Proactive Service Scaling via Operation Timing Notifications

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing service scaling technologies are inadequate in handling rapid increases in access from terminal devices, as they require time to scale out and cannot effectively manage sudden spikes in load concentration.

Innovation Solution

An apparatus that receives notifications from terminal devices indicating predetermined operation timings, allowing for proactive scaling of services based on anticipated increases or decreases in terminal device activity, thereby adjusting instance numbers and load distribution before actual access frequency changes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If scale-out is performed to distribute load and improve response performance, then response performance is recovered, but it takes time to perform the scale-out and cannot cope with rapid access concentration

Engineering Contradiction:

Improveresponse performanceVSAvoidscale-out time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs scaling operations in advance based on predicted access patterns. The prediction unit forecasts future access concentrations, and the scaling unit proactively increases instance numbers before the actual access surge occurs, eliminating the time delay between detecting load and scaling resources

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system takes preemptive action to counteract anticipated harmful effects (access concentration). By predicting future access patterns and scaling instances beforehand, the system prevents performance degradation before it happens, rather than reacting after the problem manifests

Inventive Principle:

Principle #9Preliminary anti-action

2Reliability

If instance number is increased to handle access concentration, then load distribution is improved, but device complexity and resource consumption increase

Engineering Contradiction:

Improveload distributionVSAvoidinstance management complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system dynamically adjusts the number of instances based on real-time predictions and actual access patterns. The scaling unit continuously modifies instance numbers up or down according to predicted future load, making the system flexible and adaptive rather than static, thereby optimizing resource usage while maintaining performance

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system implements a closed-loop control mechanism where the prediction unit forecasts access patterns, the scaling unit adjusts instances accordingly, and the actual access results feed back into future predictions. This continuous feedback cycle enables intelligent, automated instance management that responds to actual system conditions

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS10469618B2Adaptive scaling of a service provided for a plurality of terminal devices

Publication Date: 2019.11.05 FUJITSU LTD

AI summary

An apparatus provides a service to a plurality of terminal devices. The apparatus receives, from each of one or more terminal devices among the plurality of terminal devices, a first notification indicating a predetermined operation timing before the service is used in each terminal device. The apparatus performs scaling of the service, based on the first notifications received from the one or more terminal devices.