Preemptive Priority Scheduling Research Articles

An unsupervised approach for personalized RHM with reduced mean alert latency

Remote Health Monitoring (RHM) is an important research topic among the researchers, where many challenges are to be addressed with respect to communication, device, synchronization, data analysis, knowledge inferencing, database maintenance, security, timely notification etc. Among these multi challenges, personalization of health data and scheduling of alert generation have been focused on this work. Recognizing the regular health pattern of each individual helps in diagnosing the disease accurately (reduces the False Alarm Ratio (FAR)) and provides the necessary treatment earlier. Similarly, in real time, with multiple patients, the latency should be minimal for timely alert generation. To address these two challenges, a Density-based K- means clustering (DbK-meansC) approach has been proposed in this work that personalize the vital health values. From the personalized health values the abnormalities in the health status of a person can be detected earlier. Here the health records are continuously updated with respect to health values that reflects in personalization of health records. If any abnormality noted in the health values, then the proposed work sends an alert message to the caretaker / the respective doctor using a dynamic preemptive priority scheduling scheme. The scheduling is done with respect to the severity levels of the vital health values of each individual respectively. The arrived results show that the proposed personalized abnormality detection RHM model generate alerts with minimum latency in terms of response and waiting time in a multi patient environment. With proper personalization, the obtained specificity and sensitivity are 91.56% and 92.87% respectively and the computational time is reduced as the degree of personalization increases.

An Improved Queuing Model for Reducing Average Waiting Time of Emergency Surgical Patients Using Preemptive Priority Scheduling

Our research objective is to reduce the Average Waiting Time for patients in an Emergency Department of public sector hospital. We have based our model on M/M/s Queuing System, our study revealssignificant findings on arrival rate of patients. During this simulation, we have used a preemptive priority scheduling model. In our practice, the arrival rate followed a Poisson distribution, averaging 30 patients per hour, with the Mean Service time of1.5 hours and Average Waiting Time recorded around 12.13 minutes. This research offersvaluable help to achieve better time management in emergency departments of high-density medical facilities.

Idempotence-Based Preemptive GPU Kernel Scheduling for Embedded Systems

Mission-critical embedded systems simultaneously run multiple graphics-processing-unit (GPU) computing tasks with different criticality and timeliness requirements. Considerable research effort has been dedicated to supporting the preemptive priority scheduling of GPU kernels. However, hardware-supported preemption leads to lengthy scheduling delays and complicated designs, and most software approaches depend on the voluntary yielding of GPU resources from restructured kernels. We propose a preemptive GPU kernel scheduling scheme that harnesses the idempotence property of kernels. The proposed scheme distinguishes idempotent kernels through static source code analysis. If a kernel is not idempotent, then GPU kernels are transactionized at the operating system (OS) level. Both idempotent and transactionized kernels can be aborted at any point during their execution and rolled back to their initial state for reexecution. Therefore, low-priority kernel instances can be preempted for high-priority kernel instances and reexecuted after the GPU becomes available again. Our evaluation using the Rodinia benchmark suite showed that the proposed approach limits the preemption delay to 18 ms in the 99.9th percentile, with an average delay in execution time of less than 10 percent for high-priority tasks under a heavy load in most cases.

Utilizing priority-based packet scheduling based on preemptive priority scheduling in wireless sensor networks

In this paper, each node has three levels of priority queues. Real-time packets are placed into the highest-priority queue and can preempt data packets in other queues. Non-real-time packets are placed into two other queues based on a certain threshold of their estimated processing time. Leaf nodes have two queues for real-time and non-real-time data packets since they do not receive data from other nodes and thus, reduce end-to-end delay. The priority packet scheduling scheme outperforms conventional schemes in terms of average data waiting time and end-to-end delay and also it reduces sensor energy consumption.

