A desirable property of any deployed artificial intelligence is generalization across domains, i.e. data generation distribution under a specific acquisition condition. In medical imagining applications the most coveted property for effective deployment is Single Domain Generalization (SDG), which addresses the challenge of training a model on a single domain to ensure it generalizes well to unseen target domains. In multi-center studies, differences in scanners and imaging protocols introduce domain shifts that exacerbate variability in rare class characteristics. This paper presents our experience on SDG in real life deployment for two exemplary medical imaging case studies on seizure onset zone detection using fMRI data, and stress electrocardiogram based coronary artery detection. Utilizing the commonly used application of diabetic retinopathy, we first demonstrate that state-of-the-art SDG techniques fail to achieve generalized performance across data domains. We then develop a generic expert knowledge integrated deep learning technique DL+EKE and instantiate it for the DR application and show that DL+EKE outperforms SOTA SDG methods on DR. We then deploy instances of DL+EKE technique on the two real world examples of stress ECG and resting state (rs)-fMRI and discuss issues faced with SDG techniques.

Model Recovery (MR) builds physics-guided digital twins from data but runs inefficiently on GPUs due to iterative ODE solvers and memory-bound kernels. We introduce ModEl Recovery IN fpgabased Dynamic Architecture (MERINDA), based on replacing ODE solver with a GRU-based streaming dataflow and co-designs fixedpoint compute and on-chip memory (BRAM tiling, heterogeneous DSP/LUT mapping). On representative MR workloads, MERINDA yields up to 6.3× fewer cycles and 99.3% lower energy than an LTC-based FPGA baseline, enabling real-time edge deployment.

Generalizing image classification across domains remains challenging in critical tasks such as fundus image–based diabetic retinopathy (DR) grading and resting-state fMRI seizure onset zone (SOZ) detection. When domains differ in unknown causal factors, achieving cross-domain generalization is difficult, and there is no established methodology to objectively assess such differences without direct metadata or protocol-level information from data collectors, which is typically inaccessible. We first introduce domain conformal bounds (DCB), a theoretical framework to evaluate whether domains diverge in unknown causal factors. Building on this, we propose GenEval, a multi-modal Vision Language Models (VLM) approach that combines foundational models (e.g., MedGemma-4B) with human knowledge via Low-Rank Adaptation (LoRA) to bridge causal gaps and enhance single-source domain generalization (SDG). Across eight DR and two SOZ datasets, GenEval achieves superior SDG performance, with average accuracy of 69.2% (DR) and 81% (SOZ), outperforming the strongest baselines by 9.4% and 1.8%, respectively. Code and models are available at: https://github.com/IMPACT-Lab-ASU/GenEval.

This article presents an AI-enabled Personalization Management (AIIM) software for human-in-the-loop, human-in-the-plant learning-enabled systems (LES). AIIM can be integrated with LES software to aid a human user in achieving safe and effective operation under dynamically changing contexts. AIIM consists of: (a) an AI technique to derive model coefficient of a physics-guided surrogate model from operational data shared following privacy norms, and (b) continuous model conformance to identify key changes in LES operational behavior that may jeopardize safety. We demonstrate two capabilities of AIIM, personalization and unknown error detection, through case studies that span a significant breadth of dynamic context change scenarios including (a) involuntary change in user context such as medication-induced glucose metabolism change in automated insulin delivery (AID), (b) actuation failure such as cartridge blockage in AID, (c) latent sensor error in aviation, and (d) unknown coding error in autonomous car software patches. We compare AIIM personalization with human-in-the-loop and self-adaptive model-predictive control design in real-life and simulation settings, to show safe and improved diabetes management.

Understanding the physical laws that govern real-world data is fundamental to achieving safe and explainable operation of mission-critical autonomous systems (MCAS)—a cornerstone of physical AI. Model Recovery (MR) serves as a key mechanism for inferring governing equations directly from data. However, deploying MR within MCAS must contend with stringent latency, computational, and power constraints, making edge-AI acceleration essential. Field-Programmable Gate Arrays (FPGAs) provide an attractive hardware substrate due to their reconfigurability and real-time processing capability. Yet, existing MR techniques often rely on computationally intensive nonlinear optimization or the numerical solution of multiple ordinary differential equations (ODEs) embedded within neural architectures, leading to high compute and memory overheads. To address these challenges, this article introduces MERINDA (Model Recovery in Dynamic Architecture), an FPGA-accelerated MR framework that integrates Gated Recurrent Units (GRUs) with an invertible mapping parameterized as a linear combination of nonlinear basis functions. We theoretically establish that MERINDA is functionally equivalent to Neural Ordinary Differential Equation (NODE)-based MR architectures, while eliminating the need for repeated ODE integration during training and inference. Empirical evaluations on benchmark datasets against Extracting sparse Model from ImpLicit dYnamics (EMILY), Sparse Identification of Nonlinear Dynamics (SINDY), and Physics-Informed Neural Networks with Sparse Regression (PINN+SR) demonstrate that MERINDA achieves comparable accuracy with substantial gains in processing speed, energy efficiency, and DRAM utilization. We further analyze the energy–memory tradeoff in MERINDA, showing that optimizing one resource directly impacts the other under fixed accuracy constraints. Using mixed-integer programming, we derive resource-aware optimal hyperparameters and construct the Pareto front that compares FPGA edge deployment against Mobile GPU (M-GPU) and server-class Graphics Processing Units (GPU) platforms. Our results highlight MERINDA’s energy efficiency, reduced training time, and smaller memory footprint, reinforcing its viability for deployment in resource-constrained autonomous systems.

Model Recovery (MR) enables safe, explainable decision-making in mission-critical autonomous systems (MCAS) by learning governing dynamical equations, but its deployment on edge devices is hindered by the iterative nature of neural ordinary differential equations (NODE), which are inefficient on FPGAs. Memory and energy consumption are the main concern of applying MR on edge devices for real-time running MR. We propose MERINDA, a novel FPGA-accelerated MR framework that replaces iterative solvers with a parallelizable neural architecture equivalent to NODEs. MERINDA achieves nearly 11× lower DRAM usage and 2.2× faster runtime compared to mobile GPUs. Experiments reveal an inverse relationship between memory and energy at fixed accuracy, highlighting MERINDA’s suitability for resource-constrained, real-time MCAS. “The implementation and datasets are publicly available at github.com/ImpactLabASU/ECAI2025.”

Recovering a physics-driven model, i.e. a governing set of equations of the underlying dynamical systems, from the real-world data has been of recent interest. Most existing methods either operate on simulation data with unrealistically high sampling rates or require explicit measurements of all system variables, which is not amenable in real-world deployments. Moreover, they assume the timestamps of external perturbations to the physical system are known a priori, without uncertainty, implicitly discounting any sensor time-synchronization or human reporting errors. In this paper, we propose a novel liquid time constant neural network (LTC-NN) based architecture to recover underlying model of physical dynamics from real-world data. The automatic differentiation property of LTC-NN nodes overcomes problems associated with low sampling rates, the input dependent time constant in the forward pass of the hidden layer of LTC-NN nodes creates a massive search space of implicit physical dynamics, the physics model solver based data reconstruction loss guides the search for the correct set of implicit dynamics, and the use of the dropout regularization in the dense layer ensures extraction of the sparsest model. Further, to account for the perturbation timing error, we utilize dense layer nodes to search through input shifts that results in the lowest reconstruction loss. Experiments on four benchmark dynamical systems, three with simulation data and one with the real-world data show that the LTC-NN architecture is more accurate in recovering implicit physics model coefficients than the state-of-the-art sparse model recovery approaches. We also introduce four additional case studies (total eight) on real-life medical examples in simulation and with real-world clinical data to show effectiveness of our approach in recovering underlying model in practice.

