Decentralized cellular networks have emerged to increase network accessibility by distributing infrastructure ownership over independent entities. Unlike the centralized setting, these architectures can allow users to connect to any untrusted base station without prior subscription. However, verification of the service is necessary in the absence of trust for commensurate payments by the user. Further, any method of verification must be non-intrusive and reliably agreed upon by the involved parties. To this end, we describe two-sided measurements where both the users and the providers independently assess the cellular service. We find that reconciling measurements from different layers of the cellular stack for a diverse set of matching observations is challenging but not impossible. Hence, new use cases such as a decentralized slicing marketplace, and contract-free roaming can be enabled by two-sided measurements. We envision applying two-sided measurements to real-time, on-demand network slicing and present an architecture that is capable of offering, as well as verifying, such slices in a scalable manner.

Human perception is at the core of lossy video compression and yet, it is challenging to collect data that is sufficiently dense to drive compression. In perceptual quality assessment, human feedback is typically collected as a single scalar quality score indicating preference of one distorted video over another. In reality, some videos may be better in some parts but not in others. We propose an approach for collecting finer-grained user feedback through an interactive tool that allows direct optimization of perceptual quality given a fixed bitrate. To this end, we built a novel web-tool which allows users to paint spatio-temporal importance maps over videos. The tool allows for interactive successive refinement: we iteratively re-encode the original video according to the painted importance maps, while maintaining the same bitrate, thus allowing the user to visually see the trade-off of assigning higher importance to one spatio-temporal part of the video at the cost of others. We use this tool to collect data in-the-wild (10 videos, 17 users) and utilize the obtained importance maps in the context of x264 coding to demonstrate that the tool can indeed be used to generate videos which, at the same bitrate, look perceptually better through a subjective study (n = 26) - and are 1.9 times more likely to be preferred by viewers. We plan on collecting a large-scale dataset using the tool for automated perceptual compression in the future. The code for the tool and dataset can be found at https://github.com/jenyap/video-annotation-tool.git.

Sharing forecasts of network timeseries data, such as cellular or electricity load patterns, can improve independent control applications ranging from traffic scheduling to power generation. Typically, forecasts are designed without knowledge of a downstream controller's task objective, and thus simply optimize for mean prediction error. However, such task-agnostic representations are often too large to stream over a communication network and do not emphasize salient temporal features for cooperative control. This paper presents a solution to learn succinct, highly-compressed forecasts that are co-designed with a modular controller's task objective. Our simulations with real cellular, Internet-of-Things (IoT), and electricity load data show we can improve a model predictive controller's performance by at least 25% while transmitting 80% less data than the competing method. Further, we present theoretical compression results for a networked variant of the classical linear quadratic regulator (LQR) control problem.

Agricultural soil moisture measurement is usually done with extensive in situ sensor deployments. These sensor networks are often difficult to install and maintain. Ground penetrating radars have also been used to do fine-grained moisture measurements in farm fields, but usually require the radar to be in or near contact with the soil. In this paper we propose a hybrid approach that combines an in situ backscatter reflector with an ultra-wideband radar that is small enough to be handheld or mounted to a drone. The underground backscatter reflector allows for accurate time-of-flight measurements. The time-of-flight is determined by the permittivity of the soil, which is influenced primarily by the soil water content for non-saline soils. We performed both laboratory and in situ measurements, achieving an average accuracy within 0.013 cm3/ cm3of the ground truth with a 90th percentile of 0.034 cm3/cm3. This demonstrates the feasibility of our approach.

We present a sensing system that determines soil moisture via RF using backscatter tags paired with a commodity ultra-wideband RF transceiver. Despite decades of research confirming the benefits, soil moisture sensors are still not widely adopted on working farms for three key reasons: the high cost of sensors, the difficulty of deploying and maintaining these sensors, and the lack of reliable internet access in rural areas. We seek to address some of these obstacles by designing a low-cost soil moisture sensing system that uses a hybrid approach of pairing completely wireless backscatter tags with a mobile reader.(p)(/p)We designed and built a backscatter tag prototype and tested our system both in laboratory and in situ at an organic farm field. Our backscatter tag has a projected battery lifetime of up to 15 years on 4xAA batteries, and can operate at a depth of at least 30cm and up to 75cm. It achieves an average accuracy within 0.01-0.03cm3/cm3of the ground truth with a 90th percentile of 0.034cm3/cm3, which is comparable to state-of-the-art commercial soil sensors, at an order of magnitude lower cost.

Cameras are key enablers for a wide range of IoT use cases including smart cities, intelligent transportation, AI-enabled farms, and more. These IoT applications require cloud software (including models) to act on the images. However, traditional task oblivious compression techniques are a poor fit for delivering images over low power IoT networks that are lossy and limited in capacity. The key challenge is their brittleness against packet loss; they are highly sensitive to small amounts of packet loss requiring retransmission for transport, which further reduces the available capacity of the network. We propose Starfish, a design that achieves better compression ratios and is graceful with packet loss. In addition to that, Starfish features content-awareness and task-awareness, meaning that we can build specialized codecs for each application scenario and optimized for task objectives, including objective/perceptual quality as well as AI tasks directly. We carefully design the DNN architecture and use an AutoML method to search for TinyML models that work on extremely low power/cost AIoT accelerators. Starfish is not only the first image compress framework that works on a $3 AIoT accelerators but also outperforms JPEG, a well-established baseline, by up to 3x, in terms of bandwidth efficiency and up to 2.5x as efficient in energy consumption. It also features graceful and gradual performance degradation in the presence of packet loss. The application-level simulation indicates that Starfish could deliver 3.7x images while providing better image quality.

