Automated Queue Weight Calculation for Fair Scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication network systems lack a systematic method to ensure fair and accurate weight allocation in fair scheduling schemes, particularly during changes in connections, leading to potential unfairness and inefficiencies in bandwidth distribution.
Innovation Solution
A method and system for automatically computing weights for fair scheduling schemes by using overbooking ratios to bias weight contributions, ensuring that connections with lower overbooking ratios receive greater weight, thereby maintaining fairness and efficiency in bandwidth allocation across multiple categories of service.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If service providers manually configure queue weights in fair scheduling schemes, then bandwidth allocation can be adjusted to reflect service priorities, but the system becomes complex and requires operator involvement that is time-consuming and error-prone
Solution Approach 1:
The system automatically computes queue weights using the formula Wi = Σ(αj·CIRj·[1-1/OVBCIRj] + βj·EIRj) without requiring operator intervention. The weights are self-adjusted based on connection parameters and overbooking ratios, eliminating manual configuration errors and time-consuming operations while maintaining precision through systematic calculation
Solution Approach 2:
The patent transforms the static manual weight configuration into dynamic parameter-driven automatic computation. By using connection parameters (CIR, EIR) and overbooking ratios (OVBCIR, OVBEIR) as input parameters, the system automatically adjusts queue weights to reflect current network conditions and service priorities, achieving both ease of operation and measurement precision
2Productivity
If service providers overbook bandwidth to maximize utilization, then link capacity is efficiently used, but during peak demand traffic volume exceeds link capacity causing buffer overflow and packet dropping
Solution Approach 1:
The system dynamically adjusts queue weights based on real-time connection parameters and overbooking ratios. During peak demand, the automatic weight computation adapts to current traffic conditions, ensuring that connections with lower overbooking ratios (higher priority) receive appropriate bandwidth shares, thereby maintaining reliability while maximizing utilization through flexible resource allocation
Solution Approach 2:
The patent implements a feedback mechanism where queue weights are continuously computed based on connection parameters and overbooking ratios. This feedback loop ensures that when traffic volume approaches link capacity, the scheduling algorithm automatically prioritizes connections with lower overbooking ratios, preventing buffer overflow and packet dropping while maintaining high bandwidth utilization
3Adaptability or versatility
If connections are added or removed from the link, then network flexibility is improved, but queue weights become unfair and inaccurate requiring manual reconfiguration
Solution Approach 1:
The system automatically recalculates queue weights whenever connections are added or removed, using the formula Wi = Σ(αj·CIRj·[1-1/OVBCIRj] + βj·EIRj). This self-service mechanism ensures weight fairness is maintained without manual reconfiguration, as the computation automatically reflects the current set of active connections and their parameters
Solution Approach 2:
The patent makes the weight configuration dynamic by continuously computing weights based on current connection parameters and overbooking ratios. When connections are added or removed, the system automatically adapts the queue weights to maintain fairness, eliminating the need for static manual configuration and ensuring accuracy reflects the current network state
Data Source
AI summary
A method for communication includes setting respective overbooking ratios for multiple categories of data traffic, and assigning respective bandwidth allocations to a plurality of connections for transmitting the data traffic in one or more of the categories over a network. The data traffic from the connections is coupled into respective queues, such that each of the queues is associated with one or more of the connections. Respective weights are computed for the queues responsively to the bandwidth allocations and to the overbooking ratios of the categories of the data traffic to be transmitted on the connections that are associated with each of the queues. A multiplexer multiplexes among the queues responsively to the respective weights so as to transmit the data traffic from the connections over a link in the network.