Non-linearities in simulation arise from the time variance in wire- less mobile networks when integrated with human in the loop, human in the plant (HIL-HIP) physical systems under dynamic con- texts, leading to simulation slowdown. Time variance is handled by deriving a series of piece wise linear time invariant simulations (PLIS) in intervals, which are then concatenated in time domain. In this paper, we conduct a formal analysis of the impact of dis- cretizing time-varying components in wireless network-controlled HIL-HIP systems on simulation accuracy and speedup and evaluate trade-offs with reliable guarantees. We develop an accurate simula- tion framework for an artificial pancreas wireless network system that controls blood glucose in Type 1 Diabetes patients with time varying properties such as, physiological changes associated with psychological stress and meal patterns. PLIS approach achieves accurate simulation with > 2.1 times speedup than a non-linear system simulation for the given dataset.

Safety regulation of safety-critical agent-based cyber-physical systems (CPS) which are manufactured in large scale such as next-gen aircrafts, autonomous driving vehicles, and medical devices is a multifaceted problem. CPS deployments can be presented with new safety-critical scenarios and novel inputs. Hence, operational characteristics of the CPS can be quite different from its safety approved design. This article considers a safety assurance solution where operational data from the sensors and actuators in the field of deployment is fed back to the manufacturing process through the Internet of Things infrastructure to assure and improve operational safety. It considers two cases: 1) model-aware, where the safety assured CPS design is fully specified; 2) modelagnostic, where limited specifications exist. For both the cases, it presents a data science based approach, N-HyMn, that learns a hybrid automaton model of the operational characteristics of the CPS from the input/output (I/O) traces of the observable parameters. For the model-aware case, it investigates the presence of inconsistencies between the learned model and the specifications model provided by the manufacturer, thus facilitating the detection of safety problems that may have been overlooked. For the modelagnostic case, it can detect potential safety failures. We show the usage of N-HyMn on the Medtronic Minimed 670 G system. N-HyMn correctly infers the hybrid automaton specifications of the Minimed 670 G and was able to detect a self-adaptation mechanism that is not declared explicitly in the certification documents of the U Food and Drug Administration. N-HyMn has a computational complexity of O(kn2), where k is the number of samples in the I/O trace, and n is the number of continuous variables.

AI-enabled Cyber-physical systems (CPS) such as artificial pancreas (AP) or autonomous cars are using machine learning to make several critical decisions. The system is subject to inputs and scenarios which are not observed during training and the expected outputs are not known. Hence, popular model based verification techniques that characterize behavior of a control system before deployment using predictive models may be inaccurate and often result in incorrect safety analysis results. In addition, regulatory agencies are required to regulate safety-critical AI enabled CPS to ensure their operational safety. However, high complexity of the system result in myriad of safety concerns all of which may not only be comprehensively tested before deployment but also may not even be detected during design and testing phase. In this work, we propose a tool to help regulatory agencies compare the operation of the CPS with the specifications given by the manufacturer to ensure that the operation results conform with the safety assured design of a CPS.

In the recognition problem, a canonical form that expresses the spatio-temporal relation of concepts for a given class can potentially increase accuracy. Concepts are defined as attributes that can be recognized using a soft matching paradigm. We consider the specific case study of American Sign Language (ASL) to show that canonical forms of classes can be used to recognize unseen gestures. There are several advantages of a canonical form of gestures including translation between gestures, gesture-based searching, and automated transcription of gestures into any spoken language. We applied our technique to two independently collected datasets: a) IMPACT Lab dataset: 23 ASL gestures each executed three times from 130 first time ASL learners as training data and b) ASLTEXT dataset: 190 gestures each executed six times on an average. Our technique was able to recognize 19 arbitrarily chosen previously unseen gestures in the IMPACT dataset from seven individuals who are not a part of 130 and 34 unseen gestures from the ASLTEXT dataset without any retraining. Our normalized accuracy on the ASLTEXT dataset is 66% which is 13.6 % higher than the state-of-art technique. Comparison with deep learning techniques revealed that incorporation of concept level knowledge can potentially alleviate under-fitting problems.

Instruments onboard spacecraft acquire large amounts of data which is to be transmitted over a very low bandwidth. Consequently for some missions, the volume of data collected greatly exceeds the volume that can be downlinked before the next orbit. This necessitates the introduction of an intelligent autonomous decision making module that maximizes the return of the most scientifically relevant dataset over the low bandwidth for experts to analyze further. We propose an iterative rule based approach, guided by expert knowledge, to represent scientifically interesting geological landforms with respect to expert selected attributes. The rules are utilized to assign a priority based on how novel a test instance is with respect to its rule. High priority instances from the test set are used to iteratively update the learned rules. We then determine the effectiveness of the proposed approach on images acquired by a Mars orbiter and observe an expert-acceptable prioritization order generated by the rules that can potentially increase the return of scientifically relevant observations.

The post-graduate enrollment statistic for deaf and hard of hearing (DHH) in Science, Technology, Math and Engineering (STEM) fields is very low compared to the hearing population. This drastically reduces DHH representation in the Information Technology (IT) workforce or academic research. DHH students generally use sign language interpreters to understand lecture materials but technically qualified interpreters are rare. These days, traditional in-person classes are being replaced with Massive Open Online Courses (MOOC). MOOCs improve access to materials, but hinder opportunities for collaboration which is vital for the DHH population. In this work, we propose DAVEE, a Virtual Reality (VR) classroom experience that facilitates live interpretation. During live sessions, DHH students can ask questions, receive feedback and have interactions with other students. The lectures and the interpretations can also be recorded for offline viewing.

Eating activity monitoring using wearable sensors can potentially enable interventions based on eating speed to mitigate the risks of critical healthcare problems such as obesity or diabetes. Eating actions are poly-componential gestures composed of sequential arrangements of three distinct components interspersed with gestures that may be unrelated to eating. This makes it extremely challenging to accurately identify eating actions. The primary reasons for the lack of acceptance of state-of-the-art eating action monitoring techniques include the following: (i) the need to install wearable sensors that are cumbersome to wear or limit the mobility of the user, (ii) the need for manual input from the user, and (iii) poor accuracy in the absence of manual inputs. In this work, we propose a novel methodology, IDEA, that performs accurate eating action identification within eating episodes with an average F1 score of 0.92. This is an improvement of 0.11 for precision and 0.15 for recall for the worst-case users as compared to the state of the art. IDEA uses only a single wristband and provides feedback on eating speed every 2 min without obtaining any manual input from the user.

Recent research has shown that reliable recognition of sign language words and phrases using user-friendly and noninvasive armbands is feasible and desirable. This work provides an analysis and implementation of including fingerspelling recognition (FR) in such systems, which is a much harder problem due to lack of distinctive hand movements. A novel algorithm called DyFAV (Dynamic Feature Selection and Voting) is proposed for this purpose that exploits the fact that fingerspelling has a finite corpus (26 alphabets for the American Sign Language (ASL)). Detailed analysis of the algorithm used as well as comparisons with other traditional machine-learning algorithms is provided. The system uses an independent multiple-agent voting approach to identify letters with high accuracy. The independent voting of the agents ensures that the algorithm is highly parallelizable and thus recognition times can be kept low to suit real-time mobile applications. A thorough explanation and analysis is presented on results obtained on the ASL alphabet corpus for nine people with limited training. An average recognition accuracy of 95.36% is reported and compared with recognition results from other machine-learning techniques. This result is extended by including six additional validation users with data collected under similar settings as the previous dataset. Furthermore, a feature selection schema using a subset of the sensors is proposed and the results are evaluated. The mobile, noninvasive, and real-time nature of the technology is demonstrated by evaluating performance on various types of Android phones and remote server configurations. A brief discussion of the user interface is provided along with guidelines for best practices.

