Dynamic Weighted-Fair Load-Balancing for Network Traffic Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current load-balancing techniques in computer networks are inefficient as they do not account for dynamic link attributes such as bandwidth, delay, and error rates, leading to unfair distribution of traffic across equal cost multiple paths.
Innovation Solution
Implementing dynamic weighted-fair load-balancing by using dynamic link utilization information to determine the amount of traffic to forward over each equal cost best path, with the forwarding node adjusting traffic based on real-time link conditions without altering the shortest path first algorithm.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If equal cost multiple paths are used for load-balancing, then traffic distribution is improved, but fairness among paths is worsened due to unequal link attributes
Solution Approach 1:
The patent changes the parameter of traffic distribution by introducing dynamic weights based on link attributes (bandwidth, delay, error rates) instead of equal distribution. The forwarding node calculates a weight for each path proportional to its available bandwidth and adjusts traffic forwarding accordingly, transforming the static equal-cost model into a dynamic attribute-aware model that resolves the fairness issue while maintaining productivity benefits
Solution Approach 2:
The patent applies dynamics by making the load-balancing weights adaptive and time-varying rather than static. The forwarding node continuously monitors link utilization and dynamically adjusts the weight of each path based on current network conditions, allowing the system to respond to changing bandwidth availability, delay, and error rates, thereby achieving fair load-balancing under varying conditions
2Reliability
If dynamic link utilization information is collected and processed, then load-balancing fairness is improved, but system complexity is worsened
Solution Approach 1:
The patent implements feedback by having the forwarding node continuously monitor link utilization information and use this feedback to dynamically adjust traffic distribution weights. The system collects real-time data on bandwidth, delay, and error rates, processes this information to calculate appropriate weights, and applies these weights to subsequent forwarding decisions, creating a closed-loop control system that improves fairness without requiring complex manual configuration
Solution Approach 2:
The forwarding node performs self-service by autonomously calculating path weights and adjusting traffic distribution based on monitored link attributes without external intervention. The node independently evaluates its own egress links, determines the best paths, and dynamically reallocates traffic, eliminating the need for manual configuration changes or complex external control mechanisms
Data Source
AI summary
In one embodiment, a node identifies a plurality of equal cost best paths to a destination, the best paths having one or more associated links. The node receives dynamic link utilization information for the associated links, and determines an amount of traffic to the destination to forward over each of the equal cost best paths, the amount being dynamically dependent upon the dynamic link utilization of the associated links for each equal cost best path.