILIENCE AND STEERING - A simplified explanation of the abstract

This abstract first appeared for US patent application 17956035 titled 'SYSTEM FOR MACHINE LEARNING (ML) BASED NETWORK RESILIENCE AND STEERING

Simplified Explanation

The patent application describes a machine learning-based system for network resilience and steering, where network traffic is rerouted in response to operational failures.

• The system monitors data movement across network ports.
• It extracts network performance indicators associated with the data movement.
• A machine learning subsystem determines if a network port is indicative of operational failure based on the performance indicators.
• The system identifies the network port cluster and triggers rerouting of network traffic to a redundant port via an intermediate switch.

Potential Applications

This technology could be applied in various industries where network reliability and resilience are critical, such as telecommunications, data centers, and cloud computing.

Problems Solved

This technology addresses the issue of network downtime and disruptions by proactively rerouting traffic in response to potential failures, ensuring continuous network operation.

Benefits

- Improved network reliability and resilience - Reduced downtime and disruptions - Proactive network management and optimization

Potential Commercial Applications

The technology could be utilized by network equipment manufacturers, service providers, and large enterprises to enhance the reliability and performance of their networks.

Possible Prior Art

One possible prior art could be traditional network redundancy and failover mechanisms that are not based on machine learning algorithms. These systems may lack the ability to proactively predict and respond to network failures like the described innovation.

How does the machine learning subsystem determine the threshold for identifying operational failure based on network performance indicators?

The patent application does not provide specific details on how the machine learning subsystem sets the threshold for determining operational failure. Further information on the training data and algorithms used for this purpose would be helpful.

What are the potential limitations or challenges of implementing this system in a real-world network environment?

The patent application does not discuss any potential limitations or challenges that may arise when implementing this system in practical network settings. Understanding the scalability, compatibility, and performance impact of the system would be crucial for its successful deployment.

Original Abstract Submitted

Systems, computer program products, and methods are described herein for machine learning (ML) based system for network resilience and steering. An example system monitors data movement across one or more network ports; extracts network performance indicators associated with the data movement; determines, via a machine learning (ML) subsystem, that a status of a first network port is indicative of operational failure based on at least the network performance indicators; determines that the first network port is associated with a first network port cluster; determines a redundant network port and an intermediate network switch associated with the first network port cluster; and triggers the intermediate network switch to reroute a portion of network traffic from the first network port to the redundant network port in response to the status of the first network port.