We consider a video delivery problem in which a server multicasts a single video to several users over a wireless broadcast channel. Users arrive and depart asynchronously, and when a user arrives, he or she wishes to...
详细信息
ISBN:
(纸本)9781479934096
We consider a video delivery problem in which a server multicasts a single video to several users over a wireless broadcast channel. Users arrive and depart asynchronously, and when a user arrives, he or she wishes to watch the video from its beginning. Under a natural stochastic model for this problem, the optimal scheduling algorithm can be described by dynamic programming, but it is too complex to be practical. We describe a suite of approximations to the optimal scheme that lead to practical scheduling algorithms. The algorithms work with partially observed state, multirate multicast, and a variety of cost functions. Numerical results show significant performance gains over previously known schemes.
A multimedia server has to provide bandwidth compatible best QoS perception for end users. It has to perform transcoding to serve users under different network environments and with different devices. In this paper, w...
详细信息
ISBN:
(纸本)9781467364997
A multimedia server has to provide bandwidth compatible best QoS perception for end users. It has to perform transcoding to serve users under different network environments and with different devices. In this paper, we proposed a stability-driven hierarchical scheduling algorithm for a cloud-based video streaming system to speed up the video transcoding process for real-time service applications. It helps to coordinate the system operations and dynamically adjust the number of slots so that the cloud clusters can finish the process more efficiently. Experimental results showed that the proposed scheduling control methods help to maintain good system load balancing. The resource utilization of the entire cloud clusters can be as high as 98%, and the total transcoding time can be reduced by 10%-19%.
It is important for ultra-dependable system to guarantee real-time performance. In this paper, an on-line hard real-time scheduling technique called HRTCS is presented, which is applicable for scheduling packets (mess...
详细信息
ISBN:
(纸本)9780769532875
It is important for ultra-dependable system to guarantee real-time performance. In this paper, an on-line hard real-time scheduling technique called HRTCS is presented, which is applicable for scheduling packets (messages) over a link. The scheduling technique can rapidly judge the schedulability and then automatically generate a bus table to schedule periodic and aperiodic packets. Using HRTCS not only guarantees the hard real time performance but also avoids the blockage and interruption of the packet transmission. Test results show that HRTCS can reduce the scheduling overhead and get higher bandwidth utilization than traditional scheduling algorithms. In addition, the FOLS policy of HRTCS provides a method to handle communication traffic variation rapidly during application system running. Therefore, HRTCS perfectly meets the demand of hard real-time communication on the ultra-dependable system.
This paper presents a scheduling algorithm that improves on other approaches when dealing with the synthesis of control-flow dominated behavioral descriptions. It achieves this through the use of a constraint- driven ...
详细信息
ISBN:
(纸本)0818670398
This paper presents a scheduling algorithm that improves on other approaches when dealing with the synthesis of control-flow dominated behavioral descriptions. It achieves this through the use of a constraint- driven path-based scheduling algorithm. The sub- optimality of the oriqinal path-based algorithms when dealing with loops is overcome through a new technique for pipelining different loop iterations during execution path generation. Results show that the algorithm always generates the fastest solution in terms of clock cycles.
In recent years, manY researchers have proposed several algorithms to schedule critical tasks in a homogeneous multiprocessor system for obtaining a shorter scheduling length. However, for heterogeneous computing syst...
详细信息
ISBN:
(纸本)9781424446001
In recent years, manY researchers have proposed several algorithms to schedule critical tasks in a homogeneous multiprocessor system for obtaining a shorter scheduling length. However, for heterogeneous computing systems, such methods may lead to lengthen the execution of other non-critical tasks. In this paper, a Non-critical Path Earliest-Finish (NPEF) scheduling algorithm for heterogeneous computing systems has been proposed to eliminate the problem mentioned above. From the experimental results, the proposed method is proven to be an effective scheduling scheme in heterogeneous computing environments.
Real-time embedded systems usually integrate multiple functionalities of different criticality levels on a shared hardware platform. For these mixed-criticality real-time systems it is a challenging problem to efficie...
