Automated Data Center Expansion via Telemetry Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current data center management systems face challenges in predicting and managing hardware resource needs across multiple data centers, leading to inefficiencies in resource allocation and potential security concerns due to shared hardware resources.

Innovation Solution

A system that utilizes timeseries telemetry data to predict hardware requests and resource utilization, determining physical location sources, destinations, and amounts of hardware, enabling automated expansion and optimization of data center infrastructure through cloud management and virtualization technologies.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual IT teams manage hardware allocation across data centers, then flexibility in resource management is maintained, but productivity is reduced due to manual processes

Engineering Contradiction:

Improvemanual resource management flexibilityVSAvoidresource allocation efficiency

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The system enables automated self-service for hardware resource management by using machine learning models to predict future resource needs and automatically generate procurement requests, eliminating the need for manual IT team intervention while maintaining operational flexibility

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical processes with automated electronic systems, using telemetry data collection, machine learning prediction algorithms, and automated procurement workflows to substitute human-operated resource allocation processes

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Device complexity

If shared hardware resources are used across multiple data centers, then device complexity is reduced, but security risks increase due to potential contamination between clients

Engineering Contradiction:

Improvehardware infrastructure simplicityVSAvoiddata security risks

Core Design Contradiction:

Device complexityVSObject-affected harmful factors

Solution Approach 1:

The system segments hardware resources by assigning dedicated hardware to specific clients based on predicted needs, creating isolated resource partitions that prevent cross-client contamination while maintaining simplified overall infrastructure through centralized management

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by predicting future resource requirements using machine learning models and procuring dedicated hardware in advance, ensuring security isolation is established before any potential security incidents can occur

Inventive Principle:

Principle #10Preliminary action

3Reliability

If dedicated hardware is deployed for each client, then security is improved through isolation, but device complexity and costs increase

Engineering Contradiction:

Improvedata security through hardware isolationVSAvoidhardware infrastructure complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system dynamically changes the parameter of hardware allocation from static dedicated assignments to dynamic assignments based on predicted resource utilization patterns, achieving security isolation only when and where needed while reducing overall infrastructure complexity

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system implements feedback loops by continuously collecting telemetry data, analyzing resource utilization patterns, and adjusting hardware allocation decisions accordingly, ensuring optimal security and resource efficiency without excessive complexity

Inventive Principle:

Principle #23Feedback

4Device complexity

If hardware procurement is done reactively based on current needs, then device complexity is minimized, but loss of time occurs due to delayed resource availability

Engineering Contradiction:

Improveprocurement process simplicityVSAvoidhardware acquisition time

Core Design Contradiction:

Device complexityVSLoss of time

Solution Approach 1:

The system performs preliminary procurement actions by using machine learning models to predict future hardware needs and initiating procurement processes in advance, ensuring resources are available when needed without complex real-time decision-making

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces reactive manual procurement processes with proactive automated systems that use telemetry data and prediction algorithms to trigger procurement workflows at optimal times, reducing both complexity and time loss

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12117919B2Global automated data center expansion

Publication Date: 2024.10.15 EMC IP HLDG CO LLC

AI summary

A system can determine timeseries telemetry data of resource utilization of respective data centers of a group of data centers maintained by the system. The system can predict respective hardware requests based on future resource utilization based on the timeseries telemetry data, the hardware requests comprising respective hardware requests at respective data centers of the group of data centers. The system can predict respective future times at which the respective hardware requests will occur. The system can determine respective physical location sources of hardware, respective physical location destinations of hardware, and respective amounts of hardware based on the respective hardware requests and the respective future times. The system can store an indication of the respective physical location sources of hardware, respective physical location destinations of hardware, and respective amounts of hardware.