Kok-Kiong Yap

Carving research slices out of your production networks with OpenFlow

1. SLICED PROGRAMMABLE NETWORKS OpenFlow [4] has been demonstrated as a way for researchers to run networking experiments in their production network. Last year, we demonstrated how an OpenFlow controller running on NOX [3] could move VMs seamlessly around an OpenFlow network [1]. While OpenFlow has potential [2] to open control of the network, only one researcher can innovate on the network at a time. What is required is a way to divide, or slice, network resources so that researchers and network administrators can use them in parallel. Network slicing implies that actions in one slice do not negatively affect other slices, even if they share the same underlying physical hardware. A common network slicing technique is VLANs. With VLANs, the administrator partitions the network by switch port and all traffic is mapped to a VLAN by input port or explicit tag. This coarse-grained type of network slicing complicates more interesting experiments such as IP mobility or wireless handover. Here, we demonstrate FlowVisor, a special purpose OpenFlow controller that allows multiple researchers to run experiments safely and independently on the same production OpenFlow network. To motivate FlowVisor’s flexibility, we demonstrate four network slices running in parallel: one slice for the production network and three slices running experimental code (Figure 1). Our demonstration runs on real network hardware deployed on our production network at Stanford and a wide-area test-bed with a mix of wired and wireless technologies.

Investigating network architectures for body sensor networks

The choice of network architecture for body sensor networks is an important one because it significantly affects overall system design and performance. Current approaches use propagation models or specific medium access control protocols to study architectural choices. The issue with the first approach is that the models do not capture the effects of interference and fading. Further, the question of architecture can be raised without imposing a specific MAC protocol. In this paper, we first evaluate the star and multihop network topologies against design goals, such as power and delay efficiency. We then design experiments to investigate the behavior of electromagnetic propagation at 2.4 GHz through and around the human body. Along the way, we develop a novel visualization tool to aid in summarizing information across all pairs of nodes, thus providing a way to discern patterns in large data sets visually. Our results suggest that while a star architecture with nodes operating at low power levels might suffice in a cluttered indoor environment, nodes in an outdoor setting will have to operate at higher power levels or change to a multihop architecture to support acceptable packet delivery ratios. Through simple analysis, the potential increase in packet delivery ratio by switching to a multihop architecture is evaluated.

Slicing home networks

Despite the popularity of home networks, they face a number of systemic problems: (i)Broadband networks are expensive to deploy; and it is not clear how the cost can be shared by several service providers; (ii) Home networks are getting harder to manage as we connect more devices, use new applications, and rely on them for entertainment, communication and work|it is common for home networks to be poorly managed, insecure or just plain broken; and (iii) It is not clear how home networks will steadily improve, after they have been deployed, to provide steadily better service to home users. In this paper we propose slicing home networks as a way to overcome these problems. As a mechanism, slicing allows multiple service providers to share a common infrastructure; and supports many policies and business models for cost sharing. We propose four requirements for slicing home networks: bandwidth and traffic isolation between slices, independent control of each slice, and the ability to modify and improve the behavior of a slice. We explore how these requirements allow cost-sharing, outsourced management of home networks, and the ability to customize a slice to provide higher-quality service. Finally, we describe an initial prototype that we are deploying in homes.

MAX: human-centric search of the physical world

MAX is a system that facilitates human-centric search of the physical world. It allows humans to search for and locate objects as and when they need it instead of organizing them a priori. It provides location information in a form natural to humans, i.e., with reference to identifiable landmarks (e.g., on the dining table) rather than precise coordinates. MAX was designed with the following objectives: (i) human-centric operation, (ii) privacy, and (iii) efficient search of any tagged object. In the system, all physical objects, from documents to clothing, can be tagged and people locate objects using an intuitive search interface. To make search efficient, MAX adopts a hierarchical architecture consisting of tags (bound to objects), sub-stations (bound to landmarks) and base-stations (bound to localities). Tags can be marked as either public or private, with private tags searchable only by the owner. MAX also provides for privacy of physical spaces.MAX requires minimal initial configuration, and is robust to reconfiguration of the physical space. To optimize system performance, we present a methodology to design energy and delay optimal query protocols for a variety of device choices. We have implemented MAX using Crossbow motes and conducted user trials in a 5m by 5m cluttered office. The user feedback was positive, demonstrating the feasibility of MAX for human-centric search. We contend that a MAX-like search system will enable sharing (e.g., books on a college campus) and trading (e.g., buying and selling used books) of physical resources, and will be the engine for a host of new applications.

