A Theory for the Initial Allocating of Real Time Tasks in Distributed Systems

Referring to a set of real time tasks with arriving time,executing time and deadline,this paperdiscusses the problem of polynomial time initial-allocating approximation algorithms in a distributedsystem and five new results are gained which provide a theory for the designing of initial-allocating algorithmsof real time tasks.

Overload problem research on aperiodic real-time tasks

In this paper, a novel scheduling mechanism is proposed to handle the real-time overload problem by maximizing the cumulative values of three types of tasks： the soft, the hard and the imprecise tasks. The simulation results show that the performance of our presented mechanism in this paper is greatly improved, much better than that of the other three mechanisms： earliest deadline first （EDF）, highest value first （HVF） and highest density first （HDF）, under the same conditions of all nominal loads and task type proportions.

Assigning Real-Time Tasks in Environmentally Powered Distributed Systems

Harvesting energy for execution from the environment (e.g., solar, wind energy) has recently emerged as a feasible solution for low-cost and low-power distributed systems. When real-time responsiveness of a given application has to be guaranteed, the recharge rate of obtaining energy inevitably affects the task scheduling. This paper extends our previous works in?[1] [2] to explore the real-time task assignment problem on an energy-harvesting distributed system. The solution using Ant Colony Optimization (ACO) and several significant improvements are presented. Simulations compare the performance of the approaches, which demonstrate the solutions effectiveness and efficiency.

Homology Priority Task Scheduling in μC/OS-Ⅱ Real-Time Kernel

μC/OS-Ⅱ is an open source real-time kernel adopting priority preemptive schedule strategy. Aiming at the problem of μC/OS-Ⅱ failing to support homology priority tasks scheduling, an approach for solution is proposed. The basic idea is adding round-robin scheduling strategy in its original scheduler in order to schedule homology priority tasks through time slice roundrobin. Implementation approach is given in detail. Firstly, the Task Control Block （TCB） is extended. And then, a new priority index table is created, in which each index pointer points to a set of homology priority tasks. Eventually, on the basis of reconstructing μC/OS-Ⅱ real-time kernel, task scheduling module is rewritten. Otherwise, schedulability of homology task supported by modified kernel had been analyzed, and deadline formula of created homology tasks is given. By theoretical analysis and experiment verification, the modified kernel can support homology priority tasks scheduling, meanwhile, it also remains preemptive property of original μC/OS-Ⅱ.

An Efficient Real-Time Fault-Tolerant Scheduling Algorithm Based on Multiprocessor Systems

In the context of real-time fault-tolerant scheduling in multiprocessor systems, Primary-backup scheme plays an important role. A backup copy is always preferred to be executed as passive backup copy whenever possible because it can take the advantages of backup copy de-allocation technique and overloading technique to improve schedulability. In this paper, we propose a novel efficient fault-tolerant ratemonotonic best-fit algorithm efficient fault-tolerant rate-monotonic best-fit （ERMBF） based on multiprocessors systems to enhance the schedulability. Unlike existing scheduling algorithms that start scheduling tasks with only one processor. ERMBF pre-allocates a certain amount of processors before starting scheduling tasks, which enlarge the searching spaces for tasks. Besides, when a new processor is allocated, we reassign the task copies that have already been assigned to the existing processors in order to find a superior tasks assignment configuration. These two strategies are all aiming at making as many backup copies as possible to be executed as passive status. As a result, ERMBF can use fewer processors to schedule a set of tasks without losing real-time and fault-tolerant capabilities of the system. Simulation results reveal that ERMBF significantly improves the schedulability over existing, comparable algorithms in literature.

Energy-Efficient Deterministic Fault-Tolerant Scheduling for Embedded Real-Time Systems

By combining fault-tolerance with power management, this paper developed a new method for aperiodic task set for the problem of task scheduling and voltage allocation in embedded real-time systems. The scbedulability of the system was analyzed through checkpointing and the energy saving was considered via dynamic voltage and frequency scaling. Simulation results showed that the proposed algorithm had better performance compared with the existing voltage allocation techniques. The proposed technique saves 51.5% energy over FT-Only and 19.9% over FT ＋ EC on average. Therefore, the proposed method was more appropriate for aperiodic tasks in embedded real-time systems.

MODEL-BASED DEVELOPMENT OF REAL-TIME SOFTWARE SYSTEM FOR ELECTRONIC UNIT PUMP SYSTEM

A real-time operating system （RTOS）, also named OS, is designed based on the hardware platform of MC68376, and is implemented in the electronic control system for unit pump in diesel engine. A parallel and time-based task division method is introduced and the multi-task software architecture is built in the software system for electronic unit pump （EUP） system. The V-model software development process is used to control algorithm of each task. The simulation results of the hardware-in-the-loop simulation system （HILSS） and the engine experimental results show that the OS is an efficient real-time kernel, and can meet the real-time demands of EUP system; The built multi-task software system is real-time, determinate and reliable. V-model development is a good development process of control algorithms for EUP system, the control precision of control system can be ensured, and the development cycle and cost are also decreased.

