Register Now & Save Up to $200 - Early Bird Rates Expire Wednesday, August 15th CLICK HERE

AGENDA

Days


Tracks

Monday, October 01, 2018
9:00am
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
Opening Remarks
R-00
Senior Director for Technology and Industry Development Huawei Technologies (USA)
  Research
  Tutorial Training
9:15am
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
Fog Computing for Robotics and Industrial Automation – The FORA Project
R-01
Associate Professor in Distributed Systems and Security and Professor in Computer Engineering DTU Compute, Technical University of Denmark and Centre for Applied Autonomous Sensor Systems, Örebro University
We are at the beginning of a new industrial revolution, Industry 4.0, which will only become a reality through the convergence of Operational and Information Technologies (OT & IT), and this convergence will be achieved through Fog Computing. In this talk, I will introduce the Fog computing paradigm from a particular perspective as the glue between IoT, Cloud, and Edge computing. Then, I will present the FORA (Fog Computing for Robotics and Industrial Automation) project, a H2020 European Training Network (ETN) that will fund and train 15 PhD candidates in the area of Fog Computing, during the period 2017-2021. Last but not least, I will focus on one of the key aspects of this “Fog revolution,” namely cybersecurity.
Register me
  Research
9:40am
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
Fog Computing and Communications for QoE-Aware Multimedia Services
R-02
Professor National Taiwan University
Video streaming is among the most popular applications for mobile network. DASH-based adaptive video streaming is has been deployed to provide better video steaming Quality of Experience (QoE). On the other hand, the emerging fog computing and networking paradigm enables better system performance of latency sensitive applications. In this talk, system design challenges and solutions in fog-based computing/communications/caching systems will be discussed. We proposed an integrated framework of MPEG-DASH SAND service and hierarchical Fog computing architecture to provide better multimedia QoE. The proposed multimedia fog architecture along with the proposed resource allocation mechanisms optimize user QoE in fog-based video streaming services.
Register me
  Research
10:05am
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
Fog Computing as a Key Enabler of Smart/Autonomous Vehicles
R-03
Postdoctoral Research Scientist Princeton University
Fog computing enables on-time service delivery with high reliability while addressing several challenges associated with the use of cloud computing, such as network delay/failure or cost overheads of transmitting data to the cloud. Fog computing is a distributed horizontal architecture that exploits computational, storage, and networking resources along the cloud-to-thing continuum. In this presentation, I will discuss promising characteristic of fog computing that can revolutionize the vehicle industry. I will present how we have developed a fog-oriented application development framework for vehicles that integrates programmability, connectivity, and security into isolated vehicles. The proposed framework enables rapid development of new vehicular applications for already-in-market vehicles, significantly enhancing the vehicle security, passenger safety, and driving experience. It is formed around a security/privacy-friendly programmable fog node (known as SmartCore) and a middleware that enables developers to interact with the vehicle's built-in components in a safe and secure manner, preventing numerous potential threats against Internet-connected vehicles.
Register me
  Research
10:55am
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
Blockchain and Its Application to Microgrid Management
R-04
Associate Dean (Research) College of Engineering, Nanyang Technological University
In this talk, we will first brief the principles behind blockchain, i.e., decentralization, time irreversibility and anonymity. Following that, we will use microgrid management under distributed renewables generations, to illustrate how blockchain could potentially transform P2P electricity trading. We will conclude this presentation with some caution about applying blockchain blindly for new applications.
Register me
  Research
11:20am
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
Fog-enabled Intelligent IoT Services
R-05
Professor, School of Information Science and Technology Co-Director, Shanghai Institute of Fog Computing Technology (SHIFT) ShanghaiTech University, China
Fog computing has recently attracted a lot of attention from communication, computing and control communities. Together with cloud computing, edge computing, and sea computing, the research and development of fog computing technologies aims at supporting future intelligent services and societies by providing multi-layer computing resources and a horizontal service architecture across a variety of IoT networks and applications. Specifically, fog computing enables on-site data processing, information retrieval, knowledge creation, performance optimization and real-time decisions in ambient service environments.
Register me
  Research
11:45am
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
Machine Learning in the Fog for Industrial IoT
R-06
CTO and Director of IoT and Embedded Engineering Software Design Solutions, Inc
