RFID applications for taking inventory and processing transactions in point-of-sale (POS) systems improve operational efficiency but are not designed to provide insights about customers' interactions with products. We bridge this gap by solving the proximity grouping problem to identify groups of RFID tags that stay in close proximity to each other over time. We design DeepTrack, a framework that uses deep learning to automatically track the group of items carried by a customer during her shopping journey. This unearths hidden purchase behaviors helping retailers make better business decisions and paves the way for innovative shopping experiences such as seamless checkout (`a la Amazon Go). DeepTrack employs a recurrent neural network (RNN) with the attention mechanism, to solve the proximity grouping problem in noisy settings without explicitly localizing tags. We tailor DeepTrack's design to track not only mobile groups (products carried by customers) but also flexibly identify stationary tag groups (products on shelves). The key attribute of DeepTrack is that it only uses readily available tag data from commercial off-the-shelf RFID equipment. Our experiments demonstrate that, with only two hours training data, DeepTrack achieves a grouping accuracy of 98.18% (99.79%) when tracking eight mobile (stationary) groups.

Retailers are aiming to enhance customer experience by automating the checkout process. The key impediment here is the effort to manually align the product barcode with the scanner, requiring sequential handling of items without blocking the line-of-sight of the laser beam. While recent systems such as Amazon Go eliminate human involvement using an extensive array of cameras, we propose a privacy-preserving alternative, RFGo, that identifies products using passive RFID tags. Foregoing continuous monitoring of customers throughout the store, RFGo scans the products in a dedicated checkout area that is large enough for customers to simply walk in and stand until the scan is complete (in two seconds). Achieving such low-latency checkout is not possible with traditional RFID readers, which decode tags using one antenna at a time. To overcome this, RFGo includes a custom-built RFID reader that simultaneously decodes a tag's response from multiple carrier-level synchronized antennas enabling a large set of tag observations in a very short time. RFGo then feeds these observations to a neural network that accurately distinguishes the products within the checkout area from those that are outside. We build a prototype of RFGo and evaluate its performance in challenging scenarios. Our experiments show that RFGo is extremely accurate, fast and well-suited for practical deployment in apparel stores.

Evolved-Multimedia Broadcast Multicast Services (eMBMS) is a set of features in LTE networks to deliver bandwidth-intensive multimedia content on a point-to-multipoint basis to subscribers. The notion of a Single Frequency Network (SFN) in eMBMS allows base stations to synchronize and transmit signals in a coordinated fashion across the same frequency-time radio resources using a common modulation rate. While SFN boosts the channel quality of users via transmit diversity gain, the use of a common rate across base stations results in reduced utilization for those that can individually support much higher data rates for their users, even without the notion of an SFN. Excluding such base stations from the SFN helps them utilize their resources better by not being constrained by the common rate, but creates additional inter-cell interference from their independent transmissions. Striking a balance between SFN cooperation and resource utilization is crucial for efficiently delivering broadcast content as well as other unicast flows. We design BoLTE, which carefully addresses this tradeoff and evaluate it using a prototype implementation over an SFN testbed, realized over a cloud-based radio access network system, as well as large-scale NS3 simulations. We show that BoLTE improves overall system throughput by around 40%.

The static capacity provisioning in traditional WiFi networks (WLANs) cannot cope with the high spatiotemporal traffic variations in high-density venues such as conference centers, stadiums etc. To guarantee reliable performance, venue owners are forced to over-provision their WLANs based on worst-case traffic demand estimations, increasing capital and operational expenses. We propose AmorFi, a radically new way of deploying WLANs to handle peak traffic demands with average-case provisioning. Our key idea is to decouple baseband processing from RF transmission (inspired by the cloud-RAN concept in cellular networks) and introduce software programmability to flexibly allocate WiFi capacity in real time based on varying traffic demands. We implement AmorFi using off-the-shelf WiFi APs over a RF-over-fiber cloud-RAN testbed. Our experiments and simulations demonstrate that the software-defined capacity allocation enabled with AmorFi delivers more than $2x$ throughput than traditional WLANs.

