Packet Switching Queues With Adaptive Buffers for Bounded Delay
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network communication technologies struggle to enforce deterministic latency bounds in long distance scenarios without centralized control, especially in 5G networks, where traditional queuing mechanisms fail to provide consistent delay guarantees, making it difficult to meet DetNet requirements.
Innovation Solution
A network device with FIFO queues and a round-robin service policy, coupled with adaptable buffer capacities, allows for independent QoS and capacity trade-offs, enabling distributed latency management through threshold-based buffer adjustments and signaling protocols.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional queuing mechanisms (DiffServ) are used, then low latency can be provided, but deterministic latency bounds cannot be enforced
Solution Approach 1:
The patent implements dynamic buffer capacity adjustment where each network device can adapt its buffer capacity independently based on local conditions. This dynamic mechanism allows the system to maintain deterministic latency bounds by adjusting buffer sizes in response to threshold crossings, resolving the contradiction between low latency and deterministic guarantees
Solution Approach 2:
The patent changes the parameter of buffer capacity dynamically at each network device. By adjusting this key parameter based on local threshold crossings and using it in delay bound calculations, the system achieves deterministic latency enforcement without requiring centralized control, thus resolving the reliability/determinism issue while maintaining low latency
2Loss of time
If buffer capacity is increased to reduce latency, then delay bounds improve, but network capacity utilization deteriorates
Solution Approach 1:
The patent employs dynamic buffer capacity adjustment where each device independently adapts its buffer size based on local threshold crossings. This dynamic approach allows the system to optimize the trade-off between delay bounds and capacity utilization locally, avoiding the need for large fixed buffers while maintaining deterministic latency guarantees
Solution Approach 2:
The patent dynamically changes buffer capacity parameters at each network device based on local conditions and threshold crossings. This parameter adaptation enables each device to achieve optimal delay bounds while maintaining efficient capacity utilization, resolving the contradiction between these two performance metrics
3Reliability
If centralized control is implemented to enforce delay bounds, then deterministic latency can be guaranteed, but system complexity and scalability worsen
Solution Approach 1:
The patent segments the centralized control function into distributed autonomous decisions at each network device. Each device independently monitors its own buffer threshold crossings and adjusts its buffer capacity without requiring centralized coordination, thus maintaining deterministic delay guarantees while reducing system complexity and improving scalability
Solution Approach 2:
The patent implements self-service mechanisms where each network device autonomously manages its own buffer capacity based on local threshold crossings. This self-service approach eliminates the need for centralized control while maintaining deterministic latency bounds, resolving the contradiction between reliability and system complexity
Data Source
AI summary
Disclosed is a network device (1) for packet switching in accordance with a bounded end-to-end delay. The network device comprises a plurality (11) of n first-in first-out, FIFO, queues, being servable in accordance with a round-robin based service policy and a fixed packet processing time (T). A respective queue of the plurality is associated with a bounded delay (Dmax) depending on the service policy of the plurality of queues and being a function of an adaptable buffer capacity (Be) of the respective queue. The network device further comprises a processor (12), being configured to determine a threshold crossing of an extent of reservation of the buffer capacity of the respective queue; and to adapt the buffer capacity of the respective queue in accordance with the determined threshold crossing. This enables network devices of a network to trade off QoS and capacity locally in a distributed manner, without a centralized controller.