Improving scheduling techniques in heterogeneous systems with dynamic, on-line optimisations

Computational performance increasingly depends on parallelism, and many systems rely on heterogeneous resources such as GPUs and FPGAs to accelerate computationally intensive applications. However, implementations for such heterogeneous systems are often hand-crafted and optimised to one computation scenario, and it can be challenging to maintain high performance when application parameters change. In this paper, we demonstrate that machine learning can help to dynamically choose parameters for task scheduling and load-balancing based on changing characteristics of the incoming workload. We use a financial option pricing application as a case study. We propose a simulation of processing financial tasks on a heterogeneous system with GPUs and FPGAs, and show how dynamic, on-line optimisations could improve such a system. We compare on-line and batch processing algorithms, and we also consider cases with no dynamic optimisations.

Transparent Scheduling of Composite Web Services

Composite Web Services (CWS) aggregate multiple Web Services in one logical unit to accomplish a complex task (e.g. business process). This aggregation is achieved by defining a workflow that orchestrates the underlying Web Services in a manner consistent with the desired functionality. Since CWS can aggregate atomic and other CWS they foster the development of service layers and reuse of already existing functionality. An important issue in the deployment of services is their run-time performance under various loads. Due to the complex interactions of the underlying services, a CWS they can exhibit problematic and often difficult to predict behaviours in overload situations. This paper focuses on the use of request scheduling for improving CWS performance in overload situations. Different scheduling policies are investigated in regards to their effectiveness in helping with bulk arrivals.

Multi-level genetic algorithm for the resource-constrained re-entrant scheduling problem in the flow shop

The re-entrant flow shop scheduling problem (RFSP) is regarded as a NP-hard problem and attracted the attention of both researchers and industry. Current approach attempts to minimize the makespan of RFSP without considering the interdependency between the resource constraints and the re-entrant probability. This paper proposed Multi-level genetic algorithm (GA) by including the co-related re-entrant possibility and production mode in multi-level chromosome encoding. Repair operator is incorporated in the Multi-level genetic algorithm so as to revise the infeasible solution by resolving the resource conflict. With the objective of minimizing the makespan, Multi-level genetic algorithm (GA) is proposed and ANOVA is used to fine tune the parameter setting of GA. The experiment shows that the proposed approach is more effective to find the near-optimal schedule than the simulated annealing algorithm for both small-size problem and large-size problem. © 2013 Published by Elsevier Ltd.

Learning Technology in Scheduling Based on the Mixed Graphs

We propose the adaptive algorithm for solving a set of similar scheduling problems using learning technology. It is devised to combine the merits of an exact algorithm based on the mixed graph model and heuristics oriented on the real-world scheduling problems. The former may ensure high quality of the solution by means of an implicit exhausting enumeration of the feasible schedules. The latter may be developed for certain type of problems using their peculiarities. The main idea of the learning technology is to produce effective (in performance measure) and efficient (in computational time) heuristics by adapting local decisions for the scheduling problems under consideration. Adaptation is realized at the stage of learning while solving a set of sample scheduling problems using a branch-and-bound algorithm and structuring knowledge using pattern recognition apparatus.

The Production Scheduling in Assembly System with Evolutionary Algorithm

In this paper an evolutionary algorithm is proposed for solving the problem of production scheduling in assembly system. The aim of the paper is to investigate a possibility of the application of evolutionary algorithms in the assembly system of a normally functioning enterprise producing household appliances to make the production graphic schedule.

Recent research trend of economic-lot scheduling problems

Purpose - This research note aims to present a summary of research concerning economic-lot scheduling problem (ELSP). Design/methodology/approach - The paper's approach is to review over 100 selected studies published in the last 15 years (1997-2012), which are then grouped under different research themes. Findings - Five research themes are identified and insights for future studies are reported at the end of this paper. Research limitations/implications - The motivation of preparing this research note is to summarize key research studies in this field since 1997, when the ELSP problems have been verified as NP-hard. Originality/value - ELSP is an important scheduling problem that has been studied since the 1950s. Because of its complexity in delivering a feasible analytical closed form solution, many studies in the last two decades employed heuristic algorithms in order to come up with good and acceptable solutions. As a consequence, the solution approaches are quite diversified. The major contribution of this paper is to provide researchers who are interested in this area with a quick reference guide on the reviewed studies. © Emerald Group Publishing Limited.

Variable Neighborhood Search for the File Transfer Scheduling Problem

ACM Computing Classification System (1998): I.2.8, G.1.6.

