Task Preemption Research Articles

A Distributed Autonomous Mission Planning Method for the Low-Orbit Imaging Constellation

With the improvement of satellite autonomy, multi-satellite cooperative mission planning has become an important application. This requires multiple satellites to interact with each other via inter-satellite links to reach a consistent mission planning scheme. Considering issues such as inter-satellite link failure, external interference, and communication delay, algorithms should minimize communication costs as much as possible. The CBBA algorithm belongs to a fully distributed multi-agent task allocation algorithm, which has been introduced into multi-satellite autonomous task planning scenarios and achieved good planning results. This paper mainly focuses on the communication problem, and proposes an improved algorithm based on it, which is called c-CBBA. The algorithm is designed with task preemption strategy and single-chain strategy to reduce the communication volume. The task preemption strategy is an accelerated convergence mechanism designed for the convergence characteristics of CBBA, while the single-chain strategy is a communication link pruning strategy designed for the information exchange characteristics of satellites. Experiments in various scenarios show that the algorithm can effectively reduce communication volume while ensuring the effectiveness of task planning.

디지털 무역의 국제적 쟁점과 향후 과제

Purpose – The aim of this research is to analyze the international issues of digital trade and present future tasks. Design/methodology/approach – This research is used in analyzing the literature review and the domestic and foreign legislation for legal research related to digital trade. Findings – With the 4th Industrial Revolution, the global industrial structure and business paradigm are facing a new period of transformation different from the previous. However, laws and systems do not meet the rate of change in the overall structure of the industry, which shows the same pattern not only in Korea but also in the international community. Companies that supply digital goods, such as electronic transmissions using these gaps, are trying to avoid taxes, and international organizations have come to discuss new measures such as introducing digital taxes to prevent such tax avoidance. Therefore, this research confirmed the current status of digital trade and international issues, and presented opinions on Korea's preemptive tasks and countermeasures. Research implications – First, the E-commerce tariff moratorium perpetuation on electronic transmission should be reviewed. Second, a solution to the problem of personal information protection arising from data transactions between countries should be prepared. Third, measures should be prepared to protect intellectual property rights caused by the characteristics of digital transactions. Fourth, terms used in digital trade-related laws and regulations should be unified for consistent digital trade agreements and efficient policies. Fifth, a dedicated digital trade organization should be established to collect statistical data on digital trade and exchange opinions between government and companies.

QoS-Aware Co-Scheduling for Distributed Long-Running Applications on Shared Clusters

To achieve a high degree of resource utilization, production clusters need to co-schedule diverse workloads – including both batch analytic jobs with short-lived tasks and long-running applications (LRAs) that execute for a long time frame from hours to months – onto the shared resources. Microservice architecture advances the manifestation of distributed LRAs (DLRAs), comprising multiple interconnected microservices that are executed in long-lived distributed containers and serve massive user requests. Detecting and mitigating QoS violation become even more intractable due to the network uncertainties and latency propagation across dependent microservices. However, current resource managers are only responsible for resource allocation among applications/jobs but agnostic to runtime QoS such as latency at application level. The state-of-the-art QoS-aware scheduling approaches are dedicated for monolithic applications, without considering the temporal-spatio performance variability across distributed microservices. In this paper, we present <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Toposch</small> , a new scheduling and execution framework to prioritize the QoS of DLRAs whilst balancing the performance of batch jobs and maintaining high cluster utilization through harvesting idle resources. <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Toposch</small> tracks footprints of every single request across microservices and uses critical path analysis, based on the end-to-end latency graph, to identify microservices that have high risk of QoS violation. Based on microservice and node level risk assessment, we intervene the batch scheduling by adaptively reducing the visible resources to batch tasks and thus delaying their execution to give way to DLRAs. We propose a prediction-based vertical resource auto-scaling mechanism, with the aid of resource-performance modeling and fine-grained resource inference and access control, for prompt recovery of QoS violation. A cost-effective task preemption is leveraged to ensure a low-cost task preemption and resource reclamation during the auto-scaling. <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Toposch</small> is integrated with Apache YARN and experiments show that <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Toposch</small> outperforms other baselines in terms of performance guarantee of DLRAs, at an acceptable cost of batch job slowdown. The tail latency of DLRAs is merely 1.12x of the case of executing alone on average in <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Toposch</small> with a 26% JCT increase of Spark analytic jobs.