Mobile crowd-sensing (MCS) enables development of context-aware applications by mining relevant information from a large set of devices selected in an ad hoc manner. For example, MCS has been used for real-time monitoring such as Vehicle ad hoc Networks-based traffic updates as well as offline data mining and tagging for future use in applications with location-based services. However, MCS could be potentially used for much more demanding applications such as real-time perpetrator tracking by online mining of images from nearby mobile users. A recent example is tracking the miscreant responsible for the Boston bombing. We present a new design approach for tracking using MCS for such complex processing in real time. Since MCS applications assume an unreliable underlying computational platform, most typically sample size for recruited devices is guided by concerns such as fault tolerance and reliability of information. As the real-time requirements get stricter coupled with increasing complexity of data-mining approaches, the communication and computation overheads can impose a very tight constraint on the sample size of devices needed for realizing real-time operation. This results in trade-off in acquiring context-relevant data and resource usage incurred while the real-time operation requirements get updated dynamically. Such effects have not been properly studied and optimized to enable real-time MCS applications such as perpetrator tracking. In this article, we propose ContextAiDe architecture, a combination of API, middleware, and optimization engine. The key innovation in ContextAiDe is context-optimized recruitment for execution of computation- and communication-heavy MCS applications in edge environment. ContextAiDe uses a notion of two types of contexts, exact (hard constraints), which have to be satisfied, and preferred (soft constraints), which may be satisfied to a certain degree. By adjusting the preferred contexts, ContextAiDe can optimize the operational overheads to enable real-time operation. ContextAiDe provides an API to specify contexts requirements and the code of MCS app, offload execution environment, a middleware that enables context-optimized and a fault-tolerant distributed execution. ContextAiDe evaluation using a real-time perpetrator tracking application shows reduced energy consumption of 37.8%, decrease in data transfer of 24.8%, and 43% less time compared to existing strategy. In spite of a small increase in the minimum distance from the perpetrator, iterations of optimization tracks the perpetrator successfully. Pro-actively learning the context and using stochastic optimization strategy minimizes the performance degradation caused due to uncertainty (<20%) in usage-dependent contexts.

Eating activity monitoring using wearable sensors can potentially enable interventions based on eating speed for critical healthcare problems such as obesity or diabetes. We propose a novel methodology, IDEA that performs accurate eating action identification and provides feedback on eating speed. IDEA uses a single wristband with IMU sensors and functions without any manual intervention from the user. The F1 score for eating action identification was 0.92.

Cyber-physical control systems involve a discrete computational algorithm to control continuous physical systems. Often the control algorithm uses predictive models of the physical system in its decision making process. However, physical system models suffer from several inaccuracies when employed in practice. Mitigating such inaccuracies is often difficult and have to be repeated for different instances of the physical system. In this paper, we propose a model guided deep learning method for extraction of accurate prediction models of physical systems, in presence of artifacts observed in real life deployments. Given an initial potentially suboptimal mathematical prediction model, our model guided deep learning method iteratively improves the model through a data driven training approach. We apply the proposed approach on the closed loop blood glucose control system. Using this proposed approach, we achieve an improvement over predictive Bergman Minimal Model by a factor of around 100.

State-of-the-art techniques for eating activities analysis in dietary monitoring require significant user intervention, which is reported to be one of the major reasons for low adherence. There are limited works using wearables for fine-grained analysis of eating activities in terms of the eating speed, the type of food consumed, and the portion sizes. In this paper, we propose FIT-EVE&ADAM, an armband based diet monitoring system that provides such fine-grained analysis, triggered by a single hand gesture. The system collects the user's gesture using sensors such as electromyogram embedded in the armband device, along with food image data using color and thermal cameras. Finally, a novel feature selection method is applied on the data features to estimate eating speed and caloric intake with high accuracy (0.96 F1 score).

Feature extraction and Machine Learning (ML) techniques are required to reduce high variability of biometric data in Biometric Authentication Systems (BAS) toward improving system utilization (acceptance of legitimate subjects). However, reduction in data variability, also decreases the adversary’s effort in manufacturing legitimate biometric data to break the system (security strength). Typically for BAS design, security strength is evaluated through variability analysis on data, regardless of feature extraction and ML, which are essential for accurate evaluation. In this research, we provide a geometrical method to measure the security strength in BAS, which analyzes the effects of feature extraction and ML on the biometric data. Using the proposed method, we evaluate the security strength of five state-of-the-art electroencephalogram-based authentication systems, on data from 106 subjects, and the maximum achievable security strength is 83 bits.

In Biometric Authentication Systems (BAS), the variability amongst population biometric data ensures distinctiveness, and helps minimizing false acceptance of non-subject data. However, higher variability implies temporal variations for a given subject, which can potentially reject subject data. Such variations are suppressed using feature extraction and Machine Learning (ML) techniques for improving the performance, but also reduce the adversary’s effort in breaking the system (security strength) using forged data. Typically for BAS design, performance and security strength are evaluated in isolation using experimental analysis. This research provides an analytical approach to evaluate the BAS performance and strength, and their trade-off, by modeling the biometric data, and studying the effect of feature extraction and ML configurations on processing the data. Experimental analysis on 106 subjects’ brain signal validates the analytical methodology results.

Normalized Difference Vegetation Index (NDVI) time series is used to study different land cover dynamics such as change, compare vegetation dynamics between years and analyze intra-annual components. A nonlinear cosine model of the NDVI time series with a constant frequency is used to account for the time-varying nature of the land cover parameters due to seasonality or change. The Extended Kalman Filter (EKF) is used to estimate these parameters, which introduces linearization and negatively impacts the state estimation accuracy. This paper proposes using a Particle Filter (PF) for state estimation to better address nonlinearity in the model. The cosine model is modified to capture frequency variations to account for changes in the vegetation growth cycle caused by abrupt phenomenon such as forest fires. PF obtains better state estimates than EKF, capturing the intra-annual components and time-varying frequency of the model accurately.

Recent research has shown that reliable recognition of sign language words and phrases using user-friendly and non-invasive armbands is feasible and desirable. This work provides an analysis and implementation of including fingerspelling recognition (FR) in such systems, which is a much harder problem due to lack of distinctive hand movements. A novel algorithm called DyFAV (Dynamic Feature Selection and Voting) is proposed for this purpose that exploits the fact that fingerspelling has a finite corpus (26 letters for ASL). The system uses an independent multiple agent voting approach to identify letters with high accuracy. The independent voting of the agents ensures that the algorithm is highly parallelizable and thus recognition times can be kept low to suit real-time mobile applications. The results are demonstrated on the entire ASL alphabet corpus for nine people with limited training and average recognition accuracy of 95.36% is achieved which is better than the state-of-art for armband sensors. The mobile, non-invasive, and real time nature of the technology is demonstrated by evaluating performance on various types of Android phones and remote server configurations.

