Xinjie Guan

Energy efficient virtual network embedding for green data centers using data center topology and future migration

We formulate energy efficient virtual network embedding that incorporates energy costs of operation and migration for nodes and links.We prove the NP-hardness of the problem and develop a heuristic algorithm to minimize the energy consumption.We consider a practical intra-DC architecture to further improve energy efficiency.We conduct extensive evaluations and comparisons with existing algorithms to show that the proposed algorithm substantially saves energy consumption and allows high acceptance ratios. With the rapid proliferation of data centers, their energy consumption and greenhouse gas emissions have significantly increased. Some efforts have been made to control and lower energy consumption of data centers such as, proportional energy consuming hardware, dynamic provisioning, and virtualization machine techniques. However, it is still common that many servers and network resources are often underutilized, and idle servers spend a large portion of their peak power consumption.We first build a novel model of virtual network embedding in order to minimize energy usage in data centers for both computing and network resources by taking practical factors into consideration. Due to the NP-hardness of the proposed model, we develop a heuristic algorithm for virtual network scheduling and mapping. In doing so, we specifically take the expected energy consumption at different times, virtual network operation and future migration costs, and a data center architecture into consideration. Our extensive evaluation results show that our algorithm could reduce energy consumption up to 40% and take up to a 57% higher number of virtual network requests over other existing virtual mapping schemes.

Reliability and Scalability Issues in Software Defined Network Frameworks

Software Defined Network (SDN) structure has been proposed for its flexibility in deployment and management. As an implementation of SDN structure, OpenFlow protocol decouples data plane and control plane so that flexible and programmable installation and management of forwarding rules are allowed. However, on the other hand, the decoupled structure raises additional computational and network resources consumption that even may lead to fatal disasters. In this study, we examine the issues of reliability and scalability of SDN under disaster scenarios on a GENI test-bed. Observations from our experiments show that more attention should be paid to improve the reliability and scalability of SDN and its frameworks.

Application Oriented Dynamic Resource Allocation for Data Centers Using Docker Containers

Docker offers an opportunity for further improvement in data centers’ (DCs) efficiency. However, existing models and schemes fall short to be efficiently used for Docker container-based resource allocation. We design a novel application oriented Docker container (AODC)-based resource allocation framework to minimize the application deployment cost in DCs, and to support automatic scaling while the workload of cloud applications varies. We then model the AODC resource allocation problem considering features of Docker, various applications’ requirements, and available resources in cloud data centers, and propose a scalable algorithm for DCs with diverse and dynamic applications and massive physical resources.

Topology and migration-aware energy efficient virtual network embedding for green data centers

With the rapid proliferation of data centers, their energy consumption and green house gas emissions have significantly increased. Some efforts have been made to control and lower energy consumption of data centers such as proportional energy consuming hardware, dynamic provisioning and virtual-ization machine techniques. However, it is still common that many servers and network resources are often underutilized, and idle servers spend a large portion of their peak power consumption. We first built a novel model of a network virtualization in order to minimize energy usage in data centers for both computing and network resources by taking practical factors into consideration. Due to the NP-hardness of the proposed model, we have developed a heuristic algorithm for virtual network scheduling and mapping, considering expected energy consumption at different times, a data center architecture, and virtual network migration, as well as operation costs. Our evaluation results show that our algorithm could reduce energy consumption up to 40%, and take up to 57% higher number of virtual network requests over other existing virtual mapping schemes.

Application deployment using Microservice and Docker containers: Framework and optimization

Abstract To improve the scalability and elasticity of application deployment and operation in cloud computing environments, new architectures and techniques are developed and studied, e.g., microservice architecture, and Docker container. Especially, Docker container enables the sharing on operation system and supporting libraries, which is more lightweight, prompt and scalable than Hypervisor based virtualization. These features make it ideally suit for applications deployed in microservice architecture. However, existing models and schemes, which are mostly designed for Hypervisor based virtualization techniques, fall short to be efficiently used for Docker container based application deployment. To take the benefits of microservice architecture and Docker containers, we explore the optimization of application deployment in cloud data centers using microservice and Docker containers. Our goal is to minimize the application deployment cost as well as the operation cost while preserving service delay requirements for applications. In this paper, we first formulate the application deployment problem by examining the features of Docker, the requirements of microservice-based applications, and available resources in cloud data centers. We further propose a communication efficient framework and a suboptimal algorithm to determine the container placement and task assignment. The proposed algorithm works in a distributed and incremental manner, which makes it scalable to massive physical resources and diverse applications under the framework. We validate the efficiency of our solution through comparisons with three existing strategies in Docker Swarm using real traces from Google Cluster. The evaluation results show that the proposed framework and algorithm provide more flexibility and save more cost than existing strategies.

A dynamic location management service for group applications in cellular networks

Mobile telephony is rapidly evolving with new services, and one-to-many group applications, such as Push to Talk over Cellular services, are expected to be more prevalent in the near future. The core issue that needs to be addressed in order for such services to be practical on a large scale is efficiency. Cellular providers are virtualizing network functions to introduce services in an agile and cost effective manner. Location management is a key control task in cellular network operations. We propose and develop an efficient group location management scheme as a virtualized network function for group cellular applications. The performance improvement is mainly achieved by the virtualized and separate group management architecture and an efficient dynamic group profiling algorithm. We conduct theoretical analyses of our scheme for signaling cost and performance gains under diverse traffic conditions. Furthermore, we carry out extensive evaluations using both real traces and synthetic human mobility data, and we validate the efficiency of the proposed scheme in both location updates and paging.

Ant colony optimization based energy efficient virtual network embedding

The rapid proliferation of data centers has significantly increased energy consumption and green house gas emissions. Attention has focused on greening the data centers. Energy efficient virtual network embedding (EE-VNE) has been studied to save energy consumption in data centers, which has been proved to be NP-hard. Especially, when considering multiple data centers with evolving virtual network resources requirements, it becomes much more challenging to approach an optimal solution in a reasonable amount of time. We propose an Ant Colony Optimization based Energy Efficient Virtual Network Embedding and scheduling (ACO-EE-VNE) to minimize energy usage in multiple data centers for both computing and network resources by modeling the EE-VNE as a construction graph. In addition, we reduce the space complexity of ACO-EE-VNE by developing a novel way to track and update the pheromone. Our extensive evaluation results show that our ACO-EE-VNE could reduce energy consumption up to 52% and double the acceptance ratio compared with existing virtual network embedding algorithms.

Efficient Location Management Scheme for Group Applications in Cellular Networks

Mobile telephony is rapidly evolving, and one-tomany group applications, such as Push to Talk over Cellular (PoC) services, are expected to be more prevalent in the near future. The core issue that needs to be addressed in order for such services to be practical on a large scale is the efficiency. Location management is a key control task in cellular network operations. We propose an efficient group location anagement scheme for group cellular applications, using a Group Location Register (GLR) architecture and a dynamic group profiling algorithm. We have performed theoretical analysis of our scheme, and further conducted extensive evaluations using both real traces and synthetic human mobility data to show the efficiency of our scheme in both location updates and paging.