We propose the Multimodal Clinical Benchmark for Emergency Care (MC-BEC), a comprehensive benchmark for evaluating foundation models in Emergency Medicine using a dataset of 100K+ continuously monitored Emergency Department visits from 2020-2022. MC-BEC focuses on clinically relevant prediction tasks at timescales from minutes to days, including predicting patient decompensation, disposition, and emergency department (ED) revisit, and includes a standardized evaluation framework with train-test splits and evaluation metrics. The multimodal dataset includes a wide range of detailed clinical data, including triage information, prior diagnoses and medications, continuously measured vital signs, electrocardiogram and photoplethysmograph waveforms, orders placed and medications administered throughout the visit, free-text reports of imaging studies, and information on ED diagnosis, disposition, and subsequent revisits. We provide performance baselines for each prediction task to enable the evaluation of multimodal, multitask models. We believe that MC-BEC will encourage researchers to develop more effective, generalizable, and accessible foundation models for multimodal clinical data.

We consider the task of personalizing ASR models while being constrained by a fixed budget on recording speaker specific utterances. Given a speaker and an ASR model, we propose a method of identifying sentences for which the speaker’s utterances are likely to be harder for the given ASR model to recognize. We assume a tiny amount of speaker-specific data to learn phoneme-level error models which help us select such sentences. We show that speaker’s utterances on the sentences selected using our error model indeed have larger error rates when compared to speaker’s utterances on randomly selected sentences. We find that fine-tuning the ASR model on the sentence utterances selected with the help of error models yield higher WER improvements in comparison to fine-tuning on an equal number of randomly selected sentence utterances. Thus, our method provides an efficient way of collecting speaker utterances under budget constraints for personalizing ASR models.

We show cloud developers how to right size data center (DC) capacity for geo-distributed applications deployed on several multi-megawatt DCs, possibly also using many smaller edge DCs. Note that capacity considerations for a geo-distributed infrastructure do not decompose into individual DC capacity planning. When edge DCs are used, heterogeneous availability and costs affect the capacity split between the edge and core DCs. Non-uniform spatial distribution of clients and interdependence between latency and availability constraints make it non-trivial to provision the right capacity at each DC. We develop a geo-distributed capacity planning framework to capture the key factors that influence capacity, ranging from application demand patterns, latency and availability requirements, DC cost-availability trade-offs, and data replication overheads. We apply our framework to a realistic application and DC infrastructure setting to gather insights into how capacity should be provisioned and allocated across DCs for a representative set of requirements and costs.

Cloud datacenters must ensure high availability for the hosted applications and failures can be the bane of datacenter operators. Understanding the what, when and why of failures can help tremendously to mitigate their occurrence and impact. Failures can, however, depend on numerous spatial and temporal factors spanning hardware, workloads, support facilities, and even the environment. One has to rely on failure data from the field to quantify the influence of these factors on failures. Towards this goal, we collect failures data along with many parameters that might influence failures from two large production datacenters with very diverse characteristics. We show that multiple factors simultaneously affect failures, and these factors may interact in non-trivial ways. This makes conventional approaches that study aggregate characteristics or single parameter influences, rather inaccurate. Instead, we build a multi-factor analysis framework to systematically identify influencing factors, quantify their relative impact, and help in more accurate decision making for failure mitigation. We demonstrate this approach for three important decisions: spare capacity provisioning, comparing the reliability of hardware for vendor selection, and quantifying flexibility in datacenter climate control for cost-reliability trade-offs.

While there has been prior work to underprovision the power distribution infrastructure for a datacenter to save costs, the ability to underprovision the backup power infrastructure, which contributes significantly to capital costs, is little explored. There are two main components in the backup infrastructure - Diesel Generators (DGs) and UPS units - which can both be underprovisioned (or even removed) in terms of their power and/or energy capacities. However, embarking on such underprovisioning mandates studying several ramifications - the resulting cost savings, the lower availability, and the performance and state loss consequences on individual applications - concurrently. This paper presents the first such study, considering cost, availability, performance and application consequences of underprovisioning the backup power infrastructure. We present a framework to quantify the cost of backup capacity that is provisioned, and implement techniques leveraging existing software and hardware mechanisms to provide as seamless an operation as possible for an application within the provisioned backup capacity during a power outage. We evaluate the cost-performance-availability trade-offs for different levels of backup underprovisioning for applications with diverse reliance on the backup infrastructure. Our results show that one may be able to completely do away with DGs, compensating for it with additional UPS energy capacities, to significantly cut costs and still be able to handle power outages lasting as high as 40 minutes (which constitute bulk of the outages). Further, we can push the limits of outage duration that can be handled in a cost-effective manner, if applications are willing to tolerate degraded performance during the outage. Our evaluations also show that different applications react differently to the outage handling mechanisms, and that the efficacy of the mechanisms is sensitive to the outage duration. The insights from this paper can spur new opportunities for future work on backup power infrastructure optimization.