We introduce the design and implementation of BackCam, a low-power wireless camera sensor platform that supports continuous realtime vision applications, all using commodity radios. In the lowest power mode, our camera board consumes only 9.7mW and continuously transmits images for over one month on two AA batteries. We introduce a novel power management system that incorporates input from the camera itself to increase battery life up to 62%. Using images and system metadata as input, we designed a feedback system between the sensor and the gateway. This allows dynamic vision application requirements to be met while consuming as little power as possible. For example, our system can temporarily increase the resolution after an object of interest is detected, then reduce it again after it has disappeared. This increases the accuracy of simplistic facial recognition by at least 25% compared to operating constantly in the lowest power mode. We implement communications using a full-duplex WiFi backscatter radio, ensuring compatibility with commodity WiFi devices. We also designed an efficient data streaming and compression pipeline straight from the camera to the backscatter transmitter, allowing us to minimize latency and avoid expensive memory writes. We deployed BackCam in a real office environment, and as a proof-of-concept, implemented basic realtime face detection and recognition.

We present BurstTracker, the first tool that developers can use to detect if the LTE downlink is the bottleneck for their applications. BurstTracker is driven by our discovery that the proprietary LTE downlink schedulers running on LTE base stations allocate resources to users in a way that reveals if a user's downlink queue runs empty during a download. We demonstrate that BurstTracker works across Tier-1 cellular providers and across a variety of network conditions. We also present a case study that shows how application developers can use this tool in practice. Surprisingly, with BurstTracker, we find that the LTE downlink may not be the bottleneck for video streaming on several Tier-1 providers, even during peak hours at busy locations. Rather, transparent TCP middleboxes deployed by these providers lead to downlink underutilization, because they force Slow-Start Restart. With a simple workaround, we improve video streaming bitrate on busy LTE links by 35%.

Modern mobile networks are facing unprecedented growth in demand due to a new class of traffic from Internet of Things (IoT) devices such as smart wearables and autonomous cars. Future networks must schedule delay-tolerant software updates, data backup, and other transfers from IoT devices while maintaining strict service guarantees for conventional real-time applications such as voice-calling and video. This problem is extremely challenging because conventional traffic is highly dynamic across space and time, so its performance is significantly impacted if all IoT traffic is scheduled immediately when it originates. In this paper, we present a reinforcement learning (RL) based scheduler that can dynamically adapt to traffic variation, and to various reward functions set by network operators, to optimally schedule IoT traffic. Using 4 weeks of real network data from downtown Melbourne, Australia spanning diverse traffic patterns, we demonstrate that our RL scheduler can enable mobile networks to carry 14.7% more data with minimal impact on existing traffic, and outpeforms heuristic schedulers by more than 2x. Our work is a valuable step towards designing autonomous, "self-driving" networks that learn to manage themselves from past data.

Popular SSD-based key-value stores consume a large amount of DRAM in order to provide high-performance database operations. However, DRAM can be expensive for data center providers, especially given recent global supply shortages that have resulted in increasing DRAM costs. In this work, we design a key-value store, MyNVM, which leverages an NVM block device to reduce DRAM usage, and to reduce the total cost of ownership, while providing comparable latency and queries-per-second (QPS) as MyRocks on a server with a much larger amount of DRAM. Replacing DRAM with NVM introduces several challenges. In particular, NVM has limited read bandwidth, and it wears out quickly under a high write bandwidth.

We believe that most future video uploaded over the network will be consumed by machines for sensing tasks such as automated surveillance and mapping rather than for human consumption. Today's systems typically collect raw data from distributed sensors, such as drones, with the computer vision logic implemented in the cloud using deep neural networks (DNNs). They use standard video encoding techniques, send it over the network, and then decompress it at the cloud before using the vision DNN. In other words, data encoding and distribution is decoupled from the sensing goal. This is bandwidth inefficient because video encoding schemes, such as MPEG4, might send data tailored for human perception but irrelevant for the overall sensing goal.

With the increase in adoption of SDN, programmable switches are becoming an attractive mechanism for enabling network operators to configure protocols without replacing networking hardware. This paper argues that the functionality of programmable switches can be extended beyond network operations to the application layer, in order to achieve significant end-to-end application performance improvements. To illustrate the potential of this new concept, we develop AppSwitch, a packet switch that also performs load balancing for key-value storage systems. Unlike existing key-value load balancers, which require each request to send an extra message to a proxy server, AppSwitch requires only a single message from the key-value client to the server. This results in a 2x reduction in end-to-end average latency and 2x throughput improvement. We implemented AppSwitch on PISCES, a P4 programmable version of Open vSwitch. Finally, we demonstrate that AppSwitch can be deployed transparently, without any changes to the key-value clients and servers.

Location information is crucial for enabling many applications in the era of Internet-of-Things (IoT). Localizing IoT devices using existing ubiquitous WiFi infrastructure enables rapid and universal deployment of IoT devices empowered with localization service. However, current WiFi-based localization systems require the target, that needs to be localized, to be equipped with a WiFi radio that actively transmits WiFi signals. Since a WiFi radio consumes lots of power for data transmission, such radio cannot be used in energy-impoverish IoT devices (for example, locating a pill bottle in an elder's apartment). This paper presents WiTag, the first system that reuses existing WiFi infrastructures for localizing low-power backscatter tags. We build upon recent work on low power tags that communicate via backscattering ambient WiFi signals and introduce novel modeling of the backscattered signal received at WiFi access points to localize the target IoT device. We prototype WiTag using off-the-shelf WiFi chips and a customized backscatter tag and show that it achieves sub-meter localization error. Thus, WiTag achieves localization error comparable to that of state-of-the-art WiFi based localization systems while consuming orders of magnitude lower power at the target IoT devices.