Multiple QoS provisioning with pre-emptive priority schedulers in multi-resource OFDMA networks

In this paper, we present an analytical framework for the performance evaluation of a pre-emptive priority scheduler in multi-resource networks, like those using Orthogonal Frequency Division Multiple Access (OFDMA). We focus on Quality of Service (QoS)-guaranteed traffic for which QoS is guaranteed to individual users by restricting the number of admitted users. For this, the QoS-constrained capacity, in terms of the number of supported users, needs to be ascertained a priori. The QoS-constrained capacity is a function of users’ QoS requirements, channel conditions, and radio resource allocation algorithms, which in this work is the pre-emptive priority scheduler. It is, thus, a variable quantity and mostly obtained using time-consuming offline computer simulations. Mathematical models, on the other hand, are timely and accurate, allowing the capacity to be derived in real-time as a function of the current network configuration. Existing works on mathematical modelling of pre-emptive priority schedulers have mostly focussed on single servers or multiple servers where a single server is assigned to each user. In contrast, OFDMA networks have multiple radio resources, i.e., multiple servers and each user may need more than one radio resource for a single packet transmission, i.e. it is a multi-resource system, which has been accounted for in this paper. We classify the users based on their resource requirements and model the pre-emptive priority scheduler as a multi-class, multi-server, multi-resource, non-work conserving queueing system. We derive its QoS metrics like average delay, packet drop probability, throughput, etc., from its continuous-time Markov Chain. We then use the derived QoS metrics to obtain the QoS-constrained capacity and design a threshold based predictive call admission control unit. We have validated the results using extensive discrete event simulations.

A Delay Optimal Multiclass Packet Scheduler for General M2M Uplink

The uplink data arriving at the Machine-to-Machine (M2M) Application Server (AS) via M2M Aggregators (MAs) is fairly heterogeneous along several dimensions such as maximum permissible packet delay, arrival rate, and payload size, thus necessitating the design of Quality-of-Service (QoS) aware packet schedulers. In this paper, we classify the M2M uplink data into multiple QoS classes and use sigmoidal function to map the delay requirements of each class onto utility functions. We propose a delay-optimal multiclass packet scheduler at AS obtained by iteratively searching for the optimal fraction of time-sharing between all preemptive priority scheduling policies, such that it maximizes a proportionally fair system utility metric. The iterative optimization process leads to reduced complexity, thus facilitating its online implementation. We then extend this work to determine a jointly optimal packet scheduler at the MAs and AS. We significantly reduce its computational complexity by iteratively solving a distributed optimization problem, independently at MAs and AS. Using Monte Carlo simulations, we show that the proposed joint packet scheduler outperforms other state-of-the-art packet schedulers and results in (desirable) near-minimal delay-jitter for delay-sensitive traffic at the expense of (tolerable) higher delay-jitter for delay-tolerant traffic.

A Modified Priority Preemptive Algorithm for CPU Scheduling

Abstract Priority Preemptive scheduling algorithm is a popular among various other algorithms for scheduling CPU, however it leads to the problem of starvation which happens when processes with lower priority are not given any chance of CPU utilization due to continuous CPU usage by processes with higher priorities. To eradicate this problem here, we have proposed a new algorithm for scheduling CPU which we call it as Modified Priority Preemptive Scheduling Algorithm based on a new approach where we are executing priority Preemptive scheduling in a round robin fashion taking the time quanta equal to the shortest burst time of all the available processes. On analyzing the results, it is observed that modified Preemptive algorithm not only solves the problem of starvation but also enhances the performance of regular Priority Preemptive algorithm by lowering the mean turnaround time and mean waiting time.

Fuzzy Based Dynamic Packet Priority Determination and Queue Management method For Wireless Sensor Network

Wireless sensor networks are made up of large number of resource-constrained sensor nodes. Scheduling of different types of packets at sensor nodes is of crucial importance to reduce sensors' energy consumption, end-to-end data transmission delays and packet loss. Majority of the existing packet scheduling algorithms such as first come first serve (FCFS), preemptive priority scheduling and non-preemptive priority scheduling are not adaptive to changes in the data traffic. They also have more processing overhead and large communication delays. We propose fuzzy-based dynamic packet priority determination and queue management mechanism. In the proposed scheme, each node determines priority of packets dynamically and queues them accordingly. The proposed scheme increases fairness in scheduling and the energy efficiency by delivering the packets before their expiry. The results demonstrate that this enhanced approach outperforms FCFS and dynamic multilevel priority queue scheduling algorithms in terms of throughput, end-to-end delay and average residual energy.

