Multitenant Server Dependency Mapping via ML State Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large organizations face challenges in efficiently, effectively, and securely managing data flows between internal and external computer systems, particularly with multitenant servers where current methods fail to accurately identify tenant applications involved in data flows, leading to reduced monitoring effectiveness and increased risk of unauthorized data use.
Innovation Solution
A machine-learning based multitenant server application dependency mapping system that uses a framework to learn data flow patterns across the enterprise network, predicting server states and computing transition probabilities to accurately map data flows through multitenant infrastructure components, treating the network as a dynamic graph for link prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multitenant servers are used to optimize resource capacity and reduce costs, then resource utilization and cost efficiency are improved, but the ability to accurately identify tenant applications involved in data flows deteriorates
Solution Approach 1:
The patent segments the identification problem by creating separate identification pathways for different data flow scenarios. It divides the multitenant server environment into identifiable tenant contexts using telemetry data segmentation, allowing each tenant's data flows to be tracked independently despite sharing infrastructure.
Solution Approach 2:
The patent introduces telemetry data as an intermediary element that mediates between the multitenant server infrastructure and the identification system. This intermediary captures and transmits information about tenant applications' data flows, enabling accurate identification without requiring changes to the underlying multitenant architecture.
2Measurement precision
If multitenant servers are omitted due to identification problems, then measurement precision is improved, but resource capacity optimization and cost savings deteriorate
Solution Approach 1:
The patent implements preliminary action by establishing telemetry data collection and identification mechanisms before data flows occur. The system proactively captures tenant application information and establishes identification patterns in advance, enabling accurate tracking when multitenant servers are actively used.
Solution Approach 2:
The patent implements feedback loops where telemetry data continuously informs the identification system about tenant application states and data flow patterns. This feedback mechanism maintains high identification accuracy while allowing multitenant servers to operate at full capacity, as the system adaptively learns and adjusts to the shared infrastructure environment.
3Device complexity
If traditional data flow monitoring methods are used without machine learning, then system complexity is reduced, but the ability to accurately map data flows through multitenant components deteriorates
Solution Approach 1:
The patent implements self-service by enabling the system to automatically learn and adapt to multitenant server patterns without extensive manual configuration. The machine learning model autonomously analyzes telemetry data, identifies tenant applications, and maps data flows, reducing the need for complex manual setup while maintaining high accuracy.
Solution Approach 2:
The patent applies parameter changes by transforming static identification rules into dynamic, learning-based parameters. The system evolves its identification capabilities over time by adjusting model parameters based on observed telemetry patterns, enabling accurate data flow mapping through multitenant components without proportionally increasing system complexity.
Data Source
AI summary
A multitenant server application dependency mapping system maps data flows through multitenant infrastructure components through the use of a machine learning model framework that continually learns data flow patterns across the enterprise network and predicts the state of any given server. The multitenant server application dependency mapping system treats the network architecture as a whole and collects data accordingly, and uses that data to compute state probabilities conditioned upon both a point in time (and the observed prior states retrieved from the historical telemetry data. This provides a way to predict the likelihood of observing a tenant state being occupied, while also accounting for variations among the activity levels of various application. To forecast future states of all infrastructure components, the transition probabilities from tenant state to tenant state are then computed through time and used as inputs to the model to provide an accurate reconstruction of the data flows through all multitenant infrastructure components.