WSS Mesh Network Dynamic Bandwidth Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data center networks face challenges in dynamically managing communication bandwidth, leading to inefficient resource utilization, increased energy consumption, and high hardware and management costs due to static oversubscription ratios and complex physical layouts.
Innovation Solution
A network system incorporating a wavelength selective switch (WSS) mesh network and dense wavelength division multiplexing (DWDM) multiplexers/de-multiplexers, coupled with a controller that dynamically allocates bandwidth based on communication demand, allowing for flexible configuration of the WSS mesh network and top-tier switches.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If static oversubscription ratios are used in data center networks, then hardware costs are reduced, but resource utilization efficiency deteriorates
Solution Approach 1:
The patent implements dynamic bandwidth allocation by replacing static oversubscription ratios with real-time configuration of wavelength selective switches. The system continuously monitors communication demands between server sets and dynamically adjusts bandwidth allocation, allowing the network to adapt to changing traffic patterns while maintaining cost-effective hardware utilization.
Solution Approach 2:
The system changes the parameter of bandwidth allocation from fixed to variable by using wavelength selective switching technology. Different wavelength channels can be dynamically assigned and reconfigured based on actual communication demands, enabling efficient resource utilization without requiring excessive hardware capacity.
2Productivity
If dynamic bandwidth allocation is implemented, then resource utilization efficiency is improved, but device complexity increases
Solution Approach 1:
The patent introduces a controller as an intermediary device that manages the complexity of dynamic bandwidth allocation. The controller receives communication demand information, determines appropriate wavelength configurations, and controls the wavelength selective switches accordingly, thereby simplifying the overall system architecture while enabling dynamic resource allocation.
Solution Approach 2:
The system replaces manual or mechanical network configuration with automated optical switching control. The wavelength selective switches are programmatically controlled based on monitored communication demands, substituting complex manual configuration processes with automated optical signal routing.
3Power
If more physical links are added to handle communication demand, then bandwidth capacity is improved, but hardware costs and energy consumption increase
Solution Approach 1:
The patent makes existing physical links multi-functional by enabling dynamic reconfiguration of wavelength channels. The same physical infrastructure can serve different communication pairs at different times by changing wavelength assignments, thereby providing increased bandwidth capacity without adding more physical links or hardware.
Solution Approach 2:
The system adds the dimension of wavelength multiplexing to the physical network infrastructure. By utilizing multiple wavelength channels on existing fiber links, the network achieves higher bandwidth capacity without increasing the physical number of links, effectively moving from a two-dimensional (spatial) to a three-dimensional (spatial + spectral) network architecture.
4Adaptability or versatility
If wavelength selective switches are deployed, then network scalability is improved, but device complexity increases
Solution Approach 1:
The patent segments the network switching function into multiple wavelength selective switches, each handling specific wavelength channels. This segmentation allows the network to scale by adding individual WSS units rather than replacing entire switching fabrics, thereby improving scalability while managing complexity through modular deployment.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution enables efficient use of computing resources, reduces energy consumption, and enhances network scalability by allowing dynamic allocation of communication bandwidth, thereby reducing physical links and hardware costs.
Implementation Method 1
multiple dense wavelength division multiplexing (DWDM) multiplexers/de-multiplexers
Implementation Method 2
wavelength selective switch (WSS) mesh network includes a plurality of WSS components. Each WSS component includes a common port and multiple switching ports
Data Source
AI summary
According to at least one aspect, a network system includes a wavelength selective switch (WSS) mesh network, multiple dense wavelength division multiplexing (DWDM) multiplexers/de-multiplexers, and a controller. The WSS mesh network includes a plurality of WSS components. Each WSS component includes a common port and multiple switching ports. The plurality of WSS components are coupled to each other through corresponding switching ports. Each DWDM multiplexer/de-multiplexer is coupled to one of multiple sets of servers via a respective top tier switch and respective aggregation nodes and coupled to a common port of a WSS component of the WSS mesh network. The controller is configured to obtain indications of communication bandwidth demand for communications between the multiple sets of servers, determine a configuration for the WSS mesh network based on the obtained indications of communication bandwidth demand, and cause the WSS components and the top tier switches to be configured according to the determined configuration.