Data Processing Velocity Control for Stream Systems

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Data stream processing systems face challenges in managing non-uniform data stream velocities, leading to potential data loss and reduced reliability due to exceeding processing capabilities during peak data influx, especially in applications like financial services and telecommunications.

Innovation Solution

A data processing method that predicts traffic peaks using historical data, adjusts data receiving velocity, and employs cache queues to store excess data, ensuring that data is not lost during peak periods by reducing the data stream velocity and utilizing both receiving and sending cache queues to manage data flow effectively.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the data stream velocity is increased to process more data, then the processing capability is improved, but data loss occurs when the velocity exceeds the maximum processing capability

Engineering Contradiction:
Improvedata processing capabilityVSAvoiddata loss
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system performs preliminary actions by predicting future traffic peaks using historical data before they occur. The prediction module analyzes historical traffic patterns to forecast upcoming data surges, allowing the system to proactively adjust receiving velocity and utilize cache queues in advance, preventing data loss before it happens.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms where the prediction module continuously monitors actual traffic against predicted traffic, and the receiving velocity is dynamically adjusted based on this feedback. The cache queue status also provides feedback to control the receiving velocity, creating a closed-loop control system that maintains reliability while optimizing throughput.

Inventive Principle:
Principle #23Feedback

2Reliability

If the data receiving velocity is reduced to prevent data loss, then data reliability is improved, but the processing efficiency decreases

Engineering Contradiction:
Improvedata loss preventionVSAvoiddata processing efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system dynamically adjusts the data receiving velocity based on real-time conditions and predictions rather than maintaining a fixed velocity. The receiving velocity control module modifies the velocity adaptively according to predicted traffic peaks, current cache queue status, and actual processing capability, optimizing both reliability and efficiency under varying conditions.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the parameter of receiving velocity based on traffic conditions. During normal periods, the velocity is maintained at higher levels for efficiency. When traffic peaks are predicted or detected, the velocity parameter is reduced to prevent data loss, and cache queues are utilized to buffer the excess data.

Inventive Principle:
Principle #35Parameter changes

3Reliability

If cache queues are used to store excess data, then data loss is prevented, but the system complexity increases

Engineering Contradiction:
Improvedata loss preventionVSAvoidsystem structure
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

Cache queues serve as intermediary buffers between the data source and the processing operators. These queues decouple the receiving side from the processing side, allowing independent optimization of each. The prediction module and velocity control act as additional intermediaries that manage the flow through the cache queues, preventing data loss while maintaining manageable system complexity through modular design.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3499357B1Data processing method and physical machine
Publication Date: 2020.12.30 HUAWEI TECH CO LTD
  • EP3499357B1 patent drawingFigure 1-a~1-b
  • EP3499357B1 patent drawingFigure 2~3
  • EP3499357B1 patent drawingFigure 4~5

AI summary

The present invention discloses a data processing method and a physical machine, so as to reduce a data loss in a process in which an executor processes data in a data stream. Embodiments of the present invention provide the data processing method, the method is applied to a physical machine in a stream system, the physical machine includes a first executor, and the method includes: predicting traffic of a to-be-processed data stream of the first executor in a first time period according to historical information about processing data by the first executor, so as to obtain prediction information of the traffic of the data stream in the first time period, where the historical information includes traffic information of data processed by the first executor in a historical time period, and the traffic prediction information includes predictors of traffic at multiple moments in the first time period; if the traffic prediction information includes a predictor that exceeds a threshold, reducing a data obtaining velocity of the first executor from a first velocity to a second velocity; and obtaining a first data set of the to-be-processed data stream at the second velocity.