Latency-Aware Mobile Edge Computing Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile networks face challenges in maintaining low latency required by applications like autonomous driving and augmented reality, as network congestion increases latency, and existing solutions fail to dynamically adjust processing locations based on real-time latency measurements.
Innovation Solution
Implementing a latency-aware mobile edge computing routing system that uses latency measurements to dynamically determine the optimal location within the network for processing applications, utilizing computing resources deployed at various network locations, including near the user equipment and the core network, to ensure target latency specifications are met.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If computing resources are centralized in the core network, then device complexity is reduced, but network latency increases due to congestion and distance
Solution Approach 1:
The patent segments the centralized core network computing resources into distributed edge computing nodes deployed at multiple network locations (base stations, access points, and core network locations). This segmentation allows applications to be processed closer to user equipment, reducing network latency while maintaining manageable device complexity through modular deployment
Solution Approach 2:
The patent introduces a new spatial dimension for computing resource deployment by placing edge computing nodes at multiple network locations along the network path between user equipment and the core network. This dimensional expansion enables dynamic selection of processing locations based on latency requirements, resolving the contradiction between centralized simplicity and distributed performance
2Loss of time
If edge computing nodes are deployed throughout the network, then network latency is reduced, but device complexity increases
Solution Approach 1:
The patent designs edge computing nodes with universal functionality that can handle multiple application types and workloads. Each node is capable of performing general-purpose computing tasks, allowing a single node deployment to serve diverse application requirements. This multi-functionality reduces the number of specialized nodes needed, thereby limiting the increase in device complexity while maintaining low latency benefits
Solution Approach 2:
The patent dynamically changes operational parameters of edge computing nodes based on network conditions and application requirements. The latency-aware routing controller adjusts which nodes are active, their processing priorities, and resource allocation in real-time. This dynamic parameter adjustment allows the system to adapt to changing conditions without requiring permanent complex infrastructure, effectively managing device complexity
3Device complexity
If processing location is fixed, then device complexity is reduced, but adaptability to network conditions deteriorates
Solution Approach 1:
The patent implements dynamic processing location selection through a latency-aware routing controller that continuously monitors network latency conditions and adjusts application routing in real-time. The system dynamically determines the optimal edge computing node for each application based on current network conditions, transforming the static processing location into a dynamic, adaptive parameter. This dynamics capability allows the system to respond to changing network conditions without requiring complex manual reconfiguration
Solution Approach 2:
The patent establishes a feedback loop where the latency-aware routing controller continuously measures actual network latency, compares it against target latency requirements, and adjusts routing decisions accordingly. This closed-loop feedback mechanism enables automatic adaptation to network conditions, improving versatility while keeping control complexity manageable through rule-based decision algorithms
Data Source
AI summary
A location for application processing is selected based on latency measurements associated with a mobile network. Instead of performing application processing at a predetermined location within a network, the application processing for an application is located within the network based on latencies measured within the network as well as other considerations. For instance, the determination of the location within the network can be based on latency measurements, target latency specifications of an application, the availability of computing resources at a location, and the like. A latency aware routing controller selects one or more locations to perform application processing. The locations may include computing resources located at or near the wireless base station (BS), between the base station and other locations within the network, at the core network, at the Internet, and/or at other locations to provide applications with the computing resources to perform the application processing.