A multi‐queue priority‐based task scheduling algorithm in fog computing environment

AbstractFog computing is a novel, decentralized and heterogeneous computing environment that extends the traditional cloud computing systems by facilitating task processing near end‐users on computing resources called fog nodes. These diverse and resource‐constrained fog devices process a large volume of tasks generated by various fog applications. These tasks are generated by various applications, some of which may be latency‐sensitive, while others may tolerate some degree of delay in their normal functions. Task scheduling determines when a task should be allocated to a computing resource and how long that task can occupy the assigned resource. The majority of task scheduling algorithms focus on prioritizing the latency‐sensitive tasks only, which results in the long waiting time for the other type of tasks. Hence, these priority‐based schedulers cause task starvation for less important tasks while achieving delay‐optimal results for latency‐sensitive tasks. As a result, in this paper, we propose MQP, a multi‐queue priority‐based preemptive task scheduling approach that achieves a balanced task allocation for those applications that can tolerate a certain amount of processing delay and the latency‐sensitive fog applications. At run‐time, the MQP algorithm categorizes tasks as short and long based on their burst time. MQP algorithm maintains a separate task queue for each task category and dynamically updates the time slot value for preemption. The proposed technique's major purpose is to reduce response time for those data‐intensive applications in the fog computing environment, which include both latency‐sensitive tasks and tasks which are less latency‐sensitive, thereby addressing the starvation problem for less latency‐sensitive tasks. A smart traffic management case study is created to model a scenario with both latency‐sensitive short and less latency‐sensitive long tasks. We implement the MQP algorithm using iFogSim and confirm that it reduces the service latencies for long tasks. Simulation results show that the MQP algorithm allocates tasks to a fog device more efficiently and reduces the service latencies for long tasks. The average value of percentage reduction in the latency across all experimental configurations achieved is 22.68% and 38.45% in comparison to First Come‐First Serve and shortest job first algorithms.

Lower and upper bounds for scheduling energy-consuming tasks with storage resources and piecewise linear costs

This paper considers the problem of scheduling a set of time- and energy-constrained preemptive tasks on a discrete time horizon. At each time period, the total energy required by the tasks that are in process can be provided by two energy sources: a reversible one and a non-reversible one. The non-reversible energy source can provide an unlimited amount of energy for a given period but at the expense of a time-dependent piecewise linear cost. The reversible energy source is a storage resource. The goal is to schedule each task preemptively inside its time window and to dispatch the required energy to the sources at each time period, while satisfying the reversible source capacity constraints and minimizing the total cost. We propose a mixed integer linear program of pseudo-polynomial size to solve this NP-hard problem. Acknowledging the limits of this model for problem instances of modest size, we propose an iterative decomposition matheuristic to compute an upper bound. The method relies on an efficient branch-and-price method or on a local search procedure to solve the scheduling problem without storage. The energy source allocation problem for a fixed schedule can in turn be solved efficiently by dynamic programming as a particular lot-sizing problem. We also propose a lower bound obtained by solving the linear programming relaxation of a new extended formulation by column generation. Experimental results show the quality of the bounds compared to the ones obtained using mixed integer linear program.

EPTS: Energy-saving pre-emptive task scheduling for homogeneous cloud systems

The importance of cloud computing grows staggeringly by the day as newer technology is introduced resulting in greater connectivity across systems worldwide inculcating higher demand for resources supplied by cloud providers. Every datacentre responsible for providing these resources consumes a hefty amount of power and cloud service providers have to bear the monetary costs that come with it. Recent studies show that energy consumption of resources at utilizations over 70% grows non-linearly and hence it is best to avoid resources reaching high levels of utilization. In this paper, we introduce EPTS (Energy-saving Pre-emptive Task Scheduling) that utilizes the 0-70% interval of utilization of resources and evenly distributes the energy consumption of tasks by pre-empting tasks consuming high amounts of power by less power-demanding tasks. These pre-empted tasks are rescheduled into the virtual machines where they may result in lower utilization rates, hence increasing energy conservation. We compare EPTS with MaxUtil and FCFS (First Come First Serve) via thorough experimentation on different synthetic datasets and show that EPTS outperforms MaxUtil and FCFS by approximately 50% in terms of energy consumption.

