Cloud Architecture Matching for Complex On-Premises Migration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying an optimally suited cloud architecture for migrating an on-premises system is challenging due to the large number of parameters and varying cloud providers, leading to potential mismatches and delays in the migration process.
Innovation Solution
A neural network model is trained using convolutional filters, ReLu activation functions, and max pooling to efficiently recommend a suitable cloud architecture by accounting for various parameters of both the on-premises and cloud systems, thereby ensuring optimal compatibility and reducing computational complexity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual or ad-hoc methods are used to identify cloud architecture, then flexibility in decision-making is maintained, but recommendation accuracy and migration efficiency deteriorate due to the large number of parameters and varying cloud providers
Solution Approach 1:
A neural network model is introduced as an intermediary between the complex set of input parameters (on-premises system specifications, migration requirements) and the output (recommended cloud architecture). The neural network automatically processes and integrates multiple parameters including database edition, version, RAC, database size, CPU cores, workload type, network bandwidth, and outage window to produce accurate migration recommendations, resolving the contradiction between accuracy and complexity
Solution Approach 2:
The patent replaces manual ad-hoc decision-making processes with an automated neural network system. Convolutional filters, ReLu activation functions, and max pooling operations substitute for human analysis of numerous parameters, systematically evaluating compatibility between on-premises systems and target cloud architectures across multiple cloud providers without human intervention
2Measurement precision
If a comprehensive analysis of multiple parameters is performed to ensure optimal compatibility, then migration accuracy is improved, but computational time and resource consumption increase
Solution Approach 1:
The neural network model is pre-trained with comprehensive parameter relationships and compatibility rules before actual migration planning. During deployment, the pre-trained model quickly processes new input parameters through established convolutional filters and activation functions, providing accurate compatibility assessments without requiring extensive computational time for each individual migration scenario
Solution Approach 2:
The system applies max pooling operations to selectively extract and prioritize the most critical feature maps from the convolutional layers, focusing computational resources on the most significant compatibility factors rather than processing all parameters with equal depth, thereby reducing overall computational time while maintaining accuracy
3Adaptability or versatility
If multiple cloud architectures from different vendors are evaluated, then adaptability and choice are improved, but the complexity of identification and comparison increases
Solution Approach 1:
The neural network model is designed with universal functionality to evaluate cloud architectures from multiple different vendors using a unified framework. The same convolutional filters and processing layers assess compatibility across diverse cloud providers, standardizing the evaluation process while maintaining the ability to handle vendor-specific architectures and parameters
Solution Approach 2:
The system applies different convolutional filters to different layers of the neural network, with each filter specialized for detecting specific features and compatibility aspects. This allows the model to handle the heterogeneity of multiple cloud architectures by applying appropriate local analysis techniques to different portions of the input data
Data Source
AI summary
This disclosure relates to cloud migration. In some aspects, a method includes receiving, by one or more computing devices, a plurality of parameters associated with an on-premises system to be migrated to a cloud architecture, the plurality of parameters including an identifier of the on-premises system, identifiers of components of the on-premises system, and migration requirements; extracting, from the plurality of parameters, a set of input parameters substantially affecting a migration of the on-premises system to the cloud architecture; identifying a target cloud architecture, selected from a plurality of cloud architectures, that i) is compliant with the set of input parameters, and ii) satisfies one or more threshold conditions associated with the migration; determining, a set of output parameters representing features of the target cloud architecture; and training, a neural network model using the set of input parameters and the set of output parameters.