Edge Network Load Balancer for Accelerated Function Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current edge computing systems face challenges in efficiently managing service requests and load balancing across edge resources, leading to suboptimal performance and latency in processing tasks, especially in applications requiring real-time processing like autonomous vehicles.
Innovation Solution
A system for load balancing service requests in an edge network that includes an edge device, edge gateway, and network devices capable of communicating with edge resources, utilizing load balancer logic units to determine the most suitable compute devices for processing requests based on service level agreements and quality-of-service requirements, and employing accelerator devices for accelerated function execution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If service requests are distributed across multiple edge resources without intelligent load balancing, then resource utilization increases, but processing latency increases and service quality deteriorates
Solution Approach 1:
The load balancer logic unit continuously monitors service queue telemetry data including latency metrics, resource utilization, and performance indicators from edge devices. This feedback mechanism enables dynamic adjustment of request routing decisions to optimize both processing efficiency and latency, resolving the contradiction between distributing requests across multiple resources and maintaining low latency.
Solution Approach 2:
The system dynamically selects which edge device processes each service request based on real-time conditions such as current load, latency measurements, and resource availability. This dynamic routing approach allows the system to adapt to changing conditions, improving processing efficiency while minimizing latency by directing requests to the most suitable available resource.
2Speed
If traditional processors are used for all operations, then system simplicity is maintained, but processing speed and performance decrease
Solution Approach 1:
The system segments processing tasks by routing different types of service requests to appropriate processing resources. Standard requests are handled by traditional processors, while requests requiring accelerated processing are directed to AI/ML accelerator devices. This segmentation enables the system to achieve high processing speeds for suitable tasks while maintaining overall system manageability through clear routing rules.
Solution Approach 2:
The load balancer logic unit acts as an intermediary that intelligently routes service requests between traditional processors and AI/ML accelerator devices. This mediator component manages the complexity of having multiple processing types by providing a unified interface and decision-making layer, allowing the system to leverage accelerated processing speeds without overwhelming complexity.
3Reliability
If service requests are processed without considering service level agreements, then resource allocation is simplified, but service quality and reliability deteriorate
Solution Approach 1:
The system incorporates service level agreement parameters such as maximum latency thresholds, minimum service quality requirements, and reliability targets into the load balancing decision-making process. By changing the parameters considered in request routing from simple load metrics to SLA-aware metrics, the system achieves improved service reliability while managing complexity through parameter-based decision rules.
Data Source
AI summary
Technologies for load balancing on a network device in an edge network are disclosed. According to one embodiment, a network device receives, in the edge network, a request to access a function. The request includes one or more performance requirements. The network device identifies, as a function of an evaluation of the performance requirements and on monitored properties of each device associated with the network device, one or more of the devices to service the request. The network device selects one of the identified devices according to a load balancing policy and sends the request to the selected device.