We introduce the design and implementation of FreeRider, the first system that enables backscatter communication with multiple commodity radios, such as 802.11g/n WiFi, ZigBee, and Bluetooth, while these radios are simultaneously used for productive data communication. Furthermore, we are, to our knowledge, the first to implement and evaluate a multi-tag system. The key technique used by FreeRider is codeword translation, where a tag can transform a codeword present in the original excitation signal into another valid codeword from the same codebook during backscattering. In other words, the backscattered signal is still a valid WiFi, ZigBee, or Bluetooth signal. Therefore, commodity radios decode the backscattered signal and extract the tag's embedded information. More importantly, FreeRider does codeword translation regardless of the data transmitted by these radios. Therefore, these radios can still do productive data communication. FreeRider accomplishes codeword translation by modifying one or more of the three dimensions of a wireless signal --- amplitude, phase and frequency. A tag ensures that the modified signal is still comprised of valid codewords that come the same codebook as the original excitation signal. We built a hardware prototype of FreeRider, and our empirical evaluations show a data rate of ~60kbps in single tag mode, 15kbps in multi-tag mode, and a backscatter communication distance up to 42m when operating on 802.11g/n WiFi.

Today, experiencing virtual reality (VR) is a cumbersome experience which either requires dedicated infrastructure like infrared cameras to track the headset and hand-motion controllers (e.g., Oculus Rift, HTC Vive), or provides only 3-DoF (Degrees of Freedom) tracking which severely limits the user experience (e.g., Samsung Gear). To truly enable VR everywhere, we need position tracking to be available as a ubiquitous service. This paper presents WiCapture, a novel approach which leverages commodity WiFi infrastructure, which is ubiquitous today, for tracking purposes. We prototype WiCapture using off-the-shelf WiFi radios and show that it achieves an accuracy of 0.88 cm compared to sophisticated infrared-based tracking systems like the Oculus, while providing much higher range, resistance to occlusion, ubiquity and ease of deployment.

The rapid growth in mobile connectivity is enabling phones to support a wide range of societally-important applications. In this work, we show that broad classes of popular mobile applications have distinct radio resource allocation signatures. Using this insight, we design a mobile application classifier, and demonstrate that (1) an application can infer its own type solely from its resource allocation patterns, and (2) anyone can accurately infer the type of application being served by each session on a particular cell tower. We present our findings by showing the breakdown of applications being served by an LTE base station belonging to a Tier 1 US provider in downtown Palo Alto. Our work encourages an open discussion about LTE standards, and whether they might need to be enhanced to mask features that can be exploited to infer application type from signals broadcast over the air.

Today, experiencing virtual reality (VR) is a cumbersome experience which either requires dedicated infrastructure like infrared cameras to track the headset and hand-motion controllers (e.g. Oculus Rift, HTC Vive), or provides only 3-DoF (Degrees of Freedom) tracking which severely limits the user experience (e.g. Samsung Gear VR). To truly enable VR everywhere, we need position tracking to be available as a ubiquitous service. This paper demonstrates WiCapture, a novel approach which leverages commodity WiFi infrastructure, which is ubiquitous today, for tracking purposes. We prototyped WiCapture using off-the-shelf WiFi radios and demonstrated that it achieves an accuracy of 0.88 cm compared to sophisticated infrared-based tracking systems like the Oculus Rift, while providing much higher range, resistance to occlusion, ubiquity and ease of deployment.

Big Data analytics and new problems in social networks, computational biology, and web connectivity led to a renewed research interest in graph processing. Due to "irregularity" of graph computations, efficient parallel graph processing faces a set of software and hardware challenges debated in literature. In this paper, by utilizing hardware performance counters, we characterize system bottlenecks, resource usage, and the efficiency of popular graph applications on the modern commodity hardware. We analyze selected graph applications (implemented in the Galois framework) on a variety of graph datasets: both scale-free graphs and meshes. Our profiling shows that with an increased number of cores the analyzed graph applications achieve a good speedup, which is highly correlated with utilized memory bandwidth. Contrary to traditional past stereotypes, we find that graph applications significantly benefit from hardware prefetchers. Moreover, the use of transparent huge pages (THP) exhibits a "double win" impact: 1) THP significantly decrease the TLB misses and page walk durations, and 2) THP boost the hardware prefetchers' performance. These insights shed light to understand the performance of emerging systems with large memories. Our profiling framework reports hardware counter values over time. It reveals the danger of using averages for a bottleneck and resource usage analysis: many applications have a time-varying behavior and stretch the usage of system resources to their peak. We discuss the new insights and remaining challenges for guiding the design of future hardware and software components for efficient graph processing.

Cellular operators want to be able to deploy small cells with the same ease as WiFi access points, to quickly address traffic hotspots in dense urban areas. However, deploying small cells has not been easy. The reason is that due to scarcity of licensed spectrum, small cells need to use the same spectrum as the existing macro cells, and they need to explicitly coordinate their spectrum usage with each other to manage interference. The challenge is that this coordination needs to happen with latencies less than a millisecond, otherwise adding small cells does not help scale the overall network capacity. Implementing such tight coordination in dense urban deployments has not been easy in practice.