Beamforming is a signal processing technique with numerous benefits in wireless communication. Unlike traditional omnidirectional communication, it focuses the energy of the transmitted and/or the received signal in a particular direction. Although beamforming has been extensively studied on conventional systems such as WiFi, little is known about its practical impact on performance in orthogonal frequency-domain multiple access (OFDMA) small-cell deployments. Since OFDMA schedules multiple clients (users) in the same frame in contrast to WiFi, designing intelligent scheduling mechanisms and at the same time leveraging beamforming is a challenging task. Unlike downlink, we show that the integration of beamforming with uplink scheduling projects an interesting tradeoff between beamforming gain on the one hand, and the power-pooling gain resulting from joint multiuser scheduling on the other hand. This, in turn, makes the uplink scheduling problem even hard to approximate. To address this, we propose algorithms that are simple to implement, yet provably efficient with a worst-case guarantee of 1/2. We implement our algorithms on a real WiMAX small-cell platform integrated with an eight-element phased-array beamforming antenna. Evaluations from both prototype implementation and trace-driven simulations show that the algorithms deliver throughput gains of over 40% compared to an omnidirectional scheme.

Cloud-based radio access networks (C-RAN) have been proposed as a cost-efficient way of deploying small cells. Unlike conventional RANs, a C-RAN decouples the baseband processing unit (BBU) from the remote radio head (RRH), allowing for centralized operation of BBUs and scalable deployment of light-weight RRHs as small cells. In this work, we argue that the intelligent configuration of the front-haul network between the BBUs and RRHs, is essential in delivering the performance and energy benefits to the RAN and the BBU pool, respectively. We propose FluidNet-a scalable, light-weight framework for realizing the full potential of C-RAN. FluidNet deploys a logically re-configurable front-haul to apply appropriate transmission strategies in different parts of the network and hence cater effectively to both heterogeneous user profiles and dynamic traffic load patterns. FluidNet's algorithms determine configurations that maximize the traffic demand satisfied on the RAN, while simultaneously optimizing the compute resource usage in the BBU pool. We prototype FluidNet on a 6 BBU, 6 RRH WiMAX C-RAN testbed. Prototype evaluations and large-scale simulations reveal that FluidNet's ability to re-configure its front-haul and tailor transmission strategies provides a 50% improvement in satisfying traffic demands, while reducing the compute resource usage in the BBU pool by 50% compared to baseline schemes.

We consider the problem of maximizing the alphafairness utility over the downlink of a heterogeneous wireless network (HetNet) by jointly optimizing the association of users to transmission points (TPs) and the activation fractions of all TPs. Activation fraction of each TP is the fraction of the frame duration for which it is active, and together these fractions influence the interference seen in the network. To address this joint optimization problem we adopt an approach wherein the activation fractions and the user associations are optimized in an alternating manner. The sub-problem of determining the optimal activation fractions is solved using an auxiliary function method that we show is provably convergent and is amenable to distributed implementation. On the other hand, the sub-problem of determining the user association is solved via a simple combinatorial algorithm. Meaningful performance guarantees are derived and a distributed variant offering identical guarantees is also proposed. The significant benefits of using the proposed algorithms are then demonstrated via realistic simulations.

Every night, many smartphones are plugged into a power source for recharging the battery. Given the increasing computing capabilities of smartphones, these idle phones constitute a sizeable computing infrastructure. Therefore, for an enterprise which supplies its employees with smartphones, we argue that a computing infrastructure that leverages idle smartphones being charged overnight is an energy-efficient and cost-effective alternative to running certain tasks on traditional servers. While parallel execution models and schedulers exist for servers, smartphones face a unique set of technical challenges due to the heterogeneity in CPU clock speed, variability in network bandwidth, and lower availability than servers. In this paper, we address many of these challenges to develop CWC-a distributed computing infrastructure using smartphones. We implement and evaluate a prototype of CWC that employs a novel scheduling algorithm to minimize the makespan of a set of computing tasks. Our evaluations using a testbed of 18 Android phones show that CWC's scheduler yields a makespan that is 1.6× faster than other simpler approaches.

Next generation wireless networks (i.e., WiMAX, LTE) provide higher bandwidth and spectrum efficiency leveraging smaller (femto) cells with orthogonal frequency division multiple access (OFDMA). The uncoordinated, dense deployments of femtocells however, pose several unique challenges relating to interference and resource management in OFDMA femtocell networks. Towards addressing these challenges, we propose RADION, a distributed resource management framework that effectively manages interference across femtocells. RADION's core building blocks enable femtocells to opportunistically determine the available resources in a completely distributed and efficient manner. Further, RADION's modular nature paves the way for different resource management solutions to be incorporated in the framework. We implement RADION on a real WiMAX femtocell testbed deployed in a typical indoor setting. Two distributed solutions are enabled through RADION and their performance is studied to highlight their quick self-organization into efficient resource allocations.

