Micro-broker Communication Modes in Stream Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Stream processing platforms face challenges in efficiently managing data communications between operators due to limitations in existing communication modes, which do not effectively adapt to relative locations, operator characteristics, and stream popularity, leading to suboptimal performance and resource utilization.

Innovation Solution

The implementation of micro-brokers that determine and support various communication modes such as shared queues, shared memory, point-to-point connections, or message brokers based on the relative locations and popularity of data streams, using instructions from a platform controller and network quality information to optimize data transmission between operators.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a single communication mode is used for all operator communications, then system complexity is reduced, but communication efficiency and resource utilization deteriorate

Engineering Contradiction:
Improvecommunication mode managementVSAvoiddata communication efficiency
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The system dynamically selects communication modes (shared queue, shared memory, point-to-point connection, or message broker) based on real-time conditions including relative operator locations, stream popularity, and network quality. This dynamic adaptation resolves the contradiction by allowing the system to optimize communication efficiency for each specific scenario while maintaining manageable complexity through automated mode selection.

Inventive Principle:
Principle #15Dynamics

2Productivity

If micro-brokers dynamically determine communication modes based on multiple factors, then communication efficiency improves, but system complexity increases

Engineering Contradiction:
Improvedata transmission efficiencyVSAvoidmicro-broker decision logic
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The micro-broker incorporates feedback mechanisms that continuously monitor stream popularity, operator locations, and network quality to inform communication mode selections. This feedback-driven approach enables efficient adaptive decision-making without requiring overly complex manual configuration, as the system learns and adjusts based on observed performance metrics.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The micro-broker acts as an intermediary component that centralizes the complex decision-making logic for mode selection. By isolating this complexity in a dedicated intermediary component rather than distributing it throughout the entire system, the patent manages overall system complexity while still achieving dynamic optimization of communication efficiency.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If traditional message brokers are used for all communications, then communication reliability is maintained, but latency and resource utilization worsen

Engineering Contradiction:
Improvecommunication reliabilityVSAvoidcommunication latency
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system applies different communication modes tailored to specific local conditions: shared memory for co-located operators on the same host, shared queues for operators on different hosts, and message brokers for distributed systems. This local quality approach ensures reliability is maintained where needed while minimizing latency by using more direct communication paths when conditions permit.

Inventive Principle:
Principle #3Local quality

Data Source

PatentUS10812606B2Supporting communications in a stream processing platform
Publication Date: 2020.10.20 NOKIA SOLUTIONS & NETWORKS OY
  • US10812606B2 patent drawing
  • US10812606B2 patent drawing
  • US10812606B2 patent drawing

AI summary

Various example embodiments for supporting communications for stream processing platforms are described. Various example embodiments for supporting communications in a stream processing platform may be configured to use micro-brokers to support communications in a stream processing platform by providing micro-brokers configured to support communications between operators of operator groups of the stream processing platform. Various example embodiments for supporting communications in a stream processing platform may be configured to use micro-brokers to support communications in the stream processing platform by providing micro-brokers configured to support communications between operators of operator groups of the stream processing platform using various communication modes (e.g., shared queues for communications between operators of the same operator group, shared memory of a host computer for communications between operators of different operator groups in the same host computer, point-to-point connections or message brokers for communications between operators in different host computers, or the like) based on various considerations.