Memory devices represent a key component of datacenter total cost of ownership (TCO), and techniques used to reduce errors that occur on these devices increase this cost. Existing approaches to providing reliability for memory devices pessimistically treat all data as equally vulnerable to memory errors. Our key insight is that there exists a diverse spectrum of tolerance to memory errors in new data-intensive applications, and that traditional one-size-fits-all memory reliability techniques are inefficient in terms of cost. For example, we found that while traditional error protection increases memory system cost by 12.5%, some applications can achieve 99.00% availability on a single server with a large number of memory errors without any error protection. This presents an opportunity to greatly reduce server hardware cost by provisioning the right amount of memory reliability for different applications. Toward this end, in this paper, we make three main contributions to enable highly-reliable servers at low datacenter cost. First, we develop a new methodology to quantify the tolerance of applications to memory errors. Second, using our methodology, we perform a case study of three new dataintensive workloads (an interactive web search application, an in-memory key -- value store, and a graph mining framework) to identify new insights into the nature of application memory error vulnerability. Third, based on our insights, we propose several new hardware/software heterogeneous-reliability memory system designs to lower datacenter cost while achieving high reliability and discuss their trade-off. We show that our new techniques can reduce server hardware cost by 4.7% while achieving 99.90% single server availability.

Emerging mobile applications that sense context are poised to delight and entertain us with timely news and events, health tracking, and social connections. Unfortunately, sensing algorithms quickly drain the phone's battery. Developers can overcome battery drain by carefully optimizing context sensing but that makes programming with context arduous and ties applications to current sensing hardware. These types of applications embody a twist on the classic tension between programmer productivity and performance due to their combination of requirements.

Peak power management of datacenters has tremendous cost implications. While numerous mechanisms have been proposed to cap power consumption, real datacenter power consumption data is scarce. To address this gap, we collect power demands at multiple spatial and fine-grained temporal resolutions from the load of geo-distributed datacenters of Microsoft over 6 months. We conduct aggregate analysis of this data, to study its statistical properties. With workload characterization a key ingredient for systems design and evaluation, we note the importance of better abstractions for capturing power demands, in the form of peaks and valleys. We identify and characterize attributes for peaks and valleys, and important correlations across these attributes that can influence the choice and effectiveness of different power capping techniques. With the wide scope of exploitability of such characteristics for power provisioning and optimizations, we illustrate its benefits with two specific case studies.

A growing number of mobile apps are exploiting smartphone sensors to infer user behavior, activity, or context. Inference requires training using labeled ground truth data. Obtaining labeled data for new apps is a "chicken-egg" problem. Without a reasonable amount of labeled data, apps cannot provide any service. But until an app provides useful service it is not worth installing and has no opportunity to collect user data. This paper aims to address this problem. Our intuition is that even though users are different, they exhibit similar patterns on certain sensing dimensions. For instance, different users may walk and drive at different speeds, but certain speeds will indicate driving for all users. These common patterns could be used as "seeds" to model new users through semi-supervised learning. We prototype a technique to automatically extract the commonalities to seed personalized inference models for new users. We evaluate the proposed technique through example apps and real world data.

The availability of multiple sensors on mobile devices offers a significant new capability to enable rich user and context aware applications. Many of these applications run in the background to continuously sense user context. However, running these applications on mobile devices can impose a significant stress on the battery life, and the use of supplementary low-power processors has been proposed on mobile devices for continuous background activities. In this paper, we experimentally and analytically investigate the design considerations that arise in the efficient use of the low power processor and provide a thorough understanding of the problem space. We answer fundamental questions such as which segments of the application are most efficient to be hosted on the low power processor, and how to select an appropriate low power processor. We discuss our measurements, analysis, and results using multiple low power processors and existing phone platforms.

Battery life is a critical performance and user experience metric on mobile devices. However, it is difficult for app developers to measure the energy used by their apps, and to explore how energy use might change with conditions that vary outside of the developer's control such as network congestion, choice of mobile operator, and user settings for screen brightness. We present an energy emulation tool that allows developers to estimate the energy use for their mobile apps on their development workstation itself. The proposed techniques scale the emulated resources including the processing speed and network characteristics to match the app behavior to that on a real mobile device. We also enable exploring multiple operating conditions that the developers cannot easily reproduce in their lab. The estimation of energy relies on power models for various components, and we also add new power models for components not modeled in prior works such as AMOLED displays. We also present a prototype implementation of this tool and evaluate it through comparisons with real device energy measurements.

Many context aware applications can benefit from using high-level sensing results with semantic meanings (e.g, busy/idle). This paper proposes a platform design that provides high-level "virtual sensor" abstractions and enables new virtual sensors to be bootstrapped from existing ones.

As mobile apps become more closely integrated into our everyday lives, mobile app interactions ought to be rapid and responsive. Unfortunately, even the basic primitive of launching a mobile app is sorrowfully sluggish: 20 seconds of delay is not uncommon even for very popular apps.

