Programmable Switch Workload Distribution for Far-Edge vRAN Traffic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional methods for distributing workloads in RANs, particularly in far-edge datacenters, incur high energy and capital costs, degrade end-to-end performance, and require additional physical space, making them unsuitable for meeting 5G performance requirements.
Innovation Solution
Distribute workloads to virtual RANs (vRANs) via programmable switches at far-edge cloud datacenters, leveraging real-time network information to dynamically redirect traffic to available vRANs based on packet headers, without the overheads of traditional server-based systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional server-based workload distribution is used, then load balancing can be achieved, but energy costs and capital costs increase significantly
Solution Approach 1:
The patent introduces a controller as an intermediary component that manages workload distribution across multiple servers. The controller receives workload distribution requests, determines optimal server assignments based on current server states, and redirects traffic accordingly. This intermediary approach enables intelligent load balancing without requiring each server to run resource-intensive load-balancing software, thereby reducing overall energy consumption while maintaining reliable workload distribution.
2Ease of operation
If dedicated servers running load-balancing software are used, then traffic allocation can be managed, but end-to-end performance degrades
Solution Approach 1:
The patent extracts the load-balancing functionality from individual servers and consolidates it into a dedicated controller. Instead of each server running load-balancing software that consumes server resources and degrades performance, the controller handles all traffic allocation decisions centrally. This extraction allows servers to focus solely on their primary processing functions, improving end-to-end performance while the controller maintains ease of traffic allocation management.
3Productivity
If traditional server-based systems are deployed, then workload processing can be achieved, but additional physical space is required
Solution Approach 1:
The patent makes the controller a multi-functional component that handles workload distribution, traffic redirection, and server state monitoring all in one device. By consolidating these functions into a single controller rather than requiring separate dedicated servers for each function, the system reduces the total physical space needed in the datacenter while maintaining full workload processing capability across multiple servers.
4Reliability
If workload redirection is implemented, then fault tolerance improves, but system complexity increases
Solution Approach 1:
The patent implements a feedback mechanism where the controller continuously monitors server states and uses this information to make intelligent workload distribution decisions. The controller receives feedback about server availability and performance, dynamically adjusts traffic routing to maintain fault tolerance, and redirects workloads around failed servers. This feedback-driven approach improves fault tolerance while keeping system complexity manageable through automated decision-making rather than complex manual configurations.
Data Source
AI summary
Aspects of the present disclosure relate to allocating workloads to vRANs via programmable switches at far-edge cloud datacenters. Traditionally, traffic allocation is handled by dedicated servers running load-balancing software. However, rerouting RAN traffic to such servers increases both energy and capital costs, degrades end-to-end performance, and requires additional physical space, all of which are undesirable or even infeasible for a RAN far-edge datacenter. Since switches are located in the path of data traffic, workflow policies can be designed to inspect packet headers of incoming traffic, evaluate real-time network information, determine available vRAN instances, and update the packet headers to steer the incoming traffic for processing. As network conditions change, the workflow policies enable the switch to dynamically redirect workloads to alternative vRANs for processing. As a result, RAN processing efficiency and fault tolerance are improved—even with changing network conditions and spikes in data traffic.