Perceptive Scaling Computing Resources via News Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automatic scaling methods fail to account for external, unknown events such as political, legal, or environmental factors, leading to significant outages when systems are overwhelmed, as they rely on historical data that cannot predict such events.
Innovation Solution
A perceptive scaling system that analyzes electronic news sources to identify future events, determines their impact, and formulates a scaling strategy to adjust computing resources before the event occurs, using machine-learning-based text analysis and metadata to anticipate and prepare for increased load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If historical data-based scaling methods are used, then system scaling is automated, but the system cannot predict external unknown events leading to outages
Solution Approach 1:
The system performs preliminary actions by analyzing electronic news sources to identify future events before they occur. The event analysis component detects upcoming events and their characteristics, allowing the system to proactively scale computing resources in advance rather than reacting after overload occurs. This preliminary detection and preparation resolves the contradiction by enabling both automation and adaptability to external events.
Solution Approach 2:
The patent introduces an intermediary event analysis component that mediates between external news sources and the scaling system. This intermediary analyzes news content to identify future events, extracts their characteristics, and translates them into scaling strategies. This mediator enables the system to adapt to external unknown events while maintaining automated control, resolving the contradiction between reliability and adaptability.
2Reliability
If computing resources are increased in advance, then system resilience to future events is improved, but resource waste occurs if events do not materialize
Solution Approach 1:
The system applies partial action by scaling only the specific computing resources needed for the predicted event rather than uniformly increasing all resources. The scaling strategy is tailored to the event type and affected resources, scaling only what is necessary. This resolves the contradiction by improving resilience to specific events while minimizing resource waste through targeted rather than blanket scaling.
Solution Approach 2:
The system changes parameters by dynamically adjusting scaling decisions based on event confidence levels and impact assessments. Rather than fixed pre-scaling, the system modifies resource allocation parameters based on analyzed event characteristics, allowing it to scale appropriately only when events are likely to occur, thus improving resilience while reducing waste from unnecessary scaling.
3Adaptability or versatility
If manual scaling strategies are used, then scaling decisions can be customized, but the process is time-consuming and cannot keep pace with rapid events
Solution Approach 1:
The system implements self-service by automatically analyzing news sources, identifying future events, determining their characteristics, and generating scaling strategies without human intervention. The event analysis component and scaling strategy generator work autonomously to detect events and implement appropriate scaling, maintaining customization while achieving rapid automated response that manual processes cannot match.
Solution Approach 2:
The system uses feedback mechanisms by continuously monitoring news sources and adjusting scaling strategies based on event analysis results. The system learns from event outcomes and refines its detection and scaling decisions, enabling both customized scaling approaches and rapid automated response. This feedback loop resolves the contradiction by maintaining adaptability while achieving high-speed automated scaling.
Data Source
AI summary
Perceptive scaling of computing resources is disclosed. News sources can be analyzed to identify a future event as well as an occurrence date and type of the event. A computing resource affected by the event can be determined based on the type of event. A scaling strategy can be formulated for the computing resource, such as scaling up or out, to address resource load introduced by the event. The extent of scaling can be determined based on the predicted impact of the event on the computing resource. Subsequently, the scaling strategy can be scheduled for execution before the occurrence date. The scaling strategy can later be terminated or deactivated after the event terminates.