Optimal revenue management in two class pre-emptive delay dependent Markovian queues

In this paper, we present a comparative study on the total revenue generated with pre-emptive and non pre-emptive priority scheduler for a fairly generic problem of pricing the server’s surplus capacity in a single server Markovian queue. The specific problem is to optimally price the server’s surplus capacity by introducing a new class of customers (secondary class) without affecting the pre-specified service level of its current customers (primary class) when pre-emption is allowed. Pre-emptive scheduling is used in various applications. First, a finite step algorithm is proposed to obtain global optimal operating and pricing parameters for this problem. These optimal operating and pricing parameters constitute a unique Nash equilibrium in a certain two player non cooperative game. We then describe the range of service level where pre-emptive scheduling gives feasible solution and generates some revenue while non pre-emptive scheduling has infeasible solution. Further, some complementary conditions are identified to compare revenue analytically for certain range of service level where strict priority to secondary class is optimal. Our computational examples show that the complementary conditions adjust in such a way that pre-emptive scheduling always generates more revenue. Theoretical analysis is found to be intractable for the range of service level when pure dynamic policy is optimal. Hence, extensive numerical examples are presented to describe different instances. It is noted in numerical examples that pre-emptive scheduling generates at least as much revenue as non pre-emptive scheduling. A certain range of service level is identified where improvement in revenue is quite significant.

On the compatibility of exact schedulability tests for global fixed priority pre-emptive scheduling with Audsley’s optimal priority assignment algorithm

Audsley's optimal priority assignment (OPA) algorithm can be applied to multiprocessor scheduling provided that three conditions hold with respect to the schedulability tests used. In this short paper, we prove that no exact test for global fixed priority pre-emptive scheduling of sporadic tasks can be compatible with Audsley's algorithm, and hence the OPA algorithm cannot be used to obtain an optimal priority assignment for such systems.

Global and Partitioned Multiprocessor Fixed Priority Scheduling with Deferred Preemption

This article introduces schedulability analysis for Global Fixed Priority Scheduling with Deferred Preemption (gFPDS) for homogeneous multiprocessor systems. gFPDS is a superset of Global Fixed Priority Preemptive Scheduling (gFPPS) and Global Fixed Priority Nonpreemptive Scheduling (gFPNS). We show how schedulability can be improved using gFPDS via appropriate choice of priority assignment and final nonpreemptive region lengths, and provide algorithms that optimize schedulability in this way. Via an experimental evaluation we compare the performance of multiprocessor scheduling using global approaches: gFPDS, gFPPS, and gFPNS, and also partitioned approaches employing FPDS, FPPS, and FPNS on each processor.

A Dynamic Packet Scheduling Scheme with Multilevel Priority for Wireless Sensor Network

Packet scheduling is one of the critical issues in wireless sensor networks. In WSNs most existing scheduling mechanisms use FCFS, non-preemptive or preemptive priority algorithms. However, most of these algorithms incur high processing overhead and high end-to-end transmission delay due to the FCFS concept and starvation of real time and nonreal time data packets in non-preemptive and preemptive priority scheduling algorithms. Also, these packet scheduling algorithms are predetermined and hence cannot change in application requirements of WSNs. Therefore, in this paper, we propose a dynamic multilevel priority (DMP) packet scheduling algorithm to overcome the short comes like starvation of real time data, end-to-end or data transmission delay, and to make the packet scheduling dynamic. It is well known that in DMP scheduling scheme, nodes are organized in hierarchical structure and each node (except those nodes which are located at last level of hierarchical structure) has three level of priority queues in which real time data packets go to highest priority queue and non-real time data packets go to other two queues based on certain threshold levels of their estimated processing time. The DMP scheme proposed in this work was implemented with network simulator (NS2) v.2.32. The results obtained (end-to-end delay, average waiting time, network lifetime, and energy consumption) indicate the proposed DMP scheme is superior to existing first come first serve (FCFS) packet scheduling scheme. General Terms Wireless Sensor Network, FCFS.