Industrial systems have unique requirements and constraints that impact the design of IoT solutions for industrial use. Industrial equipment has a long lifetime, measured often in decades, and existing legacy edge sensors that are suitable for harsh environments. Situated between the legacy Edge and the to-far-away Cloud, the Fog provides a suitable location for localized processing, including some types of Machine Learning. The Fog is near to the edge data sources, but with enough power, bandwidth, and local context to make Fog processing more capable than simple Edge processing. Ed will discuss how Fog processing is particularly suited to Industrial IoT, and how the techniques in Machine Learning can be partitioned into Cloud and Fog components. He will discuss best practices in Industrial IoT development and case studies of successful deployments.
Register me
  Research
12:10pm
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
Towards Intelligence on the Edge: Restructuring Computing to Enable the Next Generation of the IoT
R-07
Assistant Professor of Electrical and Computer Engineering Duke University
Fog computing holds the promise of making the Internet of Things applications adaptive and intelligent. To fulfill this promise, the computing operations that have been designed to work in centralized cloud systems need to be adapted to simultaneously take advantage of both local ("edge") devices and supporting cloud computing elements, along the cloud-to-things continuum. This talk describes our ongoing efforts in bringing intelligence to the edge: experimental characterizations of the properties of different edge and cloud execution options, restructuring machine learning operations to fit edge computing settings and constraints, and applying advanced edge-based intelligence in augmented reality applications.
Register me
  Research
12:35pm
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
Open Carrier Interfaces as an Enabler for Edge-Supported Services
R-14
Postdoctoral Research Fellow UC Berkeley Netsys Lab
Edge computing is an increasingly important theme for carriers and application developers. This talk will outline how a merging of serverless computing and an open-carrier interface can facilitate the growth of edge-supported services. In this model, carriers open up their edge facilities to third-party application providers (hereafter called tenants) by offering the ability to deploy network edge processing on-demand without operator intervention. There are two keys to this Open Carrier Interface (OCI) model. First, the relevant edge processing is only invoked when clients associated with that tenant attach at an edge. Thus, much like serverless computing, the cost of OCI is proportional to the usage, greatly reducing the barriers to deploying new global services. Second, the carrier interface allows the tenant to specify an overall application interaction pattern, which controls where their clients traffic should be directed and provides edge-based lookup and redirection services. The combination of these two features provides a fully-automated and cost-effective way for third-parties to deploy new global services that are enhanced by edge support.
Register me
  Research
2:00pm
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
OmniEyes: a Fog-based AI Platform for Interconnected Mobile Cameras
R-08
Professor Graduate Institute of Communication Engineering, National Taiwan University
The production of video content is witnessing a paradigm shift from professional studios to individuals. As a result, video distribution is also experiencing a shift from pure distributors such as Netflix to social media such as Facebook Live, Periscope, Snapchat, etc. Although users now have easy access to videos content generated by individuals, it is very difficult for them to access mobile videos generated by various devices. This type of video data contains contents with public interests, and can be monetized via a new video sharing/distribution platform. Unlike sharing videos generated by personal smartphones or webcams, collection and utilization of mobile videos face new technical and business challenges. From the technical perspectives, transport and storage of video data consume a significant amount of network bandwidth and storage spaces, especially when these videos are generated “on-the-go”. As a result, local processing of video data depending on the application requirements will be needed. From the business perspective, the incentive and easiness of sharing videos by individual and business contributors, privacy preservation, and monetization of video content also must be handled jointly. In this talk, a distribution platform with fog-based computing is introduced. The platform makes be use of crowd-sourcing, a novel closed-loop machine-learning architecture, and cloud-fog co-training mechanisms. With this platform, mobile devices adapt themselves to various information retrieval requests and to improve accuracy over time.
Register me
  Research
  Tutorial Training
2:25pm
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
The Future Power-Edge Platform for the Smart Grid
R-09
Professor University of Electronic Science and Technology of China
