A compendium of processor allocation strategies for two-dimensional mesh connected systems

Multiple processor systems are an integral part of today's high-performance computing environment. Such systems are often configured as a two-dimensional grid of processors called a mesh. Tasks compete for rectangular submeshes of this mesh. The choice of submesh allocation strategy can significantly affect the level of processor utilization and a task's waiting time. In addition, the execution speed of various allocation algorithms varies widely, which can further affect system performance. This paper describes and categorizes several submesh allocation strategies, including a previously unreported method that is superior to other methods in terms of execution speed. The paper includes results of simulation studies used to compare the performance characteristics of the most efficient allocation strategies in each category.     

基于异步奖励深度确定性策略梯度的边缘计算多任务资源联合优化

移动边缘计算（MEC）系统中,因本地计算能力和电池能量不足,终端设备可以决定是否将延迟敏感性任务卸载到边缘节点中执行。针对卸载过程中用户任务随机产生且系统资源动态变化问题,提出了一种基于异步奖励的深度确定性策略梯度（asynchronous reward deep deterministic policy gradient,ARDDPG）算法。不同于传统独立任务资源分配采用顺序等待执行的策略,该算法在任务产生的时隙即可执行资源分配,不必等待上一个任务执行完毕,以异步模式获取任务计算奖励。ARDDPG算法在时延约束下联合优化了任务卸载决策、动态带宽分配和计算资源分配,并通过深度确定性策略梯度训练神经网络来探索最佳优化性能。仿真结果表明,与随机策略、基线策略和DQN算法相比,ARDDPG算法在不同时延约束和任务生成率下有效降低了任务丢弃率和系统的时延和能耗。     

Allocating Independent Tasks to Parallel Processors: An Experimental Study

We study a scheduling or allocation problem with the following characteristics: The goal is to execute a number of unspecified tasks on a parallel machine in any order and as quickly as possible. The tasks are maintained by a central monitor that will hand out batches of a variable number of tasks to requesting processors. A processor works on the batch assigned to it until it has completed all tasks in the batch, at which point it returns to the monitor for another batch. The time needed to execute a task is assumed to be a random variable with known mean and variance, and the execution times of distinct tasks are assumed to be independent. Moreover, each time a processor obtains a new batch from the monitor, it suffers a fixed delay. The challenge is to allocate batches to processors in such a way as to achieve a small expected overall finishing time. We introduce a new allocation strategy, the Bold strategy, and show that it outperforms other strategies suggested in the literature in a number of simulations.     

Caching-based task scheduling for edge computing in intelligent manufacturing

Tasks have high requirements for response delay and security in intelligent manufacturing. Industrial data have the characteristics of high privacy. However, cloud services are difficult to implement for low latency-sensitive applications and privacy data tasks. Therefore, the offloading technology in edge computing can offload the computing tasks of terminal devices to the edge of the network, which can effectively reduce the delay and match the needs of intelligent manufacturing. Unreasonable task scheduling cannot meet the needs of real-time scheduling between edge servers and cloud servers. In this paper, we establish a joint low-delay optimization model of task scheduling and dynamic replacement-release caching (DRRC) mechanism, which couples a privacy selection strategy for tasks to protect privacy. Tasks are scheduled to different location by the privacy of sensitive data, which can improve the security of data and meet the calculation request of different tasks. DRRC mechanism caches tasks according to the size of the task and replaces it with the weight of the task data, and adds automatic release mechanism. To solve the task scheduling strategy, we design the improved genetic-differential evolution algorithm. Extensive simulations reveal that the proposed algorithm has a better performance in minimizing latency compared with other scheduling algorithms. At the same time, the caching mechanism has a better hit rate.

     

边缘计算中协作计算卸载与动态任务调度

在边缘计算场景中,通过将部分待执行任务卸载到边缘服务器执行能够达到降低移动设备的负载、提升移动应用性能和减少设备开销的目的.对于时延敏感任务,只有在截止期限内完成才具有实际意义.但是边缘服务器的资源往往有限,当同时接收来自多个设备的数据传输及处理任务时,可能造成任务长时间的排队等待,导致部分任务因超时而执行失败,因此无法兼顾多个设备的性能目标.鉴于此,在计算卸载的基础上优化边缘服务器端的任务调度顺序.一方面,将时延感知的任务调度建模为一个长期优化问题,并使用基于组合多臂赌博机的在线学习方法动态调整服务器的调度顺序.另一方面,由于不同的任务执行顺序会改变任务卸载性能提升程度,因而影响任务卸载决策的有效性.为了增加卸载策略的鲁棒性,采用了带有扰动回报的深度Q学习方法决定任务执行位置.仿真算例证明了该策略可在平衡多个用户目标的同时减少系统的整体开销.     