Multi-Robot Preemptive Task Scheduling with Fault Recovery: A Novel Approach to Automatic Logistics of Smart Factories.

This paper presents a novel approach for Multi-Robot Task Allocation (MRTA) that introduces priority policies on preemptive task scheduling and considers dependencies between tasks, and tolerates faults. The approach is referred to as Multi-Robot Preemptive Task Scheduling with Fault Recovery (MRPF). It considers the interaction between running processes and their tasks for management at each new event, prioritizing the more relevant tasks without idleness and latency. The benefit of this approach is the optimization of production in smart factories, where autonomous robots are being employed to improve efficiency and increase flexibility. The evaluation of MRPF is performed through experimentation in small-scale warehouse logistics, referred to as Augmented Reality to Enhanced Experimentation in Smart Warehouses (ARENA). An analysis of priority scheduling, task preemption, and fault recovery is presented to show the benefits of the proposed approach.

Multiple Wirelessly Powered Sensing Platform Scheduling Algorithm Based on Dynamic Priority Preemption

The available energy of a wirelessly powered sensing platform is not enough, and there are constant real‐time tasks to join the wirelessly powered sensing platform to run. So the wirelessly powered sensing system composed of many wirelessly powered sensing platforms is easy to enter the overloaded state, which may cause some tasks not to be executed on time. Therefore, to obtain as much task value as possible for the wirelessly powered sensing system when it is under the overloaded state, it is essential to design a reasonable task scheduling algorithm to arrange the task execution order. In this paper, we propose a policy named Wirelessly Dynamic Allocation Priority (WDAP) policy suitable for the wirelessly powered sensing system. The proposed WDAP is divided into a dynamic task priority allocation policy and a dynamic node priority allocation policy. Firstly, this paper analyzes the dynamic value density based on task value and execution time, studies the urgency of execution according to the execution time and the remaining idle time, and proposes the energy intensity through the task energy consumption and execution time. Based on the three impact factors of dynamic value density, urgency, and energy intensity, a policy for dynamic task priority allocation is proposed. Then, a policy for dynamic node priority allocation is proposed by combining the available energy and the energy acquisition speed of the nodes. Finally, the algorithm suitable for the wirelessly powered sensing system is proposed named Wirelessly Dynamic Real‐time Task Scheduling (WDRTS) algorithm based on the WDAP. The algorithm clarifies the execution order of each task, responds to high‐priority tasks first, and effectively guarantees task benefits. The experimental results show that compared with the main algorithms used in the literature among which is Generalized Earliest Deadline First, the WDRTS algorithm reduces the number of preemptive tasks by at least 36.49% and increases the successful scheduling rate of tasks by at least 15.17% and the overall system task income by at least 16.37% under high load.

Preemptive and Low Latency Datacenter Scheduling via Lightweight Containers

Datacenters are evolving to host heterogeneous workloads on shared clusters to reduce the operational cost and achieve higher resource utilization. However, it is challenging to schedule heterogeneous workloads with diverse resource requirements and QoS constraints. On one hand, latency-critical jobs need to be scheduled as soon as they are submitted to avoid any queuing delays. On the other hand, best-effort long jobs should be allowed to occupy the cluster when there are idle resources to improve cluster utilization. The challenge lies in how to minimize the queuing delays of short jobs while maximizing cluster utilization. In this article, we propose and develop BIG-C, a container-based resource management framework for data-intensive cluster computing. The key design is to leverage lightweight virtualization, a.k.a, containers, to make tasks preemptable in cluster scheduling. We devise two types of preemption strategies: immediate and graceful preemptions and show their effectiveness and tradeoffs with loosely-coupled MapReduce workloads as well as iterative, in-memory Spark workloads. Based on the mechanisms for task preemption, we further develop job-level and task-level preemptive policies as well as a preemptive fair share cluster scheduler. Our implementation on Yarn and evaluation with synthetic and production workloads show that low job latency and high resource utilization can be both attained when scheduling heterogeneous workloads on a contended cluster.