We consider the problem of maximizing the proportional fairness (PF) utility over heterogeneous wireless networks (HetNets) by jointly exploiting cell dormancy (cell ON-OFF) - wherein some transmission nodes from a set of interest are made inactive - and load balancing (user association) - wherein users are associated to the active transmission nodes in that set with each user being associated with only one node. We establish that this joint optimization problem which is a discrete optimization problem, is strongly NP-hard. Nevertheless, we prove that the load balancing sub-problem for any given set of active transmission nodes is not NP-hard but instead can be re-formulated as an asymmetric assignment problem and hence can be optimally solved in an efficient manner. In addition, we propose another lower complexity greedy algorithm for the load balancing sub-problem which offers a near-optimal average-case performance and a worst-case performance guarantee. We then propose a low-complexity algorithm for the joint optimization problem. Simulations over an example LTE HetNet topology reveal the superior performance of the proposed algorithms and underscore the significant benefits of jointly exploiting cell dormancy and load balancing.

We consider the problem of maximizing the proportional fairness (PF) utility over heterogeneous cellular networks (HetNets) by jointly exploiting partial muting-wherein the high power macro transmission node in a set of transmission nodes of interest can be made inactive for a specified fraction of the available time-frequency resource- and load balancing (user association)-wherein each user can be associated to (i.e., configured to receive data from) any one transmission node in that set. This joint problem is a mixed optimization problem in which there are finitely many choices for the muting fraction and the user association, but there are a continuum of ways in which each transmission node can partition the available resource among the users associated to it. While this mixed optimization problem seems intractable, we systematically construct efficient approximation algorithms, one of which is approximately optimal in that it yields a system utility that is no less than the optimal utility minus a constant. In addition, we propose another lower complexity greedy algorithm and proceed to demonstrate the superior performance of the proposed algorithms via simulations over an example LTE HetNet topology.

Mobile operators are leveraging WiFi to relieve the pressure posed on their networks by the surging bandwidth demand of applications. However, operators often lack intelligent mechanisms to control the way users access their WiFi networks. This lack of sophisticated control creates poor network utilization, which in turn degrades the quality of experience (QoE). To meet user traffic demands, it is evident that operators need solutions that optimally balance user traffic across cellular and WiFi networks. Motivated by the lack of practical solutions in this space, we design and implement ATOM - an end-to-end system for adaptive traffic offloading for WiFi-LTE deployments. ATOM has two novel components: (i) A network interface selection algorithm that maps user traffic across WiFi and LTE to optimize user QoE and (ii) an interface switching service that seamlessly re-directs ongoing user sessions in a cost-effective and standards-compatible manner. Our evaluations on a real LTE-WiFi testbed using YouTube traffic reveals that ATOM reduces video stalls by 3-4 times compared to naive solutions.

We consider the problem of maximizing the proportional fairness (PF) system utility over heterogeneous wireless networks (HetNets) by jointly exploiting cell dormancy (cell ON-OFF)-wherein some transmission points from a set of interest can be made inactive-and load balancing (user association)-wherein users are associated to the active transmission points in that set, with each user being associated with only one point. We establish that this joint optimization problem, which is a discrete optimization problem, is NP-hard. Nevertheless, we prove that the load balancing subproblem for any given set of active transmission points is not NP-hard but instead can be reformulated as an asymmetric assignment problem and hence can be optimally solved in an efficient manner. In addition, we show that some generalized load balancing problems that incorporate multiuser diversity gains can also be optimally and efficiently solved. We propose another lower complexity greedy algorithm for the load balancing subproblem that offers a worst-case performance guarantee and describe a simple way to approximately realize a given input user association via biasing factors. We then derive low-complexity algorithms for the joint optimization problem, including one based on a successive approximation method that has hitherto been used for continuous nonconvex optimization problems. Simulations over an example Long-Term Evolution HetNet topology reveal the superior performance of the proposed algorithms and underscore the significant benefits of jointly exploiting cell dormancy and load balancing.

