Grid computing is the enabling technology for high performance computing in scientific and large scale applications. Grid computing introduces a number of fascinating issues to resource management. Grid scheduling is ...
详细信息
ISBN:
(纸本)9783642221699
Grid computing is the enabling technology for high performance computing in scientific and large scale applications. Grid computing introduces a number of fascinating issues to resource management. Grid scheduling is a vital component of a Grid infrastructure. Reliability, efficiency (in terms of time consumption) and effectiveness in resource utilization are the desired quality attributes of Grid scheduling systems. Many algorithms have been developed for Grid scheduling. In our previous work, we proposed two scheduling algorithms (the Multilevel Hybrid scheduling Algorithm and the Multilevel Dual Queue scheduling Algorithm) for optimum utilization of CPUs in a Grid computing environment. In this paper, we propose two more flavours of Multilevel Dual Queue scheduling algorithms, i.e. the Dynamic Multilevel Dual Queue scheduling Algorithm using Median and the Dynamic Multilevel Dual Queue scheduling Algorithm using Square root. We evaluate our proposed Grid scheduling, in comparison to other well known scheduling algorithms, on an SGI super computer using parts of the 'AuverGrid' workload trace. The main purpose of scheduling algorithms is to execute jobs optimally, i.e. with minimum average waiting, turnaround and response times. An extensive performance comparison is presented using real workload traces to evaluate the efficiency of the scheduling algorithms. To facilitate the research, a software tool has been developed which produces a comprehensive simulation of a number of Grid scheduling algorithms. The tool's output is in the form of scheduling performance metrics. The experimental results, based on performance metrics, demonstrate that our proposed scheduling algorithms yield improvements in terms of performance and efficiency. Our proposed scheduling algorithms also support true scalability, that is, they maintain an efficient approach when increasing the number of CPUs or nodes. This paper also includes a statistical analysis of the 'AuverGrid' real workl
作者:
John, Jullian U.Pillay, ShaminiUCSI
Centre for Research Excellence UCSI Heights No.1 Jalan Menara Gading 56000 Kuala Lumpur Malaysia School of Engineering
UCSI University College Sedaya International UCSI Heights No.1 Jalan Menara Gading 56000 Kuala Lumpur Malaysia
This paper presents a performance review on three basic scheduling algorithms employed for the High Speed Downlink Packet Access (HSDPA) in the Universal Mobile Telecommunication Systems (UMTS) networks. These algorit...
详细信息
ISBN:
(纸本)0889865906
This paper presents a performance review on three basic scheduling algorithms employed for the High Speed Downlink Packet Access (HSDPA) in the Universal Mobile Telecommunication Systems (UMTS) networks. These algorithms are employed at the Node B - also known as the base station - to schedule the time-slots and orthogonal codes for the transmission of data packets to the users. The basic algorithms studied in this simulation are the Round Robin (RR), Maximum Carrier-to-interference ratio (M-CI) and the Proportional Fairness (PF). The algorithms are compared and analysed in terms of cell throughput, user bit rates, and resource distribution fairness. M-CI provided the highest cell throughput and user bit rate with over 41% more throughput than the RR. RR on the other hand showed a very fair resource distribution. The PF algorithm was a trade-off between the M-CI and RR, and provided 14% more cell throughput than the RR and significantly better resource distribution than the M-CI.
We investigate the performance of TCP under several packet scheduling algorithms at the router. Our main focus is how fair service can be provided for elastic applications sharing the link capacity. For this purpose, ...
详细信息
Many high-end computing (HEC) centers and commercial data centers adopt parallel file systems (PFSs) as their storage solutions. As the number of applications concurrently accessing a PFS grows in both quantity and va...
详细信息
ISBN:
(纸本)9781457704284
Many high-end computing (HEC) centers and commercial data centers adopt parallel file systems (PFSs) as their storage solutions. As the number of applications concurrently accessing a PFS grows in both quantity and variety, it is expected that scheduling algorithms for data access will play an increasingly important role in PFS service quality. However, it is costly and disruptive to thoroughly research scheduling mechanisms in deployed peta- or exascale systems, compounded by the complexity in scheduling policy implementation and experimental data gathering. While a few parallel file system simulation frameworks have been proposed (e.g., [1,2]), their goals have not been in the scheduling algorithm evaluation. In this paper, we propose PFSsim, a simulator designed for the purpose of evaluating I/O scheduling algorithms in PFS. PFSsim is a trace-driven simulator based on the network simulation framework OMNeT++ [23] and the disk system simulator DiskSim [21]. A flexible scheduler module is provided for scheduling algorithm deployment, and the system characteristics are highly configurable. We have simulated PVFS2 on PFSsim, and the experimental results show that PFSsim is capable of simulating the system characteristics and showing the performance of the scheduling algorithms.
The aviation industry faces increasingly complex scheduling challenges, necessitating intelligent solutions. To address this need, an intelligent scheduling system based on artificial intelligence has been designed an...
详细信息
Radar systems require complex implementation and tests that not always are available for researchers. That is why modelling and simulation methodologies are often necessary to perform radar processing algorithms. Thes...
详细信息
ISBN:
(纸本)9780889868083
Radar systems require complex implementation and tests that not always are available for researchers. That is why modelling and simulation methodologies are often necessary to perform radar processing algorithms. These skills are effective such as for realizing the design, model and experiments, and as for the validity of the obtained results. The radar that has been developed is multifunction radar, MFAR (Multi-Function Array Radar), which joins inside the same system, and simultaneously, the classic functions of tracking and surveillance, and all the functions related to the communication, countermeasures, and calibration. All these functions constitute the tasks to execute. The task scheduler is a key element of the radar, since it realizes the planning and distribution of the energy and time resources to be shared and used by all those tasks. This paper presents schedulers based on the use of task queues. Multiple schedulers have been designed and studied, and it has been realized a comparative analysis of the different performed schedulers. A specific software tool has been designed and developed to perform the radar system, and to do all the experiments. An appropriate set of radar characteristics has been selected to evaluate the kindness of the task scheduler working.
This paper presents an efficient algorithm for scheduling vaccination process which is based on the CPU scheduling algorithms of an operating system. Based on a custom-designed scoring system of the given schedule, an...
详细信息
We describe a model for competitive online scheduling algorithms. Two servers, each with a single observable queue, compete for customers. Upon arrival, each customer strategically chooses the queue with minimal expec...
详细信息
Automated Planning & scheduling Systems are nowadays applied in a wide range of spacecraft, from satellites to Mars rovers. The planner is responsible for the generation of valid plans that determine the activitie...
详细信息
The paper presents several production scheduling algorithms and their software implementation in an experimental program system developed in the program environment of the MATLAB system. The main characteristics and f...
详细信息
ISBN:
(纸本)9789897581113
The paper presents several production scheduling algorithms and their software implementation in an experimental program system developed in the program environment of the MATLAB system. The main characteristics and functionality of the individual software modules are described and illustrated by numerical examples.
暂无评论