Proactive Anomaly Detection in Microservice Applications
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current anomaly detection systems for microservice applications lack the ability to consider spatial and temporal dependencies among services, leading to increased false positives and inefficiencies in monitoring and performance optimization.
Innovation Solution
A computer-implemented method that collects trace data and specifications for normal behavior in microservice applications, generates request contextual features, trains a neural network model, and predicts anomalous behavior using these features to provide proactive alerts and resource management capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional anomaly detection systems are used for microservice applications, then the system structure is simple, but the detection precision is low and false positives increase
Solution Approach 1:
The patent introduces a neural network model as an intermediary between the microservice application and the anomaly detection system. This model processes trace data and contextual features to generate anomaly predictions, thereby improving detection precision while managing system complexity through a dedicated intermediate component rather than complexifying the entire system.
Solution Approach 2:
The patent replaces traditional rule-based or statistical anomaly detection mechanisms with a neural network-based system. This substitution enables the system to learn complex patterns and dependencies in microservice trace data, significantly improving anomaly detection precision while the neural network handles the computational complexity internally.
2Measurement precision
If neural network models are trained on request contextual data, then anomaly detection precision is improved, but the loss of time for data processing increases
Solution Approach 1:
The patent implements preliminary action by pre-processing trace data and generating contextual features during normal system operation, before anomaly detection is needed. The neural network model is trained in advance on historical data, so when actual anomaly detection is required, the processing time is minimized as the model is already prepared and can directly evaluate new trace data.
3Reliability
If comprehensive trace data is collected for training, then the reliability of anomaly detection is improved, but the quantity of data to be processed increases
Solution Approach 1:
The patent applies the extraction principle by selectively extracting relevant contextual features from comprehensive trace data. Instead of processing all raw trace data, the system identifies and extracts key features such as request patterns, service dependencies, and performance metrics that are most relevant for anomaly detection, thereby maintaining high reliability while reducing the volume of data that needs to be processed.
Solution Approach 2:
The patent segments the comprehensive trace data into distinct contextual features and categories. By dividing the data into meaningful segments such as request contextual features, service dependency features, and performance metrics, the system can process each segment efficiently while maintaining the overall reliability of anomaly detection through the combined information.
Data Source
AI summary
Embodiments of the present invention provide computer implemented methods, computer program products and computer systems. For example, embodiments of the present invention can, in response to receiving a request, collect trace data and specifications for a sequence of requests for normal behavior of a microservice application. Embodiments of the present invention can then generate request contextual features from the collected trace data and specification. Embodiments of the present invention can then train a neural network model based on the generated contextual features; and predicting anomalous behavior of the microservice application using the trained neural network model.