Pervasive Brain Mobile Interfaces (BMoI) can be made more accurate and time efficient when knowledge from other sensors and computation power from available devices in the Internet of Things (IoT) infrastructure are utilized. This paper takes the example of Neuro-Movie (nMovie), an interactive movie application that blurs movie scenes based on mental state, to illustrate and analyze optimization opportunities when BMoI is interfaced with IoT. The three way trade-off between accuracy, real-time operation, and energy efficiency can be optimized through usage of physiological responses from IoT sensors and prediction algorithms. Latency and power models of BMoI are developed for thorough analysis of the trade-offs. Experiments on 10 volunteers show that: a) utilizing electrocardiogram responses to psychological stimulus increases the accuracy of mental state recognition by almost 10%, b) predictive models cover computation and communication latencies in the system to satisfy real-time requirements, and c) use of predictive models allows duty cycling of smartphone WiFi that potentially saves upto 71.6% communication energy.

Machine learning algorithms are widely used in cyber forensic biometric systems to analyze a subject's truthfulness in an interrogation. An analytical method (rather than experimental) to evaluate the security strength of these systems under potential cyber attacks is essential. In this paper, we formalize a theoretical method for analyzing the immunity of a machine learning based cyber forensic system against evidence tampering attack. We apply our theory on brain signal based forensic systems that use neural networks to classify responses from a subject. Attack simulation is run to validate our theoretical analysis results.

Communication and collaboration between deaf people and hearing people is hindered by lack of a common language. Although there has been a lot of research in this domain, there is room for work towards a system that is ubiquitous, non-invasive, works in real-time and can be trained interactively by the user. Such a system will be powerful enough to translate gestures performed in real-time, while also being flexible enough to be fully personalized to be used as a platform for gesture based HCI. We propose SCEPTRE which utilizes two non-invasive wrist-worn devices to decipher gesture-based communication. The system uses a multi-tiered template based comparison system for classification on input data from accelerometer, gyroscope and electromyography (EMG) sensors. This work demonstrates that the system is very easily trained using just one to three training instances each for twenty randomly chosen signs from the American Sign Language(ASL) dictionary and also for user-generated custom gestures. The system is able to achieve an accuracy of 97.72% for ASL gestures.

In this paper, we propose MT-Diet, a smartphone-based automated diet monitoring system that interfaces a thermal camera with a smartphone and identifies types of food consumed at the click of a button. The system uses thermal maps of a food plate to increase accuracy of segmentation and extraction of food parts, and combines thermal and visual images to improve accuracy in the detection of cooked food. Test results on 80 different types of cooked food show that MT-Diet can isolate food parts with an accuracy of 97.5% and determine the type of food with an accuracy of 88.93%, which is a significant improvement (nearly 25%) over the state-of-the-art.

This paper designs a holistic global workload management solution which explores diversities of a set of geo-distributed data centers and energy buffering in order to minimize the electricity cost, reduce the peak power drawn from utilities while maintaining the carbon capping requirement of the data centers. The prior work often designed solutions to address each of the aforementioned energy and cost optimization separately, disregarding the possible conflicts between the solutions' objectives. We propose a holistic solution to concurrently optimize the aforementioned potentially competing objectives. The proposed solution combines the techniques from Lyapunov optimization and predictive solution in order to manage the tradeoffs of electricity cost and carbon footprint reduction, and electricity cost and peak power cost reduction, respectively. The predicted data center parameters, being a significant aid to near optimally manage energy buffering and smoothing data centers' peak power draw, adversely affect the peak power cost due to the parameters' prediction error. The proposed holistic solution adapts stochastic programing to take the predicted parameters' randomness into consideration for minimizing the harmful impact of the prediction error. Our trace-based study confirms our analytical result that our holistic solution balances all the tradeoffs towards achieving energy and cost sustainability. Also our solution removes up to 66% of the prediction error impact in increasing the cost.

Smart mobile medical computing systems (SMDCSes), e.g., mobile medical applications use context information from the environment to provide useful and often critical healthcare services such as continuous monitoring and control of blood glucose levels by infusion of insulin. Given the unsupervised nature of operation of SMDCSes, context changes that are unaccounted for can cause unprecedented faults leading to violation of requirements such as safety, energy sustainability and reliability. Analysis of SMDCSes for testing requirements violations necessitates consideration of context dependent interactions between the SMDCS software, represented by discrete operating modes and its environment, represented by non-linear partial differential equations over space and time. An intractable number of context change sequence and lack of closed form solutions to differential equations makes the requirements analysis of SMDCSes a challenging task. This paper proposes a novel technique to analyze SMDCSes taking into account the dynamic changes in the context and the constant interaction of the computing systems with the physical environment. To show the usage of the technique, Ayushman pervasive health monitoring system is considered as an example SMDCS. Analytical results show that practices considered healthy for a person such as mobility may not be beneficial when an SMDCS is controlling health.

Sensors aesthetically embedded in accessoriessuch as jewelry, piercings or contact lenses arebeing proposed recently. These symbiotic wearable wirelesssensors are envisioned to operate on scarce harvestedenergy resources from the human body. In addition tothe hardware and software constraints arising from theform-factor and low energy operations, there are safetyrequirements such as avoidance of physical injury. Thedesign implications of these requirements are non-intuitiveand may involve estimation of human physiological dynamics. The physical impact of a sensor operation canbe controlled by appropriate design of multiple sensorcomponents such as processor, radio, and optimization ofdata algorithm. For example, the risk of thermal injury totissue can be reduced by limiting the sensing frequency, the computation power, and the radio duty cycle of bodyworn sensor. Hence, it is a challenging task to trace backa cause of a physical impact to hardware and softwaredesign decisions in a sensor. This paper proposes a novelnon-linear optimization framework to consider safety andsustainability requirements that depend on the humanphysiology and derive system level design parameters of asensor. We demonstrate our methodology using three casestudies: a) continuously monitoring ECG sensor sustainedby body heat, b) thermally safe network of implantedsensors, and c) infusion pump control algorithm to avoidhypo-glycemia.

Many medical control devices used in case of critical patients have model predictive controllers (MPC). MPC estimate the drug level in the parts of patients body based on their human physiology model to either alarm the medical authority or change the drug infusion rate. This model prediction has to be completed before the drug infusion rate is changed i.e. every few seconds. Instead of mathematical models like the Pharmacokinetic models more accurate models such as spatio-temporal drug diffusion can be used for improving the prediction and prevention of drug overshoot and undershoot. However, these models require high computation capability of platforms like recent many core GPUs or Intel Xeon Phi (MIC) or IntelCore i7. This work explores thread level and data level parallelism and computation versus communication times of such different model predictive applications used in multiple patient monitoring in hospital data centers exploiting the many core platforms for maximizing the throughput (i.e. patients monitored simultaneously). We also study the energy and performance of these applications to evaluate them for architecture suitability. We show that given a set of MPC applications, mapping on heterogeneous platforms can give performance improvement and energy savings.