A new scheduling method for enhanced quality of experience in LTE systems

In this paper a new approach to the resource allocation and scheduling mechanism that reflects the effect of user's Quality of Experience is presented. The proposed scheduling algorithm is examined in the context of 3GPP Long Term Evolution (LTE) system. Pause Intensity (PI) as an objective and no-reference quality assessment metric is employed to represent user's satisfaction in the scheduler of eNodeB. PI is in fact a measurement of discontinuity in the service. The performance of the scheduling method proposed is compared with two extreme cases: maxCI and Round Robin scheduling schemes which correspond to the efficiency and fairness oriented mechanisms, respectively. Our work reveals that the proposed method is able to perform between fairness and efficiency requirements, in favor of higher satisfaction for the users to the desired level. © VDE VERLAG GMBH.

A nettó jelenérték maximalizálása erőforrás-korlátos projektekben - egy új harmóniakereső metaheurisztika (A harmony search metaheuristic for the resourceconstrained project scheduling problem with discounted cash flows)

Ebben a tanulmányban a szerző egy új harmóniakereső metaheurisztikát mutat be, amely a minimális időtartamú erőforrás-korlátos ütemezések halmazán a projekt nettó jelenértékét maximalizálja. Az optimális ütemezés elméletileg két egész értékű (nulla-egy típusú) programozási feladat megoldását jelenti, ahol az első lépésben meghatározzuk a minimális időtartamú erőforrás-korlátos ütemezések időtartamát, majd a második lépésben az optimális időtartamot feltételként kezelve megoldjuk a nettó jelenérték maximalizálási problémát minimális időtartamú erőforrás-korlátos ütemezések halmazán. A probléma NP-hard jellege miatt az egzakt megoldás elfogadható idő alatt csak kisméretű projektek esetében képzelhető el. A bemutatandó metaheurisztika a Csébfalvi (2007) által a minimális időtartamú erőforrás-korlátos ütemezések időtartamának meghatározására és a tevékenységek ennek megfelelő ütemezésére kifejlesztett harmóniakereső metaheurisztika továbbfejlesztése, amely az erőforrás-felhasználási konfliktusokat elsőbbségi kapcsolatok beépítésével oldja fel. Az ajánlott metaheurisztika hatékonyságának és életképességének szemléltetésére számítási eredményeket adunk a jól ismert és népszerű PSPLIB tesztkönyvtár J30 részhalmazán futtatva. Az egzakt megoldás generálásához egy korszerű MILP-szoftvert (CPLEX) alkalmaztunk. _______________ This paper presents a harmony search metaheuristic for the resource-constrained project scheduling problem with discounted cash flows. In the proposed approach, a resource-constrained project is characterized by its „best” schedule, where best means a makespan minimal resource constrained schedule for which the net present value (NPV) measure is maximal. Theoretically the optimal schedule searching process is formulated as a twophase mixed integer linear programming (MILP) problem, which can be solved for small-scale projects in reasonable time. The applied metaheuristic is based on the "conflict repairing" version of the "Sounds of Silence" harmony search metaheuristic developed by Csébfalvi (2007) for the resource-constrained project scheduling problem (RCPSP). In order to illustrate the essence and viability of the proposed harmony search metaheuristic, we present computational results for a J30 subset from the well-known and popular PSPLIB. To generate the exact solutions a state-of-the-art MILP solver (CPLEX) was used.

A comparative study of block scheduling and traditional scheduling on academic achievement

The purpose of this study was to evaluate the effectiveness of an alternate day block schedule design (n = 419) versus a traditional six-period schedule design (n = 623) on the academic achievement of the graduating classes in two schools in which the design was used respectively. Academic achievement was measured by (a) two standardized tests: the Florida Comprehensive Assessment Test Sunshine State Standards (FCAT-SSS) in mathematics and reading for 9th and 10th grade and the Scholastic Reading Inventory Test (SRI) for 9 th, 10th, and 11th grade; (b) three school grades: the mathematics final course grades for 9th, 10th, and 11th grade, the English final course grades for 9th, 10th, 11th, and 12th grade and the graduating GPA. A total of five repeated measure analyses of variance (ANOVAs) were conducted to analyze the difference between the two schools (representing the two designs) with respect to five achievement indicators (FCAT-SSS mathematics scores, FCAT-SSS reading scores, SRI scores, mathematics final course grades, and English final course grades). The between-subject factor for the five ANOVAs was the schedule design and the within-subject factor was the time the tests were taken or the time the course grades were issued. T-tests were performed on all eighth grade achievement indicators to ensure there were no significant differences in achievement between the two cohorts prior to entering high school. An independent samples t-test was conducted to analyze the difference between the two schedule designs with respect to graduating GPA. Achievement in the alternate day block schedule design was significantly higher than in the traditional six-period schedule design for some of the locally assigned school grades. The difference between the two types of schedule designs was not significant for the standardized measures (the FCAT-SSS in reading and mathematics and the SRI). This study concludes that the use of an alternate day block schedule design can be considered an educational tool that can help improve the academic achievement of students as measured by local indicators of achievement; but, apparently the design is not an important factor in achievement as measured by state examinations such as the FCAT-SSS or the SRI.