We present HitchHike, a low power backscatter system that can be deployed entirely using commodity WiFi infrastructure. With HitchHike, a low power tag reflects existing 802.11b transmissions from a commodity WiFi transmitter, and the backscattered signals can then be decoded as a standard WiFi packet by a commodity 802.11b receiver. Hitch-Hike's key invention is a novel technique called codeword translation, which allows a backscatter tag to embed its information on standard 802.11b packets by just translating the original transmitted 802.11b codeword to another valid 802.11b codeword. This allows any 802.11b receiver to decode the backscattered packet, thus opening the doors for widespread deployment of low-power backscatter communication using widely available WiFi infrastructure. We show experimentally that HitchHike can achieve an uplink throughput of up to 300Kbps at ranges of up to 34m and ranges of up to 54m where it achieves a throughput of around 200Kbps.

We present xFabric, a novel datacenter transport design that provides flexible and fast bandwidth allocation control. xFabric is flexible: it enables operators to specify how bandwidth is allocated amongst contending flows to optimize for different service-level objectives such as minimizing flow completion times, weighted allocations, different notions of fairness, etc. xFabric is also very fast, it converges to the specified allocation one-to-two order of magnitudes faster than prior schemes. Underlying xFabric, is a novel distributed algorithm that uses in-network packet scheduling to rapidly solve general network utility maximization problems for bandwidth allocation. We evaluate xFabric using realistic datacenter topologies and highly dynamic workloads and show that it is able to provide flexibility and fast convergence in such stressful environments.

Switches today provide a small menu of scheduling algorithms. While we can tweak scheduling parameters, we cannot modify algorithmic logic, or add a completely new algorithm, after the switch has been designed. This paper presents a design for a {\em programmable} packet scheduler, which allows scheduling algorithms---potentially algorithms that are unknown today---to be programmed into a switch without requiring hardware redesign.

Should applications receive special treatment from the network? And if so, who decides which applications are preferred? This discussion, known as net neutrality, goes beyond technology and is a hot political topic. In this paper we approach net neutrality from a user's perspective. Through user studies, we demonstrate that users do indeed want some services to receive preferential treatment; and their preferences have a heavy-tail: a one-size-fits-all approach is unlikely to work. This suggests that users should be able to decide how their traffic is treated. A crucial part to enable user preferences, is the mechanism to express them. To this end, we present network cookies, a general mechanism to express user preferences to the network. Using cookies, we prototype Boost, a user-defined fast-lane and deploy it in 161 homes.

We present the first low power backscatter system that can be deployed completely using commodity WiFi infrastructure. With this system, a low power tag reflects existing 802.11b transmissions from a commodity WiFi transmitter, and the backscattered signals can be decoded as a standard WiFi packet by a commodity 802.11b receiver. The key invention is a novel technique called \textbf{codeword translation}, which allows a backscatter tag to embed its information on standard 802.11b packets by just translating the original transmitted 802.11b codeword to another valid 802.11b codeword. This allows any 802.11b receiver to decode the backscattered packet, thus opening the doors for widespread deployment of low-power backscatter communication using widely available WiFi infrastructure. We show experimentally that we can achieve an uplink throughput of up to 1Mbps at ranges of up to 8m and ranges of up to 50m where it achieves a throughput of around 100Kbps, which is twice as better than the recently published passive WiFi system.

Large graph processing has attracted much renewed attention due to its increased importance for a social network analysis. The efficient parallel graph processing faces a set of software and hardware issues, discussed in literature. The main cause of these challenges is the "irregularity" of graph computations and related difficulties in efficient parallelization of graph processing. Unbalanced computations, caused by uneven data partitioning, can affect application scalability. Moreover, the issue of poor data locality is another major concern, that makes the graph processing applications memory-bound. In this paper, we aim to profile how large, parallel graph applications (based on Galois framework) utilize modern systems, in particular, memory subsystem. We found that modern graph processing frameworks executed on the latest Intel multi-core systems (a single node server) exhibit a good data locality and achieve a good speedup with an increased number of cores, contrary to traditional past stereotypes. The application processing speedup is highly correlated with utilized memory bandwidth. At the same time, our measurements show that the memory bandwidth is not a bottleneck, and the analyzed graph applications are memory-latency bound. These new insights can help us in matching the resource demands of the graph processing applications to future system design parameters.

As datacenter speeds scale to 100 Gb/s and beyond, traditional congestion control algorithms like TCP and RCP converge slowly to steady sending rates, which leads to poorer and less predictable user performance. These reactive algorithms use congestion signals to perform gradient descent to approach ideal sending rates, causing poor convergence times. In this paper, we propose a proactive congestion control algorithm called PERC, which explicitly computes rates independently of congestion signals in a decentralized fashion. Inspired by message-passing algorithms with traction in other fields (e.g., modern Low Density Parity Check decoding algorithms), PERC improves convergence times by a factor of 7 compared to reactive explicit rate control protocols such as RCP. This fast convergence reduces tail flow completion time (FCT) significantly in high speed networks; for example, simulations of a realistic workloads in a 100 Gb/s network show that PERC achieves up to 4x lower 99th percentile FCT compared to RCP.

Packet scheduling in switches is not programmable; operators only choose among a handful of scheduling algorithms implemented by the manufacturer. In contrast, other switch functions such as packet parsing and header processing are becoming programmable [10, 3, 6]. This paper presents a programmable packet scheduler that allows operators to program a variety of scheduling algorithms.

We present BackFi, a novel communication system that enables high throughput, long range communication between very low power backscatter devices and WiFi APs using ambient WiFi transmissions as the excitation signal. Specifically, we show that it is possible to design devices and WiFi APs such that the WiFi AP in the process of transmitting data to normal WiFi clients can decode backscatter signals which the devices generate by modulating information on to the ambient WiFi transmission. We show via prototypes and experiments that it is possible to achieve communication rates of up to 5 Mbps at a range of 1 m and 1 Mbps at a range of 5 meters. Such performance is an order to three orders of magnitude better than the best known prior WiFi backscatter system [27,25]. BackFi design is energy efficient, as it relies on backscattering alone and needs insignificant power, hence the energy consumed per bit is small.