Internet data centers, typically distributed across the world in order to provide timely and reliable Internet service, have been increasingly pressurized to reduce their carbon footprint and electricity cost. Particularly, data centers will soon be required to abide by carbon capping polices which impose carbon footprint limits to encourage brown energy conservation. We propose an online algorithm, called OnlineCC, for minimizing the operational cost while satisfying the carbon footprint reduction target of a set of geo-distributed data centers. OnlineCC makes use of Lyapunov optimization technique while operating without long-term future information, making it attractive in the presence of uncertainties associated with data center information e.g., input workload. We prove that OnlineCC achieves a near optimal operational cost (electricity cost) compared to the optimal algorithm with future information, while bounding the potential violation of carbon footprint target, depending on the Lyapunov control parameter, namely V. We also give a heuristic for finding V which significantly shortens the search space to adjust its value. Finally, we perform a trace-based simulation study and a small scale experiment to complement the analysis. The results show that OnlineCC reduces cost by more than 18% compared to a prediction-based online solution while resulting in equal or smaller carbon footprint.

The article presents an access control model called Criticality Aware Access Control (CAAC) for criticality (emergency) management in smart infrastructures. Criticalities are consequences of events which take a system (in our case, a smart infrastructure) into an unstable state. They require the execution of specific response actions in order to bring them under control. The principal aim of CAAC is to grant the right set of access privileges (to facilitate response action execution), at the right time, to the right set of subjects, for the right duration, in order to control the criticalities within the system. In this regard, the CAAC model uses a stochastic model called the Action Generation Model to determine the required response actions for the combination of criticalities present within the system. It then facilitates response actions by adaptively altering the privileges to specific subjects, in a proactive manner, without the need for any explicit access requests. In this article, we formalize the CAAC model and validate it based on two design goals - proactivity and adaptiveness. Finally, we present a case study demonstrating CAAC’s operation on an oil-rig platform in order to aid in the response to health- and fire-related criticalities.

Privacy of physiological data collected by a network of embedded sensors on human body is an important issue to be considered. Physiological signal-based security is a light weight solution which eliminates the need for security key storage and complex exponentiation computation in sensors. An important concern is whether such security measures are vulnerable to attacks, where the attacker is in close proximity to the BSN and senses physiological signals through processes such as electromagnetic coupling. Recent studies show that when two individuals are in close proximity, the electrocardiogram of one person gets coupled to the electroencephalogram of the other, thus indicating a possibility of proximity-based security attacks. This paper proposes a model-driven approach to proximity-based attack on security using physiological signals and evaluates its feasibility. Results show that a proximity-based attack can be successful even without the exact reconstruction of the physiological data sensed by the attacked BSN.

Privacy of physiological data collected by a network of embedded sensors on human body is an important issue to be considered. Physiological signal-based security is a light weight solution which eliminates the need for security key storage and complex exponentiation computation in sensors. An important concern is whether such security measures are vulnerable to attacks, where the attacker is in close proximity to the BSN and senses physiological signals through processes such as electromagnetic coupling. Recent studies show that when two individuals are in close proximity, the electrocardiogram of one person gets coupled to the electroencephalogram of the other, thus indicating a possibility of proximity-based security attacks. This paper proposes a model-driven approach to proximity-based attack on security using physiological signals and evaluates its feasibility. Results show that a proximity-based attack can be successful even without the exact reconstruction of the physiological data sensed by the attacked BSN.

Energy buffering, has been proposed to store renewable energy and low cost electricity in Energy Storage Devices (ESDs) and use it judiciously to reduce electricity bill in Internet data centers. Recent research have considered long term variation in electricity price, renewable power and workload and have shown the efficiency of energy buffering in reducing electricity bill. However, these aspects of data centers exhibit both long and short term variation. Further, there is inherent heterogeneity in ESD physical characteristics (e.g., charging and discharging rates). We hypothesize that a multi-tier energy buffering management can leverage the heterogeneity in ESD characteristics and better optimize utilization of renewable energy and low-cost power in presence of both short and long term variabilities in a data center. This paper proposes an analytical study of multi-tier workload and energy buffering management technique that frames each tier as an optimization problem and solves them in an online and proactive way using Receding Horizon Control (RHC). Our study shows that multi-tier energy buffering management increases the utilization of the renewables by upto two times compared to one-tier management.

Phase imbalance has been considered as a source of inefficiency in the data center that causes energy loss due to line impedance and increases reactive power. Strategies assume high loss due to phase imbalance and propose sophisticated energy management algorithms including phase balance aware workload scheduling algorithm and dynamic power distribution unit assignment to servers. However, such attempts do not utilize an objective measure of the inefficiencies due to phase imbalance to evaluate the significance of their contributions. Excessive imbalance in a three phase load has various undesirable effects. This paper, first objectively characterizes the inefficiencies due to phase imbalance and then provides numerical measures of the losses in realistic data center deployments. Phase imbalanced load in a delta configuration results in reduced power factor, which is undesirable for several reasons. Also, an imbalanced load (both in delta or star configuration), results in higher line currents, leading to higher line loss. However, this increase in loss is a fraction of a percentage of the energy consumed. The paper also discusses effects of work load scheduling on phase imbalance, and how to minimize the same.

Implementing requirements verified body worn medical sensors and smart phones, acting as base stations, in Body Sensor Networks (BSNs), is of extreme importance for development of reliable pervasive health monitoring systems (PHMS). Models of BSNs have been used to analyze designs with respect to requirements such as energy consumption, lifetime, and network reliability under dynamic context changes due to user mobility. This paper proposes Health-Dev that takes a high level specification of requirements verified BSN design and automatically generates both the sensor and smart phone code. Case studies related to energy efficiency and mobility aware network reliability show whether the resulting implementation satisfies the requirements set forth in the design phase.

There exists an interference due to colocating applications which depends on the applications' workload types, degrades the performance and affects the energy consumption of applications. We hypothesize the interference energy consumption and model it as “interference coefficient” and use it to develop an application-aware colocation management policy to colocate the applications in data centers. Including the interference effect in simulations using synthetic workload in the colocation management policy results energy savings of up to 8%.

The advent of smart phones has enabled health care anywhere and anytime. With pervasive health care, a person can perform necessary day to day tasks while his health is recorded, controlled, and processed continuously using on body sensors and actuators to capture abnormalities, trends, and causes. In such a scenario, seamless operation of the pervasive health management system (PHMS), given dynamic changes in the context induced by mobility of the user is of utmost importance. Such context changes dynamically affect many aspects such as the processing requirements of the health management application, the available energy sources, the interaction between a medical device with the human body. For social acceptability of PHMSes, they have to be tested and verified for their safe, energy sustainable (long term) and reliable operation under such dynamically changing environment. This paper proposes a novel technique to analyze PHMSes under mobility induced dynamic changes in the context and constant interaction of the medical device with the human body. Results show that human mobility induced context changes can cause unsafe conditions such as drug overdose.

Dynamic Application Hosting Management (DAHM) is proposed for geographically distributed data centers, which decides on the number of active servers and on the workload share of each data center. DAHM achieves cost-efficient application hosting by taking into account: (i) the spatio-temporal variation of energy cost, (ii) the data center computing and cooling energy efficiency, (iii) the live migration cost, and (iv) any SLA violations due to migration overhead or network delay. DAHM is modeled as fixed-charge min-cost flow and mixed integer programming for stateless and stateful applications, respectively, and it is shown NP-hard. We also develop heuristic algorithms and prove, when applications are stateless and servers have an identical power consumption model, that the approximation ratio on the minimum total cost is bounded by the number of data centers. Further, the heuristics are evaluated in a simulation study using realistic parameter data; compared to a performance-oriented application assignment, that is, hosting at the data center with the least delay, the potential cost savings of DAHM reaches 33%. The savings come from reducing the total number of active servers as well as leveraging the cost efficiency of data centers. Through the simulation study, the article further explores how relaxing the delay requirement for a small fraction of users can increase the cost savings of DAHM.

