Edge Data Node Container Routing for Distributed Service Scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In large-scale distributed content delivery networks, efficiently providing edge computing services in complex server clusters is challenging due to the need for caching, scheduling, computing, monitoring, and storage across numerous node servers.
Innovation Solution
A network edge computing method that involves receiving service requests, routing them to containers based on service ports, using a load balancing mechanism, and determining edge data node information for service requests, ensuring efficient processing and reliability through container migration and backup services.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a large-scale distributed content delivery network is used to provide edge computing services, then the service coverage and capacity are improved, but the system complexity and difficulty of management increase
Solution Approach 1:
The patent segments the edge computing services into independent containers that can be deployed and managed separately on different node servers. Each container encapsulates specific computing functions, allowing the large-scale network to be divided into manageable functional units that can be independently provisioned, monitored, and maintained across the distributed infrastructure
Solution Approach 2:
The patent introduces a gateway as an intermediary component that mediates between service requests and the containerized edge computing services. The gateway handles service routing, load balancing, and coordination across multiple node servers, simplifying the management complexity by providing a unified interface that abstracts the underlying distributed system
2Adaptability or versatility
If multiple services such as caching, scheduling, computing, monitoring, and storage are provided across numerous node servers, then the functionality and service quality are improved, but the operational complexity increases
Solution Approach 1:
The patent implements multi-functionality by designing containers that can perform multiple edge computing services including caching, scheduling, computing, monitoring, and storage. These universal container templates can be deployed across numerous node servers, allowing the same service functionality to be replicated and managed consistently across the entire distributed network through standardized operations
Solution Approach 2:
The patent uses container copying to replicate service functionality across multiple node servers. Instead of manually configuring each server, service containers are copied and deployed automatically across the distributed network, ensuring consistent service operations while reducing the complexity of managing multiple identical service instances across numerous servers
3Productivity
If service requests are routed to containers on node servers, then the edge computing service efficiency is improved, but the risk of service interruption due to server failure increases
Solution Approach 1:
The patent implements prior cushioning by pre-configuring backup containers and failover mechanisms before server failures occur. When a node server hosting edge computing containers experiences failure, the system automatically activates pre-prepared backup containers on other node servers, ensuring service continuity without interruption to end users
4Reliability
If containers are migrated between servers to ensure service continuity, then the reliability is improved, but the complexity of service management increases
Solution Approach 1:
The gateway acts as an intermediary that manages container migration between servers. When service continuity is required, the gateway coordinates the migration process, handling the complexity of stopping containers on source servers, transferring them to target servers, and restarting them. This abstracts the migration complexity from the overall system management
Data Source
AI summary
A network edge computing method includes receiving, by an edge data node, a service request at least processed by network edge computation scheduling; and routing, according to a service port involved in the service request, the service request to a container of the edge data node, to be processed by the container.