5G Network Function Placement Across Specialized Compute Instances
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computing systems in 5G networks are often configured monolithically, leading to inefficient use of computational resources, increased costs, and decreased network quality due to the lack of intelligent resource allocation.
Innovation Solution
A computing system with separate compute instances configured for processor-heavy and high-throughput tasks, dynamically scaling network functions based on demand, allowing for optimized resource allocation and improved performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If computing resources are configured in a monolithic way, then system simplicity is maintained, but computational resource efficiency decreases and costs increase
Solution Approach 1:
The patent segments computing resources into different compute instances with specialized configurations (e.g., compute instances optimized for processor-heavy network functions versus those optimized for high-throughput functions). This segmentation allows each compute instance to be tailored to specific workload requirements, improving overall computational resource efficiency while maintaining manageable system complexity through standardized segmentation categories.
2Reliability
If computing resources are configured in a monolithic way, then deployment simplicity is maintained, but network quality decreases
Solution Approach 1:
The patent applies local quality by configuring different compute instances with locally optimized properties matched to specific network function requirements. For example, compute instances are configured with specific CPU, memory, or storage characteristics depending on the particular network function being executed, ensuring that each local component operates at optimal performance for its intended purpose while contributing to overall network quality.
3Productivity
If compute instances are specialized for specific functions, then functional performance is improved, but system flexibility decreases
Solution Approach 1:
The patent implements dynamics by enabling the system to dynamically select and scale appropriate compute instances based on current network demands. The system can dynamically allocate specialized compute instances to specific network functions as needed, allowing the architecture to adapt to varying workloads while maintaining high performance through specialized hardware configurations.
Solution Approach 2:
The patent achieves universality by creating a multi-functional computing platform that can support multiple types of network functions through standardized interfaces and protocols. While individual compute instances are specialized, the overall system can accommodate diverse network functions (processor-heavy, high-throughput, memory-intensive) by deploying appropriate compute instance types, thus maintaining versatility.
4Productivity
If network functions are dynamically scaled, then resource allocation efficiency is improved, but system complexity increases
Solution Approach 1:
The patent applies feedback mechanisms that enable the system to monitor network function performance and demand in real-time, automatically adjusting compute instance allocation accordingly. This feedback-driven dynamic scaling improves resource allocation efficiency by ensuring compute resources are allocated based on actual usage patterns while reducing manual management complexity through automated decision-making.
Data Source
AI summary
The disclosed technology includes determining, based at least in part on a first set of properties, a first group of network functions; determining, based at least in part on the second set of properties, a second group of network functions; instantiating the first group of network functions on one or more of compute instances of a first set of compute instances, the first set of compute instances characterized at least in part by the first set of properties; instantiating the second group of network functions on one or more of the compute instances of a second set of compute instances, the second set of compute instances characterized at least in part by the second set of properties; and providing 5G cellular service to a user equipment using at least some of the first group of network functions and the second group of network functions.