Microservice Resource Estimation Model for Quality of Service Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In microservice architecture-based applications, it is challenging to optimally set target resource values for each component to ensure quality of service, as the impact of each component on the overall service quality is unknown, leading to inefficient resource allocation and potential deployment of useless resources.
Innovation Solution
An information processing apparatus that uses machine learning to create an estimation model based on workload and resource usage data, allowing for the calculation of quality of service estimates and subsequent optimization of resource allocation to meet quality of service targets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If target resource values are set for each component in microservice architecture, then quality of service can be ensured, but it is difficult to optimally set these values as the impact of each component on overall service quality is unknown
Solution Approach 1:
The patent replaces manual or rule-based resource allocation mechanisms with a machine learning-based estimation model. The model automatically learns the impact of each component on overall service quality from historical data, substituting complex human judgment and trial-and-error processes with an automated computational system that provides optimal resource allocation recommendations.
Solution Approach 2:
The estimation model acts as an intermediary between workload information/resource usage data and quality of service outcomes. It processes input data about component performance and resource consumption to generate estimated quality of service values, thereby mediating the complex relationship between individual component configurations and overall service quality without requiring direct human analysis of all possible interactions.
2Reliability
If resources are increased for each component to ensure service quality, then quality of service improves, but resource waste increases due to deployment of useless resources
Solution Approach 1:
The patent changes the parameter optimization approach from uniform or heuristic-based resource allocation to data-driven parameter optimization using machine learning. The estimation model analyzes historical workload and resource usage patterns to determine the optimal resource allocation parameters for each component, ensuring that resources are allocated precisely where needed to achieve quality of service targets without excessive provisioning.
Solution Approach 2:
The patent applies local quality optimization by treating each microservice component individually rather than applying uniform resource allocation rules across all components. The estimation model evaluates and optimizes resource allocation for each specific component based on its unique characteristics, workload patterns, and impact on overall service quality, thereby avoiding the resource waste that occurs with blanket allocation strategies.
3Productivity
If machine learning estimation model is implemented to predict quality of service, then optimal resource allocation can be achieved, but system complexity and computational overhead increase
Solution Approach 1:
The patent implements preliminary action by pre-training the machine learning estimation model using historical workload and resource usage data before deployment. This preliminary training phase allows the model to learn patterns and relationships in advance, so that during actual operation, the model can quickly provide accurate quality of service estimates without adding significant computational overhead to the real-time system. The complex learning process is performed beforehand, not during production operations.
Data Source
AI summary
An information processing apparatus comprises a controller. The controller is configured to execute: acquiring a plurality of datasets, each of the datasets being configured with a combination of training data and a correct answer label; and implementing machine learning of an estimation model using the acquired plurality of datasets, wherein the training data includes workload information about an application constructed based on a microservice architecture and resource use information about resources used for each of components included in the application, in a learning target environment, the correct answer label is configured to show a true value of quality of service of the application, and the machine learning comprises training the estimation model such that, for each of the datasets, an estimated value of the quality of service calculated with the estimation model based on the training data corresponds to the true value shown by the correct answer label.