移动边缘计算中的卸载决策与资源分配策略

为在移动边缘计算服务器计算资源有限的情况下最小化系统总成本,提出一种多用户卸载决策与资源分配策略。优化任务执行位置选择和计算资源分配过程,对基于精英选择策略的遗传算法在编码、交叉、变异等操作方面进行改进,设计联合卸载决策与资源分配的improve-eGA算法。实验结果表明,与All_local、All_offload、RANDOM和CGA等算法相比,improve-eGA在迭代次数、任务周期数、任务传输数据量等影响因素下系统总成本均为最低,验证了所提策略的有效性。     

移动边缘计算中基于Lyapunov的任务卸载与资源分配算法

移动边缘计算（MEC）通过将计算和存储资源部署在无线网络边缘,使得用户终端可将计算任务卸载到边缘服务器进行处理,从而缓解终端设备资源受限与高性能任务处理需求之间的冲突。但随着任务卸载规模的不断增加,执行任务所产生的功耗急剧上升,严重影响了MEC系统的收益。建立任务队列动态调度模型,以队列上溢概率为约束构建最大化系统平均收益的资源优化模型。考虑到资源优化问题为不同时隙下的耦合问题,运用Lyapunov优化理论设计一种基于单时隙的资源分配算法,将优化问题转化为用户本地计算资源分配、功率和带宽资源分配以及MEC服务器计算资源分配3个子问题并分别进行求解。仿真结果表明,该算法在满足用户QoS需求的同时能够有效提高MEC系统的时间平均收益。     

基于边缘计算的新型任务卸载与资源分配策略

针对移动边缘计算（MEC）中密集型任务卸载时，系统开销较大和延时抖动明显的问题，提出一种新型资源分配策略。首先在系统时延约束下，分析了系统任务执行开销与终端设备的资源分配机制；其次建立了基于计算卸载和任务分配的联合凸优化目标；最后采用拉格朗日乘子法进行迭代更新得到最优解。仿真结果表明，所提任务卸载与资源分配方案在保证用户服务质量的同时降低了任务执行开销，并有效提升了MEC系统性能。     

Task allocation techniques for distributed computing systems: a review

An efficient strategy to allocate tasks to processors in distributed computer systems is required for proper utilization of available computational power. Various task allocation models developed so far have the basic assumption that an application program is suitably divided into a number of subtasks or modules and the execution costs of modules and intermodule communication costs are also known. The subdivision of a given program into modules is assumed to be carried out by a software mechanism which forms a separate discipline of research work.The task allocation models developed earlier did not consider various constraints like load balancing, precedence relations, timing constraints, etc. Most of the recent works in the formulation of task allocation strategies take into account a number of constraints. This paper presents a brief outline of the various available models and algorithms for task allocation with suggestions for possible future directions in the field.     

Average-case performance analysis of scheduling random parallel tasks with precedence constraints on mesh connected multicomputer systems

We investigate the problem of scheduling parallel tasks with precedence constraints on mesh connected multicomputer systems. It is still an open problem on whether there exists an approximation algorithm with finite asymptotic worst-case and/or average-case performance bound for this scheduling problem. As an early attempt to solve our problem, we propose and analyze the performance of a level-by-level scheduling algorithm LL. In fact, we solve a special case of the problem when all tasks request for square submeshes and run on a square mesh system whose size is a power of 2. There are three basic techniques in algorithm LL, i.e., the level-by-level scheduling strategy for handling precedence constraints, the largest-task-first algorithm for scheduling tasks in the same level, and the two-dimensional buddy system for system partitioning and processor allocation. Algorithm LL does not have a finite worst-case performance bound; however, it has quite acceptable average-case performance. The main contribution of the paper is to show that under the assumptions that task sizes are independent and identically distributed (i.i.d.) random variables with a common probability distribution, and that task execution times are i.i.d. random variables with finite mean and variance, and that the probability distributions of task sizes and execution times are independent of each other, for wide task graphs and typical task size distributions, algorithm LL has an asymptotic average-case performance bound about two for all probability distributions of task execution times.     