This paper presents the design and implementation of SpotFi, an accurate indoor localization system that can be deployed on commodity WiFi infrastructure. SpotFi only uses information that is already exposed by WiFi chips and does not require any hardware or firmware changes, yet achieves the same accuracy as state-of-the-art localization systems. SpotFi makes two key technical contributions. First, SpotFi incorporates super-resolution algorithms that can accurately compute the angle of arrival (AoA) of multipath components even when the access point (AP) has only three antennas. Second, it incorporates novel filtering and estimation techniques to identify AoA of direct path between the localization target and AP by assigning values for each path depending on how likely the particular path is the direct path. Our experiments in a multipath rich indoor environment show that SpotFi achieves a median accuracy of 40 cm and is robust to indoor hindrances such as obstacles and multipath.

This paper presents demonstration of a real-time full duplex point-to-point link, where transmission and reception occurs in the same spectrum band simultaneously between a pair of full-duplex radios. This demo first builds a full duplex radio by implementing self-interference cancellation technique on top of a traditional half duplex radio architecture. We then establish a point-to-point link using a pair of these radios that can transmit and receive OFDM packets. By changing the environmental conditions around the full-duplex radios we then demonstrate the robustness of the self-interference cancellation to adapt to the changing environment.

This paper presents, FastForward (FF), a novel full duplex relay that constructively forwards signals such that wireless network throughput and coverage is significantly enhanced. FF is a Layer 1 in-band full duplex device, it receives and transmits signals directly and simultaneously on the same frequency. It cleanly integrates into existing networks (both WiFi and LTE) as a separate device and does not require changes to the clients. FF's key invention is a constructive filtering algorithm that transforms the signal at the relay such that when it reaches the destination, it constructively combines with the direct signals from the source and provides a significant throughput gain. We prototype FF using off-the-shelf software radios running a stock WiFi PHY and show experimentally that it provides a 3× median throughput increase and nearly a 4× gain at the edge of the coverage area.

A basic precept of wireless communications is that radios cannot transmit and receive at the same time on the same frequency. This long-held assumption has informed several aspects of wireless: from radio design, to PHY, MAC and network layer designs for all kinds of wireless networks. In this talk, I will describe our research on invalidating this fundamental assumption. Specifically, I will describe the evolution of our research on self-interference cancellation over the last three years which has now shown that realizing in-band full duplex radios is possible and practical, and discuss the impact this is beginning to have on future wireless network architectures. I will also highlight the cross-disciplinary nature of the research spanning RF, DSP, PHY and MAC, and discuss both the challenges and opportunities in attacking problems that span several disciplines.

Now that our smartphones have multiple interfaces (WiFi, 3G, 4G, etc.), we have preferences for which interfaces an application may use. We may prefer to stream video over WiFi because it is fast, but VoIP over 3G because it gives continued connectivity. We also have relative preferences, such as giving Netflix twice as much capacity as Dropbox. This means our mobile devices need to schedule packets in keeping with our preferences while making use of all the capacity available. This is the natural domain of fair queuing, and this paper is about the design of a packet scheduler to meet these requirements. We show that traditional fair queueing schedulers cannot take into account a user's preferences for some interfaces over others. We present a novel packet scheduler called miDRR that meets our needs by generalizing DRR for multiple interfaces. We demonstrate a prototype running in Linux and show that it works correctly and can easily run at the speeds we need.

This paper asks the following question: could we transform the radios found in our personal gadgets into powerful multipurpose scanning devices that can detect and locate tumors, guns, buried human bodies, a la the Star Trek Tricoder? Our key insight is that if radios could measure the backscatter of their own transmissions (i.e. reflections from the environment of their transmissions), then Tricorder-style powerful object detection and localization algorithms could be realized. In this paper we focus specifically on backscatter measurement, we describe novel circuits and algorithms that can be added to existing radios to enable them to accurately and concurrently receive and disentangle their own transmissions' reflections and infer its properties.

In this paper we present pFabric, a minimalistic datacenter transport design that provides near theoretically optimal flow completion times even at the 99th percentile for short flows, while still minimizing average flow completion time for long flows. Moreover, pFabric delivers this performance with a very simple design that is based on a key conceptual insight: datacenter transport should decouple flow scheduling from rate control. For flow scheduling, packets carry a single priority number set independently by each flow; switches have very small buffers and implement a very simple priority-based scheduling/dropping mechanism. Rate control is also correspondingly simpler; flows start at line rate and throttle back only under high and persistent packet loss. We provide theoretical intuition and show via extensive simulations that the combination of these two simple mechanisms is sufficient to provide near-optimal performance.

This paper presents the design and implementation of the first in-band full duplex WiFi radios that can simultaneously transmit and receive on the same channel using standard WiFi 802.11ac PHYs and achieves close to the theoretical doubling of throughput in all practical deployment scenarios. Our design uses a single antenna for simultaneous TX/RX (i.e., the same resources as a standard half duplex system). We also propose novel analog and digital cancellation techniques that cancel the self interference to the receiver noise floor, and therefore ensure that there is no degradation to the received signal. We prototype our design by building our own analog circuit boards and integrating them with a fully WiFi-PHY compatible software radio implementation. We show experimentally that our design works robustly in noisy indoor environments, and provides close to the expected theoretical doubling of throughput in practice.