Recent works have shown the usefulness of network and application layer protocols that connect low-power sensor nodes directly to multiple applications and users on the Internet. We propose a security solution for this scenario. While previous works have provided security support for various communication patterns in sensor networks, such as among nodes, from nodes to a base station, and from users to nodes, the security of communication from sensor nodes to multiple users has not been sufficiently addressed. Specifically, we explore this design space and develop a security solution, named Secure Tiny Web Service, for efficient authentication of data sent by a resource-constrained sensor node to multiple users, using digital signatures. We investigate the resource overheads in communication and computation of four suitable signature schemes—the Elliptic Curve Digital Signature Algorithm, the (elliptic curve) Schnorr signature, and the Boneh–Lynn–Shacham and Zhang–Safavi-Naini–Susilo short signature schemes. We implement these schemes on two popular sensor node architectures (based on AVR ATmega128L and MSP430 processors with 802.15.4 radios) and experimentally characterize relevant trade-offs.

Workload consolidation is very attractive for cloud platforms due to several reasons including reduced infrastructure costs, lower energy consumption, and ease of management. Advances in virtualization hardware and software continue to improve resource isolation among consolidated workloads but a particular form of resource interference is yet to see a commercially widely adopted solution - the interference due to shared processor caches. Existing solutions for handling cache interference require new hardware features, extensive software changes, or reduce the achieved overall throughput. A crucial requirement for effective consolidation is to be able to predict the impact of cache interference among consolidated workloads. In this paper, we present a practical technique for predicting performance interference due to shared processor cache which works on current processor architectures and requires minimal software changes. While performance degradation can be empirically measured for a given placement of consolidated workloads, the number of possible placements grows exponentially with the number of workloads and actual measurement of degradation is thus not practical for every possible placement. Our technique predicts the degradation for any possible placement using only a linear number of measurements, and can be used to select the most efficient consolidation pattern, for required performance and resource constraints. An average prediction error of less than 4% is achieved across a wide variety of benchmark workloads, using Xen VMM on Intel Core 2 Duo and Nehalem quad-core processor platforms. We also illustrate the usefulness of our prediction technique in realizing better workload placement decisions for given performance and resource cost objectives.

Trajectory-based services require continuous user location sensing. GPS is the most common outdoor location sensor on mobile devices. However, the high energy consumption of GPS sensing prohibits it to be used continuously in many applications. In this paper, we propose a Low Energy Assisted Positioning (LEAP) solution that carefully partitions the GPS signal processing pipeline and shifts delay tolerant position calculations to the cloud. The GPS receiver only needs to be on for less than a second to collect the sub-millisecond level propagation delay for each satellites signal. With a reference to a nearby object, such as a cell tower, the LEAP server can infer the rest of the information necessary to perform GPS position calculation. We analyze the accuracy and energy benefit of LEAP and use real user traces to show that LEAP can save up to 80% GPS energy consumption in typical trajectory-based service scenarios.

No abstract available.

Virtualization is often used in cloud computing platforms for its several advantages in efficiently managing resources. However, virtualization raises certain additional challenges, and one of them is lack of power metering for virtual machines (VMs). Power management requirements in modern data centers have led to most new servers providing power usage measurement in hardware and alternate solutions exist for older servers using circuit and outlet level measurements. However, VM power cannot be measured purely in hardware. We present a solution for VM power metering, named Joulemeter. We build power models to infer power consumption from resource usage at runtime and identify the challenges that arise when applying such models for VM power metering. We show how existing instrumentation in server hardware and hypervisors can be used to build the required power models on real platforms with low error. Our approach is designed to operate with extremely low runtime overhead while providing practically useful accuracy. We illustrate the use of the proposed metering capability for VM power capping, a technique to reduce power provisioning costs in data centers. Experiments are performed on server traces from several thousand production servers, hosting Microsoft's real-world applications such as Windows Live Messenger. The results show that not only does VM power metering allows virtualized data centers to achieve the same savings that non-virtualized data centers achieved through physical server power capping, but also that it enables further savings in provisioning costs with virtualization.

Cloud computing offers users the ability to access large pools of computational and storage resources on demand. Multiple commercial clouds already allow businesses to replace, or supplement, privately owned IT assets, alleviating them from the burden of managing and maintaining these facilities. However, there are issues that must be addressed before this vision of utility computing can be fully realized. In existing systems, customers are charged based upon the amount of resources used or reserved, but no guarantees are made regarding the application level performance or quality-of-service (QoS) that the given resources will provide. As cloud providers continue to utilize virtualization technologies in their systems, this can become problematic. In particular, the consolidation of multiple customer applications onto multicore servers introduces performance interference between collocated workloads, significantly impacting application QoS. To address this challenge, we advocate that the cloud should transparently provision additional resources as necessary to achieve the performance that customers would have realized if they were running in isolation. Accordingly, we have developed Q-Clouds, a QoS-aware control framework that tunes resource allocations to mitigate performance interference effects. Q-Clouds uses online feedback to build a multi-input multi-output (MIMO) model that captures performance interference interactions, and uses it to perform closed loop resource management. In addition, we utilize this functionality to allow applications to specify multiple levels of QoS as application Q-states. For such applications, Q-Clouds dynamically provisions underutilized resources to enable elevated QoS levels, thereby improving system efficiency. Experimental evaluations of our solution using benchmark applications illustrate the benefits: performance interference is mitigated completely when feasible, and system utilization is improved by up to 35% using Q-states.