Cyber-physical systems (CPSs) couple their cyber and physical parts to provide mission-critical services, including automated pervasive health care, smart electricity grid, green cloud computing, and surveillance with unmanned aerial vehicles (UAVs). CPSs can use the information available from the physical environment to provide such ubiquitous, energy-efficient and low-cost functionalities. Their operation needs to ensure three key properties, collectively referred to as S3: 1) safety: avoidance of hazards; 2) security: assurance of integrity, authenticity, and confidentiality of information; and 3) sustainability: maintenance of long-term operation of CPSs using green sources of energy. Ensuring S3 properties in a CPS is a challenging task given the spatio-temporal dynamics of the underlying physical environment. In this paper, the formal underpinnings of recent CPS S3 solutions are aligned together in a theoretical framework for cyber-physical interactions, empowering CPS researchers to systematically design solutions for ensuring safety, security, or sustainability. The general applicability of this framework is demonstrated with various exemplar solutions for S3 in diverse CPS domains. Further, insights are provided on some of the open research problems for ensuring S3 in CPSs.

This Special Issue presents papers that cover key features of Cyber - Physical Systems (CPS), including new research and technology advances, open problems, and technical challenges with the papers organized into three categories: theoretical foundations, small-scale applications, and large-scale applications.

A two-tier Internet data center management scheme, TACOMA, with thermal-aware server provisioning (TASP) in one tier, and thermal-aware workload distribution (TAWD) in the other is proposed. TASP and TAWD coordinate to maximize the energy savings by leveraging the workload dynamics, at coarse and fine time scale, respectively. TACOMA is aware of the QoS constraints, the energy proportionality of servers, and the potential trade-off between cooling and computing power. The obtained energy savings are a combination of suspending idle servers, using servers at their peak efficiency, and avoiding heat recirculation.

Body area networks (BANs) are networks of medical devices implanted within or worn on the human body. Analysis and verification of BAN designs require (i) early feedback on the BAN design and (ii) high-confidence evaluation of BANs without requiring any hazardous, intrusive, and costly deployment. Any design of BAN further has to ensure (i) the safety of the human body, that is, limiting any undesirable side-effects (e.g., heat dissipation) of BAN operations (involving sensing, computation, and communication among the devices) on the human body, and (ii) the sustainability of the BAN operations, that is, the continuation of the operations under constrained resources (e.g., limited battery power in the devices) without requiring any redeployments. This article uses the Model Based Engineering (MBE) approach to perform design and analysis of BANs. In this regard, first, an abstract cyber-physical model of BANs, called BAN-CPS, is proposed that captures the undesirable side-effects of the medical devices (cyber) on the human body (physical); second, a design and analysis tool, named BAND-AiDe, is developed that allows specification of BAN-CPS using industry standard Abstract Architecture Description Language (AADL) and enables safety and sustainability analysis of BANs; and third, the applicability of BAND-AiDe is shown through a case study using both single and a network of medical devices for health monitoring applications.

A distributed cyber-physical system (DCPS) may receive and induce energy-based interference to and from its environment. This article presents a model and an associated methodology that can be used to (i) schedule tasks in DCPSs to ensure that the thermal effects of the task execution are within acceptable levels, and (ii) verify that a given schedule meets the constraints. The model uses coarse discretization of space and linearity of interference. The methodology involves characterizing the interference of the task execution and fitting it into the model, then using the fitted model to verify a solution or explore the solution space.

With recent advances in smart phones and wearable sensors, Body Sensor Networks (BSNs) have been proposed for use in continuous, remote electrocardiogram (ECG) monitoring. In such systems, sampling the ECG at clinically recommended rates (250 Hz) and wireless transmission of the collected data incurs high energy consumption at the energy-constrained body sensor. The large volume of collected data also makes data storage at the sensor infeasible. Thus, there is a need for reducing the energy consumption and data size at the sensor, while maintaining the ECG quality required for diagnosis. In this paper, we propose GeM-REM, a resource-efficient ECG monitoring method for BSNs. GeM-REM uses a generative ECG model at the base station and its lightweight version at the sensor. The sensor transmits data only when the sensed ECG deviates from model-based values, thus saving transmission energy. Further, the model parameters are continually updated based on the sensed ECG. The proposed approach enables storage of ECG data in terms of model parameters rather than data samples, which reduces the required storage space. Implementation on a sensor platform and evaluation using real ECG data from MIT-BIH dataset shows transmission energy and data storage reduction ratios of 42.1:1 and 37.3:1 respectively, which are better than state of the art ECG data compression schemes.

Dynamic Application Hosting Management (DAHM) allows clouds to dynamically host applications in data centers at different locations based on: (i) spatio-temporal variation of energy price, (ii) data center computing and cooling energy efficiency, (iii) Virtual Machine (VM) migration cost for the applications, and (iv) any SLA violations due to migration overhead or network delay. DAHM is complementary to dynamic workload distribution problem and is modeled as mixed integer programming; online algorithms are developed to solve the problem. The algorithms are evaluated in a simulation study using realistic data and compared with performance-oriented application assignment, i.e., hosting the application at a data center whose delay is the least. Our simulations results indicate that DAHM can potentially save up to 20% cost while incurring only a nominal increase in SLA violations. The savings are obtained by exploiting the cost efficiency variation as well as reducing the total number of VMs employed to host applications.

RF-based localization has gained popularity as a low-cost solution to support position awareness in ad hoc networks. The received signal strength (RSS) measured by pairs of nodes can be used to obtain either range estimates or connectivity information. It is not clear, however: 1) when a range-based scheme should be used in favor of a connectivity-based one, and 2) how to optimally convert the RSS into connectivity data. This paper uses analysis of the Fisher information and the Cramér-Rao bound (CRB) to answer these questions. Solutions are found by comparing the network connectivity against two values: the critical connectivity (CC) and the optimal connectivity (OC). After discussing the properties of both values, we show how their approximation can be used to improve the performance of RF-based localization systems.

Cloud is the state-of-the-art back-end infrastructure for most large-scale web services. This paper studies what effect energy proportionality has on the energy savings of cloud data center management, under various equipment compositions and power densities. Our findings show that although it is a common expectation that improved energy proportionality should diminish the benefits of power management's server provisioning, this is not true in all cases. Results show that equipping server provisioning with thermal awareness can keep it as a useful technique when the data center exhibits power consumption heterogeneity and non-uniform heat recirculation phenomena.

With the increasing popularity of Internet-based information retrieval and cloud computing, saving energy in Internet data centers (a.k.a. hosting centers, server farms) is of increasing importance. Current research approaches are based on dynamically adjusting the active server set in order to turn off a portion of the servers and save energy without compromising the quality of service; the workload is then distributed, conventionally equally (i.e. balanced), across the active servers. Although there is ample work that demonstrates energy savings through dynamic server provisioning, there is little work on thermal-aware server provisioning. This paper provides a formulation of the thermal aware active server set provisioning (TASP), in a nonlinear minimax binary integer programming form, and a series of heuristic approaches to solving them, namely MiniMax, bb-sLRH, CP-sLRH and sLRH. Furthermore, it introduces thermal-aware workload distribution (TAWD) among the active servers. The proposed heuristics are evaluated using a thermal model of the ASU HPCI data center, while the request traffic is based on real web traces of the 1998 FIFA World Cup as well as the SPECweb2009 suite. The TASP heuristics are found to outperform a power-aware-only server set selection scheme (CPSP), by up to 9.3% for the simulated scenario. The order of achieved energy efficiency is: MiniMax (9.3% savings), CP-sLRH (9.2%), bb-sLRH (8.6%), sLRH (5.8%), compared to CPSP.