Cloud-based radio access networks (C-RAN) have been proposed as a cost-efficient way of deploying small cells. Unlike conventional RANs, a C-RAN decouples the baseband processing unit (BBU) from the remote radio head (RRH), allowing for centralized operation of BBUs and scalable deployment of light-weight RRHs as small cells. In this work, we argue that the intelligent configuration of the front-haul network between the BBUs and RRHs, is essential in delivering the performance and energy benefits to the RAN and the BBU pool, respectively. We then propose FluidNet - a scalable, light-weight framework for realizing the full potential of C-RAN. FluidNet deploys a logically re-configurable front-haul to apply appropriate transmission strategies in different parts of the network and hence cater effectively to both heterogeneous user profiles and dynamic traffic load patterns. FluidNet's algorithms determine configurations that maximize the traffic demand satisfied on the RAN, while simultaneously optimizing the compute resource usage in the BBU pool. We prototype FluidNet on a 6 BBU, 6 RRH WiMAX C-RAN testbed. Prototype evaluations and large-scale simulations reveal that FluidNet's ability to re-configure its front-haul and tailor transmission strategies provides a 50% improvement in satisfying traffic demands, while reducing the compute resource usage in the BBU pool by 50% compared to baseline transmission schemes.

The wide channels feature combines two adjacent channels to form a new, wider channel to facilitate high-data-rate transmissions in multiple-input-multiple-output (MIMO)-based IEEE 802.11n networks. Using a wider channel can exacerbate interference effects. Furthermore, contrary to what has been reported by prior studies, we find that wide channels do not always provide benefits in isolation (i.e., one link without interference) and can even degrade performance. We conduct an in-depth, experimental study to understand the implications of wide channels on throughput performance. Based on our measurements, we design an auto-configuration framework called ACORN for enterprise 802.11n WLANs. ACORN integrates the functions of user association and channel allocation since our study reveals that they are tightly coupled when wide channels are used. We show that the channel allocation problem with the constraints of wide channels is NP-complete. Thus, ACORN uses an algorithm that provides a worst-case approximation ratio of O(1/Δ + 1), with Δ being the maximum node degree in the network. We implement ACORN on our 802.11n testbed. Our evaluations show that ACORN: 1) outperforms previous approaches that are agnostic to wide channels constraints; it provides per-AP throughput gains ranging from 1.5 × 6×; and 2) in practice, its channel allocation module achieves an approximation ratio much better than the theoretically predicted O(1/Δ + 1).

To meet the capacity demands from ever-increasing mobile data usage, mobile network operators are moving toward smaller cell structures. These small cells, called femtocells, use sophisticated air interface technologies such as orthogonal frequency division multiple access (OFDMA). While femtocells are expected to provide numerous benefits such as energy efficiency and better throughput, the interference resulting from their dense deployments prevents such benefits from being harnessed in practice. Thus, there is an evident need for a resource management solution to mitigate the interference that occurs between collocated femtocells. In this paper, we design and implement one of the first resource management systems, FERMI, for OFDMA-based femtocell networks. As part of its design, FERMI: 1) provides resource isolation in the frequency domain (as opposed to time) to leverage power pooling across cells to improve capacity; 2) uses measurement-driven triggers to intelligently distinguish clients that require just link adaptation from those that require resource isolation; 3) incorporates mechanisms that enable the joint scheduling of both types of clients in the same frame; and 4) employs efficient, scalable algorithms to determine a fair resource allocation across the entire network with high utilization and low overhead. We implement FERMI on a prototype four-cell WiMAX femtocell testbed and show that it yields significant gains over conventional approaches.

Every night, a large number of idle smartphones are plugged into a power source for recharging the battery. Given the increasing computing capabilities of smartphones, these idle phones constitute a sizeable computing infrastructure. Therefore, for an enterprise which supplies its employees with smartphones, we argue that a computing infrastructure that leverages idle smartphones being charged overnight is an energy-efficient and cost-effective alternative to running tasks on traditional server infrastructure. While parallel execution and scheduling models exist for servers (e.g., MapReduce), smartphones present a unique set of technical challenges due to the heterogeneity in CPU clock speed, variability in network bandwidth, and lower availability compared to servers.

The increase in mobile data usage is pushing broadband operators towards deploying smaller cells (femtocells) and sophisticated access technologies such as OFDMA. The expected high density of deployment and uncoordinated operations of femtocells however, make interference management both critical and extremely challenging. Femtocells have to use the same access technology as traditional macrocells. Given this, understanding the impact of the system design choices (originally tailored to well-planned macrocells) on interference management, forms an essential first step towards designing efficient solutions for next-generation femtocells. This in turn is the focus of our work. With extensive measurements from our WiMAX OFDMA femtocell testbed, we characterize the impact of various system design choices on interference. Based on the insights from our measurements, we discuss several implications on how to efficiently operate a femtocell network.