Shared sensing infrastructures that allow multiple applications to share deployed sensors are emerging and Internet protocol based access for such sensors has already been prototyped and deployed. As a large number of applications start accessing shared sensors, the efficiency of resource usage at the embedded nodes and in the network infrastructure supporting them becomes a concern. To address this, we develop methods that detect when common data and common stream processing is requested by multiple applications, including cases where only some of the data is shared or only intermediate processing steps are common. The communication and processing is then modified to eliminate the redundancies. Specifically, we use an interval-cover graph to minimize communication redundancies and a joint data flow graph optimization to remove computational redundancies. Both methods operate online and allow application requests to be dynamically added or removed. The proposed methods are evaluated using applications on a road traffic sensing infrastructure.

Mobile applications often need location data, to update locally relevant information and adapt the device context. While most smartphones do include a GPS receiver, it's frequent use is restricted due to high battery drain. We design and prototype an adaptive location service for mobile devices, a-Loc, that helps reduce this battery drain. Our design is based on the observation that the required location accuracy varies with location, and hence lower energy and lower accuracy localization methods, such as those based on WiFi and cell-tower triangulation, can sometimes be used. Our method automatically determines the dynamic accuracy requirement for mobile search-based applications. As the user moves, both the accuracy requirements and the location sensor errors change. A-Loc continually tunes the energy expenditure to meet the changing accuracy requirements using the available sensors. A Bayesian estimation framework is used to model user location and sensor errors. Experiments are performed with Android G1 and AT&T Tilt phones, on paths that include outdoor and indoor locations, using war-driving data from Google and Microsoft. The experiments show that a-Loc not only provides significant energy savings, but also improves the accuracy achieved, because it uses multiple sensors.

A sensor network data gathering and visualization infrastructure is demonstrated, comprising of global sensor networks (GSN) middleware and Microsoft SensorMap. Users are invited to actively participate in the process of monitoring real-world deployments and can inspect measured data in the form of contour plots overlayed onto a high resolution map and a digital topographic model. Users can go back in time virtually to search for interesting events or simply to visualize the temporal dependencies of the data. The system presented is not only interesting and visually enticing for non-expert users but brings substantial benefits to environmental scientists. The easily installed data acquisition component as well as the powerful data sharing and visualization platform opens up new ground in collaborative data gathering and interpretation in the spirit of Web 2.0 applications.

We present SenseWeb, an open and scalable infrastructure for sharing and geocentric exploration of sensor data streams. SenseWeb allows sensor owners to share data streams across multiple applications and users, thus amortizing sensor deployment costs effectively. It also provides mechanisms to transparently index and cache data, to process spatio-temporal queries on real-time and historic data, and to aggregate and present results on a geocentric web interface. In this paper, we present the architecture of SenseWeb, its techniques to enable global sharing of heterogeneous sensors, and its mapbased front-end for spatio-temporal data exploration. We enable interactive geocentric data exploration in the mapbased front-end using techniques for rapidly changing map overlaid visualizations of numerous data streams. We also demonstrate flexibility and scalability of the architecture by evaluating a deployed prototype of SenseWeb, which has been publicly available since March 2008.

A great opportunity exists to fuse information from populations of privately-held sensors to create useful sensing applications. For example, GPS devices, embedded in cellphones and automobiles, might one day be employed as distributed networks of velocity sensors for traffic monitoring and routing. Unfortunately, privacy and resource considerations limit access to such data streams. We describe principles of community sensing that offer mechanisms for sharing data from privately held sensors. The methods take into account the likely availability of sensors, the context-sensitive value of sensor information, based on models of phenomena and demand, and sensor owners' preferences about privacy and resource usage. We present efficient and well-characterized approximations of optimal sensing policies. We provide details on key principles of community sensing and highlight their use within a case study for road traffic monitoring.

There are many scenarios where interoperability is required for sensor devices. We demonstrate one approach to achieve interoperability: using web services. Hosting a Web service challenges the battery- life, bandwidth, and processing power constraints of low power sensor nodes. We demonstrate a lightweight implementation on MSP430 based sensor nodes with 802.15.4 radios. The implementation allows standards compliant web service clients to use the sensors but minimizes code size and energy at the sensor nodes. It allows sensor nodes to enter sleep modes. We prototype an example application for a home sensor network along with two types of sensor nodes required for it. We also show how our system enables sensor nodes to be used easily from applications written in high level languages using existing development tools.