PREEMPTIVE PRIORITY SCHEDULING WITH AGING TECHNIQUE FOR EFFECTIVE DISASTER MANAGEMENT IN CLOUD

Cloud computing has intern the attention of today’s leading IT industries offering huge potential for more flexible, readily scalable and cost effective IT operation. There is a significant anticipation for emergent innovation and expanded capabilities of a cloud-based environment as the cloud services are still in the infant stage. With all technology innovation, the biggest gain will be realized when the Cloud services are efficiently utilized. One of the prime contributions of Cloud is its capacity to handle a huge amount of data for either processing or storing. The inadequacy of this model is that it is prone to disaster. Some of the popular scheduling techniques applied by the researchers and leading IT industries are Round Robin, Preemptive scheduling etc. This research focuses on a novel approach for disaster management through efficient scheduling mechanism.This paper presents a Priority Preemptive scheduling (PPS) with aging of the low priority jobs in Cloud for disaster management. The implementation results show that the jobs at any instance of time are provided with the resources and henceforth preventing them to enter the starvation, which is one of the prime causes for disaster.

Analysis of Hierarchical Scheduling for Heterogeneous Traffic Over Network

Scheduling real time and non real time packets at network nodes has an important impact by reducing the processing overhead, queuing delay and response time. Most of the existing packet scheduling algorithms used in network based on First-In First-Out (FIFO), non-preemptive priority, and preemptive priority scheduling. However, these algorithms incur a large processing overhead, queuing delay and response time and are not dynamic to the data traffic changes. In this paper, we present a new hierarchical scheduling algorithm to assign priority, Hierarchical Hybrid EDF/FIFO which can not only serve the real time traffic but also provide best effort service to non real time traffic. To examine our approach for scheduling, we realized our analytical study to express the worst case queuing delay and the worst case response time for different traffics. The simulation results showed that the Hierarchical hybrid EDF/FIFO achieved the minimum packet delay and adequate loss packet for non real time traffic when compared with Hierarchical FIFO. In general, the performances of our approach draw near to Hierarchical EDF which confirms the effectiveness of this approach.

Dynamic Multilevel Priority Packet Scheduling Scheme for Wireless Sensor Network

Scheduling different types of packets, such as realtime and non-real-time data packets, at sensor nodes with resource constraints in Wireless Sensor Networks (WSN) is of vital importance to reduce sensors' energy consumptions and end-to-end data transmission delays. Most of the existing packet-scheduling mechanisms of WSN use First Come First Served (FCFS), non-preemptive priority and preemptive priority scheduling algorithms. These algorithms incur a high processing overhead and long end-to-end data transmission delay due to the FCFS concept, starvation of high priority real-time data packets due to the transmission of a large data packet in nonpreemptive priority scheduling, starvation of non-real-time data packets due to the probable continuous arrival of real-time data in preemptive priority scheduling, and improper allocation of data packets to queues in multilevel queue scheduling algorithms. Moreover, these algorithms are not dynamic to the changing requirements of WSN applications since their scheduling policies are predetermined. In this paper, we propose a Dynamic Multilevel Priority (DMP) packet scheduling scheme. In the proposed scheme, each node, except those at the last level of the virtual hierarchy in the zone-based topology of WSN, has three levels of priority queues. Real-time packets are placed into the highest-priority queue and can preempt data packets in other queues. Non-real-time packets are placed into two other queues based on a certain threshold of their estimated processing time. Leaf nodes have two queues for real-time and non-real-time data packets since they do not receive data from other nodes and thus, reduce end-to-end delay. We evaluate the performance of the proposed DMP packet scheduling scheme through simulations for real-time and non-real-time data. Simulation results illustrate that the DMP packet scheduling scheme outperforms conventional schemes in terms of average data waiting time and end-to-end delay.

DESIGN & DEVELOPMENT OF REAL-TIME MULTITASKING MICROKERNEL BASED ON ARM7TDMI FOR INDUSTRIAL AUTOMATION

A real-time microkernel is the near-minimum amount of software that can provide the mechanisms needed to implement a real-time operating system. Real-time systems are those systems whose response is deterministic in time. In our research a 32-task Real Time Microkernel is designed using which multi tasking can be done on the targeted processor ARM7TDMI. Two sets of functions are developed in this research work. First one is Operating System functions and second is application functions. Operating System functions are mainly for carrying out task creation, multi-tasking, scheduling, context switching and Inter task communication. The process of scheduling and switching the CPU (Central Processing Unit) between several tasks is illustrated in this paper. The number of application functions can vary between 1 to 32. Each of these application functions is created as a task by the microkernel and scheduled by the pre-emptive priority scheduler. Multi tasking of these application tasks is demonstrated in this paper.

