Adaptive Traffic Throttling via Peer Node Rate Computation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In computer networks, server farms face challenges in managing network traffic to prevent abuse of contracted transaction processing rates, leading to clogged traffic and reduced performance, which affects customer satisfaction.
Innovation Solution
Implementing adaptive throttling across multiple network nodes by obtaining traffic rate data from peer nodes, computing a maximum permissible rate, and using a gatekeeper module to govern the number of transactions admitted for processing, thereby controlling traffic on a period-by-period basis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traffic is not properly managed, then users can exceed their contracted transaction processing rate, but network traffic becomes clogged and transaction processing performance is reduced
Solution Approach 1:
The patent implements preliminary action by computing and setting maximum permissible rates for each network node before traffic arrives. The gatekeeper module uses these pre-computed rates to admit or reject transactions at the network node level, preventing congestion before it occurs rather than reacting to it after the fact. This proactive approach ensures that the total admitted traffic does not exceed the contracted processing rate while still allowing legitimate transactions to be processed.
2Stability of the object's composition
If adaptive throttling is implemented across multiple network nodes, then network stability is improved, but communication overhead between nodes increases
Solution Approach 1:
The patent applies segmentation by dividing the traffic management function into independent components at each network node. Each node autonomously computes its own maximum permissible rate based on peer node data, and the gatekeeper module independently enforces this rate locally. This segmentation eliminates the need for continuous centralized coordination, reducing communication overhead while maintaining overall network stability through distributed decision-making.
Solution Approach 2:
The system implements periodic action by having network nodes exchange traffic rate data at specific intervals rather than continuously. Each node computes maximum permissible rates based on periodically updated information from peers, and the gatekeeper module applies these rates in periodic cycles. This periodic approach maintains network stability through regular coordination while significantly reducing communication overhead compared to continuous interaction.
3Reliability
If a gatekeeper module is used to govern transactions admitted for processing, then traffic abuse is prevented, but device complexity increases
Solution Approach 1:
The patent implements self-service by enabling each network node to autonomously compute its own maximum permissible rate using data from peer nodes. The gatekeeper module at each node independently makes admission decisions based on locally-computed rates without requiring complex centralized control or manual configuration. This self-service approach enhances reliability through distributed decision-making while minimizing system complexity by eliminating the need for elaborate coordination mechanisms.
Data Source
AI summary
One embodiment of a method of throttling network traffic comprises obtaining traffic rate data from available peer network nodes; computing a maximum permissible rate for a network node based on the traffic rate data from the peer network nodes, wherein the maximum permissible rate represents a maximum number of transactions permitted to pass into that network node for processing during a current period; and employing the maximum permissible rate to govern a number of transactions admitted for processing by the network node in the current period.