The Stanford OpenRoads deployment

We have built and deployed OpenRoads [11], a testbed that allows multiple network experiments to be conducted concurrently in a production network. For example, multiple routing protocols, mobility managers and network access controllers can run simultaneously in the same network. In this paper, we describe and discuss our deployment of the testbed at Stanford University. We focus on the challenges we faced deploying in a production network, and the tools we built to overcome these challenges. Our goal is to gain enough experience for other groups to deploy OpenRoads in their campus network.

Making use of all the networks around us: a case study in android

Poor connectivity is common when we use wireless networks on the go. A natural way to tackle the problem is to take advantage of the multiple network interfaces on our mobile devices, and use all the networks around us. Using multiple networks at a time makes makes possible faster connections, seamless connectivity and potentially lower usage charges. The goal of this paper is to explore how to make use of all the networks with todays technology. Specifically, we prototyped a solution on an Android phone. Using our prototype, we demonstrate the benefits (and difficulties) of using multiple networks at the same time.

To Hop or Not to Hop: Network Architecture for Body Sensor Networks

As Body Sensor Networks (BSNs) advance to fulfill the promise of continuous, non-intrusive, remote monitoring of patients, it is important that we achieve efficient communication between energy constrained on-body sensors. An important design choice which has significant impact on achieving this goal is the network architecture. Star architecture has been the natural choice for BSNs due to the short distances between the nodes. In this paper, we revisit this choice by quantitatively studying architecture choices using data from experiments conducted by deploying nodes operating at the 2.4 GHz band on actual human volunteers. We compare the star and multihop architectures to highlight their respective performance characteristics. In particular, we use our data to construct multihop networks with routes that maximize end-to-end Packet Delivery Ratio (PDR) and routes that minimize the average number of retransmissions. Since BSNs span an entire spectrum of applications, each with its unique constraints and requirements, there is no solution that is optimal for all applications. Instead, we show the performance across a variety of metrics and the trade-offs that are achievable. We see that a multihop network minimizing retransmissions has several advantages including having better network lifetime as well as the lowest delay and energy consumption.

Link layer behavior of body area networks at 2.4 GHz

Body Area Networks (BANs) can perform the task of continuous, remote monitoring of a patients physiological signals in diverse environments. Apart from providing healthcare professionals with extensive logs of a patients physiological history, BANs can be used to identify and react to emergency situations. We identify three important factors that afflict wireless communication in BANs: impermeability of the human body to radio waves at frequencies commonly used in BANs, efficient operation in mobile and time-varying environments, and mission-critical requirements for quick response to emergencies. An understanding of the link layer behavior of wireless sensor nodes placed on the body is crucial to address these and other challenges such as reducing energy consumption and increasing network lifetime. In this paper, we investigate link layer behavior by placing nodes on the body and directly measuring metrics of interest to engineers such as packet delivery ratio (PDR) and RSSI. Emulating a possible real-life BAN operating at the 2.4 GHz band with 12 sensor nodes, we collect over 80 hours of data from 14 volunteers in

Putting home users in charge of their network

3

Scheduling packets over multiple interfaces while respecting user preferences

different environments that BANs are expected to operate in. We analyze the data to reveal several link layer characteristics to provide insight and guidelines for the designing of BANs. We also evaluate the performance of common routing metrics on our data. Our analysis helps us make the following conclusions. Link PDR is highly affected by the environment and not significantly by the volunteer for the experiment. Routing between nodes on the same side of the body is preferred to routing between nodes on the opposite sides. For links with the same source, failure of packet transmission to a certain node, in some cases, implies the increased probability of reception for other nodes. Most errors occur in bursts of length 1, but a small fraction occur in longer periods (