Distributed Cloud System with Core Edge Local Architecture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing edge computing systems face challenges such as insufficient management methods for multiple clusters, inadequate network structures for high-speed connections, insufficient performance when resources are scarce, and inefficient use of Open Container Initiative (OCI) technology, leading to latency and inadequate collaborative solutions.
Innovation Solution
A distributed cloud system with a core cloud, edge cloud, and local cloud architecture that includes a scheduler for task processing, snapshot image management, and high-speed network connections between clusters, utilizing shared storage to reduce snapshot image transmission and enabling efficient service migration and data processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple clusters are used in edge computing systems, then service availability and resource utilization are improved, but system complexity and management difficulty increase
Solution Approach 1:
The system segments cloud resources into multiple independent clusters distributed at different locations (core cloud, regional clouds, edge clouds). Each cluster can operate independently and be managed separately, which improves service availability through redundancy while maintaining manageable complexity through modular architecture.
Solution Approach 2:
The patent introduces a service mesh as an intermediary layer between service instances and the network. The service mesh handles service discovery, load balancing, and communication protocols automatically, reducing the operational complexity of managing multiple clusters while maintaining high service availability.
2Productivity
If centralized cloud processing is used, then resource consolidation is improved, but transmission delay and processing latency increase
Solution Approach 1:
The patent transitions from purely centralized processing to a multi-dimensional distributed architecture spanning core cloud, regional clouds, and edge clouds at different hierarchical levels. This dimensional distribution allows resources to be consolidated strategically while placing computation closer to data sources, reducing transmission delay through hierarchical data flow patterns.
Solution Approach 2:
Different levels of the cloud hierarchy provide different services with local optimization. Edge clouds perform latency-sensitive operations locally, regional clouds handle medium-scale processing, and core cloud manages large-scale consolidation. This local quality approach balances resource consolidation benefits with transmission delay minimization at appropriate granularities.
3Ease of manufacture
If existing OCI technology is used, then containerization is simplified, but performance and response speed deteriorate
Solution Approach 1:
The patent modifies OCI technology parameters by implementing custom resource managers and performance tuners that adjust scheduling policies, memory management, and CPU affinity settings. These parameter changes optimize container performance for specific workloads while maintaining the simplicity of OCI-based containerization, achieving both ease of deployment and high response speed.
Solution Approach 2:
The system introduces dynamic resource allocation and performance tuning capabilities that adapt container resource assignments in real-time based on workload characteristics. This dynamic approach allows the system to maintain simple OCI containerization while optimizing performance by adjusting parameters such as resource limits, priorities, and isolation levels based on actual runtime conditions.
4Adaptability or versatility
If snapshot images are transmitted between edge clouds, then service migration is enabled, but transmission time and bandwidth consumption increase
Solution Approach 1:
The system performs preliminary actions by caching snapshot images in local storage at edge clouds and regional clouds before actual migration is needed. When service migration is required, the system retrieves pre-cached snapshots locally rather than transmitting them across the network, significantly reducing transmission time while maintaining full migration capability.
Solution Approach 2:
Instead of transmitting complete service state snapshots across networks during migration, the system uses copying mechanisms where service states are replicated to storage systems at target locations. This copying approach enables service migration while minimizing network transmission time by using local storage caches and differential copying techniques.
Data Source
AI summary
Disclosed herein are a distributed cloud system, a data processing method of a distributed cloud system, and a storage medium. The data processing method of a distributed cloud system includes receiving a request of a user for an edge cloud and controlling a distributed cloud system, wherein the distributed cloud system comprises a core cloud including a large-scale resource, the edge cloud, and a local cloud including a middle-scale resource between the core cloud and the edge cloud, processing tasks corresponding to the user request through a scheduler of the core cloud, distributing the tasks based on a queue, and aggregating results of processed tasks, and providing processed data in response to a request of the user, wherein the distributed cloud system provides a management function in case of failure in the distributed cloud system.