Edge Computing Latency Adaptation via Service Layer Radio Application
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless network schedulers face challenges in providing low latency for latency-critical applications due to their best effort and fair scheduling approaches, leading to unacceptable variance in latency and jitter, which is detrimental for applications like autonomous vehicles and real-time gaming.
Innovation Solution
Implementing a method that selects an edge computing system near a base station to provision latency-critical applications, using a service layer radio application (SLRA) for real-time communication with the scheduler, and optimizing resource allocation based on current application requirements and cell conditions to minimize latency and jitter.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a best effort and fair scheduling approach is used by wireless network schedulers, then resource allocation is simple and fair, but latency variance and jitter become unacceptable for latency-critical applications
Solution Approach 1:
The patent applies local quality by differentiating scheduling strategies based on application type. Latency-critical applications receive dedicated scheduling with guaranteed low latency, while other applications use standard scheduling. This is implemented through QoS parameters and application-specific scheduling policies that provide tailored service quality for different traffic types.
Solution Approach 2:
The patent implements dynamics through real-time adaptation of scheduling parameters based on current network conditions and application requirements. The scheduler dynamically adjusts resource allocation, priority levels, and timing parameters to maintain optimal latency performance for critical applications while adapting to changing network load and conditions.
2Loss of time
If edge computing systems are deployed nearby base stations to reduce latency, then roundtrip-time is minimized, but system complexity increases
Solution Approach 1:
The patent applies universality by designing edge computing nodes that perform multiple functions: they serve as computing resources for latency-critical applications, act as network anchors for scheduling decisions, and function as data processing points. This multi-functionality reduces the need for separate dedicated components and simplifies the overall system architecture.
Solution Approach 2:
The patent merges the edge computing system with the existing wireless network infrastructure by integrating computing functions into base stations or co-locating them with network elements. This consolidation combines previously separate functions (network transmission and data processing) into unified nodes, reducing system complexity while maintaining low latency.
3Productivity
If resources are dynamically allocated based on real-time conditions, then latency is optimized for critical applications, but control complexity increases
Solution Approach 1:
The patent implements feedback mechanisms where the scheduler continuously monitors network conditions, application performance, and resource utilization. This feedback information is used to dynamically adjust scheduling decisions, ensuring optimal latency performance. The feedback loop includes metrics like packet delay, throughput, and queue status that trigger real-time scheduling adaptations.
Solution Approach 2:
The patent applies preliminary action by pre-configuring QoS parameters, scheduling policies, and resource reservations for latency-critical applications before they begin execution. This advance preparation includes establishing dedicated resource pools, pre-calculating scheduling priorities, and setting up buffer allocations, which reduces the complexity of real-time control decisions.
Data Source
AI summary
The present disclosure refers to a method comprising: a) selecting an edge computing system (212) of a plurality of edge computing systems each located nearby a respective base station (211) of a wireless network (110) and deployed and managed by a network provider, the selected edge computing system (212) being configured to provision at least one latency critical application (214) which is to be provided to at least one end user device (230) in a cell via the base station (211) serving the cell and located nearby the selected edge computing system (212), b) provisioning, at the selected edge computing system (212), the at least one latency critical application (214) and a service layer radio application (SLRA) (215) for communication with a scheduler associated with the base station (211); c) transferring transmission specific data in real time between the at least one latency critical application (214) and the scheduler associated with the base station (211) via the service layer radio application (SLRA) (215) which is implemented on both, the selected edge computing system (212) and the scheduler, and d) continuously optimizing allocation of resources in the cell by taking into account current status and operation requirements of the at least one latency critical application (214) and/or continuously optimizing current use of the resources in the cell by using those transmission specific data for adapting the at least one latency critical application (214) in real time to current conditions on the cell. The present disclosure also refers to an appropriate system and an appropriate computer-readable medium.