Packet Pair Transmission for Network Capacity Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for assessing network capacity during real-time communication sessions are inefficient, particularly in varying bandwidth conditions, as they require multiple resources and do not allow for quick determination of maximum capacity at session establishment.
Innovation Solution
A method and apparatus that transmit a stream of packet pairs to assess network capacity by determining if the number of packet pairs is above a threshold, and if not, configure future transmissions to include more packet pairs, causing temporary congestion to estimate link capacity early in a session.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to assess network capacity by monitoring all UDP/IP packets, then the assessment is comprehensive, but the process is time-consuming and cannot provide quick capacity determination at session establishment
Solution Approach 1:
The patent segments the packet stream into specific packet pairs for capacity assessment. Instead of analyzing all packets, it focuses on transmitting and monitoring specific pairs of packets (probe packets) to determine network capacity. This segmentation enables quick capacity assessment by concentrating measurement efforts on representative packet pairs rather than processing the entire packet stream comprehensively.
Solution Approach 2:
The patent performs preliminary capacity assessment actions at session establishment by transmitting packet pairs before normal data transmission begins. This preliminary action allows the network capacity to be determined in advance, enabling optimal transmission parameter selection before the actual communication session starts, thus avoiding time-consuming assessments during the session.
2Loss of time
If packet pairs are transmitted to assess network capacity, then the capacity can be determined quickly, but additional resources are required to inform the receiving terminal to expect packet pairs
Solution Approach 1:
The patent implements self-service by making the receiving terminal autonomously identify packet pairs through embedded markers within the packets themselves. The transmitting terminal inserts identification markers into probe packets, and the receiving terminal automatically detects these markers to recognize packet pairs without requiring external notification or additional control channel resources. This eliminates the need for separate signaling resources while enabling quick capacity assessment.
3Reliability
If the number of packet pairs is increased to ensure accurate capacity assessment, then the assessment becomes more reliable, but the transmission overhead increases
Solution Approach 1:
The patent applies partial action by transmitting a limited number of packet pairs sufficient for capacity assessment rather than continuously transmitting excessive packets. The system determines the minimum necessary number of packet pairs to achieve reliable capacity measurement, balancing assessment reliability with transmission overhead by using just enough probe packets to confidently determine network capacity without unnecessary redundancy.
Data Source
AI summary
There is provided an apparatus comprising: at least one processor; and a memory comprising code that, when executed on the at least one processor, causes the apparatus to: transmit, or arrange to transmit, a stream of packets to another apparatus; determine, at a first time, whether or not the number of packet pairs in the stream is above a threshold; and, if the number of packet pairs in the stream is determined to be below the threshold, configure future packet transmissions to the other apparatus to have more packet pairs.