Beamforming is a signal processing technique with numerous benefits. Unlike with omni-directional communications, it focuses the energy of the transmitted and/or the received signal in a particular direction. Although beamforming has been extensively studied on conventional systems such as WiFi, little is known about its practical impact on OFDMA femtocell deployments. Since OFDMA schedules multiple clients (users) in the same frame (in contrast to WiFi), designing intelligent scheduling mechanisms and at the same time leveraging beamforming, is a challenging task.

Next generation wireless networks (i.e., WiMAX, LTE) provide higher bandwidth and spectrum efficiency leveraging smaller (femto) cells with orthogonal frequency division multiple access (OFDMA). The uncoordinated, dense deployments of femtocells however, pose several unique challenges relating to interference and resource management in these networks. Towards addressing these challenges, we propose RADION, a distributed resource management framework that effectively manages interference across femtocells. RADION's core building blocks enable femtocells to opportunistically find the available resources in a completely distributed and efficient manner. Further, RADION's modular nature paves the way for different resource management solutions to be incorporated in the framework. We implement RADION on a real WiMAX femtocell testbed deployed in a typical indoor setting. We extensively evaluate two solutions integrated with RADION, both via prototype implementation and simulations and quantify their performance in terms of quick and efficient self-organization.

Selecting high performance routes in wireless networks requires the exchange of link quality information among nodes. Adversaries can manipulate this functionality by advertising fake qualities for links; by doing so, they can attract routes and subsequently launch pernicious attacks. Our measurements suggest that malicious route attraction can fatally impact throughput. We design a framework that is effective against both independent and colluding attackers. In the latter case, we consider both local and remote colluders. With local collusion, malicious nodes exchange and advertise fake routing information to increase the probability of being selected as relays. Remote collusion refers to nodes residing in distant parts of the network that (i) create sybil identities in a local neighborhood and / or (ii) utilize link quality reports to advertise fake links. Our framework combines packet signing and frequency hopping to accurately detect the adversaries. We implement the framework on our testbed and conduct experiments to assess its efficacy. We observe that our framework provides significant throughput benefits by detecting attackers with 90% accuracy.

The demand for increased spectral efficiencies is driving the next generation broadband access networks towards deploying smaller cells (femtocells) with sophisticated air interface technologies (Orthogonal Frequency Division Multiple Access or OFDMA). The projected dense deployment of femtocells however, makes interference and hence resource management both critical and extremely challenging. In this paper, we design and implement one of the first resource management systems, FERMI, for OFDMA-based femtocell networks. As part of its design, FERMI (i) provides resource isolation in the frequency domain (as opposed to time) to leverage power pooling across cells to improve capacity; (ii) uses measurement-driven triggers to intelligently distinguish clients that require just link adaptation from those that require resource isolation; (iii) incorporates mechanisms that enable the joint scheduling of both types of clients in the same frame; and (iv) employs efficient, scalable algorithms to determine a fair resource allocation across the entire network with high utilization and low overhead. We implement FERMI on a prototype four-cell WiMAX femtocell testbed and show that it yields significant gains over conventional approaches.

Channel Bonding (CB) combines two adjacent frequency bands to form a new, wider band to facilitate high data rate transmissions in MIMO-based 802.11n networks. However, the use of a wider band with CB can exacerbate interference effects. Furthermore, CB does not always provide benefits in interference-free settings, and can even degrade performance in some cases. We conduct an in-depth, experimental study to understand the implications of CB. Based on this study we design an auto-configuration framework, ACORN, for enterprise 802.11n WLANs. ACORN integrates the functions of user association and channel allocation, since our study reveals that they are tightly coupled when CB is used. We show that the channel allocation problem with the constraints of CB is NP-complete. Thus, ACORN uses an algorithm that provides a worst case approximation ratio of [EQUATION] with Δ being the maximum node degree in the network. We implement ACORN on our 802.11n testbed. Our experiments show that ACORN (i) outperforms previous approaches that are agnostic to CB constraints; it provides per-AP throughput gains from 1.5x to 6x and (ii) in practice, its channel allocation module achieves an approximation ratio much better than [EQUATION].