Software Defined Prober Adaptive Network Delay Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network delay measurement methods are inflexible and costly, as they often require complex computations for routing probe packets and cannot effectively detect delays on individual links in communication networks, leading to inefficient resource usage and delayed detection of congestion issues.
Innovation Solution
A software-defined prober (SD prober) that uses a pseudo-random walk of probe packets with binary exponential backoff to adaptively measure network delays, adjusting weights based on historical measurements to focus more probes on delay-prone regions, thereby reducing measurement costs and improving detection efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If complex computations are used for routing probe packets, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent uses simple, lightweight probe packets that can be quickly generated and discarded, replacing complex routing computations with simple probabilistic forwarding based on weight values. Each probe packet carries minimal information and follows straightforward forwarding rules, making the measurement process computationally inexpensive while maintaining adequate precision through statistical aggregation of multiple probes.
Solution Approach 2:
The patent changes the routing parameter from complex path computation to simple weight-based probabilistic selection. By representing link quality as a single weight value that can be adjusted dynamically, the system simplifies the routing decision process while still achieving precise delay measurements through adaptive weight adjustment based on observed network conditions.
2Measurement precision
If probe packets are sent via random and shortest paths, then measurement coverage is improved, but measurement costs increase
Solution Approach 1:
The patent applies different probing strategies to different parts of the network by assigning specific weight values to different links based on their characteristics and historical performance. Instead of uniformly probing all paths, the system concentrates measurement resources on links with higher weights (indicating potential delay issues), achieving better local detection coverage while reducing overall measurement costs.
Solution Approach 2:
The patent uses a sufficient number of probe packets to achieve reliable delay measurements without sending excessive probes. By using binary exponential backoff to adjust the number of probes based on observed conditions, the system sends enough probes to accurately measure delay on critical links while avoiding waste on links that are clearly performing well, optimizing the trade-off between measurement coverage and cost.
3Adaptability or versatility
If binary exponential backoff is used to adjust link weights, then adaptability is improved, but device complexity increases
Solution Approach 1:
The patent implements dynamic adaptability through binary exponential backoff, which automatically adjusts the probing intensity and link weight selection based on observed network conditions. When delays are detected, the system increases probing on affected links; when conditions improve, it reduces probing. This dynamic adjustment provides high adaptability to changing network conditions while using a relatively simple algorithmic approach.
Solution Approach 2:
The patent uses feedback from observed delay measurements to adjust link weights and future probe routing decisions. The binary exponential backoff mechanism incorporates feedback by doubling the probe count (or adjusting weights) when delays are detected and halving it when conditions improve, creating a simple but effective closed-loop control system that adapts to network conditions without requiring complex algorithms.
Data Source
AI summary
In one embodiment, a method includes determining, by one or more processors, a weight of a link between a first node and a second node of a network, wherein the weight is proportional to a probability value of forwarding a probe packet from the first node to the second node of the network. The method also includes adjusting, by the processors, the weight of the link between the first node and the second node using binary exponential backoff. The method further includes determining, by the processors, to forward the probe packet to the second node of the network based on the adjusted weight of the link and one or more field values of the probe packet.