Programmable Switch Load Balancing for Virtualized RAN Workloads
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The integration of cloud networks with radio access networks (RAN) in virtualized environments faces challenges in efficiently utilizing server resources, leading to potential workload overload, processing delays, and increased energy consumption, particularly in far-edge datacenters with limited space and power capacity.
Innovation Solution
Implementing programmable switches at far-edge datacenters to monitor and balance workloads in real-time by leveraging real-time network information, enabling dynamic workload redistribution across servers without the overhead of traditional server-based systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional server-based workload management is used in vRAN, then processing capacity can be increased, but system complexity and energy consumption increase
Solution Approach 1:
The patent extracts the workload management function from the server domain and places it in the data plane (network infrastructure). The programmable switch independently monitors and balances workloads without requiring server-based management systems, thereby reducing system complexity while maintaining processing capacity.
Solution Approach 2:
The patent introduces a programmable switch as an intermediary component between radio units and servers. This switch actively monitors workload metrics and dynamically redistributes traffic to prevent overload, providing intelligent workload management without the complexity of server-based control systems.
2Reliability
If more server resources are allocated to handle peak workloads, then processing reliability is improved, but energy consumption and space requirements increase
Solution Approach 1:
The patent implements dynamic workload balancing where the programmable switch continuously monitors workload metrics and redistributes traffic in real-time based on current server capacity. This allows the system to adapt to varying load conditions without requiring permanently allocated server resources, reducing energy consumption while maintaining reliability.
Solution Approach 2:
The patent performs preliminary workload balancing by proactively monitoring workload metrics and redistributing traffic before servers become overloaded. This preventive approach avoids processing delays and data loss without requiring excess server capacity to be constantly available.
3Measurement precision
If workload monitoring and balancing is performed in the control plane, then decision accuracy is improved, but processing time increases
Solution Approach 1:
The patent moves workload monitoring and balancing operations from the control plane to the data plane. This dimensional shift allows the programmable switch to monitor and balance workloads in real-time as traffic flows through it, eliminating the time delay associated with control plane processing while maintaining accurate workload detection through direct observation of data traffic.
Data Source
AI summary
During a first transmission time interval (TTI) of a vRAN, data traffic between a radio unit (RU) of a cellular network and a first vRAN instance of the vRAN is monitored. The first vRAN instance executes on a first server of the vRAN and the first vRAN instance is configured to perform PHY layer processing and L2 processing of the data traffic. Based on the data traffic between the RU of the cellular network and the first vRAN instance during the first TTI, a workload at the first vRAN instance during a second TTI is estimated.