Dynamic Backup PCE Load Balancing Across Network Domains
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Path computation elements (PCEs) become critical components in computer networks, and their failure or performance issues directly impact rerouting times of tunnels, especially in inter-domain scenarios where traffic is highly critical, and existing mechanisms struggle to maintain acceptable response times without cumbersome solutions like manually adding additional PCEs.
Innovation Solution
A dynamic PCE load-balancing mechanism where a backup PCE in a second domain is informed of path computation information from a first PCE, and bi-directional tunnels are established to allow the backup PCE to load balance service requests, effectively distributing the workload and maintaining performance even in failure scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a backup PCE is introduced to handle failures, then network reliability is improved, but the complexity of PCE management increases
Solution Approach 1:
The patent merges the functions of primary and backup PCEs into a unified load-balancing system. Multiple PCEs are combined to form a collaborative group that shares path computation responsibilities, where backup PCEs actively participate in handling requests alongside primary PCEs, transforming the traditional standby backup model into an active load-sharing architecture.
Solution Approach 2:
The patent enables PCEs to serve multiple functions simultaneously. Backup PCEs not only provide failover capabilities but also actively participate in load balancing and path computation for multiple domains. A single PCE can serve as backup for multiple primary PCEs and handle requests from multiple domains, reducing the overall number of PCEs needed while improving reliability.
2Loss of time
If manual configuration of additional PCEs is performed to maintain response times, then response time is improved, but ease of operation deteriorates
Solution Approach 1:
The patent establishes preliminary relationships between primary and backup PCEs in advance, creating pre-configured backup groups and defining backup relationships before failures occur. This preliminary setup includes pre-establishing trust relationships and backup configurations, so that when failures occur, the system can immediately activate backup PCEs without manual intervention or time-consuming configuration.
Solution Approach 2:
The patent implements self-service mechanisms where the PCE system automatically manages backup relationships and load balancing without manual configuration. The system autonomously detects failures, activates appropriate backup PCEs, and redistributes load based on current system state, eliminating the need for manual PCE addition and configuration while maintaining optimal response times.
3Device complexity
If path computation requests are concentrated on a single PCE, then device complexity is reduced, but productivity deteriorates due to overburdening
Solution Approach 1:
The patent segments the path computation workload across multiple PCEs organized in primary-backup groups. Instead of concentrating all requests on a single PCE, the system divides the computation load by routing requests to appropriate PCEs within each domain's backup group, enabling parallel processing and preventing any single PCE from becoming a bottleneck.
Solution Approach 2:
The patent implements dynamic load balancing where the system adapts to changing conditions in real-time. When PCEs become overloaded or failures occur, the system dynamically redistributes path computation requests among available PCEs in the backup groups, optimizing throughput based on current system state rather than using static load distribution.
Data Source
AI summary
In one embodiment, one or more path computation requests from path computation clients (PCCs) in a first network domain are received at a first border router (BR) arranged at the border of the first network domain and a second network domain. The first BR learns of a path computation element (PCE) in the second network domain. The PCE in the second network domain is informed of path computation information for the first network domain. One or more tunnels are established between the first BR and the PCE in the second network domain. One or more path computation requests from PCCs in the first network domain are passed from the first BR, through the one or more tunnels, to the PCE in the second network domain, to be serviced by the PCE in the second network domain using the path computation information for the first network domain.