Handling shared resources and precedence constraints in open systems

There is an increasing demand for highly dynamic realtime systems where several independently developed applications with different timing requirements can coexist. This paper proposes a protocol to integrate shared resources and precedence constraints among tasks in such systems assuming no precise information on critical sections and computation times is available. The concept of bandwidth inheritance is combined with a capacity sharing and stealing mechanism to efficiently exchange bandwidth among needed tasks, minimising the cost of blocking.

Shared resources and precedence constraints with capacity sharing and stealing

This paper proposes a new strategy to integrate shared resources and precedence constraints among real-time tasks, assuming no precise information on critical sections and computation times is available. The concept of bandwidth inheritance is combined with a greedy capacity sharing and stealing policy to efficiently exchange bandwidth among tasks, minimising the degree of deviation from the ideal system's behaviour caused by inter-application blocking. The proposed capacity exchange protocol (CXP) focus on exchanging extra capacities as early, and not necessarily as fairly, as possible. This loss of optimality is worth the reduced complexity as the protocol's behaviour nevertheless tends to be fair in the long run and outperforms other solutions in highly dynamic scenarios, as demonstrated by extensive simulations.

Multi-stage scheduling problems with precedence constraints

Abstract not available

Earliness penalties on a single machine subject to precedence constraints: SLK due date assignment

Abstract not available

Flow shop scheduling problems under machine-dependent precedence constraints

Abstract not available

A capacity sharing and stealing strategy for open real-time systems

This paper focuses on the scheduling of tasks with hard and soft real-time constraints in open and dynamic real-time systems. It starts by presenting a capacity sharing and stealing (CSS) strategy that supports the coexistence of guaranteed and non-guaranteed bandwidth servers to efficiently handle soft-tasks’ overloads by making additional capacity available from two sources: (i) reclaiming unused reserved capacity when jobs complete in less than their budgeted execution time and (ii) stealing reserved capacity from inactive non-isolated servers used to schedule best-effort jobs. CSS is then combined with the concept of bandwidth inheritance to efficiently exchange reserved bandwidth among sets of inter-dependent tasks which share resources and exhibit precedence constraints, assuming no previous information on critical sections and computation times is available. The proposed Capacity Exchange Protocol (CXP) has a better performance and a lower overhead when compared against other available solutions and introduces a novel approach to integrate precedence constraints among tasks of open real-time systems.

The capacity exchange protocol

This paper proposes a new strategy to integrate shared resources and precedence constraints among real-time tasks, assuming no precise information on critical sections and computation times is available. The concept of bandwidth inheritance is combined with a capacity sharing and stealing mechanism to efficiently exchange bandwidth among tasks to minimise the degree of deviation from the ideal system’s behaviour caused by inter-application blocking. The proposed Capacity Exchange Protocol (CXP) is simpler than other proposed solutions for sharing resources in open real-time systems since it does not attempt to return the inherited capacity in the same exact amount to blocked servers. This loss of optimality is worth the reduced complexity as the protocol’s behaviour nevertheless tends to be fair and outperforms the previous solutions in highly dynamic scenarios as demonstrated by extensive simulations. A formal analysis of CXP is presented and the conditions under which it is possible to guarantee hard real-time tasks are discussed.

A hybrid genetic algorithm for the multi-mode resource-constrained project scheduling

A construction project is a group of discernible tasks or activities that are conduct-ed in a coordinated effort to accomplish one or more objectives. Construction projects re-quire varying levels of cost, time and other resources. To plan and schedule a construction project, activities must be defined sufficiently. The level of detail determines the number of activities contained within the project plan and schedule. So, finding feasible schedules which efficiently use scarce resources is a challenging task within project management. In this context, the well-known Resource Constrained Project Scheduling Problem (RCPSP) has been studied during the last decades. In the RCPSP the activities of a project have to be scheduled such that the makespan of the project is minimized. So, the technological precedence constraints have to be observed as well as limitations of the renewable resources required to accomplish the activities. Once started, an activity may not be interrupted. This problem has been extended to a more realistic model, the multi-mode resource con-strained project scheduling problem (MRCPSP), where each activity can be performed in one out of several modes. Each mode of an activity represents an alternative way of combining different levels of resource requirements with a related duration. Each renewable resource has a limited availability for the entire project such as manpower and machines. This paper presents a hybrid genetic algorithm for the multi-mode resource-constrained pro-ject scheduling problem, in which multiple execution modes are available for each of the ac-tivities of the project. The objective function is the minimization of the construction project completion time. To solve the problem, is applied a two-level genetic algorithm, which makes use of two separate levels and extend the parameterized schedule generation scheme. It is evaluated the quality of the schedules and presents detailed comparative computational re-sults for the MRCPSP, which reveal that this approach is a competitive algorithm.

