Predicting Experience Degradation in Microservice Applications
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Microservice-based applications face experience degradation due to increased traffic, leading to performance issues and service quality deterioration, necessitating effective prediction methods to maintain quality of service.
Innovation Solution
A method involving the derivation of quality of service metrics from historical event log data, clustering using a clustering algorithm, and training a support vector machine model to classify and predict experience degradation events, allowing for proactive measures to optimize microservice performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If microservice-based applications handle rapidly growing traffic, then service coverage and user reach are improved, but experience degradation and service quality deteriorate
Solution Approach 1:
The patent applies preliminary action by training a support vector machine model with historical event log data and quality of service metrics before deployment. The model learns patterns of experience degradation events in advance, enabling it to predict and prevent future degradation before it occurs, thus maintaining service quality while handling growing traffic
Solution Approach 2:
The patent implements feedback by continuously monitoring quality of service metrics (response time, throughput, error rate) from microservice operations and feeding this data back to the trained support vector machine model. The model uses this feedback to predict upcoming experience degradation events, allowing the system to adjust and maintain service quality dynamically as traffic grows
2Reliability
If quality of service metrics are monitored and analyzed in real-time, then experience degradation can be predicted, but computational complexity and processing time increase
Solution Approach 1:
The patent reduces computational complexity during operation by performing the computationally intensive model training in advance using historical data. Once trained, the support vector machine model requires only efficient prediction computations on new data, significantly reducing real-time processing requirements while maintaining high prediction accuracy
Solution Approach 2:
The patent uses historical event log data as a copy of past system behavior to train the prediction model. This allows the system to learn from historical patterns without requiring complex real-time analysis of every possible scenario, reducing computational complexity while improving prediction reliability through comprehensive historical learning
Data Source
AI summary
Techniques are disclosed to predict experience degradation in a microservice-based application comprising a plurality of microservices. Quality of service metrics are derived for each node from the historical event log data of nodes forming a plurality of directed acyclic graph (DAG) paths in the multiple-layer nodes. A clustering model clusters the plurality of quality of service metrics according to multiple levels of quality of experience and determines respective value ranges of each quality of service metric for the multiple levels of quality of experience. Each quality of service metric is labeled with one of the multiple levels of quality of service according to the respective value ranges. A support vector machine model predicts various experience degradation events which are expected to occur during the operation of the microservice-based application.