Storage Workload Migration for Carbon-Aware SLA Compliance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage systems lack a solution to manage carbon dioxide equivalent emissions while ensuring compliance with sustainability service level agreements (SLAs) without impacting performance metrics.
Innovation Solution
Implement a workload scheduler and storage controller that utilize machine learning models to dynamically migrate or tier workloads based on CO2 emission data, ensuring adherence to sustainability SLAs by predicting and proactively adjusting storage systems to minimize emissions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-generated harmful factors
If workloads are migrated dynamically to minimize CO2 emissions, then carbon emission compliance is improved, but system complexity increases due to machine learning models and workload scheduling mechanisms
Solution Approach 1:
A workload scheduler acts as an intermediary component that receives CO2 emission data from storage controllers, processes it through machine learning models, and makes intelligent decisions about workload migration. This mediator layer manages the complexity internally while presenting a simple interface for emission compliance, separating the complex ML processing from the core storage operations
Solution Approach 2:
The system implements continuous feedback loops where CO2 emission data is collected from storage controllers, analyzed by machine learning models to predict future emissions, and used to dynamically adjust workload placement. This feedback mechanism enables automatic adaptation to emission patterns without manual intervention, managing complexity through automated closed-loop control
2Measurement precision
If machine learning models are used to predict CO2 emissions, then emission management accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
Machine learning models are trained in advance on historical CO2 emission data to learn patterns and relationships between workload characteristics and emission outcomes. This preliminary training phase allows the models to make rapid predictions during runtime without performing complex calculations in real-time, reducing processing delays while maintaining high prediction accuracy
Solution Approach 2:
The system applies machine learning models selectively to workloads or time periods where emission prediction provides the most value, rather than uniformly applying complex ML processing to all scenarios. This partial application approach balances computational overhead with emission management benefits, reducing unnecessary processing time consumption
3Object-generated harmful factors
If workloads are migrated proactively before time period ends, then CO2 emission compliance is improved, but workload migration overhead increases
Solution Approach 1:
The workload migration strategy is dynamically adjusted based on predicted CO2 emission trajectories and remaining time in the reporting period. The system flexibly determines migration timing and targets by analyzing current emission rates, forecasted patterns, and SLA requirements, optimizing migration decisions to minimize overhead while ensuring compliance is achieved at the most efficient moment
Data Source
AI summary
Controlling carbon emissions by workload at the storage level is provided. A storage system that can run a workload within a remainder of a specified time period without exceeding a maximum carbon dioxide (CO2) equivalent emission threshold level defined for the workload in a sustainability service level agreement (SLA) is identified based on analyzing retrieved CO2 equivalent emission data in a time-series format from a plurality of storage controllers corresponding to a plurality of storage systems using a set of machine learning models. The workload is migrated to the storage system prior to the specified time period being met to decrease CO2 equivalent emissions of the workload in accordance with the sustainability SLA.