Scheduling pre-emptible tasks with flexible resourcing options and auxiliary resource requirements

Scheduling problems are ubiquitous and arise in numerous real-life applications. In this article situations involving resourcing flexibility, auxiliary resource requirements and pre-emption are targeted as they are particularly challenging and complex. Every activity requires an assortment of resources of different types. There are many resourcing options for each activity and exclusive resources must be shared judiciously. Multiple resources must be acquired at the same time and this requires meticulous synchronization to ensure efficiency and performance of the system. To create optimal schedules, a generic mixed integer programming (MIP) model is proposed. Our model can describe any number of additional resource types, resourcing options and permits pre-emptions. We believe this model can easily handle additional restrictions and technical conditions that may arise in practice. To demonstrate this assertion two contemporary maritime applications are considered, and necessary extensions are described. Numerical testing is performed and comments and insights concerning the solvability of instances of varying size and complexity are made. Our numerical testing shows that problems of the size encountered in industry can be solved to optimality when additional restrictions like tidal and departure windows are imposed, and some pre-emption is performed. Permitting too much pre-emption however does not result in large improvements and drastically increases the intractability of the proposed model, thus highlighting the need for advanced meta-heuristics.

Task scheduling using artificial bee foraging optimization for load balancing in cloud data centers

AbstractLoad balancing in cloud data centers is a process of distributing the incoming service requests or the incoming tasks to the available virtual machines (VMs). This can be achieved by proper scheduling mechanisms through which the tasks will be allocated to suitable VMs. Scheduling in distributed systems, such as cloud data centers, is considered to be an NP‐complete problem. An efficient method of scheduling will result in balancing the load on the VMs, thereby achieving effective resource utilization. Hence, there is a need for a new scheduling framework to perform load balancing amid considering multiple quality of service (QoS) metrics, such as makespan, response time, execution time, and task priority. Therefore, considering the above metrics, task scheduling using artificial bee foraging (TSABF) optimization is proposed to obtain an optimal schedule of tasks to VMs. The resulting optimal schedule consists of a set of VMs to which the tasks are scheduled in a preemptive manner. Task preemption is done to reduce the response and the execution time of the tasks pertaining to different priorities. The experimental results are compared to the existing honey bee behavior‐inspired load balancing (HBB‐LB) algorithm. The results show that TSABF acts as an alternative scheduling strategy to perform load balancing and also improves the QoS metrics when compared to HBB‐LB.

Task Preemption Based on Petri Nets

A business process is a logically related set of business tasks. Each task contains multiple activities, and each activity has its corresponding performers. To improve the efficiency of processes, some scheduling operations will be conducted between performers, thus causing the phenomenon of task preemption. In view of this phenomenon, a Logical Time Petri net (LTPN) is proposed to describe task preemption in concurrent business process systems. By classifying place and transition sets, the relationship between activities and performers are modeled, and then the assignment and triggering of tasks are realized. Note that we consider both the priority of the control place and time constraints, which better describe the task preemption process in business flow. In addition, we propose a novel scheduling algorithm for the task preemption model. Effectiveness and applicability of the proposed methods are verified by a case study.