We present a web service based approach to enable an evolutionary sensornet system where additional sensor nodes may be added after the initial deployment. The functionality and data provided by the new nodes is exposed in a structured manner, so that multiple applications may access them. The result is a highly inter-operable system where multiple applications can share a common evolving sensor substrate. A key challenge in using web services on resource constrained sensor nodes is the energy and bandwidth overhead of the structured data formats used in web services. Our work provides a detailed evaluation of the overheads and presents an implementation on a representative sensor platform with 48k of ROM, 10k of RAM and a 802.15.4 radio. We identify design choices that optimize the web service operation on resource constrained sensor nodes, including support for low latency messaging and sleep modes, quantifying trade-offs between the design generality and resource efficiency. We also prototyped an example application, for home energy management, demonstrating how evolutionary sensor networks can be supported with our approach.

Mobile phones have two sensors: a camera and a microphone. The widespread and ubiquitous nature of mobile phones around the world makes it attractive to build a large-scale sensor network using the phones as its sensor nodes. There are several interesting challenges in realizing such a system, such as providing efficient methods for the sensor nodes to make their data available to the network, allowing the sensor network applications to access the data from potentially disconnected and highly mobile devices, ensuring that privacy constraints are met, and allowing application developers to program the sensor network as required to build new applications. We demonstrate an initial system prototype that addresses some of these concerns.

FlashDB is a self-tuning database optimized for sensor networks using NAND flash storage. In practical systems flash is used in different packages such as on-board flash chips, compact flash cards, secure digital cards and related formats. Our experiments reveal non-trivial differences in their access costs. Furthermore, databases may be subject to different types of workloads. We show that existing databases for flash are not optimized for all types of flash devices or for all workloads and their performance is thus suboptimal in many practical systems. FlashDB uses a novel self-tuning index that dynamically adapts its storage structure to workload and underlying storage device. We formalize the self-tuning nature of an index as a two-state task system and propose a 3-competitive online algorithm that achieves the theoretical optimum. We also provide a framework to determine the optimal size of an index node that minimizes energy and latency for a given device. Finally, we propose optimizations to further improve the performance of our index. We prototype and compare different indexing schemes on multiple flash devices and workloads, and show that our indexing scheme outperforms existing schemes under all workloads and flash devices we consider.

Power management is an important concern in sensor networks, because a tethered energy infrastructure is usually not available and an obvious concern is to use the available battery energy efficiently. However, in some of the sensor networking applications, an additional facility is available to ameliorate the energy problem: harvesting energy from the environment. Certain considerations in using an energy harvesting source are fundamentally different from that in using a battery, because, rather than a limit on the maximum energy, it has a limit on the maximum rate at which the energy can be used. Further, the harvested energy availability typically varies with time in a nondeterministic manner. While a deterministic metric, such as residual battery, suffices to characterize the energy availability in the case of batteries, a more sophisticated characterization may be required for a harvesting source. Another issue that becomes important in networked systems with multiple harvesting nodes is that different nodes may have different harvesting opportunity. In a distributed application, the same end-user performance may be achieved using different workload allocations, and resultant energy consumptions at multiple nodes. In this case, it is important to align the workload allocation with the energy availability at the harvesting nodes. We consider the above issues in power management for energy-harvesting sensor networks. We develop abstractions to characterize the complex time varying nature of such sources with analytically tractable models and use them to address key design issues. We also develop distributed methods to efficiently use harvested energy and test these both in simulation and experimentally on an energy-harvesting sensor network, prototyped for this work.

Motion may be used in sensor networks to change the network configuration for improving the sensing performance. We consider the problem of controlling motion in a distributed manner for a mobile sensor network for a specific form of motion capability. Mobility itself may have a high resource overhead, hence we exploit motility , a constrained form of mobility, which has very low overheads but provides significant reconfiguration potential. We present an architecture that allows each node in the network to learn the medium and phenomenon characteristics. We describe a quantitative metric for sensing performance that is concretely tied to real sensor and medium characteristics, rather than assuming an abstract range based model. The problem of determining the desirable network configuration is expressed as an optimization of this metric. We present a distributed optimization algorithm which computes a desirable network configuration, and adapts it to environmental changes. The relationship of the proposed algorithm to simulated annealing and incremental subgradient descent based methods is discussed. A key property of our algorithm is that convergence to a desirable configuration can be proved even though no global coordination is involved. A network protocol to implement this algorithm is discussed, followed by simulations and experiments on a laboratory test bed.

Energy harvesting offers a promising alternative to solve the sustainability limitations arising from battery size constraints in sensor networks. Several considerations in using an environmental energy source are fundamentally different from using batteries. Rather than a limit on the total energy, harvesting transducers impose a limit on the instantaneous power available. Further, environmental energy availability is often highly variable and a deterministic metric such as residual battery capacity is not available to characterize the energy source. The different nodes in a sensor network may also have different energy harvesting opportunities. Since the same end-user performance may be achieved using different workload allocations at multiple nodes, it is important to adapt the workload allocation to the spatio-temporal energy availability profile in order to enable energy-neutral operation of the network. This paper describes power management techniques for such energy harvesting sensor networks. Platform design considerations as well as power scaling techniques at the node-level and network-level are described.