Data intensive computing can be defined as computation involving large datasets and complicated I/O patterns. Data intensive computing is challenging because there is a five-orders-of-magnitude latency gap between main memory DRAM and spinning hard disks; the result is that an inordinate amount of time in data intensive computing is spent accessing data on disk. To address this problem we designed and built a prototype data intensive supercomputer named DASH that exploits flash-based Solid State Drive (SSD) technology and also virtually aggregated DRAM to fill the latency gap . DASH uses commodity parts including Intel® X25-E flash drives and distributed shared memory (DSM) software from ScaleMP®. The system is highly competitive with several commercial offerings by several metrics including achieved IOPS (input output operations per second), IOPS per dollar of system acquisition cost, IOPS per watt during operation, and IOPS per gigabyte (GB) of available storage. We present here an overview of the design of DASH, an analysis of its cost efficiency, then a detailed recipe for how we designed and tuned it for high data-performance, lastly show that running data-intensive scientific applications from graph theory, biology, and astronomy, we achieved as much as two orders-of- magnitude speedup compared to the same applications run on traditional architectures.

A body area network (BAN) is a wireless network of health monitoring sensors designed to deliver personalized healthcare. Securing intersensor communications within BANs is essential for preserving not only the privacy of health data, but also for ensuring safety of healthcare delivery. This paper presents physiological-signal-based key agreement (PSKA), a scheme for enabling secure intersensor communication within a BAN in a usable (plug-n-play, transparent) manner. PSKA allows neighboring nodes in a BAN to agree to a symmetric (shared) cryptographic key, in an authenticated manner, using physiological signals obtained from the subject. No initialization or predeployment is required; simply deploying sensors in a BAN is enough to make them communicate securely. Our analysis, prototyping, and comparison with the frequently used Diffie-Hellman key agreement protocol shows that PSKA is a viable intersensor key agreement protocol for BANs.

A Body Sensor Network (BSN) is a network of economically powered, wireless, wearable, and implanted health monitoring sensors, designed to continually collect and communicate health information from the host they are deployed on. Due to the sensitive nature of the data collected, securing BSNs is important for privacy preservation and protecting the host from bodily harm. In this article, we present Physiological Value-based Security (PVS), a usable and efficient way of securing intersensor communication schemes for BSNs. The PVS scheme distributes the key used for securing a particular message along with the message itself, by hiding it using physiological values. In this way, it not only eliminates the need for any explicit key distribution, but also reduces the number of keys required at each node to meet all its secure communication requirements. We further demonstrate the use of the PVS scheme in securing cluster topology formation in BSNs. Traditional protocols for cluster formation do not consider security and are therefore susceptible to malicious attacks. We present a PVS-based cluster formation protocol which mitigates these attacks. Performance analysis of the protocol shows that compared to cluster formation protocols secured with non-PVS-based key distribution schemes, it performs efficiently.

Connectivity-based localization schemes compute the node positions using proximity information collected within the network. In many cases of practical interest, Received Signal Strength (RSS) measurements are available, and connectivity data can be obtained by comparing the RSS against a threshold. We use the Cramér-Rao bound (CRB) analysis to determine the threshold value that minimizes the localization error. The CRB is based on knowledge of the propagation model's parameters and the true node positions. Since this information is not available to a localization scheme, we approximate the optimal threshold value using a function that depends only on the number of nodes in the network. We use extensive simulations and RSS data from in-field experiments to validate the results of the proposed approach.

High-performance computing data centers have been rapidly growing, both in number and size. Thermal management of data centers can address dominant problems associated with cooling such as the recirculation of hot air from the equipment outlets to their inlets and the appearance of hot spots. In this paper, we show through formalization that minimizing the peak inlet temperature allows for the lowest cooling power needs. Using a low-complexity linear heat recirculation model, we define the problem of minimizing the peak inlet temperature within a data center through task assignment (MPIT-TA), consequently leading to minimal cooling-requirement. We also provide two methods to solve the formulation: Xlnt-GA, which uses a genetic algorithm, and Xlnt-SQP, which uses sequential quadratic programming. Results from small-scale data center simulations show that solving the formulation leads to an inlet temperature distribution that, compared to other approaches, is 2 degC to 5 degC lower and achieves about 20 to 30 percent cooling energy savings at common data center utilization rates. Moreover, our algorithms consistently outperform the minimize heat recirculation algorithm, a recirculation-reducing task placement algorithm in the literature.

Ongoing research has demonstrated the potential benefits of thermal-aware load placement in data centers to both reduce cooling costs and component failure rates. However, thermal-aware load placement techniques have not been widely deployed in existing data centers. This is mainly because they rely on a thermal map or profile of the data center, the derivation of which is an interruptive process to the data center operation. We propose a noninvasive solution of producing a thermal map; it consists of training a neural network with observed data from actual data center operation. Our results show that gathering the data and selecting a training set is a fast process, while the neural network with no hidden layers achieves the lowest mean squared error.

Power-aware and thermal-aware techniques such as power-throttling and workload manipulation have been developed to counter the increasing power density in the current data centers. The basis for any such power-aware and/or thermal-aware technique, however, depends heavily on the equipment's power consumption model assumed. The goal of this paper is to perform power-profiling of different systems-namely, the Dell PowerEdge 1855 and 1955-based on actual power measurements. Gamut (Generic Application eMUlaTor) benchmark, double-precision matrix multiplication, and convolution of two vectors are used for varying the CPU utilization and Disk I/O.

The thermal environment of data centers plays a significant role in affecting the energy efficiency and the reliability of data center operation. A dominant problem associated with cooling data centers is the recirculation of hot air from the equipment outlets to their inlets, causing the appearance of hot spots and an uneven inlet temperature distribution. Heat is generated due to the execution of tasks, and it varies according to the power profile of a task. We are looking into the prospect of assigning the incoming tasks around the data center in such a way so as to make the inlet temperatures as even as possible; this will allow for considerable cooling power savings. Based on our previous research work on characterizing the heat recirculation in terms of cross-interference coefficients, we propose a task scheduling algorithm for homogeneous data centers, called XInt, that minimizes the inlet temperatures, and leads to minimal heat recirculation and minimal cooling energy cost for data center operation. We verify, through both theoretical formalization and simulation, that minimizing heat recirculation will result in the best cooling energy efficiency. XInt leads to an inlet temperature distribution that is 2degC to 5degC lower than other approaches, and achieves about 20%-30% energy savings at moderate data center utilization rates. XInt also consistently achieves the best energy efficiency compared to another recirculation minimized algorithm, MinHR.

Dynamic networks, e.g. mobile ad hoc networks (MANETs), call for adaptive protocols that can tolerate topological changes due to nodes' mobility and depletion of battery power. Also proactivity in these protocols is essential to ensure low latency. Self-stabilization techniques for distributed systems provide both adaptivity and proactivity to make it suitable for the MANETs. However, energy-efficiency - a prime concern in MANETs with battery-powered nodes - is not guaranteed by self-stabilization. In this paper, we propose a node-based energy metric that minimizes the energy consumption of the multicast tree by taking into account the overhearing cost. We apply the metric to self-stabilizing shortest path spanning tree (SS-SPST) protocol to obtain energy-aware SS-SPST (SS-SPST-E). Using simulations, we study the energy-latency tradeoff by comparing SS-SPST-E with SS-SPSTand other MANET multicast protocols, such as ODMRP and MAODV.

