Procedure Scheduling Using System Activity Statistics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for scheduling resource-intensive procedures in computer systems lack accuracy due to unpredictable system activity patterns influenced by third-party users, leading to potential delays in other system operations.
Innovation Solution
A method that gathers system activity statistics over recurring time periods to identify high and low activity slots, calculates a threshold point, and schedules procedures during 'lull windows' of low activity, ensuring minimal disruption to system performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If procedures are scheduled based on administrator estimates of low activity periods, then scheduling simplicity is maintained, but scheduling accuracy deteriorates due to unpredictable system activity patterns
Solution Approach 1:
The system implements feedback by continuously monitoring actual system activity during scheduled procedures and comparing it against predicted activity levels. This feedback loop enables the system to learn from past scheduling decisions and adjust future scheduling predictions accordingly, improving accuracy while maintaining automated operation.
Solution Approach 2:
The system performs preliminary actions by gathering and analyzing system activity statistics over multiple recurring time periods before making scheduling decisions. This advance data collection and analysis enables more accurate prediction of low-activity periods, resolving the contradiction between automated scheduling and scheduling accuracy.
2Productivity
If resource-intensive procedures are scheduled during estimated low activity periods, then system resource utilization is improved, but system performance deteriorates when activity patterns are unpredictable
Solution Approach 1:
The system uses feedback from actual system performance during and between procedure executions to refine its activity predictions. By monitoring whether scheduled procedures actually occur during low-activity periods and what impact they have on system performance, the system can adjust its scheduling algorithm to improve both resource utilization and reliability over time.
Solution Approach 2:
The scheduling system transitions from static administrator-defined schedules to dynamic, data-driven scheduling that adapts to changing system activity patterns. The system continuously updates its understanding of system behavior based on gathered statistics, enabling it to dynamically identify optimal scheduling windows that maintain both high resource utilization and stable system performance.
3Measurement precision
If system activity statistics are gathered over multiple recurring time periods, then scheduling accuracy is improved, but data collection time increases
Solution Approach 1:
The system performs preliminary data collection in the background over multiple recurring time periods without interfering with normal system operations. By gathering activity statistics during regular system operation and processing this data systematically, the system prepares accurate scheduling information in advance while minimizing impact on system productivity.
Solution Approach 2:
The system uses periodic action by collecting and analyzing system activity statistics at regular, recurring time intervals. This periodic data collection approach enables the system to build accurate activity profiles over time while maintaining a systematic and manageable data gathering process that does not overwhelm system resources.
Data Source
AI summary
Provided are a method, system, and computer program product for using gathered system activity statistics to determine when to schedule a procedure. Selection is made of one of at least one lull window having a plurality of consecutive time slots each having an activity value lower than a threshold point comprising a low activity level among during time slots within a distribution of activity values of the time slots over recurring time periods. The procedure in the computer system is scheduled to be performed during the time slots in the lull window in a future time period.