Harvesting energy from the environment is feasible in many applications to ameliorate the energy limitations in sensor networks. In this paper, we present an adaptive duty cycling algorithm that allows energy harvesting sensor nodes to autonomously adjust their duty cycle according to the energy availability in the environment. The algorithm has three objectives, namely (a) achieving energy neutral operation, i.e., energy consumption should not be more than the energy provided by the environment, (b) maximizing the system performance based on an application utility model subject to the above energy-neutrality constraint, and (c) adapting to the dynamics of the energy source at run-time. We present a model that enables harvesting sensor nodes to predict future energy opportunities based on historical data. We also derive an upper bound on the maximum achievable performance assuming perfect knowledge about the future behavior of the energy source. Our methods are evaluated using data gathered from a prototype solar energy harvesting platform and we show that our algorithm can utilize up to 58% more environmental energy compared to the case when harvesting-aware power management is not used.

The resolution at which a sensor network collects data is a crucial parameter of performance since it governs the range of applications that are feasible to be developed using that network. A higher resolution, in most situations, enables more applications and improves the reliability of existing ones. In this paper we discuss a system architecture that uses controlled motion to provide virtual high-resolution in a network of cameras. Several orders of magnitude advantage in resolution may be achieved, depending on tolerable tradeoffs. We discuss several system design choices in the context of our prototype camera network implementation that realizes the proposed architecture. We also mention how some of our techniques may apply to sensors other than cameras. Real world data is collected using our prototype system and used for the evaluation of our proposed methods.

We discuss the use of mobility to enhance network performance for a certain class of applications in sensor networks. A major performance bottleneck in sensor networks is energy since it is impractical to replace the batteries in embedded sensor nodes post-deployment. A significant portion of the energy expenditure is attributed to communications and, in particular, the nodes close to the sensor network gateways used for data collection typically suffer a large overhead as these nodes must relay data from the remaining network. Even with compression and in-network processing to reduce the amount of communicated data, all the processed data must still traverse these nodes to reach the gateway. We discuss a network infrastructure based on the use of controllably mobile elements to reduce the communication energy consumption at the energy constrained nodes and, thus, increase useful network lifetime. In addition, our approach yields advantages in delay-tolerant networks and sparsely deployed networks. We first show how our approach helps reduce energy consumption at battery constrained nodes. Second, we describe our system prototype, which utilizes our proposed approach to improve the energy performance. As part of the prototyping effort, we experienced several interesting design choices and trade-offs that affect system capabilities and performance. We describe many of these design challenges and discuss the algorithms developed for addressing these. In particular, we focus on network protocols and motion control strategies. Our methods are tested using a practical system and do not assume idealistic radio range models or operation in unobstructed environments

Networked infomechanical systems (NIMS) introduces a new actuation capability for embedded networked sensing. By exploiting a constrained actuation method based on rapidly deployable infrastructure, NIMS suspends a network of wireless mobile and fixed sensor nodes in three-dimensional space. This permits run-time adaptation with variable sensing location, perspective, and even sensor type. Discoveries in NIMS environmental investigations have raised requirements for 1) new embedded platforms integrating many diverse sensors with actuators, and 2) advances for in-network sensor data processing. This is addressed with a new and generally applicable processor-preprocessor architecture described in this paper. Also this paper describes the successful integration of R, a powerful statistical computing environment, into the embedded NIMS node platform.

Sustainable operation of battery powered wireless embedded systems (such as sensor nodes) is a key challenge, and considerable research effort has been devoted to energy optimization of such systems. Environmental energy harvesting, in particular solar based, has emerged as a viable technique to supplement battery supplies. However, designing an efficient solar harvesting system to realize the potential benefits of energy harvesting requires an in-depth understanding of several factors. For example, solar energy supply is highly time varying and may not always be sufficient to power the embedded system. Harvesting components, such as solar panels, and energy storage elements, such as batteries or ultracapacitors, have different voltage-current characteristics, which must be matched to each other as well as the energy requirements of the system to maximize harvesting efficiency. Further, battery non-idealities, such as self-discharge and round trip efficiency, directly affect energy usage and storage decisions. The ability of the system to modulate its power consumption by selectively deactivating its sub-components also impacts the overall power management architecture. This paper describes key issues and tradeoffs which arise in the design of solar energy harvesting, wireless embedded systems and presents the design, implementation, and performance evaluation of Heliomote, our prototype that addresses several of these issues. Experimental results demonstrate that Heliomote, which behaves as a plug-in to the Berkeley/Crossbow motes and autonomously manages energy harvesting and storage, enables near-perpetual, harvesting aware operation of the sensor node.