Uma metaheurística para a programação de projectos com multi-modos e recursos limitados

Este artigo apresenta uma nova abordagem (MM-GAV-FBI), aplicável ao problema da programação de projectos com restrições de recursos e vários modos de execução por actividade, problema conhecido na literatura anglo-saxónica por MRCPSP. Cada projecto tem um conjunto de actividades com precedências tecnológicas definidas e um conjunto de recursos limitados, sendo que cada actividade pode ter mais do que um modo de realização. A programação dos projectos é realizada com recurso a um esquema de geração de planos (do inglês Schedule Generation Scheme - SGS) integrado com uma metaheurística. A metaheurística é baseada no paradigma dos algoritmos genéticos. As prioridades das actividades são obtidas a partir de um algoritmo genético. A representação cromossómica utilizada baseia-se em chaves aleatórias. O SGS gera planos não-atrasados. Após a obtenção de uma solução é aplicada uma melhoria local. O objectivo da abordagem é encontrar o melhor plano (planning), ou seja, o plano que tenha a menor duração temporal possível, satisfazendo as precedências das actividades e as restrições de recursos. A abordagem proposta é testada num conjunto de problemas retirados da literatura da especialidade e os resultados computacionais são comparados com outras abordagens. Os resultados computacionais validam o bom desempenho da abordagem, não apenas em termos de qualidade da solução, mas também em termos de tempo útil.

A Multi-DAG Model for Real-Time Parallel Applications with Conditional Execution

The 30th ACM/SIGAPP Symposium On Applied Computing (SAC 2015). 13 to 17, Apr, 2015, Embedded Systems. Salamanca, Spain.

A polynomial algorithm for special case of the one-machine scheduling problem with time-lags

The standard one-machine scheduling problem consists in schedulinga set of jobs in one machine which can handle only one job at atime, minimizing the maximum lateness. Each job is available forprocessing at its release date, requires a known processing timeand after finishing the processing, it is delivery after a certaintime. There also can exists precedence constraints between pairsof jobs, requiring that the first jobs must be completed beforethe second job can start. An extension of this problem consistsin assigning a time interval between the processing of the jobsassociated with the precedence constrains, known by finish-starttime-lags. In presence of this constraints, the problem is NP-hardeven if preemption is allowed. In this work, we consider a specialcase of the one-machine preemption scheduling problem with time-lags, where the time-lags have a chain form, and propose apolynomial algorithm to solve it. The algorithm consist in apolynomial number of calls of the preemption version of the LongestTail Heuristic. One of the applicability of the method is to obtainlower bounds for NP-hard one-machine and job-shop schedulingproblems. We present some computational results of thisapplication, followed by some conclusions.

A mixed-integer linear programming approach to the optimization of event-bus schedules: a scheduling application in the tourism sector

This paper deals with “The Enchanted Journey,” which is a daily event tour booked by Bollywood-film fans. During the tour, the participants visit original sites of famous Bollywood films at various locations in Switzerland; moreover, the tour includes stops for lunch and shopping. Each day, up to five buses operate the tour. For operational reasons, however, two or more buses cannot stay at the same location simultaneously. Further operative constraints include time windows for all activities and precedence constraints between some activities. The planning problem is how to compute a feasible schedule for each bus. We implement a two-step hierarchical approach. In the first step, we minimize the total waiting time; in the second step, we minimize the total travel time of all buses. We present a basic formulation of this problem as a mixed-integer linear program. We enhance this basic formulation by symmetry-breaking constraints, which reduces the search space without loss of generality. We report on computational results obtained with the Gurobi Solver. Our numerical results show that all relevant problem instances can be solved using the basic formulation within reasonable CPU time, and that the symmetry-breaking constraints reduce that CPU time considerably.

Data-Aware Scheduling in Datacenters

Datacenters have emerged as the dominant form of computing infrastructure over the last two decades. The tremendous increase in the requirements of data analysis has led to a proportional increase in power consumption and datacenters are now one of the fastest growing electricity consumers in the United States. Another rising concern is the loss of throughput due to network congestion. Scheduling models that do not explicitly account for data placement may lead to a transfer of large amounts of data over the network causing unacceptable delays. In this dissertation, we study different scheduling models that are inspired by the dual objectives of minimizing energy costs and network congestion in a datacenter. As datacenters are equipped to handle peak workloads, the average server utilization in most datacenters is very low. As a result, one can achieve huge energy savings by selectively shutting down machines when demand is low. In this dissertation, we introduce the network-aware machine activation problem to find a schedule that simultaneously minimizes the number of machines necessary and the congestion incurred in the network. Our model significantly generalizes well-studied combinatorial optimization problems such as hard-capacitated hypergraph covering and is thus strongly NP-hard. As a result, we focus on finding good approximation algorithms. Data-parallel computation frameworks such as MapReduce have popularized the design of applications that require a large amount of communication between different machines. Efficient scheduling of these communication demands is essential to guarantee efficient execution of the different applications. In the second part of the thesis, we study the approximability of the co-flow scheduling problem that has been recently introduced to capture these application-level demands. Finally, we also study the question, "In what order should one process jobs?'' Often, precedence constraints specify a partial order over the set of jobs and the objective is to find suitable schedules that satisfy the partial order. However, in the presence of hard deadline constraints, it may be impossible to find a schedule that satisfies all precedence constraints. In this thesis we formalize different variants of job scheduling with soft precedence constraints and conduct the first systematic study of these problems.

The Resource-Constrained Project Scheduling Problem with Work-Content Constraints

For executing the activities of a project, one or several resources are required, which are in general scarce. Many resource-allocation methods assume that the usage of these resources by an activity is constant during execution; in practice, however, the project manager may vary resource usage by individual activities over time within prescribed bounds. This variation gives rise to the project scheduling problem which consists in allocating the scarce resources to the project activities over time such that the project duration is minimized, the total number of resource units allocated equals the prescribed work content of each activity, and precedence and various work-content-related constraints are met.