分布式3D打印服务的实时多任务调度研究

针对分布式3D打印机(3DPs)在工业物联网(IIoT)中共享、协作、生产全球化的定制产品过程中,3D打印任务(3DPTs)在分布式3D打印机上分配工作量不平衡,以及提交的每个模型的定制属性和实时性等问题,文章提出了用于IIoT中个性化3D打印的实时绿色感知多任务调度架构,给出了一种稳健的在线分配算法,使得每个3D打印任务能够精确地满足用户定义属性,并且平衡了分布式3D打印机之间工作负荷,同时开发了一种基于优先级的自适应实时多任务调度(ARMPS)算法,实时调度每一个3D打印任务,满足3D打印任务的实时性以及动态性要求。在高负载下进行仿真实验,经性能评估测试,表明所提出的算法具有稳健性,调度架构具有鲁棒性和可扩展性。

一种航空装备实时系统任务快速调度方法

针对航空装备实时系统对多线程下实时任务快速调度的困难,提出了一种基于多层编码遗传算法并利用粒子群算法进行参数优化的实时系统任务快速调度方法。通过引入任务贡献矩阵,建立了以总消耗时间少和贡献值大的任务尽早完成为目标的染色体适应度值评价模型,避免重要任务的丢失。采用粒子群算法对多层编码遗传算法参数进行优化,避免陷入局部最优解,增加了收敛速度。最后对调度方法进行仿真验证,仿真结果表明,本文提出的实时系统任务快速调度模型与方法可以优化任务的执行时间,保障任务的顺利完成。通过对粒子群算法优化前和优化后的调度情况的对比,证明了优化后的模型的调度性能指标要优于参数优化前的模型,调度速度和调度效果明显提升。

通信约束下UAV集群协同拦截任务分配算法

针对多无人机协同拦截多机动目标的任务分配问题,同时考虑到真实战场环境中存在的通信约束以及探测范围约束条件,本文提出了分步一致性拍卖算法(SCBAA)。首先,对真实战场环境中存在的通信约束以及探测范围约束等问题进行了描述分析,构建了多无人机协同拦截任务分配模型,设计了综合效能函数以及相应约束条件。其次,为解决多无人机协同打击单一目标的不平衡任务分配以及冲突消解问题,将原任务分配过程分为主要任务分配以及次要任务分配两部分,通过多次拍卖以及冲突消解实现多无人机对单一目标的任务分配。仿真结果表明,该算法可有效解决通信约束条件下的分布式多无人机协同拦截问题,并适应动态环境中任务分配对实时性的要求。

面向任务协同的异构多核嵌入式系统实时调度方法

以往的异构多核嵌入式系统实时调度方法由于仅设置了系统实时调度模型的单项参数,导致系统调度时间过长。本文设计了面向任务协同的异构多核嵌入式系统实时调度方法。面向任务协同构建嵌入式系统实时调度模型,计算系统任务节点的传输情况,构建系统实时调度的数学模型,对构建的实时调度模型中的任务数据信息进行汇集,并进行自适应分析处理,以此为基础,设置实时调度模型的时间均衡控制参数和安全性系数,从而实现嵌入式系统的实时调度。通过上述设计,完成对异构多核嵌入式系统实时调度方法的设计。在仿真实验中,与以往的异构多核嵌入式系统实时调度方法相比,本文设计的面向任务协同的异构多核嵌入式系统实时调度方法的调度时间最长仅为5 s,调度时间更短。

星载操作系统中面向混合多任务类型的两级准入控制策略

随着空间技术的发展,星载操作系统从单一任务类型的封闭式系统转变为多种任务类型混合的开放式系统,此时系统的可预测性难度和不确定性增大,而现有的表调度策略已无法解决该场景下多任务类型混合调度时的可调度性分析问题,同时也不能支持系统运行时新任务的动态载入,阻碍了星载操作系统的智能化和多样化发展.针对该问题,本文以保障航天器的实时性需求及功能的可扩展性为研究目标,提出基于任务关键等级的两级准入控制策略.通过模型建立对任务的时间特性进行了描述,并全面分析了高优先级任务产生的最大干扰时间,进而分别提出基于干扰时间上界和基于响应时间分析的可调度性判定方法.实验结果表明,相较于现有算法,本文方法极大地减小了高优先级任务干扰时间的计算开销,并通过对任务运行时信息的追踪,改善了算法实时性能,提升了处理器利用率,为解决航天器系统中零散任务的准入控制问题提供了理论基础.

资源限制性并行任务固定优先级可调度性分析

异构多核平台的发展,导致并行任务需要执行在具有多样性资源的多核平台上.虽然,并行任务的某个程序片段只能在规定的资源上执行,但是这样操作可以充分利用各类不同资源的特性,达到更加快速节能处理任务的目的.同时,具有资源限制任务的可调度性研究在实时嵌入式系统领域已有一定的研究成果,但是采用的任务模型相对简单,分析方法不够精确.鉴于此,本文对具有资源限制性的并行任务在全局固定优先级调度策略下的可调度性问题进行了研究,基于单并行任务的分析方法提出了基于全局固定优先级调度策略的分析方法.首先,基于分解策略提出了高优先级任务干涉的分析方法.然后,将高优先级任务干涉分析方法和单并行任务提出的路径抽象技术相结合,推导出并行任务的最差响应时间算法.最后,通过仿真实验进行验证所提出的算法在可调度性、精确度层面的性能.实验结果表明,提出的算法在各个参数下的接受率实验符合实验预期,分析时间相对降低,但平均分析时间仍然在离线分析的可接受范围内,提出的算法能够对实时系统并行软件设计提供一定的指导价值.

