Infrastructure Control Fabric for Real-Time Data Center Capacity Queries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern data centers face inefficiencies due to the static nature of physical infrastructure, leading to underutilization and increased costs, as IT workloads are often operated with a safety margin to avoid exceeding power or cooling capacities, resulting in unnecessary resource allocation and potential disruptions.
Innovation Solution
A data center infrastructure management system with an infrastructure control fabric subsystem that enables real-time communication between independent computing devices and the data center management system, allowing devices to query and obtain power, cooling, and space information before initiating operations, thus optimizing resource usage and avoiding capacity overloads.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data centers operate with a safety margin to avoid exceeding power or cooling capacities, then system reliability is improved, but resource utilization deteriorates
Solution Approach 1:
The patent implements a feedback mechanism where the DCIM system continuously monitors power and cooling capacity usage in real-time and communicates available capacity back to IT components. This allows the system to dynamically adjust operations based on actual capacity availability rather than operating with static safety margins, thereby improving resource utilization while maintaining reliability through continuous monitoring and adaptive control.
Solution Approach 2:
The patent enables IT components to autonomously query the DCIM system for available capacity information and make their own decisions about when to operate or remain inactive based on real-time capacity data. This self-service approach eliminates the need for conservative safety margins imposed by centralized control, allowing components to fully utilize available capacity while the DCIM system ensures overall system reliability through continuous monitoring.
2Reliability
If data centers upgrade infrastructure capacity to meet maximum anticipated workloads, then system reliability is improved, but capital expenditure deteriorates
Solution Approach 1:
The patent transforms the static infrastructure capacity model into a dynamic one by implementing real-time communication between the DCIM system and IT components. The system continuously monitors actual capacity usage and dynamically adjusts available capacity allocations based on current conditions, allowing the data center to operate closer to maximum capacity without requiring permanent infrastructure upgrades for peak demand scenarios.
Solution Approach 2:
The patent changes the operational parameters from static safety margins to dynamic capacity utilization by implementing continuous monitoring and real-time communication. The DCIM system tracks actual power and cooling usage, adjusts available capacity parameters dynamically, and enables IT components to adapt their operations accordingly, reducing the need for excessive infrastructure capacity while maintaining reliability.
3Device complexity
If IT components operate without real-time capacity information, then device complexity is reduced, but harmful factors increase
Solution Approach 1:
The patent introduces the DCIM system as an intermediary between IT components and the physical infrastructure. The DCIM system handles the complexity of real-time capacity monitoring, analysis, and communication, while IT components receive simplified capacity availability information through standard interfaces. This intermediary approach adds minimal complexity to individual devices while effectively preventing capacity overloads through centralized intelligent control.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A data center infrastructure management (DCIM) system having an infrastructure control fabric (ICF) subsystem for enabling a manager component of an independent computing device to communicate directly with the DCIM system. The DCIM system, in one embodiment, may have a manageability subsystem engine for monitoring data being transmitted from the independent computing device. A domain model may be included that has an extension relating to information on the independent computing device. A services server may be used which provides a shared services infrastructure layer. The ICF subsystem may have components located in each of the manageability subsystem engine, the domain model, on the services server, and in the manager component of the independent computing device, to enable the independent computing device to directly query the DCIM system to obtain at least one of real time power, cooling and space information that is useful for the independent computing device to know before at least one of initiating an operation or continuing with an operation.