Dynamic Cloud Offloading for Edge Server Resource Spikes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
On-premises edge servers in mobile wireless telecommunications systems face memory and computing resource constraints, leading to potential crashes during transient events, and existing solutions for offloading to public clouds are inefficient or impractical due to high costs, space requirements, and lengthy setup times.
Innovation Solution
A dynamic offloading system that monitors resource utilization on-premises and automatically creates instances on preconfigured public cloud resources to handle spikes, minimizing latency and resource waste by using preconfigured cloud spaces tailored for specific or general processing needs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If resources of on-prem server are significantly increased to address transient events, then server reliability is improved, but device complexity and cost increase
Solution Approach 1:
The system pre-configures resource spaces on public cloud servers in advance with necessary infrastructure (compute resources, networking, security configurations). When transient events occur, these pre-prepared resources can be immediately activated and assigned to handle the spike in demand, eliminating the need for complex real-time provisioning while ensuring reliability during peak loads.
2Productivity
If an instance on public cloud is requested for offloading workloads, then productivity is improved, but loss of time increases due to provisioning requirements
Solution Approach 1:
Resource spaces are pre-configured on public cloud servers with all necessary infrastructure including compute resources, networking configurations, security settings, and application environments. This preliminary preparation allows instances to be activated and assigned within seconds during transient events, rather than requiring hours or days of provisioning, thus maintaining high productivity while minimizing time loss.
3Reliability
If public cloud resources are allocated for transient events, then reliability is improved, but loss of energy increases due to idle resources
Solution Approach 1:
The system dynamically allocates and de-allocates pre-configured resource spaces based on real-time monitoring of transient events. When events occur, resources are activated and assigned to handle the load; when events subside, resources are de-allocated and returned to the pool. This dynamic approach ensures reliability during peak demand while minimizing energy waste from continuously idle resources.
Solution Approach 2:
The system recovers and reuses pre-configured resource spaces after transient events conclude. Instead of leaving resources idle or permanently allocated, the system de-allocates them back to the available pool for future use, thereby maintaining reliability for subsequent events while reducing energy consumption and resource waste during inter-event periods.
4Productivity
If public cloud instance creation is performed quickly, then productivity is improved, but manufacturing precision deteriorates due to skipped configuration steps
Solution Approach 1:
All configuration steps including tenant space allocation, IP address assignment, security configurations, networking setup, and application deployment are performed in advance during the pre-configuration phase. This preliminary action ensures that when instances need to be activated during transient events, they can be deployed immediately with complete configurations, maintaining both high productivity and configuration precision without skipping any necessary steps.
Data Source
AI summary
A dynamic offloading system is provided, which monitors resource demand by one or more applications executing on an on-prem server and supply of curated cloud space on one or more registered cloud service providers to automatically create an instance and offload applications associated with spikes in the resource demand. The curated cloud space may be preconfigured for specific processing and/or more general processing. For instance, the curated cloud space may be preconfigured for offloading service applications associated with mobile traffic, which may include specific resource requirements, time or service constraints, provisioning, testing or validation. Additionally, the curated cloud space may be preconfigured for offloading websites or databases, which may have more generalized resource requirements, provisioning, testing or validation.