嵌入式多核系统中的实时混合任务调度算法

针对由周期任务和零星任务形成的实时混合任务集进行合理调度问题,文中提出了一种基于零松弛度边界公平(Boundary Fair until Zero Laxity,BFZL)的实时混合任务算法。该算法在改进边界公平(Improved Boundary Fair,I-BF)实时混合任务算法基础上,通过引入最小松弛度优先(Least Laxity First,LLF)算法中的松弛度参数来改进判定任务的优先级,并提出基于松弛度与启发式策略相结合的启发式算法改进任务的分配策略。实验结果表明,BFZL算法能够满足系统实时性,并达到了算法优化目的。通过数据对比分析可知,该算法相比于原始算法,零星任务的平均响应时间降低了约26%,上下文切换减少了约28%,迁移减少了约50%。该算法在调度开销方面也具有一定优势。

智能仓储多机器人动态任务分配方法

针对智能仓储系统中多机器人任务分配方法进行研究,根据智能仓储中物流任务数量庞大且实时新增的动态特点,创新地提出了一种总体分配并根据当前工况实时插入的动态任务分配方法,将一定时间阈值内的物流任务集合利用综合时间代价、路径代价、空载代价和任务均衡度代价的自适应多层编码遗传算法进行任务整体规划,为智能仓储系统中每个机器人分配需执行的物流任务序列及执行顺序。任务执行过程中,各机器人通过对当前自身剩余任务量成本及插入实时任务后路径成本的判断,在不影响当前任务完成总时间的情况下,对下一时间阈值内产生的实时物流任务是否插入当前执行任务序列展开竞争,实现任务的实时插入,未被实时插入的物流任务则等待下一次总体分配。实验结果表明,该方法能在缩短系统运行总时间和总路程的基础上,极大的降低机器人无任务空载等待的时间,提高系统运行效率。

实际任务背景下脑力负荷的实时监测与评估研究现状

脑力负荷是影响飞行员等关键岗位职业安全的重要风险因素之一,而任务中实时监测作业者的脑力负荷,对于及时识别疲劳状态及预防人因失误具有重大意义。从脑力工作负荷实时评估技术、任务中生物学信号获取方法、脑力任务设置方法与脑力状态识别模型构建等四个方面,本文分别介绍了实际工作场景脑力负荷监测的关键环节的研究现状、存在问题及对策;在此基础上,总结了实际工作场景中脑力负荷研究的重点:便携式生物信号采集技术的研发、考虑任务中不同生理模式与认知交互作用影响、多层次不同模态数据融合的脑力负荷评价模型。本文可以为实际动态脑力工作场景下任务负荷实时监测提供新思路,为疲劳状态的精准识别与事故预防提供充实的理论基础。

基于强化学习的并行任务实时调度方法

针对现有并行任务调度算法大多未考虑环境的不稳定性以及缺少通用性、实时性等问题,提出一种基于强化学习的并行任务实时调度方法。将任务调度建模为一个马尔可夫决策过程,通过智能体与环境的交互,使用近端策略优化方法。其中,使用仿真方法来构造奖励函数,并通过降噪自编码器为优势估计函数添加经验项,使得智能体能够学习到高效且可靠的调度策略。两个场景下的仿真对比实验结果表明,采用该方法比现有方法提升时间利用率超过17%,提高产出超过16%,能够在毫秒级时间内实时调度。

配变重过载下的配网运营动态监控平台实时任务容错调度算法

研究配变重过载下的配网运营动态监控平台实时任务容错调度算法,以解决配网运营动态监控平台执行配变重过载监控任务时可调度性差的问题。依据分层调度思想,将实时任务容错调度划分为上层调度算法和下层调度算法,通过上层调度算法利用Logistic模型预测是否存在配变重过载情况,存在配变重过载情况时,进入下层调度算法。下层调度算法利用平台的优先级属性列表,建立平台管理机执行配变重过载动态监控任务时的有效传递函数,利用码元调制方法获取平台任务调度输出,保障配网运营动态监控平台稳定执行配变重过载动态监控任务。实例分析结果表明,配网运营动态监控同时执行30个配变重过载动态监控任务时,其容错调度成功率高于93%,验证该算法具有良好的实时任务容错调度有效性。

遗传算法在任务调度中的应用研究及软件实现

本研究聚焦于遗传算法在任务调度问题中的应用研究,通过深入探讨遗传算法的基本原理和其在优化问题中的独特优势,为任务调度问题提供了一种全新的优化视角。该研究框架为任务调度问题的未来研究奠定了坚实基础,为实际应用中的性能优化提供了新的思路。