Load Mitigator Routing Analytics Between On-Box and Cloud Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information handling systems face inefficiencies in data analytics due to constraints in hardware resources and security complexities, with cloud-based analytics introducing data privacy breaches and latency, while on-the-box analytics lack processing power and productivity impact.
Innovation Solution
An information handling system that includes a cloud device with an on-the-cloud analytics device and a node device equipped with an on-the-box analytics device, data collector, data management, and load mitigator, which determines whether to route analytics to the on-the-box or on-the-cloud device based on workload requests, utilizing policy information and heat maps to optimize resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If cloud-based analytics are used, then processing power is improved, but data privacy and security are compromised
Solution Approach 1:
The analytics workload is segmented into two parts: sensitive data remains on-the-box for processing by on-premises analytics devices, while non-sensitive data is sent to cloud-based analytics devices. This segmentation allows the system to leverage cloud processing power while maintaining data privacy and security for sensitive information.
2Power
If cloud-based analytics are used, then processing power is improved, but latency increases
Solution Approach 1:
The system segments analytics workloads based on latency requirements. Time-sensitive analytics are processed on-the-box using on-premises devices to minimize latency, while non-time-sensitive analytics are offloaded to the cloud for enhanced processing power. The load mitigator dynamically routes workloads based on these criteria.
Solution Approach 2:
The system dynamically adjusts the routing of analytics workloads between on-the-box and on-the-cloud devices based on real-time conditions such as current system load, latency requirements, and data sensitivity. This dynamic approach allows the system to optimize both processing power and latency performance under varying conditions.
3Object-affected harmful factors
If on-the-box analytics are used, then data security is improved, but processing power is insufficient
Solution Approach 1:
The analytics workload is segmented based on data sensitivity and processing requirements. Sensitive data is processed on-the-box to maintain security, while non-sensitive data is processed in the cloud to access greater processing power. This segmentation resolves the contradiction by allowing both security and processing power needs to be met simultaneously.
Solution Approach 2:
The hybrid analytics system provides multi-functionality by combining on-the-box and on-the-cloud analytics capabilities. The system can handle both security-sensitive workloads and compute-intensive workloads through a unified architecture that dynamically selects the appropriate processing location based on workload characteristics.
4Object-affected harmful factors
If all analytics are processed on-the-box, then data privacy is maintained, but productivity is reduced
Solution Approach 1:
The system segments analytics workloads based on data sensitivity. Only sensitive data requires on-the-box processing to maintain privacy, while non-sensitive data can be processed in the cloud to improve productivity through enhanced processing power and resources. This segmentation allows the system to maintain privacy where necessary while improving overall productivity.
Solution Approach 2:
Instead of processing all analytics on-the-box, the system applies partial action by sending only the necessary sensitive data to on-premises devices while processing the majority of non-sensitive analytics in the cloud. This approach maintains data privacy for sensitive information while significantly improving productivity through cloud-based processing resources.
Data Source
AI summary
An information handling system includes a cloud device including an on-the-cloud analytics device, and a node device. The node device includes an on-the-box analytics device, a data collector device, a data management device, and a load mitigator device. The data collector device sources a plurality of data-producing agents within the information handling system. The data management device receives and manages data produced by the data collector. The load mitigator device receives the data from the data management device, and analyzes the data and additional system data. The additional system data is associated with the information handling system. The load mitigator device also determines whether to route analytics for the information handling system to the on-the box analytics device or to the on-the-cloud analytics. Based on the determination, the load mitigator device routes the analytics to either the on-the box analytics device or to the on-the-cloud analytics device.