6G Service Plane Architecture for Low-Latency Distributed Computing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face challenges in reducing latency, distributing data processing pipelines across devices, networks, and clouds, enabling distributed computing at scale, dynamically scaling computing for user equipment, leveraging AI/ML for network and air interface, and addressing diverse vertical requirements efficiently and cost-effectively, while ensuring security, privacy, and data integrity.
Innovation Solution
A 6G system architecture with three service planes (Compute, Data, and Communication) and three function planes (Control, User, and Management) is introduced, featuring dynamic device-network computing scaling, RDMA over radio, cloud workload offloading, computing-embedded air interface, and service chain aware transport, along with AI capabilities to enhance performance and sustainability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If data processing is centralized in cloud data centers, then computing power is sufficient, but latency increases and energy consumption rises
Solution Approach 1:
The patent segments the centralized cloud computing architecture into a hierarchical distributed structure with cloud data centers, regional cloud edges, and network edges. This segmentation brings computing resources closer to users, reducing data transmission distance and latency while maintaining sufficient computing power through coordinated operation across multiple segments.
Solution Approach 2:
The patent introduces a spatial dimension to computing resource distribution by creating a three-tier hierarchical architecture (cloud, edge, network edge). This dimensional expansion allows computing tasks to be executed at multiple locations simultaneously, reducing latency without requiring all processing to occur locally at the network edge.
2Productivity
If computing resources are distributed across devices and networks, then latency is reduced, but system complexity increases
Solution Approach 1:
The patent creates a universal service orchestration framework that manages diverse computing resources across cloud, edge, and network layers through standardized interfaces and protocols. This multi-functional orchestration system handles task allocation, resource management, and coordination uniformly across the entire distributed architecture, reducing the perceived complexity for individual components.
Solution Approach 2:
The patent introduces service orchestration and chaining functions as intermediary layers between user devices and distributed computing resources. These intermediaries abstract the complexity of resource management and task coordination, providing simplified interfaces while enabling efficient distributed computing across multiple layers of the architecture.
3Speed
If computing power is increased for better performance, then processing speed improves, but energy consumption increases
Solution Approach 1:
The patent implements dynamic service chaining that adapts computing resource allocation and processing locations based on real-time conditions such as task requirements, network status, and energy constraints. This dynamic approach allows the system to optimize the balance between processing speed and energy consumption by selecting the most efficient execution path for each specific task.
Solution Approach 2:
The patent changes the operational parameters of computing resources by introducing heterogeneous processing capabilities across different layers (cloud, edge, network edge) with varying power consumption characteristics. The service orchestration selectively adjusts which parameters (processing location, resource type, task partitioning) to use based on the specific requirements, enabling optimized trade-offs between speed and energy usage.
Data Source
AI summary
Various embodiments herein provide techniques related to sixth generation (6G) system architecture and functions. For example, embodiments may relate to one or more of: Design principle and system architecture; Orchestration frontend service; Dynamic device-network computing scaling; RDMA over radio; Cloud workload offloading to network; Computing-embedded air interface; Service chain aware transport; and/or Enabling AI capabilities. Other embodiments may be described and/or claimed.