Energy-Efficient Scheduling of Periodic Tasks on Multi-Core Processors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing edge server offloading policies do not effectively minimize power consumption, especially in scenarios involving periodic tasks represented by directed acyclic graphs (DAG tasks), and fail to consider real-time constraints and energy efficiency in vehicle ad hoc networks.
Innovation Solution
A computer-implemented method for scheduling periodic tasks across a group of multi-core processors, using a combinatorial optimization problem to minimize power consumption by assigning tasks to processing devices while ensuring total utilization does not exceed a threshold, employing heuristic algorithms like MaxMin or meta-heuristic Genetic Algorithms to generate solutions, and utilizing techniques like Global Earliest Deadline First (GEDF) or Segment-based Dynamic Frequency Scaling (SEDF) for efficient task scheduling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If existing edge server offloading policies are used to schedule periodic tasks, then task execution can be performed, but power consumption is not effectively minimized
Solution Approach 1:
The patent applies parameter changes by dynamically adjusting processor frequencies and voltages based on task characteristics and system state. The scheduling algorithm modifies operational parameters (frequency, voltage) of processing devices to minimize power consumption while ensuring timely task completion, directly resolving the contradiction between energy efficiency and task execution productivity
Solution Approach 2:
The system implements dynamic scheduling decisions by continuously monitoring task queues, processor availability, and power consumption characteristics. The algorithm dynamically assigns tasks to processing devices and adjusts execution parameters in real-time, enabling the system to adapt to changing conditions and optimize the balance between power consumption and task completion efficiency
2Reliability
If periodic DAG tasks are scheduled without considering power consumption, then real-time constraints can be met, but energy efficiency deteriorates
Solution Approach 1:
The scheduling algorithm performs preliminary analysis of task characteristics, dependencies, and execution requirements before assigning tasks to processing devices. By pre-calculating optimal task distributions and preparing execution plans that account for power consumption models, the system ensures real-time constraints are met while minimizing energy efficiency losses
Solution Approach 2:
The system implements feedback mechanisms that monitor task completion status, processor utilization, and power consumption in real-time. This feedback information is used to adjust scheduling decisions and task assignments dynamically, ensuring that real-time constraints remain satisfied while continuously optimizing energy efficiency through adaptive control
3Loss of energy
If complex optimization algorithms are applied to minimize power consumption, then energy efficiency improves, but scheduling complexity increases
Solution Approach 1:
The scheduling problem is segmented into manageable components by dividing tasks into discrete units and assigning them to individual processing devices. The algorithm handles each task assignment decision independently based on local processor state and task characteristics, breaking down the complex global optimization into simpler local decisions that collectively minimize overall power consumption
Data Source
AI summary
An energy-efficient assignment of a task set T to a group of M processing devices models the process of deciding the assignment as a combinatorial optimization problem having an objective function optimizing the power consumption of the devices when executing subsets of the tasks, under a constraint that the total utilization of the task subset assigned to each respective processing device is lower than a threshold depending on the number of its processor cores. The objective function may be: min Σi=1M Pi(τi), where τi denotes the subset of tasks allocated to the ith device, and Pi(τi) represents power consumption of the ith device when executing τi, and the constraint Uτ<sub2>i</sub2>≤Mi/4 for all the devices, where Uτ<sub2>i </sub2>is the total utilization of τi executing on the ith device, and Mi denotes the number of cores of the ith device. Solving the problem using a MaxMin or genetic algorithm gives good energy efficiency.