We present, pFabric, a minimalistic datacenter fabric design that provides near-optimal performance in terms of completion time for high-priority flows and overall network utilization. pFabric's design eliminates nearly all buffering on switches (switches have only ~20KB of buffering per port), requires almost no congestion control and uses only simple mechanisms at each switch. Specifically, switches are only required to locally and greedily decide what packets to schedule and drop according to priorities in the packet header and do not maintain any flow state or rate estimates. Rate-control is almost unnecessary, all flows start at line-rate and only slow down in the extreme case of congestion collapse. We show via simulations using realistic workloads and topologies that this simple design achieves near optimal flow completion times and network utilization.

Policy-makers, ISPs and content providers are locked in a debate about who can control the Internet traffic that flows into our homes. In this paper we argue that the user, not the ISP or the content provider, should decide how traffic is prioritized to and from the home. Home users know most about their preferences, and if they can express them well to the ISP, then both the ISP and user are better off. To test the idea we built a prototype that lets users express highlevel preferences that are translated to low-level semantics and used to control the network.

Current wireless network design is built on the ethos of avoiding interference. In this paper we question this long-held design principle. We show that with appropriate design, successful concurrent transmissions can be enabled and exploited on both the uplink and downlink. We show that this counter-intuitive approach of encouraging interference can be exploited to increase network capacity significantly and simplify network design. We design and implement name, a novel MAC and PHY protocol that exploits recently proposed rateless coding techniques to provide such concurrency. We show via a prototype implementation and experimental evaluation that name can provide a 60% increase in network capacity on the uplink compared to traditional Wifi that does omniscient rate adaptation and a $35\%$ median throughput gain on the downlink PHY layer as compared to an omniscient scheme that picks the best conventional bitrate.

Unlike their cellular counterparts, Wi-Fi networks do not have the luxury of a dedicated control plane that is decoupled from the data plane. Consequently, Wi-Fi struggles to provide many of the capabilities that are taken for granted in cellular networks, including efficient and fair resource allocation, QoS and handoffs. The reason for the lack of a control plane with designated spectrum is that it would impose significant overhead. This is at odds with Wi-Fi's goal of providing a simple, plug-and-play network.

This paper presents the design, implementation and evaluation of Picasso, a novel radio design that allows simultaneous transmission and reception on separate and arbitrary spectrum fragments using a single RF frontend and antenna. Picasso leverages this capability to flexibly partition fragmented spectrum into multiple slices that share the RF frontend and antenna, yet operate concurrent and independent PHY/MAC protocols. We show how this capability provides a general and clean abstraction to exploit fragmented spectrum in WiFi networks, handle coexistence in dense deployments as well as many other applications. We prototype Picasso, and demonstrate experimentally that a Picasso radio partitioned into four slices, each concurrently operating four standard WiFi OFDM PHY and CSMA MAC stacks, can achieve the same sum throughput as four physically separate radios individually configured to operate on the spectrum fragments. We also demonstrate experimentally how Picasso's slicing abstraction provides a clean mechanism to enable multiple diverse networks to coexist and achieve higher throughput, better video quality and latency than the best known state of the art approaches.

Many applications can benefit from the capability to simultaneously and independently use arbitrarily sized but separate spectrum fragments with a single radio and antenna. By this capability we mean that the radio can simultaneously transmit, simultaneously receive, or simultaneously transmit and receive on arbitrary but separate spectrum fragments. For example, we can use it for spectrum aggregation in fragmented ISM bands as shown in as shown in Fig. 2(A). A WiFi AP can run independent OFDM PHY and CSMA MAC protocols on two WiFi channels to simultaneously serve two legacy WiFi clients assigned to different channels and achieve significantly higher throughput than a legacy AP that is restricted to use only one channel at a time. Similarly, a WiFi client radio with such a capability can use it to simultaneously connect to multiple WiFi APs on different channels and obtain a much higher aggregate throughput than current radios that can transmit or receive on only one channel at a time.

Wireless spectrum is increasingly fragmented due to the growing proliferation of unlicensed wireless devices and piecemeal licensed spectrum allocations. Current radios are ill-equipped to exploit such fragmented spectrum since they expect large contiguous chunks of spectrum to operate on. In this paper we argue that future radios should provide full duplex signal shaping to the higher layers to systematically exploit fragmented spectrum. Such an architectural design would allow the radio to decouple the use of different spcetrum fragments. We present the design and implementation of Picasso, a system that provides such a general signal shaping abstraction. Picasso has two novel components: a self-interference cancellation technique and a programmable filter engine that enables it to simultaneously send and receive over different spectrum fragments. We provide an initial design and empirically evaluate the feasibility of both components.

Video streaming performance on wireless networks is choppy. The culprit is the unpredictable wireless medium, whose fluctuations results in fluctuating throughput and bit errors. Current video codecs are not equipped to handle such variations since they exhibit an all or nothing behavior. If the channel is strong and above a threshold, the video stream gets decoded perfectly. If not, typically nothing gets decoded. Thus, there is no graceful degradation with wireless conditions.

This paper presents a full duplex radio design using signal inversion and adaptive cancellation. Signal inversion uses a simple design based on a balanced/unbalanced (Balun) transformer. This new design, unlike prior work, supports wideband and high power systems. In theory, this new design has no limitation on bandwidth or power. In practice, we find that the signal inversion technique alone can cancel at least 45dB across a 40MHz bandwidth. Further, combining signal inversion cancellation with cancellation in the digital domain can reduce self-interference by up to 73dB for a 10MHz OFDM signal. This paper also presents a full duplex medium access control (MAC) design and evaluates it using a testbed of 5 prototype full duplex nodes. Full duplex reduces packet losses due to hidden terminals by up to 88%. Full duplex also mitigates unfair channel allocation in AP-based networks, increasing fairness from 0.85 to 0.98 while improving downlink throughput by 110% and uplink throughput by 15%. These experimental results show that a re- design of the wireless network stack to exploit full duplex capability can result in significant improvements in network performance.

