Airborne Datacenter Fleet Scaling for Disaster-Resilient Computing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional datacenters face challenges in scalability, as they require significant resources such as power, cooling, and dehumidification, leading to increased costs and risks from natural and man-made disasters, with limited flexibility to adapt to fluctuating demands or disasters.
Innovation Solution
An airborne datacenter (ADC) system comprising a datacenter assembly component (DAC) and a drive apparatus, which can be provisioned, configured, and decommissioned dynamically, allowing it to scale up or down in response to demand changes and operate as a standalone or extension to a land-based datacenter, using unmanned aerial vehicles (UAVs) for mobility and connectivity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a datacenter is expanded to meet increased demand, then processing capacity is improved, but power consumption and cooling requirements increase
Solution Approach 1:
The patent implements dynamic scalability by allowing datacenter components to be added or removed based on real-time demand. The system can dynamically provision computing resources, storage, and networking capabilities without permanent commitment, enabling the datacenter to adapt its capacity and energy consumption to match actual workload requirements.
Solution Approach 2:
The datacenter is divided into modular, independently deployable units or components. This segmentation allows individual components to be provisioned or deprovisioned based on specific demand requirements, rather than requiring expansion of the entire datacenter infrastructure, thus optimizing power consumption relative to actual needs.
2Productivity
If a datacenter is expanded to meet increased demand, then processing capacity is improved, but cooling and dehumidification requirements increase
Solution Approach 1:
The system dynamically adjusts cooling and dehumidification resources to match the actual thermal load generated by active computing components. As components are added or removed based on demand, the environmental control systems automatically scale accordingly, preventing waste of cooling resources on inactive equipment.
Solution Approach 2:
The datacenter infrastructure is designed to automatically provision and deprovision support systems including cooling and dehumidification based on the presence and operational state of computing components, without requiring manual intervention to match environmental control capacity with actual computational load.
3Reliability
If a datacenter is made fixed and reinforced to withstand disasters, then reliability is improved, but adaptability to fluctuating demands decreases
Solution Approach 1:
The patent implements a dynamic datacenter architecture where infrastructure components can be rapidly deployed, relocated, or retired in response to changing demands or disaster scenarios. This dynamic capability allows the system to maintain reliability through redundancy while simultaneously adapting to fluctuating workloads, resolving the contradiction between fixed disaster-resistant infrastructure and flexible scalability.
4Productivity
If a datacenter maintains all equipment and utilities for peak demand, then capacity is improved, but operational costs increase
Solution Approach 1:
The system implements partial provisioning where datacenter resources are allocated based on actual demand rather than maintaining full peak capacity continuously. Resources are provisioned temporarily for peak demand periods and then deprovisioned, allowing the system to achieve peak capacity when needed while avoiding the continuous operational costs of maintaining unused capacity during lower-demand periods.
Data Source
AI summary
An airborne datacenter (ADC) device includes a datacenter assembly component (DAC) and a drive apparatus. The DAC is configured to perform: provisioning the ADC including receiving, in response to a provision request, business functions and configuration information from a provisioning center connected to the ADC over a network and self-configuring the ADC with the business functions and the configuration information; datacenter operations with the ADC including receiving, from another ADC within a fleet of ADCs and over the network, processing results generated by the another ADC, performing the datacenter operations using the business functions and the processing results generated by the another ADC, and forwarding processing results of the datacenter operations to a land-based enterprise over the network; and decommissioning the ADC including transferring runtime information of the ADC, and deleting the runtime information from the ADC. The DAC includes digital processing equipment configured to perform the business functions.