一种基于深度强化学习与概率性能感知的边缘计算环境多工作流卸载方法

移动边缘计算是一种新兴的分布式和泛在计算模式,其将计算密集型和时延敏感型任务转移到附近的边缘服务器,有效缓解了移动终端资源不足的问题,显著减小了用户与计算处理节点之间的通信传输开销.然而,如果多个用户同时提出计算密集型任务请求,特别是流程化的工作流任务请求,边缘计算环境往往难以有效地进行响应,并会造成任务拥塞.另外,受...     

Cooperation Requirements Planning (CRP) for multiprocessors: Optimal assignment and execution planning

Cooperation is considered an essential attribute of intelligent multi-machine systems. It enhances their flexibility and reliability. Cooperation Requirement Planning (CRP) is the process of generating a consistent and coordinated global execution plan for a set of tasks to be completed by a multi-machine system based on the task cooperation requirements and interactions. CRP is divided into two steps: CRP-I which matches the task requirements to machine and system capabilities to generate cooperation requirements. It also generates task precedence, machine operation, and system resource constraints. CRP-II uses the cooperation requirements and various constraints to generate a task assignment and coordinated and consistent global execution plan. The global execution plan specifies an ordered sequence of actions and the machine sets that execute them such that the assigned tasks are successfully completed, all the constraints are resolved, and the desired performance measure optimized.In this paper, we describe the CRP-II methodology based on the concepts of planning for multiple goals with interactions. Each task is considered to be a goal, and the CRP-I process is viewed as generating alternate plans and associated costs to accomplish each goal. Five different interactions are specified between the various plans: action combination, precedence relation, resource sharing, cooperative action, and independent action. The CRP-II process is viewed as selecting a plan to satisfy each goal and resolving the interactions between them. A planning strategy is proposed which performs plan selection and interaction resolution simultaneously using a best-first search process to generate the optimal global plan.     

云计算环境下的节能任务调度策略的随机Petri网分析

针对当前云计算异构服务器集群环境下的高能耗问题,提出一种最小能耗优先的任务调度策略(first sche-duling with minimum energy)。该策略在调度任务时优先考虑处于运行状态的服务器,并以任务响应时间为约束,按照最小能耗原则将任务分配到相应的服务器上执行。当处于运行状态的服务器都不能满足任务对响应时间的要求时,则考虑处于休眠状态的服务器;同时,也基于最小能耗原则进行调度。采用随机Petri网工具对节能任务调度策略进行分析建模,考虑其能耗和相关性能指标。实验结果表明,该方法不仅能满足任务的QoS性能要求,而且具有较好的节能效果。     

云边环境下基于博弈论的两阶段任务迁移策略

移动边缘计算（MEC）为计算密集型应用和资源受限的移动设备之间的冲突提供了有效解决办法,但大多关于MEC迁移的研究仅考虑移动设备与MEC服务器之间的资源分配,忽略了云计算中心的巨大计算资源。为了充分利用云和MEC资源,提出一种云边协作的任务迁移策略。首先,将云边服务器的任务迁移问题转化为博弈问题;然后,证明该博弈中纳什均衡（NE）的存在以及唯一性,并获得博弈问题的解决方案;最后,提出了一种基于博弈论的两阶段任务迁移算法来求解任务迁移问题,并通过性能指标对该算法的性能进行了评估。仿真结果表明,采用所提算法所产生的总开销分别比本地执行、云中心服务器执行和MEC服务器执行的总开销降低了72.8%、47.9%和2.65%,数值结果证实了所提策略可以实现更高的能源效率和更低的任务迁移开销,并且随着移动设备数量的增加可以很好地扩展规模。     