Fidelity is one of the key considerations in data collection schemes for sensor networks. A second important consideration is the energy expense of achieving that fidelity. Data from multiple correlated sensors is collected over multi-hop routes and fused to reproduce the phenomenon. However, the same distortion may be achieved using multiple rate allocations among the correlated sensors. These rate allocations would typically have different energy cost in routing depending on the network topology. We consider the interplay between these two considerations of distortion and energy. First, we describe the various factors that affect this trade-off. Second, we discuss bounds on the achievable performance with respect to this trade-off. Specifically, we relate the network lifetime Ltto the distortion D of the delivered data. Finally, we present low-complexity approximations for the efficient computation of the Lt(D) bound

Abstract — The quality of sensing in practical sensor network deployments suffers due to the presence of obstacles in the sensing medium. If such unknown obstacles are present, and the sensor data indicates that no targets of interest are detected, then there is no easy way for the application to distinguish between the cases that there really is no target or that the targets are located in occluded regions. The obstacles may not be known before deployment and may change over time. Hence, it is of interest to develop methods which enable a sensor network to determine the presence and extent of sensing occlusions. We present one such method based on the use of a range sensor to map the obstacles in the medium. A network architecture to support efficient medium mapping facilities is presented, along with several design choices in the acquisition and update of the medium map data. We also present algorithms to rapidly acquire this data and share it among multiple nodes. All algorithms presented are implemented on prototype hardware consisting of an actuated laser and an embedded processing platform. I.

No abstract available.

No abstract available.

Actuation ability introduces a fundamentally new design dimension in wireless ad-hoc sensor networks, allowing the network to adaptively reconfigure and repair itself in response to unpredictable run-time dynamics. One of the key network resources in these systems is energy and several uncontrollable factors lead to situations where a certain segment of the network becomes energy constrained before the remaining network. The performance gets limited due to the constrained sections. We argue that in this scenario, instead of rendering the complete network useless, the remaining energy resources should be reorganized to form a new functional topology in the network. We present methods for the network to be aware of its own integrity and use actuation to improve performance when needed. This capability of the system is referred to as "self aware actuation". In this paper, we consider a network where nodes (or a subset of the nodes) have traction ability. The network uses mobility to repair the coverage loss in the area being monitored by it. We present a completely distributed energy aware algorithm (referred to as CO-Fi) for coordinated coverage fidelity maintenance in sensor networks. The energy overheads of mobility are incorporated in the algorithm, thus leaving no hidden costs. Our preliminary analysis shows that CO-Fi can significantly help improve the usable lifetime of these networks.

The performance of a sensor network may be best judged by the quality of application specific information return. The actual sensing performance of a deployed sensor network depends on several factors which cannot be accounted at design time, such as environmental obstacles to sensing. We propose the use of mobility to overcome the effect of unpredictable environmental influence and to adapt to run time dynamics. Now, mobility with its dependencies such as precise localization and navigation is expensive in terms of hardware resources and energy constraints, and may not be feasible in compact, densely deployed and widespread sensor nodes. We present a method based on low complexity and low energy actuation primitives which are feasible for implementation in sensor networks. We prove how these primitives improve the detection capabilities with theoretical analysis, extensive simulations and real world experiments. The significant coverage advantage recurrent in our investigation justifies our own and other parallel ongoing work in the implementation and refinement of self-actuated systems.

We consider the network information theoretic problem of finding the rate distortion bound when multiple correlated Gaussian sources are present. One of these is the source of interest but some side information from other sources is also transmitted to help reduce the distortion in the reproduction of the first source. The other sources are treated as helpers and are also coded. Special cases of this problem have been solved before, such as when the reproduction is lossless, when the sources are conditionally independent given one of them, or when the number of helpers is limited to one. We consider a generalized version and show that the previously derived expressions fall out as special cases of our bound. Our results can be directly utilized by designers to choose not only how many of the available sources should actually be communicated but also which sources have the highest potential to reduce the distortion.

Computer networks have historically considered support for mobile devices as an extra overhead to be borne by the system. Recently however, researchers have proposed methods by which the network can take advantage of mobile components. We exploit mobility to develop a fluid infrastructure: mobile components are deliberately built into the system infrastructure for enabling specific functionality that is very hard to achieve using other methods. Built-in intelligence helps our system adapt to run time dynamics when pursuing pre-defined performance objectives. Our approach yields significant advantages for energy constrained systems, sparsely deployed networks, delay tolerant networks, and in security sensitive situations. We first show why our approach is advantageous in terms of network lifetime and data fidelity. Second, we present adaptive algorithms that are used to control mobility. Third, we design the communication protocol supporting a fluid infrastructure and long sleep durations on energy-constrained devices. Our algorithms are not based on abstract radio range models or idealized unobstructed environments but founded on real world behavior of wireless devices. We implement a prototype system in which infrastructure components move autonomously to carry out important networking tasks. The prototype is used to validate and evaluate our suggested mobility control methods.

