This event is endorsed
and organized by

1st EAI International Conference on Machine Learning and Intelligent Communications

August 27–28, 2016 | Shanghai, People's Republic of China

Prof. Kishor S. Trivedi

ECE Dept.

Duke University, USA

Capacity Planning for Infrastructure-as-a-Service Cloud

Abstract: From an enterprise perspective, one key motivation to transform the traditional IT management into Cloud is the cost reduction of the hosted services. In an Infrastructure-as-a-Service (IaaS) Cloud, virtual machine (VM) instances share the physical machines (PMs) in the provider’s data center. Increasing the number of PMs leads to lower downtime cost at the expense of higher infrastructure and other operational costs (e.g., power consumption and cooling costs). Hence, determining the optimal PM capacity that minimize the overall cost is of interest. In this paper, we show how a cost analysis and optimization framework can be developed using stochastic availability and performance models of an IaaS Cloud. Specifically, we develop and solve a cost minimization problem to address the capacity planning in an IaaS Cloud: what is the optimal number of PMs that minimizes the total cost of ownership for a given downtime and performance requirement set by service level agreements? We use simulated annealing, a well-known stochastic search algorithm, to solve the optimization model. For each point in the search space, we need to determine, the performance, availability and power consumption requirements. Hence we develop scalable analytic models for the performance, availability and power consumption analysis of an IaaS Cloud. The essence of our approach is in reducing the complexity of analysis by dividing the overall model into multiple interacting stochastic process sub-models and then obtaining the overall solution by (fixed-point) iteration over individual sub-model solutions.


Biography: Kishor Trivedi is a Chaired Professor of ECE at Duke University. He is the author of a well-known text entitled, Probability and Statistics with Reliability, Queuing and Computer Science Applications that has been translated into Chinese. He is an IEEE Fellow and Golden Core Member of IEEE Computer Society. He has published over 600 articles and have supervised 46 Ph.D. dissertations; his h-index is 89. He is the recipient of IEEE Computer Society Technical Achievement Award for research on Software Aging and Rejuvenation. He works closely with industry in carrying out reliability /availability/performability analysis, providing short courses and in the development and dissemination of software packages such as SHARPE and SPNP. 



Prof. Xiaomin Ma

Oral Roberts University, USA

Towards Intelligent Vehicular Networking for Safety Applications

Abstract: With the development of the Intelligent Transportation System (ITS) in recent years, many vehicular communication systems and networks for manned driven vehicles, autonomous (unmanned driven) vehicles, and unmanned aerial vehicles, etc. have been proposed and widely studied to support various ITS applications. The most important type of the ITS applications is safety-related applications, which requires stringent quality of service (QoS) or reliability/performance. Research on enhancing current vehicular communication systems to meet the given quality of service (QoS) for safety applications is going on.

In this presentation, enhancement and optimization of vehicular networks for safety applications with high QoS requirements from perspective of computational intelligence or machine learning are addressed. First, a short survey of current vehicular communication systems, possible safety applications with respective QoS requirements, capacity of current vehicular networks, and challenges is given. Second, solutions to dealing with the challenges and enhancing the vehicular networking such as combination of multiple channels, device-to-device (D2D) communication, heterogeneous vehicular networking, and cloud (fog) vehicular networks for spectrum resource and traffic load sharing are summarized and discussed. Third, the intelligent components in the vehicular networking structures for the safety applications that can be formulated as QoS constraint optimization (machine learning) problems are identified so that optimal decisions on choices of channels, communication parameters, and heterogeneous network cooperation can be made and adjusted dynamically under different vehicular communication environments and traffic loads. Furthermore, the candidate computational intelligence (machine learning) algorithms and models are introduced and compared for the purpose of intelligent vehicular networks. Finally, some prospective research topics on intelligent vehicular networks for safety applications with required QoS are suggested. This research will speed up development and dissemination of next-generation vehicles equipped with wireless communication capability.


Biography: Xiaomin Ma (M’03-SM’08) received B.E. and M.E. degrees in electrical engineering in 1984 and 1989, respectively. He got the Ph.D. degree in Information engineering at the Beijing University of Posts & Telecommunications, China, in 1999. From 2000 to 2002, he was a post-doctoral fellow in the Department of Electrical and Computer Engineering, Duke University, USA. He had been teaching in the field of Electrical and Computer Engineering as an assistant professor and associate professor at the Petroleum University of China for about eight years. Then, he worked in a telecommunication company (Huawei in Beijing) for a short time. Currently, he is a professor in the Department of Engineering at Oral Roberts University in U.S. He has published over 100 papers in peer-reviewed journals and conferences. He also holds a US patent. He is the recipient of Best Paper Award in IEEE International Conference on Network Infrastructure and Digital Content. He is in Editorial Board of International Journal of Vehicular Technology, Hindawi Publish House. Also, he is a guest editor of Special Issue on "Reliable and secure VANETs" in IEEE Transactions on Dependable and Secure Computing and a guest editor of Special Issue on " Emerging Technologies in Wireless Communications" in ACM/Springer Mobile Networks & Applications (MONET). His research interests include stochastic modeling and analysis of computer and communication systems, physical layer and MAC layer of vehicular ad hoc wireless networks, computational intelligence and its applications to coding, signal processing, and control, and Quality of service (QoS) and call admission control protocols in wireless networks. He is (or was) PI, Co-PI or project leader in several projects sponsored by NSF, NSF EPSCoR, Motorola, Chinese NSF, AFOSR, and ARO, etc. Currently, he is a senior member of the IEEE.


Mr. Yuan Yao

Market Development Manager at National Instruments 

From Concept to Prototype: NI Software Defined Radio Platform and 5G Overview

Abstract: National Instruments is collaborating with top researchers focused on 5G wireless communications. The graphical system design approach combines LabVIEW Communications System Design Software with SDR Platform to help researchers innovate faster. By using this approach, engineers can reduce the time form theory to results by testing their designs in a real-world environment. In this session, you will learn the key elements of NI SDR platform and four potential technologies to make 5G a reality, which include massive MIMO, densification of network, new waveforms and mmWave communications.

Biography: Yuan Yao is the Market Development Manager at National Instruments, where he is in charge of the business and market development on RF and wireless industry and application. During the current role, Yuan has established several strategic collaborations with industrial leaders to design, simulate and prototype next generation wireless systems. Prior to this position, Yuan was the technical marketing engineer for automated test program and was responsible for marketing strategy, planning and execution for PXI and RF products lines. Yuan holds dual master degree in electronics engineering from Shanghai Jiaotong University and Technical University of Berlin respectively.