Schedulability analysis of fixed-priority systems using timed automata

In classic scheduling theory, real-time tasks are usually assumed to be periodic, i.e. tasks are released and computed with fixed rates periodically. To relax the stringent constraints on task arrival times, we propose to use timed automata to describe task arrival patterns. In a previous work, it is shown that the general schedulability checking problem for such models is a reachability problem for a decidable class of timed automata extended with subtraction. Unfortunately, the number of clocks needed in the analysis is proportional to the maximal number of schedulable task instances associated with a model, which is in many cases huge. In this paper, we show that for fixed-priority scheduling strategy, the schedulability checking problem can be solved using standard timed automata with two   extra clocks in addition to the clocks used in the original model to describe task arrival times. The analysis can be done in a similar manner to response time analysis in classic Rate-Monotonic Analysis (RMA). The result is further extended to systems with data-dependent control, in which the release time of a task may depend on the time-point at which other tasks finish their execution. For the case when the execution times of tasks are constants, we show that the schedulability problem can be solved using n+1$n+1$ extra clocks, where n$n$ is the number of tasks. The presented analysis techniques have been implemented in the Times tool. For systems with only periodic tasks, the performance of the tool is comparable with tools implementing the classic RMA technique based on equation-solving, without suffering from the exponential explosion in the number of tasks.     

Task allocation model for distributed systems

The problem of distributing tasks to processors in a distributed computing system is addressed. A task should be assigned to a processor whose capabilities are most appropriate for the execution of that task and excessive interprocessor communication is avoided. A simple algorithm for task allocation is presented. The execution costs and communication costs of the tasks are represented by arrays. A task is either assigned to a processor or fused with another task using a simple criterion. The execution and communication costs are then modified suitably. The process continues until all the tasks are assigned to processors. This algorithm also facilitates incorporation of various system constraints. It is applicable to random program structures and to a system containing any number of processors.     

同构型分布式计算机系统的启发式任务分配算法

本文讨论一种启发式任务分配方法，称之为改进的ｌｉｓｔ分配方法，它适用于分配一组具有先后关系和通信延迟的任务集到同构型分布式计算机系统上。文中描述了此分配方法的原理和算法，给出相应的仿真流程图，并对具有不同拓扑结构，任务运行时间和通信时间满足多种概率分布的任务集进行了分析和仿真。结果表明，当处理器个数小于任务集的并行度，任务粒度大于５时，任务分配效率大于８０％。     

随机任务在云计算平台中能耗的优化管理方法

针对云计算系统在运行过程中由于计算节点空闲而产生大量空闲能耗,以及由于不匹配任务调度而产生大量“奢侈”能耗的能耗浪费问题,提出一种通过任务调度方式的能耗优化管理方法.首先,用排队模型对云计算系统进行建模,分析云计算系统的平均响应时间和平均功率,建立云计算系统的能耗模型.然后提出基于大服务强度和小执行能耗的任务调度策略,分别针对空闲能耗和“奢侈”能耗进行优化控制.基于该调度策略,设计满足性能约束的最小期望执行能耗调度算法ME3PC(minimum expectation execution energy with performance constraints).实验结果表明,该算法在保证执行性能的前提下,可大幅度降低云计算系统的能耗开销.     

基于合约设计的移动边缘计算任务卸载策略研究

移动边缘计算将边缘服务器部署到无线局域网侧,将部分计算密集任务卸载到边缘云服务器,从而缩短计算服务与移动设备的距离,降低数据传输成本.考虑移动边缘计算(MEC)环境下的计算任务分配问题,通过探索用户体验敏感度的异质性,建立CPU运算周期数-数据量-价格的三元组合约模型,提出基于合约理论的计算任务分配策略,以最大化云服务商的利润为目标,同时保证移动用户的非负效益.分别讨论完整信息场景下和统计信息场景下的最优合约设计策略.仿真结果验证了所提出方案可以有效实现计算任务的卸载.     

Online optimization for scheduling preemptable tasks on IaaS cloud systems

In Infrastructure-as-a-Service (IaaS) cloud computing, computational resources are provided to remote users in the form of leases. For a cloud user, he/she can request multiple cloud services simultaneously. In this case, parallel processing in the cloud system can improve the performance. When applying parallel processing in cloud computing, it is necessary to implement a mechanism to allocate resource and schedule the execution order of tasks. Furthermore, a resource optimization mechanism with preemptable task execution can increase the utilization of clouds. In this paper, we propose two online dynamic resource allocation algorithms for the IaaS cloud system with preemptable tasks. Our algorithms adjust the resource allocation dynamically based on the updated information of the actual task executions. And the experimental results show that our algorithms can significantly improve the performance in the situation where resource contention is fierce.