A non-linear discrete stochastic optimization model for Advanced Access patient appointment scheduling

Access to healthcare is a major problem in which patients are deprived of receiving timely admission to healthcare. Poor access has resulted in significant but avoidable healthcare cost, poor quality of healthcare, and deterioration in the general public health. Advanced Access is a simple and direct approach to appointment scheduling in which the majority of a clinic's appointments slots are kept open in order to provide access for immediate or same day healthcare needs and therefore, alleviate the problem of poor access the healthcare. This research formulates a non-linear discrete stochastic mathematical model of the Advanced Access appointment scheduling policy. The model objective is to maximize the expected profit of the clinic subject to constraints on minimum access to healthcare provided. Patient behavior is characterized with probabilities for no-show, balking, and related patient choices. Structural properties of the model are analyzed to determine whether Advanced Access patient scheduling is feasible. To solve the complex combinatorial optimization problem, a heuristic that combines greedy construction algorithm and neighborhood improvement search was developed. The model and the heuristic were used to evaluate the Advanced Access patient appointment policy compared to existing policies. Trade-off between profit and access to healthcare are established, and parameter analysis of input parameters was performed. The trade-off curve is a characteristic curve and was observed to be concave. This implies that there exists an access level at which at which the clinic can be operated at optimal profit that can be realized. The results also show that, in many scenarios by switching from existing scheduling policy to Advanced Access policy clinics can improve access without any decrease in profit. Further, the success of Advanced Access policy in providing improved access and/or profit depends on the expected value of demand, variation in demand, and the ratio of demand for same day and advanced appointments. The contributions of the dissertation are a model of Advanced Access patient scheduling, a heuristic to solve the model, and the use of the model to understand the scheduling policy trade-offs which healthcare clinic managers must make. ^

Algorithms for scheduling parallel batch processing machines with non-identical job ready times

This research is motivated by a practical application observed at a printed circuit board (PCB) manufacturing facility. After assembly, the PCBs (or jobs) are tested in environmental stress screening (ESS) chambers (or batch processing machines) to detect early failures. Several PCBs can be simultaneously tested as long as the total size of all the PCBs in the batch does not violate the chamber capacity. PCBs from different production lines arrive dynamically to a queue in front of a set of identical ESS chambers, where they are grouped into batches for testing. Each line delivers PCBs that vary in size and require different testing (or processing) times. Once a batch is formed, its processing time is the longest processing time among the PCBs in the batch, and its ready time is given by the PCB arriving last to the batch. ESS chambers are expensive and a bottleneck. Consequently, its makespan has to be minimized. ^ A mixed-integer formulation is proposed for the problem under study and compared to a formulation recently published. The proposed formulation is better in terms of the number of decision variables, linear constraints and run time. A procedure to compute the lower bound is proposed. For sparse problems (i.e. when job ready times are dispersed widely), the lower bounds are close to optimum. ^ The problem under study is NP-hard. Consequently, five heuristics, two metaheuristics (i.e. simulated annealing (SA) and greedy randomized adaptive search procedure (GRASP)), and a decomposition approach (i.e. column generation) are proposed—especially to solve problem instances which require prohibitively long run times when a commercial solver is used. Extensive experimental study was conducted to evaluate the different solution approaches based on the solution quality and run time. ^ The decomposition approach improved the lower bounds (or linear relaxation solution) of the mixed-integer formulation. At least one of the proposed heuristic outperforms the Modified Delay heuristic from the literature. For sparse problems, almost all the heuristics report a solution close to optimum. GRASP outperforms SA at a higher computational cost. The proposed approaches are viable to implement as the run time is very short. ^

Efficient asynchronous scheduling algorithms for cost-effective buffered crossbar switches

