Pang-Wei Tsai

A hybrid meta-heuristic algorithm for VM scheduling with load balancing in cloud computing

AbstractVirtual machine (VM) scheduling with load balancing in cloud computing aims to assign VMs to suitable servers and balance the resource usage among all of the servers. In an infrastructure-as-a-service framework, there will be dynamic input requests, where the system is in charge of creating VMs without considering what types of tasks run on them. Therefore, scheduling that focuses only on fixed task sets or that requires detailed task information is not suitable for this system. This paper combines ant colony optimization and particle swarm optimization to solve the VM scheduling problem, with the result being known as ant colony optimization with particle swarm (ACOPS). ACOPS uses historical information to predict the workload of new input requests to adapt to dynamic environments without additional task information. ACOPS also rejects requests that cannot be satisfied before scheduling to reduce the computing time of the scheduling procedure. Experimental results indicate that the proposed algorithm can keep the load balance in a dynamic environment and outperform other approaches.

Design and Implementation of an Automatic Network Topology Discovery System for the Future Internet Across Different Domains

In part because of the limitations of the TCP/IPprotocols used by the current Internet, the Future Internet has become an attractive network research topic. Recently, several projects focused on the Future Internet have been launched around the globe based on the Open Flow platform, such as those that are part of the GENI project in the U.S., the OFELIA project of FP7 in the E.U., and the FIRST project in Korea. Because Open Flow allows researchers to design and develop innovative protocols, it could be applied in different situations for constructing desired network environments. Open Flow is not limited to single controller environment within a single network domain. It allows network engineers to construct a multi-controller environment across various network domains. In this paper, we design and implement an automatic network topology discovery mechanism based on multi-controller Open Flow network. The result has been applied to a large-scale Open Flow testbed implemented across research institutes at different sites for path-finding and management.

Network Virtualization Implementation over Global Research Production Networks

The concept of network virtualization has attracted increasing attention by researchers designing and modeling the next-generation Internet paradigm. Researchers need a new type of hybrid network to construct experimental environments for testing new services, architecture, and technologies, especially network protocols, without affecting existing traffic. This paper presents our work on implementing a large-scale testbed that has been created over production networks by integrating novel technologies such as cloud computing, software defined networking, and virtual switches. This approach provides researchers with an experimental networking testbed where traffic can be controlled via programmable virtual switches and dynamic adjustability for many types of network emulation experiments. This system also provides a feasible solution for the networking requirements of federated cloud system.

Leveraging open-source software for federated multisite SDN-cloud playground

This paper shows a prototyping and operating effort for a federated multisite SDN-Cloud playground that leverages open-source software such as OpenStack cloud, ONOS SDN controller, and Quagga router. A SDN-based federation possibility for distributed multisite cloud is verified by providing an open playground over three international sites under separate administrative domains.

Supporting Extensions of VLAN-tagged Traffic across OpenFlow Networks

This paper proposes a tag-translated mechanism enabling VLAN translation on OpenFlow networks. The mechanism offers dynamic VLAN mapping on the edge switches of OpenFlow networks, and also supports the transparent transmission of traffic flows across non-OpenFlow networks by using a centralized controller to maintain the VLAN information. The contribution of this development is twofold: the first is that it provides a dynamic setup of a virtual network from the upper level, which adds more flexibility into management and more effective usage of network resources; the second is that it provides a solution to fulfil the requirements under the specific environment of OpenFlow experimental networks in Taiwan.

Planning and Implantation of NetFPGA Platform on Network Emulation Testbed

The concepts of cloud computing and Internet applications have expanded gradually and have become more and more important. Researchers need a new, high-speed network to build experimental environments for testing new network protocolswithout affecting existing traffic. In this paper, we describe a way to integrate NetFPGA platform, OpenFlow concept and NetFPGA reference designs into anetwork testbed to improve the packet processing speed and the dynamic adjustability for network emulation experiments. Furthermore, combined with Tunneling and VPLS, the proposed network testbed can be connected to distributed network, thus providing researchers a traffic-controllable and NIC-programmable experimental networking testbed in intra-communicating part.

Control frameworks in network emulation testbeds: A survey

Abstract The network emulation testbed is a promising research area because it provides a platform to fulfill testing requirements, creating emulated environments for conducting experiments. Through such testbeds, heterogeneous resources can be well controlled as emulated environment, and new ideas can be verified in the environment without interfering the real world. Thus, it can be used to reduce the time of the developers for conducting experiment to explore new inventions. Various kinds of network emulation testbed have been around for years, and it can be expected that more testbeds will emerge. To provide an integrated perspective of network emulation testbed, this paper surveys the issues associated in developing network emulation testbeds, including the state-of-the-art of architecture, the interoperability of orchestrating resources, and the way of managing components. Several wide-area, geographically distributed and large-scale network testbeds have been reviewed and discussed. Finally, critical research findings, open issues, and possible future research directions have also been provided.

On the implementation of path switching over SDN-enabled network: A prototype

Since Software-Defined Networking (SDN) technologies have been commonly used in networking components for designing Future Internet, the fault tolerance design becomes a fundamental requirement in network deployment. This paper presents a prototype of path switching method based on OpenFlow protocol. In contrast of the traditional network architecture, this implementation provides an adaptive path switching method when link failure is detected, which reducing the time of interruption.

Data analytics for internet of things: A review

The internet of things (IoT), which provides a way to connect every “thing” via the internet to further develop a convenient environment, has been around for more than a decade. The trend of the development of IoT nowadays is to focus not only on its devices and systems but also on data analysis. The main reason is that data from sensors or systems typically contain valuable information that is very useful for improving the system performance or providing a better service to the user if we come up with a good “data analysis” solution. This paper begins with a brief review of data mining technologies for IoT. Then, a reference data analytics architecture is given to show how data analysis technologies can be applied to an IoT system. Finally, applications, open issues, and possible research directions are addressed.

Network Monitoring in Software-Defined Networking: A Review

Monitoring is an important concept in network management as it helps network operators to determine the behavior of a network and the status of its components. Traffic engineering, quality of service, and anomaly detection also depend on monitoring for decision making. Software-defined networking (SDN) is becoming increasingly popular for network provision and management tasks. This paper surveys the tasks and challenges associated with SDN, providing an overview of SDN monitoring developments. Several design concepts, research directions, and open issues are also discussed.