详细信息
ISBN:
(纸本)9781479940226
Real-time embedded systems usually integrate multiple functionalities of different criticality levels on a shared hardware platform. For these mixed-criticality real-time systems it is a challenging problem to efficiently utilize system resource to satisfy all the timing constraints on different criticality levels. A simple yet efficient algorithm EDF-VD has recently been proposed to schedule mixed-criticality real-time systems, and shown promising real-time performance. However, the competency of EDF-VD has not been fully exploited due to the imprecise underlying analysis techniques. In this paper, we develop new schedulability analysis methods for EDF-VD. Different from previous analysis methods that separate the analysis on each individual criticality level, our new analysis looks into system behavior crossing multiple criticality levels to obtain more precisely analysis results. Experiments show that our new analysis method can significantly improve guaranteed schedulability of EDF-VD, especially for systems with more criticality levels. The price paid for improved schedulability is higher analysis complexity, but a combination of our new techniques and previous methods can obtain a good balance between the analysis precision and efficiency.
To avail the benefits of a multi-antenna system, multi-user (MU) multiple-input multiple-output (MIMO) systems multiplex different user data streams spatially over timefrequency resources. However, serving dozens of u...
详细信息
ISBN:
(纸本)9781467385763
To avail the benefits of a multi-antenna system, multi-user (MU) multiple-input multiple-output (MIMO) systems multiplex different user data streams spatially over timefrequency resources. However, serving dozens of users with spatial multiplexing increases the scheduler complexity significantly. In this work, we demonstrate the computational requirements of different state-of-the-art MU-MIMO scheduling algorithms and evaluate the number of users that can be supported in real-time. To provide a fair comparison, we initially analyze the achievable sum rate of various scheduling algorithms using MATLAB for different MIMO configurations. We also propose a modification to the existing scheduling algorithm to improve the sum rate. We then implement the scheduling algorithms on Xilinx ZYNQ-ZC702 System-on-Chip (SoC) to illustrate the advantages.
To analyze scheduling algorithms in high-speed packet switching networks, two models have been proposed and widely used in the literature, namely the Guaranteed Rate (GR) server model [9] and the Latency Rate (LR) ser...
详细信息
ISBN:
(纸本)0780376323
To analyze scheduling algorithms in high-speed packet switching networks, two models have been proposed and widely used in the literature, namely the Guaranteed Rate (GR) server model [9] and the Latency Rate (LR) server model [15], While a lot scheduling algorithms have been proved to belong to GR or LR or both, it is not clear what is the relationship between them. The purpose of this paper is to investigate this relationship. We prove that if a scheduling algorithm belongs to GR, it also belongs to LR and vice versa. In addition, we review several other models that are also used for analysis of scheduling algorithms and discuss their relationship with LR model and GR model.
This paper(1) presents an efficient approach to an existing batch verification system on Identity based group signature (IBGS) which can be applied to any Mobile ad hoc network device including Vehicle Ad hoc Networks...
详细信息
ISBN:
(纸本)9781612846835
This paper(1) presents an efficient approach to an existing batch verification system on Identity based group signature (IBGS) which can be applied to any Mobile ad hoc network device including Vehicle Ad hoc Networks (VANET). We propose an optimized way to batch signatures in order to get maximum throughput from a device in runtime environment. In addition, we minimize the number of pairing computations in batch verification proposed by B. Qin et al. for large scale VANET. We introduce a batch scheduling algorithm for batch verification targeting further minimization the batch computation time.
In their widely-cited survey on mixed-criticality systems, Burns and Davis describe a very general model for representing mixed-criticality sporadic tasks. In this general model multiple estimates, at differing levels...
详细信息
ISBN:
(纸本)9781509053032
In their widely-cited survey on mixed-criticality systems, Burns and Davis describe a very general model for representing mixed-criticality sporadic tasks. In this general model multiple estimates, at differing levels of assurance, are specified for each of the three parameters-worst-case execution time (WCET), relative deadline, and period-characterizing a 3-parameter sporadic task. The preemptive uniprocessor scheduling of systems of such tasks is considered. A scheduling algorithm is presented, proved correct, and quantitatively characterized via the speedup factor metric for dual-criticality systems of such tasks. To our knowledge, this is the first work to conduct any form of analysis of task systems that are represented using this general model.
暂无评论