异构计算系统中弹性节能调度策略研究

目前,节能已成为异构计算系统中减少电量开销、提高系统可靠性和保护环境的重要研究内容.传统的节能调度策略侧重于研究如何节能而忽略了用户对任务完成时间的期望,使得任务执行效果受到较大影响.特别是当系统负载较重时,由于电压调节缺乏自适应性,导致在某些情况下(如应急服务)的任务执行效果不可容忍.文中提出一种弹性节能调度策略(Elastic Energy-Aware Scheduling,EEAS),用于动态调度异构计算系统中非周期、独立任务.EEAS策略根据系统负载情况在系统节能与用户期望之间进行权衡,即当系统负载较重时,EEAS优先考虑用户期望,通过动态调整计算节点局部队列中等待任务的执行电压提高任务完成率;当系统负载较轻时,EEAS在尽量满足用户期望的基础上最大限度地降低任务执行电压以实现节能.文中通过大量的模拟实验比较了EEAS、GEA、HVEA和LVEA的性能.实验结果表明,EEAS的调度质量优于其他策略,可有效提高系统弹性.     

一种柔性路径下的跨单元调度方法

针对单元制造系统(Cellular manufacturing system, CMS)中需要多个单元协作完成的特殊工件, 提出柔性路径下跨作业(Job shop)单元的特殊工件调度方法---基于信息素的方法(Pheromone-based approach, PBA).基于多Agent对单元制造系统建立模型, 提出了冗余单元的概念,建立了多Agent之间的协商机制.同时通过建立Agent联盟, 减少通信量的同时增强系统的鲁棒性和调度优化的全局性.实验结果表明,与常见的组合调度规则相比, 本文提出的方法在5种性能指标上具有显著优势.     

A three-fold approach for job shop problems: A divide-and-integrate strategy with immune algorithm

This paper presents a novel divide-and-integrate strategy based approach for solving large scale job-shop scheduling problems. The proposed approach works in three phases. First, in contrast to traditional job-shop scheduling approaches where optimization algorithms are used directly regardless of problem size, priority rules are deployed to decrease problem scale. These priority rules are developed with slack due dates and mean processing time of jobs. Thereafter, immune algorithm is applied to solve each small individual scheduling module. In last phase, integration scheme is employed to amalgamate the small modules to get gross schedule with minimum makespan. This integration is carried out in dynamic fashion by continuously checking the preceding module's machine ideal time and feasible slots (satisfying all the constraint). In this way, the proposed approach will increase the machine utilization and decrease the makespan of gross schedule. Efficacy of the proposed approach has been tested with extremely hard standard test instances of job-shop scheduling problems. Implementation results clearly show effectiveness of the proposed approach.     

Optimal cyclic single crane scheduling for two parallel train oilcan repairing lines

Crane is widely used to move a heavy object from one place to another not only in manufacturing industry but also service industry. As an important resource in the train oilcan repairing, crane scheduling affects directly the productivity of the systems. In this paper, we study cyclic single crane scheduling problem with two parallel train oilcan repairing lines, where jobs are loaded into the line at one end and unloaded at the other end. The processing time at each workstation must be within a given range. There is no buffer between these stations. A crane is used to move jobs between the workstations in two parallel lines. The objective is to schedule the moves to minimize the production cycle. We proposed a time way diagram for two parallel lines and developed a mixed integer linear programming model. Then we extended the model to the scheduling problem with multi-station to eliminate the bottleneck in lines. Examples are given to demonstrate the effectiveness of the model.     

Enhanced energetic reasoning-based lower bounds for the resource constrained project scheduling problem

We present new and effective lower bounds for the resource constrained project scheduling problem. This problem is widely known to be notoriously difficult to solve due to the lack of lower bounds that are both tight and fast. In this paper, we propose several new lower bounds that are based on the concept of energetic reasoning. A major contribution of this work is to investigate several enhanced new feasibility tests that prove useful for deriving new lower bounds that consistently outperform the classical energetic reasoning-based lower bound. In particular, we present the results of a comprehensive computational study, carried out on 1560 benchmark instances, that provides strong evidence that a deceptively simple dual feasible function-based lower bound is highly competitive with a state-of-the-art lower bound while being extremely fast. Furthermore, we found that an effective shaving procedure enables to derive an excellent lower bound that often outperforms the best bound from the literature while being significantly simpler.     