Buffered crossbar switches have recently attracted considerable attention as the next generation of high speed interconnects. They are a special type of crossbar switches with an exclusive buffer at each crosspoint of the crossbar. They demonstrate unique advantages over traditional unbuffered crossbar switches, such as high throughput, low latency, and asynchronous packet scheduling. However, since crosspoint buffers are expensive on-chip memories, it is desired that each crosspoint has only a small buffer. This dissertation proposes a series of practical algorithms and techniques for efficient packet scheduling for buffered crossbar switches. To reduce the hardware cost of such switches and make them scalable, we considered partially buffered crossbars, whose crosspoint buffers can be of an arbitrarily small size. Firstly, we introduced a hybrid scheme called Packet-mode Asynchronous Scheduling Algorithm (PASA) to schedule best effort traffic. PASA combines the features of both distributed and centralized scheduling algorithms and can directly handle variable length packets without Segmentation And Reassembly (SAR). We showed by theoretical analysis that it achieves 100% throughput for any admissible traffic in a crossbar with a speedup of two. Moreover, outputs in PASA have a large probability to avoid the more time-consuming centralized scheduling process, and thus make fast scheduling decisions. Secondly, we proposed the Fair Asynchronous Segment Scheduling (FASS) algorithm to handle guaranteed performance traffic with explicit flow rates. FASS reduces the crosspoint buffer size by dividing packets into shorter segments before transmission. It also provides tight constant performance guarantees by emulating the ideal Generalized Processor Sharing (GPS) model. Furthermore, FASS requires no speedup for the crossbar, lowering the hardware cost and improving the switch capacity. Thirdly, we presented a bandwidth allocation scheme called Queue Length Proportional (QLP) to apply FASS to best effort traffic. QLP dynamically obtains a feasible bandwidth allocation matrix based on the queue length information, and thus assists the crossbar switch to be more work-conserving. The feasibility and stability of QLP were proved, no matter whether the traffic distribution is uniform or non-uniform. Hence, based on bandwidth allocation of QLP, FASS can also achieve 100% throughput for best effort traffic in a crossbar without speedup.

Scheduling medical application workloads on virtualized computing systems

This dissertation presents and evaluates a methodology for scheduling medical application workloads in virtualized computing environments. Such environments are being widely adopted by providers of "cloud computing" services. In the context of provisioning resources for medical applications, such environments allow users to deploy applications on distributed computing resources while keeping their data secure. Furthermore, higher level services that further abstract the infrastructure-related issues can be built on top of such infrastructures. For example, a medical imaging service can allow medical professionals to process their data in the cloud, easing them from the burden of having to deploy and manage these resources themselves. In this work, we focus on issues related to scheduling scientific workloads on virtualized environments. We build upon the knowledge base of traditional parallel job scheduling to address the specific case of medical applications while harnessing the benefits afforded by virtualization technology. To this end, we provide the following contributions: (1) An in-depth analysis of the execution characteristics of the target applications when run in virtualized environments. (2) A performance prediction methodology applicable to the target environment. (3) A scheduling algorithm that harnesses application knowledge and virtualization-related benefits to provide strong scheduling performance and quality of service guarantees. In the process of addressing these pertinent issues for our target user base (i.e. medical professionals and researchers), we provide insight that benefits a large community of scientific application users in industry and academia. Our execution time prediction and scheduling methodologies are implemented and evaluated on a real system running popular scientific applications. We find that we are able to predict the execution time of a number of these applications with an average error of 15%. Our scheduling methodology, which is tested with medical image processing workloads, is compared to that of two baseline scheduling solutions and we find that it outperforms them in terms of both the number of jobs processed and resource utilization by 20–30%, without violating any deadlines. We conclude that our solution is a viable approach to supporting the computational needs of medical users, even if the cloud computing paradigm is not widely adopted in its current form.

Power and thermal aware scheduling for real-time computing systems

Over the past few decades, we have been enjoying tremendous benefits thanks to the revolutionary advancement of computing systems, driven mainly by the remarkable semiconductor technology scaling and the increasingly complicated processor architecture. However, the exponentially increased transistor density has directly led to exponentially increased power consumption and dramatically elevated system temperature, which not only adversely impacts the system's cost, performance and reliability, but also increases the leakage and thus the overall power consumption. Today, the power and thermal issues have posed enormous challenges and threaten to slow down the continuous evolvement of computer technology. Effective power/thermal-aware design techniques are urgently demanded, at all design abstraction levels, from the circuit-level, the logic-level, to the architectural-level and the system-level. ^ In this dissertation, we present our research efforts to employ real-time scheduling techniques to solve the resource-constrained power/thermal-aware, design-optimization problems. In our research, we developed a set of simple yet accurate system-level models to capture the processor's thermal dynamic as well as the interdependency of leakage power consumption, temperature, and supply voltage. Based on these models, we investigated the fundamental principles in power/thermal-aware scheduling, and developed real-time scheduling techniques targeting at a variety of design objectives, including peak temperature minimization, overall energy reduction, and performance maximization. ^ The novelty of this work is that we integrate the cutting-edge research on power and thermal at the circuit and architectural-level into a set of accurate yet simplified system-level models, and are able to conduct system-level analysis and design based on these models. The theoretical study in this work serves as a solid foundation for the guidance of the power/thermal-aware scheduling algorithms development in practical computing systems.^