A High-Throughput Network Processor Architecture for Latency-Critical Applications

This article presents the recent advancements on the Advanced IO Processor (AIOP), a network processor architecture designed by NXP Semiconductors. The AIOP is a multicore accelerated computing architecture where each core is equipped with dedicated hardware for rapid task switching on every hardware accelerator call. A hardware preemption controller snoops on the accelerator completions and sends task preemption requests to the cores, thus reducing the latency of real-time tasks. A technique of priority thresholding is used to avoid latency uncertainty on lower priority tasks and head-of-line blocking. In this way, the AIOP handles the conflicting requirements of high throughput and low latency for next-generation wireless applications such as WiFi and 5G. In presence of frequent preemptions, the throughput reduces by only 3% on AIOP, compared to 25% on a similar network processor. Moreover, the absolute throughput and latency numbers are 2X better. The area and power overhead of adding hardware task-scheduling and preemption is only about 3%.

Criticality based reliability against hardware Trojan attacks for processing of tasks on reconfigurable hardware

An important aspect of mixed critical systems is to execute tasks of varied criticality on the same platform. The property of full or partial reconfiguration at runtime of reconfigurable hardware or field programmable gate arrays (FPGAs) has satisfied this criterion and facilitated the processing of mixed critical tasks directly on hardware, with the aid of reconfigurable intellectual properties (IPs) or bitstreams procured from various third party IP (3PIP) vendors. However, the existing literature in this arena does not consider the associated hardware threats. Such threats are particularly dangerous as related malware like Hardware Trojan Horses (HTHs) remain dormant during testing and evade detection, but get activated at runtime and jeopardize mission critical applications. Though several works exist on hardware security, none focus on reliability driven mixed critical task processing on reconfigurable hardware against HTH attacks. In this work, we initially explore how HTHs implanted by 3PIP vendors in the bitstreams may cause active attacks. Then, we develop strategies to ensure reliability for processing of mixed critical tasks on reconfigurable hardware. Both periodic and non-periodic, i.e. aperiodic or sporadic tasks are considered. We also focus on resource constrained environments, where we adhere to frequency scaling to facilitate accommodation of tasks on limited resources. We experiment with a variety of bitstreams and performance evaluation is performed via metrics such as task success rate, task rejection rate and task preemption rate.

АКТИВІЗАЦІЯ САМООСВІТНЬОЇ ПІДГОТОВКИ ВИКЛАДАЧІВ ГУМАНІТАРНИХ ДИСЦИПЛІН ВВНЗ ІЗ ВИКОРИСТАННЯМ КЕЙС-ТЕХНОЛОГІЇ

The article is devoted to justification of scientific approaches toward the organization of self-education training of humanitarian subjects’ teachers in a higher military school as part of continuous professional education. It has been proven that case technology application contributes to the enhancement of self-educatory training competence of humanitarian subjects’ teachers due to the performance of various kinds of preemptive tasks (search and provision of information on Internet, creating reference list of Internet information resources, development of multimedia presentation in MS Power Point program, using electronic mail, chat message exchange, creation and placement of information in blogs and so on), promotes research activity of humanitarian subjects’ teachers at a higher educational establishment, establishes proper environment for practical application of acquired knowledge when performing different kinds of creative tasks.

Energy Guarantee Scheme for Real-time Systems with Energy Harvesting Constraints

The growth of environmental energy harvesting has been explosive in wireless computing systems especially when replacing or recharging batteries manually is impracticable. This work investigates the scheduling of periodic weekly hard real-time tasks under energy constraints. Based on this motivation, we proposed a real-time scheduling algorithm, namely energy guarantee dynamic voltage and frequency scaling (EG-DVFS), that utilizes the earliest deadline-harvesting (ED-H) scheduling algorithm combined with dynamic voltage and frequency scaling. This one is qualified as real-time since tasks must satisfy their timing constraints. We assume that the preemptable tasks receive dynamic priorities according to the earliest deadline first (EDF) rule. EG-DVFS adjusts the processor’s behavior by characterizing the properties of the energy source module, capacity of the stored energy as well as the harvested energy in a future duration. Specifically, tasks are executed at full processor speed if the amount of energy in the battery is enough to finish its execution. Otherwise, the processor slows down task execution to the lowest possible processor speed while still guaranteeing to meet all the timing constraints. EG-DVFS mainly depends on the on-line computation of the slack time and the slack energy with dynamic voltage and frequency selection in order to achieve an improved system performance. Experimental results show that EG-DVFS can achieve capacity savings up of up to 33% when compared to ED-H.

