Anomaly Detection in Cloud Network Data Streams
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing platforms face challenges in managing network stability due to scale and heterogeneity, with existing methods relying on heavy computational loads and human review, which are inefficient in detecting anomalies in real-time.
Innovation Solution
A system and method for machine-driven, real-time discovery of aberrant states using a decision support system that processes data streams from network devices, builds historic models, predicts future values, and detects anomalies by determining variations exceeding a threshold, updating models accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If heavy computational loads and human review are used to detect anomalies, then measurement precision is improved, but productivity deteriorates
Solution Approach 1:
The system employs machine learning models that automatically learn from historical data and autonomously detect anomalies without requiring human review. The models self-improve by continuously training on new data, enabling the system to maintain high detection accuracy while operating independently, thus resolving the contradiction between precision and productivity.
Solution Approach 2:
The patent replaces manual human review processes with automated machine learning algorithms. This substitution eliminates the need for human computational effort while maintaining or improving detection accuracy through sophisticated pattern recognition, thereby achieving both high precision and productivity simultaneously.
2Adaptability or versatility
If machine learning models are trained on historical data, then adaptability is improved, but loss of time occurs during model building
Solution Approach 1:
The system performs preliminary actions by continuously training machine learning models on historical data in advance, before anomalies need to be detected. This proactive approach ensures models are already adapted and ready for real-time detection, eliminating delays associated with last-minute model building while maintaining high adaptability.
Solution Approach 2:
The patent implements continuous model training and updating processes that operate continuously in the background. This ensures models remain adaptively tuned to current conditions without interrupting anomaly detection operations, thereby maintaining both adaptability and avoiding time loss through seamless continuous operation.
Data Source
AI summary
Novel tools and techniques for the machine discovery of aberrant states are provided. A system includes a plurality of network devices, and a decision system in communication with the plurality of network devices. Each of the plurality of network devices may be configured to generate a respective data stream. The decision system may include a processor and a non-transitory computer readable medium including instructions executable by the processor to obtain, via the plurality of network devices, one or more data streams. The decision system may build a historic model of a data stream, and determine a predicted value of the data stream at a future time, based on the historic model. The decision system may be configured to determine whether an anomaly has occurred based on a variation between a current value of the data stream and the predicted value of the data stream.