FPSL, FPCL and FPZL schedulability analysis

This paper presents the Fixed Priority until Static Laxity (FPSL), Fixed Priority until Critical Laxity (FPCL) and Fixed Priority until Zero Laxity (FPZL) scheduling algorithms for multiprocessor real-time systems. FPZL is similar to global fixed priority pre-emptive scheduling; however, whenever a task reaches a state of zero laxity it is given the highest priority. FPSL and FPCL are variants of FPZL that introduce no additional scheduling points beyond those present with fixed priority scheduling. FPSL, FPCL and FPZL are minimally dynamic algorithms, in that the priority of a job can change at most once during its execution, bounding the number of pre-emptions. Polynomial time and pseudo-polynomial time sufficient schedulability tests are derived for these algorithms. The tests are then improved by computing upper bounds on the amount of execution that each task can perform at the highest priority. An empirical evaluation shows that FPSL, FPCL, and FPZL are highly effective, with a significantly larger number of tasksets deemed schedulable by the tests derived in this paper, than by state-of-the-art schedulability tests for EDZL scheduling.

Putting Preemptive Time Petri Nets to Work in a V-Model SW Life Cycle

Preemptive Time Petri Nets (pTPNs) support modeling and analysis of concurrent timed SW components running under fixed priority preemptive scheduling. The model is supported by a well-established theory based on symbolic state space analysis through Difference Bounds Matrix (DBM) zones, with specific contributions on compositional modularization, trace analysis, and efficient overapproximation and cleanup in the management of suspension deriving from preemptive behavior. In this paper, we devise and implement a framework that brings the theory to application. To this end, we cast the theory into an organic tailoring of design, coding, and testing activities within a V-Model SW life cycle in respect of the principles of regulatory standards applied to the construction of safety-critical SW components. To implement the toolchain subtended by the overall approach into a Model Driven Development (MDD) framework, we complement the theory of state space analysis with methods and techniques supporting semiformal specification and automated compilation into pTPN models and real-time code, measurement-based Execution Time estimation, test case selection and execution, coverage evaluation.

Using Fixed Priority Pre-emptive Scheduling in Real-Time Systems

For real-time applications, task scheduling is a problem of paramount importance. Several scheduling algorithms were proposed in the literature, starting from static scheduling or cyclic executives which provide very deterministic yet inflexible behaviour, to the so called best-effort scheduling, which facilitates maximum run-time flexibility but allows only probabilistic predictions of run-time performance presenting a non-predictable and nondeterministic solution. Between these two extremes lies fixed priority scheduling algorithms, such as Rate Monotonic, that is not so efficient for real-time purposes but exhibits a predictable approach because scheduling is doing offline and guarantees regarding process deadlines could be obtained using appropriate analysis methods. This paper investigates the use of Rate Monotonic algorithm by making adjustments in order to make it more suitable for real-time applications. The factors that motivate the interest for fixed priority scheduling algorithms such Rate Monotonic when doing with real-time systems lies in its associated analysis that could be oriented in two directions: schedulability analysis and analysis of process interactions. The analyzing process is carried out using a previously implemented framework that allows modelling, simulation and schedulability analysis for a set of real-time system tasks, and some of the results obtained are presented.

Improved priority assignment for global fixed priority pre-emptive scheduling in multiprocessor real-time systems

This paper is an extended version of a paper that appeared in the proceedings of the IEEE Real-Time Systems Symposium 2009. This paper has been updated with respect to advances made in schedulability analysis, and contains a number of significant additional results. The paper addresses the problem of priority assignment in multiprocessor real-time systems using global fixed task-priority pre-emptive scheduling. We prove that Audsley's Optimal Priority Assignment (OPA) algorithm, originally devised for uniprocessor scheduling, is applicable to the multiprocessor case, provided that three conditions hold with respect to the schedulability tests used. Our empirical investigations show that the combination of optimal priority assignment policy and a simple compatible schedulability test is highly effective in terms of the number of tasksets deemed to be schedulable. We also examine the performance of heuristic priority assignment policies such as Deadline Monotonic, and an extension of the TkC priority assignment policy called DkC that can be used with any schedulability test. Here we find that Deadline Monotonic priority assignment has relatively poor performance in the multiprocessor case, while DkC priority assignment is highly effective.