Genetic algorithms for match-up rescheduling of the flexible manufacturing systems

Scheduling plays a vital role in ensuring the effectiveness of the production control of a flexible manufacturing system (FMS). The scheduling problem in FMS is considered to be dynamic in its nature as new orders may arrive every day. The new orders need to be integrated with the existing production schedule immediately without disturbing the performance and the stability of existing schedule. Most FMS scheduling methods reported in the literature address the static FMS scheduling problems. In this paper, rescheduling methods based on genetic algorithms are described to address arrivals of new orders. This study proposes genetic algorithms for match-up rescheduling with non-reshuffle and reshuffle strategies which accommodate new orders by manipulating the available idle times on machines and by resequencing operations, respectively. The basic idea of the match-up approach is to modify only a part of the initial schedule and to develop genetic algorithms (GAs) to generate a solution within the rescheduling horizon in such a way that both the stability and performance of the shop floor are kept. The proposed non-reshuffle and reshuffle strategies have been evaluated and the results have been compared with the total-rescheduling method.     

An optimal procedure for minimizing total weighted resource tardiness penalty costs in the resource-constrained project scheduling problem

We present an optimal solution procedure for minimizing total weighted resource tardiness penalty costs in the resource-constrained project scheduling problem. In this problem, we assume the constrained renewable resources are limited to very expensive equipments and machines that are used in other projects and are not available in all periods of time of a project. In other words, for each resource, there is a dictated ready date as well as a due date such that no resource can be available before its ready date but the resources are permitted to be used after their due dates by paying penalty cost depending on the resource type. We also assume that only one unit of each resource type is available and no activity needs more than it for execution. The objective is to determine a schedule with minimal total weighted resource tardiness penalty costs. For this purpose, we present a branch-and-bound algorithm in which the branching scheme starts from a graph representing a set of conjunctions (the classical finish-start precedence constraints) and disjunctions (introduced by the resource constraints). In the search tree, each node is branched to two child nodes based on the two opposite directions of each undirected arc of disjunctions. Selection sequence of undirected arcs in the search tree affects the performance of the algorithm. Hence, we developed different rules for this issue and compare the performance of the algorithm under these rules using a randomly generated benchmark problem set.     

Exact and heuristic algorithms for the aerial refueling parallel machine scheduling problem with due date-to-deadline window and ready times

The Aerial Refueling Scheduling Problem (ARSP) can be defined as determining the refueling completion times for fighter aircrafts (jobs) on multiple tankers (machines) to minimize the total weighted tardiness. ARSP can be modeled as a parallel machine scheduling with ready times and due date-to-deadline window to minimize total weighted tardiness. ARSP assumes that the jobs have different ready times and a due date-to-deadline window between refueling due date and a deadline to return without refueling. In this paper, we first formulate the ARSP as a mixed integer programming model. The objective function is a piece-wise tardiness cost that takes into account due date-to-deadline windows and job priorities. Since ARSP is NP-hard, two heuristics are proposed to obtain solutions in reasonable computation times, namely (1) modified ATC rule (MATC), (2) a simulated annealing method (SA). The proposed heuristic algorithms are tested in terms of solution quality and CPU time through computational experiments with data randomly generated to represent aerial refueling operations of an in-theater air operation. Solutions provided by both algorithms were compared to optimal solutions for problems with up to 12 jobs and to each other for larger problems with up to 60 jobs. The results show that, MATC is more likely to outperform SA especially when the problem size increases, although it has significantly worse performance than SA in terms of deviation from optimal solution for small size problems. Moreover CPU time performance of MATC is significantly better than SA in both cases.     

Compiler-assisted energy optimization for clustered VLIW processors

Clustered architecture processors are preferred for embedded systems because centralized register file architectures scale poorly in terms of clock rate, chip area, and power consumption. Although clustering helps by improving the clock speed, reducing the energy consumption of the logic, and making the design simpler, it introduces extra overheads by way of inter-cluster communication. This communication happens over long global wires having high load capacitance which leads to delay in execution and significantly high energy consumption. Inter-cluster communication also introduces many short idle cycles, thereby significantly increasing the overall leakage energy consumption in the functional units. The trend towards miniaturization of devices (and associated reduction in threshold voltage) makes energy consumption in interconnects and functional units even worse, and limits the usability of clustered architectures in smaller technologies. However, technological advancements now permit the design of interconnects and functional units with varying performance and power modes. In this paper, we propose scheduling algorithms that aggregate the scheduling slack of instructions and communication slack of data values to exploit the low-power modes of functional units and interconnects. Finally, we present a synergistic combination of these algorithms that simultaneously saves energy in functional units and interconnects to improves the usability of clustered architectures by achieving better overall energy–performance trade-offs. Even with conservative estimates of the contribution of the functional units and interconnects to the overall processor energy consumption, the proposed combined scheme obtains on average 8% and 10% improvement in overall energy–delay product with 3.5% and 2% performance degradation for a 2-clustered and a 4-clustered machine, respectively. We present a detailed experimental evaluation of the proposed schemes. Our test bed uses the Trimaran compiler infrastructure.