Distributed Analytics Server Selection in SDN
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
As software-defined networking (SDN) systems handle increasing amounts of data for advanced analytics, they face computational burdens and potential overloads, making it cumbersome to manage and process analytics tasks efficiently, especially as networks scale up.
Innovation Solution
Distributing analytics tasks to analytics servers rather than processing them centrally, with the controller selecting suitable servers based on data routing and availability, and adapting protocols for efficient data collection and processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If analytics tasks are processed centrally by the SDN controller, then comprehensive network analytics can be achieved, but the controller becomes overloaded and processing efficiency decreases
Solution Approach 1:
The patent segments analytics tasks from centralized processing and distributes them to multiple analytics servers throughout the network. Each server handles specific analytics tasks locally, dividing the overall analytics workload into manageable segments that can be processed in parallel, thereby maintaining comprehensive analytics capability while improving processing efficiency and preventing controller overload.
Solution Approach 2:
The patent transitions from a single-dimensional centralized processing model to a multi-dimensional distributed architecture. Analytics servers are positioned at different network locations (access, aggregation, core layers), creating spatial distribution across multiple dimensions. This dimensional change allows analytics processing to occur closer to data sources, reducing controller burden while maintaining comprehensive network visibility.
2Productivity
If more analytics tasks are distributed to analytics servers, then processing load on controller is reduced, but system complexity increases
Solution Approach 1:
The patent creates a universal analytics server architecture that can handle multiple types of analytics tasks (traffic analysis, security monitoring, quality of service, etc.). These multi-functional servers can be deployed at different network levels and can perform various analytics functions, reducing the need for specialized devices and simplifying system management despite the distributed nature of the architecture.
Solution Approach 2:
The patent introduces standardized communication protocols and interfaces as intermediaries between the SDN controller and analytics servers. These intermediaries manage the complexity of distributed task distribution, data collection, and result aggregation, allowing the controller to interact with multiple servers through a unified interface rather than managing each server individually, thus reducing perceived system complexity.
3Reliability
If analytics data is collected from all network nodes, then complete analytics coverage is achieved, but communication bandwidth is consumed and transmission time increases
Solution Approach 1:
The patent implements local quality by positioning analytics servers at different network locations (access, aggregation, core layers) and assigning them specific analytics tasks based on their location and capabilities. Each server processes analytics data locally at its position in the network hierarchy, providing complete analytics coverage through distributed intelligence rather than centralized collection, thereby reducing data transmission time and bandwidth consumption.
Data Source
AI summary
Distributed management of analytics tasks in a programmable network (100) having a controller (SDNC, 10, 11), a plurality of network nodes (20, N1-N5) coupled to the controller by a Data Communications Network DCN, and a plurality of analytics servers (30) each coupled to a network node, involves the controller selecting which of the analytics servers to use for an analytics task. The selection is based on how data logged by respective ones of the network nodes and needed for that analytics task, can be routed to the analytics servers. The controller sends to the selected analytics server, an indication of the analytics task and an indication of what data logged by the network nodes is to be used in the analytics task.