In-Band Signaling for In-Network Computing in Mobile Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile communication systems face challenges in efficiently controlling and managing in-network computing resources in network devices due to the absence of technical elements that can combine data centers and mobile communication systems with different application environments, making it difficult to utilize the capabilities of network/transport layers for application calculations.
Innovation Solution
A method and apparatus for controlling and managing in-network computing through in-band signaling, which involves identifying computing resources, determining tasks, and allocating them to network devices within a data transmission path without the need for a software-defined networking (SDN) controller, using a first network entity in the control plane to request, receive, and monitor computing capabilities and tasks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If in-network computing is implemented in mobile communication systems, then application processing speed and resource utilization are improved, but signaling overhead and system complexity increase
Solution Approach 1:
The patent segments the computing system into multiple network devices distributed along the data transmission path, allowing computing tasks to be performed at different locations in the network. This segmentation enables parallel processing and improves application processing speed while distributing system complexity across multiple manageable components rather than concentrating it in a single controller
Solution Approach 2:
The patent introduces an intermediary mechanism (in-band signaling embedded in data packets) that allows network devices to autonomously exchange computing capability information and task allocation data without requiring a separate SDN controller. This intermediary approach reduces signaling overhead and simplifies the overall system architecture by eliminating the need for complex external control infrastructure
2Productivity
If in-network computing tasks are allocated to multiple network devices, then resource utilization is enhanced, but task management and coordination become more difficult
Solution Approach 1:
The patent enables network devices to autonomously manage their own computing task execution by embedding task allocation information directly in data packets that traverse the network. Each network device can independently process tasks based on its own computing capabilities and current load conditions, eliminating the need for complex centralized task management and coordination mechanisms
Solution Approach 2:
The patent implements feedback mechanisms where network devices report their computing capability information and task execution status back through the data transmission path. This feedback enables dynamic task reallocation and load balancing across the network, allowing the system to adapt to changing conditions and maintain high resource utilization without requiring complex manual intervention
3Extent of automation
If traditional SDN controller architecture is used for in-network computing control, then centralized management is achieved, but signaling overhead increases
Solution Approach 1:
The patent merges the control plane and data plane by embedding task allocation and capability exchange signaling directly within the data transmission path. This merging eliminates the need for separate control signaling channels to and from a centralized SDN controller, significantly reducing signaling overhead while maintaining automated task management through in-band communication protocols
Data Source
AI summary
The present disclosure relates to a method performed by a first network entity on a control plane in a mobile communication system. The method comprises the steps of: transmitting a first message requesting in-network computing (INC)-capable information for a plurality of devices on a data transmission path; receiving, on the basis of the first message, a second message including the capable information for the plurality of devices; determining, on the basis of the second message, one or more target devices on which in-network computing is to be performed, from among the plurality of devices; and assigning in-network computing tasks to the one or more target devices, respectively.