This poster presents the design of single channel full-duplex wireless radios. The design uses a combination of RF and baseband techniques to achieve full-duplexing with minimal effect on link reliability. The poster shows two designs with different RF cancellation techniques, Antenna Cancellation and Signal Inversion Cancellation. It also discusses potential MAC and network gains with full-duplexing. It suggests ways in which a full-duplex system can solve some important problems with existing wireless systems including hidden terminals, loss of throughput due to congestion, and large end-to-end delays.

This paper presents the design, implementation and evaluation of Strider, a system that automatically achieves almost the optimal rate adaptation without incurring any overhead. The key component in Strider is a novel code that has two important properties: it is rateless and collision-resilient. First, in time-varying wireless channels, Strider's rateless code allows a sender to effectively achieve almost the optimal bitrate, without knowing how the channel state varies. Second, Strider's collision-resilient code allows a receiver to decode both packets from collisions, and achieves the same throughput as the collision-free scheduler. We show via theoretical analysis that Strider achieves Shannon capacity for Gaussian channels, and our empirical evaluation shows that Strider outperforms SoftRate, a state of the art rate adaptation technique by 70% in mobile scenarios and by upto 2.8× in contention scenarios.

The ability to detect what unlicensed radios are operating in a neigh borhood, their spectrum occupancies and the spatial directions their signals are traversing is a fundamental primitive needed by many applications, ranging from smart radios to coexistence to network management to security. In this paper we present DOF, a detector that in a single framework accurately estimates all three parameters. DOF builds on the insight that in most wireless protocols, there are hidden repeating patterns in the signals that can be used to construct unique signatures, and accurately estimate signal types and their spectral and spatial parameters. We show via experimental evaluation in an indoor testbed that DOF is robust and accurate, it achieves greater than 85% accuracy even when the SNRs of the detected signals are as low as 0 dB, and even when there are multiple interfering signals present. To demonstrate the benefits of DOF, we design and implement a preliminary prototype of a smart radio that operates on top of DOF, and show experimentally that it provides a 80% increase in throughput over Jello, the best known prior implementation, while causing less than 10% performance drop for co-existing WiFi and Zigbee radios.

Rate adaptation is a fundamental primitive in wireless networks. Since wireless channel strength varies quickly and unpredictably, senders have to constantly measure the channel and correspondingly adapt the bitrate so that the transmitted packet gets correctly decoded. Prior approaches to this problem can be divided into two classes: those that require constant and expensive feedback from the receiver about channel strength, or those that use coarse and often inaccurate inference based on packet losses to measure channel strength and decide what bitrate to use.

This paper discusses the design of a single channel full-duplex wireless transceiver. The design uses a combination of RF and baseband techniques to achieve full-duplexing with minimal effect on link reliability. Experiments on real nodes show the full-duplex prototype achieves median performance that is within 8% of an ideal full-duplexing system.

This paper describes MIXIT, a system that improves the throughput of wireless mesh networks. MIXIT exploits a basic property of mesh networks: even when no node receives a packet correctly, any given bit is likely to be received by some node correctly. Instead of insisting on forwarding only correct packets, MIXIT routers use physical layer hints to make their best guess about which bits in a corrupted packet are likely to be correct and forward them to the destination. Even though this approach inevitably lets erroneous bits through, we find that it can achieve high throughput without compromising end-to-end reliability.

Network coding substantially increases network throughput. But since it involves mixing of information inside the network, a single corrupted packet generated by a malicious node can end up contaminating all the information reaching a destination, preventing decoding. This paper introduces distributed polynomial-time rate-optimal network codes that work in the presence of Byzantine nodes. We present algorithms that target adversaries with different attacking capabilities. When the adversary can eavesdrop on all links and jam links, our first algorithm achieves a rate of , where is the network capacity. In contrast, when the adversary has limited eavesdropping capabilities, we provide algorithms that achieve the higher rate of . Our algorithms attain the optimal rate given the strength of the adversary. They are information-theoretically secure. They operate in a distributed manner, assume no knowledge of the topology, and can be designed and implemented in polynomial time. Furthermore, only the source and destination need to be modified; nonmalicious nodes inside the network are oblivious to the presence of adversaries and implement a classical distributed network code. Finally, our algorithms work over wired and wireless networks.

Network coding substantially increases network throughput. But since it involves mixing of information inside the network, a single corrupted packet generated by a malicious node can end up contaminating all the information reaching a destination, preventing decoding. This paper introducesthefirstdistributedpolynomial-timerate-optimalnetwork codes that work in the presence of Byzantine nodes. We present algorithms that target adversaries with different attacking capabilities. When the adversary can eavesdrop on all links and jam zOlinks , our first algorithm achieves a rate ofC- 2zO, where C is the network capacity. In contrast, when the adversary has limited snooping capabilities, we provide algorithms that achieve the higher rate ofC- zO. Our algorithms attain the optimal rate given the strength of the adversary. They are information-theoretically secure. They operate in a distributed manner, assume no knowledge of the topology, and can be designed and implemented in polynomial-time. Furthermore, only the source and destination need to be modified; non-malicious nodes inside the network are oblivious to the presence of adversaries and implement a classical distributed network code. Finally, our algorithms work over wired and wireless networks.

