Cloud Transfer Rate Prediction via Parameter Tuning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge of determining the maximum achievable data transfer rate between heterogeneous cloud storage services is hindered by the stateless nature of serverless functions, limiting the use of cloud platforms for data-intensive applications.
Innovation Solution
A method and system for parameter tuning that iteratively adjusts cloud parameters to achieve optimum values, generating training data to predict data transfer rates by simulating or testing cloud pairs, and using the training data to create a data model for real-time predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If cloud storage services are used for data-intensive applications, then data transfer capability is improved, but the stateless nature of serverless functions limits achievable performance
Solution Approach 1:
The patent applies parameter changes by systematically varying cloud storage parameters (thread count, buffer size, chunk size, parallelism degree) to find optimal configurations that maximize data transfer rates while working within the constraints of serverless functions. This resolves the contradiction by adapting parameters to overcome the stateless limitation.
2Productivity
If cloud parameters are tuned to maximize data transfer rate, then transfer performance is improved, but the complexity of parameter optimization increases
Solution Approach 1:
The patent uses preliminary action by pre-generating training data through systematic parameter tuning and experimentation before deployment. This creates a pre-computed knowledge base that simplifies real-time predictions, resolving the contradiction by moving the complex optimization work to an offline phase.
Solution Approach 2:
The patent applies copying by creating a trained machine learning model that replicates the complex parameter tuning behavior. Once the model is trained with optimal parameters, it copies this knowledge to make rapid predictions without re-running complex optimization algorithms, thus reducing operational complexity.
3Adaptability or versatility
If heterogeneous cloud storage services are utilized, then service versatility is improved, but achieving maximum transfer rate becomes more difficult
Solution Approach 1:
The patent applies universality by developing a unified machine learning model that works across multiple heterogeneous cloud storage services (AWS S3, Azure Blob Storage, Google Cloud Storage). The model is trained on diverse service characteristics and can predict optimal parameters for any service in the family, resolving the contradiction by creating a universal solution that adapts to different services.
Data Source
AI summary
Heterogeneous cloud storage services offered by different cloud service providers have unique deliverable performance. One key challenge is to find the maximum achievable data transfer rate from one cloud service to another. The disclosure herein generally relates to cloud computing, and, more particularly, to a method and system for parameter tuning in cloud network. The system obtains optimum value of parameters of a source cloud and a destination cloud in a cloud pair, by performing a parameter tuning. The optimum value of parameters and corresponding data transfer rate is used as a training data to generate a data model. The data model processes real-time information with respect to cloud pairs, and predicts corresponding data transfer rate.