The integrated berth allocation, quay crane assignment and scheduling problem: mathematical formulations and a case study

This paper considers the integration of three essential seaport terminal operations: the berth allocation problem, the quay crane assignment problem (QCAP), and the quay crane scheduling problem (QCSP). The paper presents a new mathematical formulation that captures all associated operations and constraints. Different quay crane operational policies are considered, namely permitting versus not permitting bay task preemption in QCSP and static versus dynamic crane allocations in QCAP. Thus, variants of the mathematical formulation are introduced to capture the different combinations of these scenarios. Due to the preemption consideration, the models include disaggregated quay crane (QC) tasks. Specifically, QC tasks are identified by single container movements as opposed to bay or stack task allocations that are commonly used in the literature. A case study based on Abu Dhabi’s container terminal is presented where the use of the proposed mathematical models are compared against the current existing operational approach. Results show that the service times can be significantly decreased by the use of the proposed models. Moreover, the policy choice effect on the total schedule is compared through simulated examples and Abu Dhabi’s container terminal case study. The results show that the policy improvements can depend on the problem’s attributes and thus a better policy cannot be generalized.

Scheduling Preemptive and Non-Preemptive Tasks of Scientific Workflows using Hybrid Instances in Cloud Environment

Scheduling Preemptive and Non-Preemptive Tasks of Scientific Workflows using Hybrid Instances in Cloud Environment

Non-Preemptive Scheduling for Mixed-Criticality Real-Time Multiprocessor Systems

Real-time scheduling for Mixed-Criticality (MC) systems has received a growing attention as real-time embedded systems accommodate various tasks with different levels of criticality. While many studies have addressed how to guarantee timing requirements for MC systems with uniprocessor and multiprocessors, most of them have focused on supporting preemptive tasks. On the other hand, there have been few studies to address non-preemptive scheduling especially for MC multiprocessor platforms, in which the jobs under execution cannot be preempted by other jobs. In this paper, we develop schedulability tests for non-preemptive scheduling, which is the first attempt for MC multiprocessor systems. To this end, we first generalize an existing NP-EDF (Non-Preemptive Earliest Deadline First) schedulability test developed for single-criticality multiprocessor systems, towards for MC multiprocessor systems. For the generalization, we introduce new timing guarantee techniques for the system transition between two different criticalities, which is one of the key features in MC systems. We next extend the proposed NP-EDF schedulability test towards NP-EDFVD (NP-EDF with Virtual Deadlines) that is specialized for MC systems, and pose a virtual deadline assignment problem. We develop an optimal virtual deadline assignment policy using a control knob of the system-level deadline-reduction parameter and then a suboptimal one for the task-level parameter. Our simulation results demonstrate that the NP-EDFVD schedulability test with the proposed virtual deadline assignment policies finds a number of additional schedulable task sets, which are not schedulable by the NP-EDF schedulability test.

Task scheduling using Ant Colony Optimization in multicore architectures: a survey

The problem of determining a set of real-time tasks that can be assigned to the multiprocessors and finding a feasible solution of scheduling these tasks among the multiprocessors is a challenging issue and known to be NP-complete. Many applications today require extensive computing power than traditional uniprocessors can offer. Parallel processing provides a cost-effective solution to this problem by increasing the number of CPUs by adding an efficient communication system between them which results much higher computing power to solve compute-intensive problems. Multiprocessor task scheduling is the key research area in high performance computing, and the goal of the task scheduling is to minimize makespan. This paper discusses various approaches adopted to solve task scheduling problem in multiprocessor systems with a bio-inspired swarm system paradigm, the Ant Colony Optimization (ACO) since ACO algorithm leads to the fair load balancing among the processors and reducing the waiting time of the tasks. The parameters such as execution time, communication cost, cache performance, total power consumption, energy consumption, high system utilization, task pre-emptions were studied to compare the task scheduling algorithms.