A key challenge in sensor networks is ensuring the sustainability of the system at the required performance level, in an autonomous manner. Sustainability is a major concern because of severe resource constraints in terms of energy, bandwidth and sensing capabilities in the system. In this paper, we envision the use of a new design dimension to enhance sustainability in sensor networks - the use of controlled mobility. We argue that this capability can alleviate resource limitations and improve system performance by adapting to deployment demands. While opportunistic use of external mobility has been considered before, the use of controlled mobility is largely unexplored. We also outline the research issues associated with effectively utilizing this new design dimension. Two system prototypes are described to present first steps towards realizing the proposed vision.

Monitoring of environmental phenomena with embedded networked sensing confronts the challenges of both unpredictable variability in the spatial distribution of phenomena, coupled with demands for a high spatial sampling rate in three dimensions. For example, low distortion mapping of critical solar radiation properties in forest environments may require two-dimensional spatial sampling rates of greater than 10 samples/m2 over transects exceeding 1000 m2. Clearly, adequate sampling coverage of such a transect requires an impractically large number of sensing nodes. This paper describes a new approach where the deployment of a combination of autonomous-articulated and static sensor nodes enables sufficient spatiotemporal sampling densityo ver large transects to meet a general set of environmental mapping demands.To achieve this we have developed an embedded networked sensor architecture that merges sensing and articulation with adaptive algorithms that are responsive to both variabilityin environmental phenomena discovered bythe mobile sensors and to discrete events discovered byst atic sensors. We begin byde scribing the class of important driving applications, the statistical foundations for this new approach, and task allocation. We then describe our experimental implementation of adaptive, event aware, exploration algorithms, which exploit our wireless, articulated sensors operating with deterministic motion over large areas. Results of experimental measurements and the relationship among sampling methods, event arrival rate, and sampling performance are presented.

The use of environmental energy is now emerging as a feasible energy source for embedded and wireless computing systems such as sensor networks where manual recharging or replacement of batteries is not practical. However, energy supply from environmental sources is highly variable with time. Further, for a distributed system, the energy available at its various locations will be different. These variations strongly influence the way in which environmental energy is used. We present a harvesting theory for determining performance in such systems. First we present a model for characterizing environmental sources. Second, we state and prove two harvesting theorems that help determine the sustainable performance level from a particular source. This theory leads to practical techniques for scheduling processes in energy harvesting systems. Third, we present our implementation of a real embedded system that runs on solar energy and uses our harvesting techniques. The system adjusts its performance level in response to available resources. Fourth, we propose a localized algorithm for increasing the performance of a distributed system by adapting the process scheduling to the spatio-temporal characteristics of the environmental energy in the distributed system. While our theoretical intuition is based on certain abstractions, all the scheduling methods we present are motivated solely from the experimental behavior and resource constraints of practical sensor networking systems.

Energy constrained systems such as sensor networks can increase their usable lifetimes by extracting energy from their environment. However, environmental energy will typically not be spread homogeneously over the spread of the network. We argue that significant improvements in usable system lifetime can be achieved if the task allocation is aligned with the spatio-temporal characteristics of energy availability. To the best of our knowledge, this problem has not been addressed before. We present a distributed framework for the sensor network to adaptively learn its energy environment and give localized algorithms to use this information for task sharing among nodes. Our framework allows the system to exploit its energy resources more efficiently, thus increasing its lifetime. These gains are in addition to those from utilizing sleep modes and residual energy based scheduling mechanisms. Performance studies for an experimental energy environment show up to 200% improvement in lifetime.

A major requirement for the mobile Internet is the wireless network access for handheld personal devices. As an alternative to the expensive 3G networks, which share 2 Mbps in several square kilometers, the use of short-range wireless technologies like Bluetooth (sharing 1 Mbps among just 7 users), has been proposed. This is much more economical as it works in the unlicensed band and leverages the existing wired broadband infrastructure. In such a Bluetooth network, however, the mobiles will move out from the range of one access point into that of another more frequently, requiring seamless handoff. We discuss a new algorithm to support fast handoff at the wireless layer. Our method exploits the continuity of the user's path and existing connection information at the older access point to reduce the handoff delay. It inter-works with IP micromobility protocols, such as cellular IP, for managing other mobility related issues at layer 3. Simulations reveal that our proposed method reduces the handoff delay by more than an order of magnitude and significantly enhances the bandwidth utilization.

Real time voice applications typically produce uniformly spaced voice packets and faithful reconstruction demands that these be played out at the same intervals. Best effort packet networks, however, produce variable delays on different packets and the receiver is required to buffer the received packets before playout. Excessive buffering delays deteriorate the system performance for interactive audio and so intelligent algorithms that keep this delay minimum while maintaining an acceptable packet loss have to be employed. In this research, we develop a new "/spl alpha/-adaptive" algorithm which offers considerable reduction in delays compared to existing algorithms, especially for low packet losses. A generic jitter control procedure is also proposed which may be used with any buffering algorithm to enhance its jitter performance without significantly affecting the delay loss tradeoff. Further, an existing algorithm based on Normalized Least Mean Squares filter is discussed and modifications are proposed for its practical implementation. All suggestions are supported by simulations on Internet delay traces.