Yongqiang Wang

On Periodic Scheduling of Bandwidth Reservations with Deadline Constraint for Big Data Transfer

The efficiency of bandwidth scheduling in high-performance networks is critical to the utilization of network resources and the satisfaction of user requests. In this paper, we formulate a periodic bandwidth scheduling problem to maximize the number of satisfied user requests for bandwidth reservation with deadline constraint on a fixed network path, referred to as multiple deadline-constrained bandwidth scheduling (M-DCBS). We show the NP-completeness of this problem and propose a Maximum User Number Resource Reservation Algorithm (MUNRRA). Extensive simulation results show that MUNRRA exhibits a superior performance over existing algorithms in terms of scheduling success ratio and execution time. Considering the popularity of the DCBS-based service model and the rapid expansion of high-performance networks in both speed and scope, the proposed scheduling algorithm has great potential to improve the network performance of big data applications that require the DCBS service for data transfer.

Bandwidth scheduling with multiple variable node-disjoint paths in high-performance networks

Many large-scale applications in science and business domains require the transfer of big data over high-performance networks for remote operations. Such big data transfer is increasingly supported by bandwidth reservation services that discover feasible and efficient routing options in dynamic network environments with time-varying resources. By exploring the flexility and capacity of variable paths, we formulate a generic problem of Bandwidth Scheduling with Two Variable Node-Disjoint Paths (BS-2VNDP), in which, we further consider two variable paths of fixed or variable bandwidth with negligible or non-negligible switching delay, referred to as 2VPFB/VB-0/1. We show the NP-completeness and propose a heuristic approach for each of them. We implement and test these proposed scheduling algorithms in both simulated and real-life networks. Extensive results show that they significantly outperform greedy scheduling methods in large-scale networks.

Periodic Scheduling of Deadline-Constrained Variable Slot-Bandwidth Reservations for Scientific Collaboration

With the maturity and proliferation of Software-Defined Networking (SDN), there has been an increasing number of network deployments that provide dedicated connections through on-demand and in- advance scheduling in support of data-intensive applications for global scientific collaboration. In such dedicated network environments, bandwidth scheduling serves as a key technique to improve the utilization of network resources and meet diverse user requests. In this paper, we formulate a periodic bandwidth scheduling problem to maximize the number of satisfied user requests for variable slot-bandwidth reservation under deadline constraint on a network path, referred to as VSBR- DC. We show that VSBR-DC is NP-complete, and propose a bandwidth scheduling algorithm based on optimal scheduling order and allocation strategy, referred to as OSOAS-BS. Extensive simulation results show that OSOAS-BS has a superior performance in terms of scheduling success ratio over three heuristic algorithms designed for performance comparison, and may be used to facilitate scientific collaboration that requires VSBR- based reservation services for coordinated data transfer over high- speed network links.

Bandwidth scheduling for big data transfer using multiple fixed node-disjoint paths

Many large-scale applications require the transfer of big data over high-performance networks for remote operations. Such requirements call for a fast bandwidth scheduling solution to discover feasible and efficient reservation options in network environments with time-varying bandwidths. We formulate a generic problem of Bandwidth Scheduling with Two Node-Disjoint Paths (BS-2NDP) to support big data transfer. In BS-2NDP, we further consider two different types of paths: (i) two fixed paths with fixed bandwidth (2FPFB), and (ii) two fixed paths with variable bandwidth (2FPVB). We prove that both 2FPFB and 2FPVB are NP-complete, and design a heuristic approach for each of them. We implement and evaluate these scheduling algorithms in both simulated and real-life networks. Extensive results show that the proposed heuristics achieve a close-to-optimal performance in small-scale networks, and significantly outperform other heuristic approaches in large-scale networks.

Periodic Scheduling of Deadline-Constrained Bandwidth Reservations for Scientific Collaboration

As Software-Defined Networking (SDN) continues to mature and proliferate, many large computing and storage facilities are now connected by high-speed links to support global scientific collaboration. In such dedicated network environments, bandwidth scheduling plays a critical role in improving the utilization of network resources and meeting diverse user requests. In this paper, we formulate a periodic bandwidth scheduling problem to maximize the number of satisfied user requests for fixed-bandwidth floating-slot reservation under deadline constraint on a network path, referred to as FBFS-DC. We prove that FBFS-DC is NP-complete, and propose a bandwidth scheduling algorithm based on product of bandwidth and slot, referred to as Product-BS. Extensive simulation-based scheduling experiments show that Product-BS has a superior performance in terms of scheduling success ratio over three heuristic algorithms designed for performance comparison. The proposed scheduling algorithm has great potential to improve the performance of collaborative scientific applications that require the FBFS service for coordinated network-based operations.

On periodic scheduling of fixed-slot bandwidth reservations for big data transfer

The efficiency of bandwidth scheduling in high-performance networks (HPNs) is critical to the utilization of network resources and the satisfaction of user requests. We consider a periodic bandwidth scheduling problem to maximize the number of satisfied fixed-slot bandwidth reservation requests, referred to as multiple fixed-slot bandwidth scheduling (MFSBS), which is shown to be NP-complete. We first design a minimum resource occupation algorithm for a special type of M-FSBS with identical slots, referred to as MinRO-IS, and further propose a generalized version of MinRO for M-FSBS with arbitrary slots. We also design four greedy algorithms for performance comparison. Extensive simulation results illustrate that both MinRO-IS and MinRO have a superior performance over the existing algorithms in the literature and the other four greedy algorithms in comparison. Considering the popularity of the FSBS-based service model and the rapid expansion of HPNs in both speed and scope, the proposed scheduling algorithms have great potential to improve the network performance of big-data applications that require the FSBS service in HPNs.

Energy-Efficient Dynamic Consolidation of Virtual Machines in Big Data Centers

There is a rapidly growing demand for computing power driven by big data applications, which is typically met by constructing large-scale data centers provisioning virtualized resources. Such data centers consume an enormous amount of energy, resulting in high operational cost and carbon dioxide emission. Meanwhile, cloud providers need to ensure Quality of Service (QoS) in the computing solution delivered to their customers, and hence must consider the power-performance trade-off. We propose a virtual machine (VM) consolidation optimization framework, consisting of three optimization processes in big data centers: (i) VM allocation, (ii) overloaded physical machine (PM) detection and consolidation, and (iii) underloaded PM detection and consolidation. We show that the optimization problem is NP-complete, and design a resource management scheme that integrates three algorithms, one for each optimization process. We implement and evaluate the proposed resource management scheme in CloudSim and conduct simulations on a real workload trace of PlanetLab. Extensive simulation results show that the proposed solution yields up to 21.5% reduction in energy consumption, 34.2% reduction in performance degradation due to migration, 70.2% reduction in SLA violation time per active host, and 68% reduction in Energy and SLA Violations (ESV), respectively, in comparison with state-of-the-art solutions.