Task Scheduler for Resource-Constrained Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Resource-constrained computation systems, such as floating sensors deployed in the ocean, face challenges in efficiently scheduling tasks due to limited energy and bandwidth, making traditional task scheduling methods infeasible.
Innovation Solution
A task scheduler that determines tasks to run based on time elapsed since last execution, builds an acyclic graph from task dependencies, merges tasks with common sub-tasks, and selects tasks for execution considering priority weights and power estimates, optimizing energy use and resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If traditional task scheduling methods are used, then all tasks can be executed systematically, but energy consumption increases and device uptime extends beyond necessary minimum
Solution Approach 1:
The patent applies partial action by selectively executing only the most essential tasks within each scheduling interval rather than running all scheduled tasks. The task scheduler evaluates task priorities, data freshness requirements, and energy constraints to determine which tasks should be executed partially (essential ones) and which can be deferred or skipped (non-essential ones), thereby reducing energy consumption while maintaining acceptable system functionality.
Solution Approach 2:
The patent changes the scheduling parameter from fixed interval execution to dynamic priority-based selection. By introducing priority weights, data freshness thresholds, and energy state considerations as variable parameters, the system adapts task execution decisions based on current conditions rather than following a rigid schedule, optimizing the balance between energy efficiency and task completion.
2Loss of information
If more tasks are executed to maximize data collection, then data completeness improves, but bandwidth consumption exceeds limited availability
Solution Approach 1:
The patent extracts and transmits only the most essential data elements that meet minimum information requirements rather than transmitting all collected data. By identifying and separating critical data (such as safety-relevant measurements or high-priority observations) from non-critical data, the system transmits only the necessary portion, reducing bandwidth consumption while preserving data completeness for essential functions.
Solution Approach 2:
The patent applies partial action by transmitting only a subset of collected data that meets essential information requirements. Rather than transmitting all available data, the system selectively transmits data based on priority, freshness, and relevance criteria, achieving adequate data completeness with reduced bandwidth consumption.
3Productivity
If device uptime is extended to complete more tasks, then task execution capability improves, but energy consumption from power-hungry processors increases
Solution Approach 1:
The patent implements periodic action by scheduling tasks to execute at specific intervals rather than continuously running the processor. The task scheduler defines periodic execution windows for different task categories, allowing the processor to remain in low-power states between scheduled execution periods, thereby maintaining task execution capability while significantly reducing overall energy consumption.
Solution Approach 2:
The patent applies preliminary action by pre-planning and scheduling task execution during low-power intervals. The system anticipates upcoming task requirements and schedules them during periods when energy consumption can be minimized, rather than executing tasks reactively when power is readily available, thus optimizing the balance between productivity and energy use.
4Reliability
If all scheduled tasks are executed, then system functionality is maintained, but device complexity and scheduling overhead increase
Solution Approach 1:
The patent segments the task scheduling system into hierarchical levels: critical tasks, important tasks, and optional tasks. This segmentation allows the scheduler to manage complexity by handling different task categories with different levels of detail and enforcement strictness, maintaining system functionality for critical operations while simplifying the scheduling of lower-priority tasks.
Solution Approach 2:
The patent applies local quality by assigning different scheduling policies and complexity levels to different task categories. Critical tasks receive deterministic scheduling with strict guarantees, while optional tasks use more flexible, less complex scheduling approaches, optimizing the balance between reliability and scheduling complexity for each local context.
Data Source
AI summary
A method and system for implementing a task scheduler are provided in a resource constrained computation system that uses meta data provided for each task (e.g. data analysis algorithm or sensor sampling protocol) to determine which tasks should be run in a particular wake cycle, the order in which the tasks are run, and how the tasks are distributed across the available compute resources. When a task successfully completes, it's time of execution is logged in order to provide a reference for when that task should be run again. Task meta data is formatted in a manner to allow for simple integration of new tasks into the processing architecture.