The smart grid is the choice to integrate green power resources into the energy distribution system, control power usage, and balance energy load. The smart meters, monitors and sensors are employed to responsible for two-way flows of electricity information to monitor and manage the electricity consumption. In a large smart grid, such devices and nodes produce tremendous amount of data that are hard to process, analyze and store even with cloud computing due to real-time response and privacy requirements. The data in the smart grid system needs to be processed at shorter response time, more efficient processing and smaller network pressure. Comparing with the cloud computing, fog/edge computing has the potential to address the concerns of response time requirement, battery life constraint, bandwidth cost saving, as well as data safety and privacy. In this talk, a fog/edge computing based smart grid model are introduced, which related to the power metering system, microgird system and monitoring system. Several applications and services based on this model are going to illustrate. The security challenges for this model will be given. Several solutions for those challenges are going to be presented, which include the real-time protection measure, lightweight encryption and authentication method. Especially, an end-to-end physical characteristic security mechanism can be implemented due to one hop distance under the fog/edge computing based smart grid model. Finally, the power fog/edge platform will be illustrated.
Register me
  Research
2:50pm
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
Infrastructure-as-a-Service (IaaS): When Cloud meets Edge to Provide Brokerage Services
R-10
Professor Singapore University of Technology and Design
By acquiring cloud-like capacities at the edge of wireless networks, fog computing is expected to further improve user experience. In this talk, we formulate a hybrid fog-cloud computing system where an fog device with limited local resources can rent more from a cloud node and perform resource allocation to minimize total long-term cost. The resource procurement and allocation decisions depend not only on the cloud’s multiple rental options but also on the fog’s local processing cost and capacity. We first propose an offline algorithm whose decisions are made with full information of future demand. Then, an online strategy is proposed in which the fog node makes irrevocable decisions in each timeslot without future information of demand. Numerical results acquired with Google cluster-usage traces indicate that the cost of the fog node can be remarkably reduced by using the aforementioned algorithms.
Register me
  Research
3:30pm
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
Computing Forecast: Cloudy with Widespread Fog and Mist Days Ahead
R-11
Senior Security Technical Lead for Cloud Computing National Institute of Standards and Technology (NIST) Computer Security Division
With 50 billion interconnected devices estimated by 2020, our personal lives and work environments are rapidly morphing in unforeseeable ways. However, such revolutionizing changes will only be able to turn our dreams into reality with the right infrastructure. Fog computing is one of the next big technologies, or service (or combination of these) that is not only going to transform the IT industry but also enable services and innovations that will change our lives. This talk will provide an overview of NIST’s fog computing conceptual model, including its key components and layers, fog computing essential and non-essential characteristics, and fog nodes attributes.
Register me
  Research
  Tutorial Training
3:55pm
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
Dispersed Computing in Dynamic Wireless Domains: Key Challenges and Some Approaches
R-13
Chief Scientist & Director Vencore Labs, Inc. PI Vencore Labs/Upenn/Princeton team, DARPA Dispersed Computing Program
In this talk, we will discuss the problem space of the DARPA Dispersed Computing (DCOMP) program that drives innovation in a number of key fog-related technologies and our own work in this space. At the top level, DCOMP is about mission-aware distributed scheduling of computations on top of an adaptive network substrate that runs proactive traffic engineering supported by cross-layer information. We will describe our ongoing work in the DCOMP space, particularly in the closed-world dynamic wireless network domain, including: (a) adaptation of the path cost concepts (available bandwidth, one-way latency) originally developed for the wired world to the shared-channel wireless domain, (b) new applications of the powerful protocol booster concept to data and control traffic, and (c) long-term speculative performance prediction based on meta-simulation. Throughout the talk, we will illustrate how the interfaces and implementation of the adaptive network substrate are significantly simplified via the use of P4 (Programming Protocol-Independent Packet Processors), with examples of protocol boosters and forwarding in the wireless domain, some of which may drive extensions of P4 itself.
Register me
  Research
  Tutorial Training
4:20pm
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
A Proximity-based Mobile Fog / Edge Computing Platform
R-12
CEO & Co-Founder Smartiply Inc.
Rapid growth in connected devices and video content consumption puts additional strain on the network and cloud resources, negatively impacting the customer experience. With an abundance of computing resources available at the network-edge, specifically the end-user edge devices, there is a significant opportunity for innovative cloud-dependent and cloud-less applications that can be enabled that have never been imagined before. Smartiply has developed and launched a proximity-based platform to seize this opportunity and become a pioneer in this space.
Register me
  Research
4:45pm
Monday - 10/1/18
Research (Grand Peninsula Ballroom E)
Wrap-up Session - IEEE Communications Society
R-15
  Research
Tuesday, October 02, 2018
Wednesday, October 03, 2018

DIAMOND SPONSORS

PLATINUM SPONSORS

GOLD SPONSORS

SILVER SPONSORS

MEDIA SPONSORS