18148529. RESOURCE ANOMALY DETECTION simplified abstract (Microsoft Technology Licensing, LLC)
Contents
- 1 RESOURCE ANOMALY DETECTION
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 RESOURCE ANOMALY DETECTION - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Key Features and Innovation
- 1.6 Potential Applications
- 1.7 Problems Solved
- 1.8 Benefits
- 1.9 Commercial Applications
- 1.10 Questions about the Technology
- 1.11 Original Abstract Submitted
RESOURCE ANOMALY DETECTION
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
Hagit Grushka of Beer-Sheva (IL)
RESOURCE ANOMALY DETECTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 18148529 titled 'RESOURCE ANOMALY DETECTION
Simplified Explanation
The patent application describes systems and methods for detecting an unstable resource in a cloud service by analyzing health time-series data and comparing it to historical data to determine anomalous behavior.
Key Features and Innovation
- Utilizes a resource behavior model trained on historical data to encode health time-series data into embeddings.
- Determines anomalous behavior by comparing embeddings to received data and calculating a reconstruction loss value.
- Compares generated embeddings to those from other similar resources to determine similarity scores for anomaly detection.
Potential Applications
This technology can be applied in cloud services, data centers, and IT infrastructure management to monitor resource stability and health.
Problems Solved
- Detecting unstable resources in cloud services.
- Improving resource management and maintenance.
- Enhancing overall system reliability and performance.
Benefits
- Early detection of resource instability.
- Proactive maintenance to prevent system failures.
- Optimal resource utilization and performance.
Commercial Applications
Cloud service providers, data center operators, and IT companies can use this technology to ensure the stability and health of their resources, leading to improved service reliability and customer satisfaction.
Questions about the Technology
What are the potential implications of using this technology in large-scale cloud environments?
This technology can significantly enhance the reliability and performance of cloud services by detecting and addressing resource instability before it leads to system failures.
How does this technology compare to traditional methods of monitoring resource health in cloud services?
This technology offers a more proactive and accurate approach to detecting anomalous behavior in resources compared to traditional monitoring methods, leading to improved system reliability and performance.
Original Abstract Submitted
Systems and methods for detecting an unstable resource of a cloud service. A set of health time-series data of a first resource is received and a resource behavior model trained on historical health time-series data of resources of a same type as the first resource is used to encode the received data into embeddings. In some examples, the model reconstructs the embeddings, compares the embeddings to the received data, and determines a reconstruction loss value for determining whether the first resource is operating in an anomalous behavior state. In some examples, the generated embeddings are compared to embeddings generated from health time-series data received from other resources of a same type as the first resource. A similarity-score is determined and used to determine whether the first resource is operating in an anomalous behavior state. The system and method further report anomalous behavior, indicating the first resource is unstable or unhealthy.
