18060753. DETECTING AN ANOMALY EVENT IN LOW DIMENSIONAL SPACENETWORKS simplified abstract (HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP)
Contents
- 1 DETECTING AN ANOMALY EVENT IN LOW DIMENSIONAL SPACENETWORKS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DETECTING AN ANOMALY EVENT IN LOW DIMENSIONAL SPACENETWORKS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
DETECTING AN ANOMALY EVENT IN LOW DIMENSIONAL SPACENETWORKS
Organization Name
HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP
Inventor(s)
Biswadeb Dutta of Chestnut Hill MA (US)
Jean-Charles Picard of Mougins (FR)
DETECTING AN ANOMALY EVENT IN LOW DIMENSIONAL SPACENETWORKS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18060753 titled 'DETECTING AN ANOMALY EVENT IN LOW DIMENSIONAL SPACENETWORKS
Simplified Explanation
The patent application describes systems and methods for reducing a number of performance metrics generated by network functions to a number of reduced dimension metrics, which can be used to detect anomalous behavior and generate a warning signal of the detected anomalous behavior. The disclosed systems and methods transform raw performance metrics in a high dimensionality space to a reduced number of metrics in a lower dimensionality space through dimensionality reduction techniques. Anomalous behavior in network performance is detected in the high dimensionality space using the reduced dimension metrics. The systems and methods convert the reduced dimension metrics back to the high dimensionality space, allowing the performance metrics from network functions to be utilized to understand and address potential problems in the network.
- Systems and methods for reducing performance metrics to detect anomalous behavior in network functions
- Transformation of raw performance metrics to reduced dimension metrics through dimensionality reduction techniques
- Detection of anomalous behavior in network performance using reduced dimension metrics
- Conversion of reduced dimension metrics back to high dimensionality space for analysis and problem-solving in the network
Potential Applications
The technology described in the patent application could be applied in various industries and sectors where network performance monitoring and anomaly detection are crucial, such as telecommunications, cybersecurity, and data centers.
Problems Solved
1. Detection of anomalous behavior in network performance metrics 2. Reduction of high dimensionality data to more manageable and actionable metrics for analysis and problem-solving
Benefits
1. Early detection of potential network issues or security threats 2. Improved network performance monitoring and management 3. Enhanced ability to address and resolve network problems efficiently
Potential Commercial Applications
Optimizing network performance in telecommunications companies Enhancing cybersecurity measures in data centers Improving data transmission efficiency in large-scale networks
Possible Prior Art
One possible prior art in this field is the use of machine learning algorithms for anomaly detection in network performance metrics. These algorithms analyze large volumes of data to identify patterns and deviations that may indicate anomalous behavior in the network.
Original Abstract Submitted
Systems and methods are provided for reducing a number of performance metrics generated by network functions to a number of reduced dimension metrics, which can be used to detect anomalous behavior and generate a warning signal of the detected anomalous behavior. The disclosed systems and methods transform raw performance metrics in a high dimensionality space to a reduced number of metrics in a lower dimensionality space through dimensionality reduction techniques. Anomalous behavior in network performance is detected in the high dimensionality space using the reduced dimension metrics. The systems and methods disclosed herein convert the reduced dimension metrics back to the high dimensionality space, such that the performance metrics from network functions can be utilized to understand and address potential problems in the network.
