Hybrid Circuit-Packet Switched Network Architecture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network architectures face inefficiencies in supporting both time-critical and time-uncritical data transmissions, as packet-switched networks struggle with latency and circuit-switched networks face bottlenecks in reconfiguration and multicast communications.
Innovation Solution
A reconfigurable network architecture with a switched-tree configuration, where switching modules can dynamically switch between circuit-switched and packet-switched modes, allowing for flexible grouping and resource allocation to adapt to changing operational requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a packet-switched network is used to transmit time-critical data streams, then flexibility and resource sharing are improved, but latency and data loss increase due to packet collisions and header processing overhead
Solution Approach 1:
The network architecture dynamically reconfigures switching modules between packet-switched and circuit-switched modes based on real-time traffic requirements. This allows the system to adapt its switching behavior dynamically, using packet-switching for flexible data transmission and circuit-switching for time-critical streams, thereby resolving the contradiction between flexibility and latency.
Solution Approach 2:
The invention changes the operational parameter of switching modules from a fixed mode to a variable mode that can switch between packet-switched and circuit-switched operations. This parameter change enables the network to optimize performance for different traffic types, reducing latency for time-critical data while maintaining flexibility for other communications.
2Reliability
If a circuit-switched network is used to transmit time-uncritical data between multiple un-paired nodes, then transmission reliability is improved, but controller bottleneck and reconfiguration delays increase due to limited controllers managing many switches
Solution Approach 1:
The network is segmented into multiple switching modules that can operate independently in different modes. This segmentation distributes the control burden and allows parallel operation of multiple switches without requiring centralized controller intervention for every reconfiguration, thereby improving both reliability and reconfiguration speed.
Solution Approach 2:
Switching modules are designed with multi-functionality, capable of operating in both circuit-switched and packet-switched modes. This universality allows the same hardware to handle different traffic types efficiently, improving productivity by eliminating the need for dedicated circuit-switched infrastructure while maintaining transmission reliability when needed.
3Reliability
If a circuit-switched network is used for multi-cast communications, then dedicated path reliability is improved, but network complexity and controller burden increase significantly
Solution Approach 1:
The network dynamically selects between circuit-switched and packet-switched modes for multi-cast communications based on requirements. For applications needing dedicated path reliability, circuit-switching is activated; for others, packet-switching suffices. This dynamic approach maintains reliability when necessary while reducing controller complexity by avoiding unnecessary circuit-switched configurations.
4Productivity
If separate packet-switched and circuit-switched networks are implemented to meet diverse requirements, then performance optimization is improved, but hardware cost and system complexity increase
Solution Approach 1:
The invention merges packet-switched and circuit-switched networks into a single unified architecture where switching modules can operate in either mode as needed. This consolidation eliminates the need for separate physical networks, reducing hardware costs and system complexity while maintaining performance optimization through dynamic mode selection.
Solution Approach 2:
Switching modules are designed as universal components capable of performing both packet-switching and circuit-switching functions. This multi-functionality allows a single network infrastructure to meet diverse performance requirements, optimizing productivity without requiring separate specialized networks, thereby reducing overall system complexity and hardware investment.
Data Source
AI summary
A dynamically reconfigurable network architecture includes a plurality of switching modules arranged in an ordered, multi-level, switched-tree configuration. A network is formed by selecting one switching module as the root and assigning it and all directly or indirectly subsidiary modules to the network. The operating mode of each switching module can be dynamically selected as either circuit-switched or packet-switched. The modules can be grouped into a single network or into a plurality of separate networks operating in parallel, including both circuit-switched and packet-switched networks. When a network is no longer needed, its operation can be halted and its resources released for reassignment to other networks. In embodiments, a selector controlled by allocation registers selects either a circuit-switching sequencer or a packet connection arbitration circuit to control the switching circuits. Switching modules can include crossbar switches. Circuit-switched connections can use TDM to share allocated physical resources.