Relaying is a fundamental building block of wireless networks. Sophisticated relaying strategies at the physical layer have been developed for a single flow, but multiple flows are typically handled by time sharing the channel between the flows at the network level. In this paper, time-sharing when forwarding two data streams at the relay is compared to joint relaying and network coding that allows the relay to combine data streams. Two commonly occurring blocks in wireless networks with both unicast and multicast traffic are considered. It is shown that joint relaying and network coding can achieve gains and even double the throughput for certain channel conditions.

Opportunistic routing is a recent technique that achieves high throughput in the face of lossy wireless links. The current opportunistic routing protocol, ExOR, ties the MAC with routing, imposing a strict schedule on routers' access to the medium. Although the scheduler delivers opportunistic gains, it misses some of the inherent features of the 802.11 MAC. For example, it prevents spatial reuse and thus may underutilize the wireless medium. It also eliminates the layering abstraction, making the protocol less amenable to extensions to alternate traffic types such as multicast.

Traditionally, interference is considered harmful. Wireless networks strive to avoid scheduling multiple transmissions at the same time in order to prevent interference. This paper adopts the opposite approach; it encourages strategically picked senders to interfere. Instead of forwarding packets, routers forward the interfering signals. The destination leverages network-level information to cancel the interference and recover the signal destined to it. The result is analog network coding because it mixes signals not bits.

This paper proposes COPE, a new architecture for wireless mesh networks. In addition to forwarding packets, routers mix (i.e., code) packets from different sources to increase the information content of each transmission. We show that intelligently mixing packets increases network throughput. Our design is rooted in the theory of network coding. Prior work on network coding is mainly theoretical and focuses on multicast traffic. This paper aims to bridge theory with practice; it addresses the common case of unicast traffic, dynamic and potentially bursty flows, and practical issues facing the integration of network coding in the current network stack. We evaluate our design on a 20-node wireless network, and discuss the results of the first testbed deployment of wireless network coding. The results show that COPE largely increases network throughput. The gains vary from a few percent to several folds depending on the traffic pattern, congestion level, and transport protocol.

In this work, we apply network coding to unicast in wireless mesh networks to improve network throughput while reducing the bandwidth and power requirements. Our Opportunistic Coding protocol encodes and decodes packets based on distributed and local decisions, in order to reduce the number of transmissions required in forwarding. Unlike prior work which focuses on theorectical analysis, we take a systems approach and study the performance through both emulations and testbed experiments. Our protocol aims to balance the tradeoff between reliable and efficient packet delivery. Preliminary results show that the real benefit of network coding can exceed the theorectically predicted gain, due to cross-layer interactions.

All over the world Global System for Mobile Communication (GSM) cellular mobile networks have been upgraded to support the "always-on" general packet radio service (GPRS). Despite the apparent availability of levels of bandwidth not dissimilar to that provided by conventional fixed-wire telephone modems, the user experience using GPRS is still considerably poor. In this paper, we examine the performance of protocols such as transmission control protocol (TCP) over GPRS, and show how certain network characteristics interact badly with TCP to yield problems such as: link underutilization for short-lived flows, excess queueing for long-lived flows, acknowledgment bunching, poor loss recovery, and gross unfairness between competing flows. We present the design and implementation of a transparent TCP proxy that mitigates many of these problems without requiring any changes to the TCP implementations in either mobile or fixed-wire end systems. The proxy is interposed in the cellular provider's network, and splits TCP connections transparently into two halves-the wired and wireless sides. Connections destined for the same mobile host are treated as an aggregate due to their statistical dependence. We demonstrate packet scheduling and flow control algorithms that use information shared between the connections to maximize performance of the wireless link, while interworking with unmodified TCP peers. We also demonstrate how fairness between flows and response to loss is improved, and that queueing and, hence, network latency is reduced. We discuss how TCP enhancing proxies could be transparently deployed, and conclude that installing such a proxy into GPRS network would be of significant benefit to users.

multiQ is a passive capacity measurement tool suitable for large-scale studies of Internet path characteristics. It is the first passive tool that discovers the capacity of multiple congested links along a path from a single flow trace, and the first tool that effectively extracts capacity information from ack-only traces. It uses equally-spaced mode gaps in TCP flows' packet interarrival time distributions to detect multiple bottleneck capacities in their relative order.We validate multiQ in depth using the RON overlay network, which provides more than 400 heterogeneous, well-understood Internet paths. We compare multiQ with two other capacity measurement tools (Nettimer and Pathrate) in the first large-scale wide-area evaluation of capacity measurement techniques, and find that multiQ is highly accurate; for instance, though multiQ is passive, it achieves the same accuracy as Pathrate, which is active.

Throughout the world, GSM cellular mobile networks are being upgraded to support the "always-on" General Packet Radio Service (GPRS). Despite the apparent availability of levels of bandwidth not dissimilar to that provided by conventional fixed-wire telephone modems, the user experience using GPRS is currently considerably worse. In this paper we examine the performance of TCP and HTTP over GPRS, and show how certain network characteristics interact badly with TCP to yield problems such as: link under-utilization for short-lived flows, excess queueing for long-lived flows, ACK compression, poor loss recovery, and gross unfairness between competing flows. We present the design and implementation of a transparent TCP proxy that mitigates many of these problems without requiring any changes to the TCP implementations in either mobile or fixed-wire end systems. The proxy transparently splits TCP connections into two halves, the wired and wireless sides. Connections destined for the same mobile host are treated as an aggregate due to their statistical dependence. We demonstrate packet scheduling and flow control algorithms that use information shared between the connections to maximise performance of the wireless link while inter-working with unmodified TCP peers. We also demonstrate how fairness between flows and response to loss is improved, and that queueing and hence network latency is reduced. We conclude that installing such a proxy into GPRS network would be of significant benefit to users.