Localization is an essential service for many wireless sensor network applications. While several localization schemes rely on anchor nodes and range measurements to achieve fine-grained positioning, we propose a range-free, anchor-free solution that works using connectivity information only. The approach, suitable for deployments with strict cost constraints, is based on the neural network paradigm of Self-Organizing Maps (SOM). We present a lightweight SOM-based algorithm to compute virtual coordinates that are effective for location-aided routing. This algorithm can also exploit the location information, if available, of few anchor nodes to compute absolute positions. Results of extensive simulations show improvements over the popular Multi-Dimensional Scaling (MDS) scheme, especially for networks with low connectivity, which are intrinsically harder to localize, and in presence of irregular radio pattern or anisotropic deployment. We analytically demonstrate that the proposed scheme has low computation and communication overheads; hence, making it suitable for resource-constrained networks.

Many applications, such as disaster response and military applications, call for proactive maintenance of links and routes in Mobile Ad hoc NETworks (MANETs) to ensure low latency during data delivery. The goal of this paper is to minimize the wastage of energy in the network due to high control traffic, which restricts the scalability and applicability of such protocols, without trading-off the low latency. We categorize the proactive protocols based on the periodic route and link maintenance operations performed; and analytically derive the optimum periods for these operations in different protocol classes. The analysis takes into account data traffic intensity, link dynamics, application reliability requirements, and the size of the network. The proposed optimization significantly reduces the control traffic for low data traffic intensity in the network and increases protocol scalability for large networks without compromising the low latency of proactive protocols.

Blade severs are being increasingly deployed in modern datacenters due to their high performance/cost ratio and compact size. In this study, we document our work on blade server based datacenter thermal management. Our goal is to minimize the total energy costs (usage) of datacenter operation while providing a reasonable thermal environment for their reliable operation. Due to special characteristics of blade servers, we argue that previously proposed power-oriented schemes are ineffective for blade server-based datacenters and that task-oriented scheduling is a more practicable approach since the contribution to the total energy cost from cooling and computing systems vary according to the utilization rates. CFD simulations are used to evaluate scheduling results of three different task scheduling algorithms: Uniform Outlet Profile (UOP), Minimal Computing Energy (MCE), and Uniform Task (UT), under four different blade-server energy consumption models: DiscreteNonOptimal (DNO), DiscreteOptimal (DO), AnalogNonOptimal (ANO), and AnalogOptimal (AO). Simulation results show that the MCE algorithm, in most cases, results in a minimal total energy cost - a conclusion that differs from the findings of previous research. UOP performs better than UT at low datacenter utilization rates, whereas UT outperforms UOP at high utilization rates.

In wireless ad hoc networks (WANETs), e.g. wireless sensor networks, battery-powered devices are constrained by limited amount of energy. Many WANET applications require that the duration (called lifetime) for which the network remains operational - until the first node exhausts its battery energy - is maximized. We study the problem of maximizing the lifetime of WANET broadcast trees under two receiver cost models: 1) the constant receiver power (CORP) model, in which a receiver consumes a fixed amount of energy for receiving an information bit; and, 2) the transmitter-receiver power tradeoff (TREPT) model, in which the amount of energy consumed by a receiver is a function of the received signal power and hence the transmitter power. We propose a graph theoretic solution for CORP model to find a maximum lifetime tree and a binary search based solution for TREPT model to determine power assignment which maximizes the lifetime of a given broadcast tree. Both polynomial- time solutions are formally proved to be optimal.

A generic theoretical framework for managing critical events in ubiquitous computing systems is presented. The main idea is to automatically respond to occurrences of critical events in the system and mitigate them in a timely manner. This is different from traditional fault-tolerance schemes, where fault management is performed only after system failures. To model the critical event management, the concept of criticality, which characterizes the effects of critical events in the system, is defined. Each criticality is associated with a timing requirement, called its window-of-opportunity, that needs to be fulfilled in taking mitigative actions to prevent system failures. This is in addition to any application-level timing requirements.The criticality management framework analyzes the concept of criticality in detail and provides conditions which need to be satisfied for a successful multiple criticality management in a system. We have further simulated a criticality aware system and its results conform to the expectations of the framework.

Access control policies define the rules for accessing system resources. Traditionally, these are designed to take a reactive view for providing access, based on explicit user request. This methodology may not be sufficient in the case of critical events (emergencies) where automatic and timely access to resources may be required to facilitate corrective actions. This paper introduces the novel concept of criticality which measures the level of responsiveness for taking such actions. The paper further incorporates criticality in an access control framework for facilitating the management of critical situations. Specific properties and requirements for such criticality aware access control are identified and a sample model is provided along with its verification

An on-off keying based minimum-energy coding scheme with coherent receiver has been shown to provide better performance than BPSK. This paper presents a closed-form expression of the BER performance of that scheme over an AWGN channel with either a coherent receiver or a noncoherent receiver. In this paper, a more conservative result is obtained due to a better characterization of the average energy per source bit. Our results show that the performance is better than BPSK only when the codeword length is greater than 63. It is shown that hard-decision decoding outperforms BPSK only when the SNR is higher than a certain threshold and that soft-decision decoding outperforms BPSK regardless of the SNR value. Recommendations for practical codeword lengths are also provided.

In a no-guarantees network such as an ad hoc network, nodes are expected to adapt to changes in network and channel conditions. As a step toward supporting voice communications in such environments, we propose an adaptation scheme that takes both voice coding (i.e., compression) and modulation as parameters. In such severe environments, the main goal is to maintain a call as opposed to providing excellent quality. To this end, our adaptation scheme demands the least cost in terms of network bandwidth when network conditions are good. As network conditions worsen, more bandwidth is needed so that an acceptable quality can be maintained. This approach is a balance between providing reasonable quality and less resource consumption (with its implication on decreasing network load thus not affecting other connections). Even though our ultimate goal is supporting voice over ad hoc networks, in this paper we present extensive simulation results over a single hop scenario. Unlike other adaptation schemes involving source coding and modulation schemes in the literature, our scheme is specific to the nature of voice, thus allowing for better perceived quality without imposing high costs. Our adaptation scheme is investigated under a Rayleigh fading channel modeled as a finite state Markov channel (FSMC). The scheme is generic enough to work for any packet voice system including VoIP over wireless. Results show that the scheme allows for supporting many more calls when compared to a non-adaptive scheme.

Personal communication services (PCS) standards such as the IS-41 and the GSM use a location management scheme, which is based on registration areas (RA). Overlapping of registration areas has been proposed to reduce the overhead of location updates in such systems. Overlapping provides multiple choices for the selection of a registration area, a feature that does not appear in environments of nonoverlapping RAs. In this paper, we demonstrate how the choice of a registration area affects the number of subsequent registrations and define the problem of optimal choice based on minimization of subsequent registrations. We study two versions of the problem: 1) the deterministic (or offline) version, in which the entire trajectory of the mobile unit is known a priori, and 2) the stochastic (or online) version, in which the trajectory of the mobile unit is not known a priori, but the system has the knowledge of the mobility pattern of the mobile. The mobility pattern is modeled as a random walk across coverage area. In the deterministic case, the method presented computes an optimal solution to the registration problem. In the stochastic case, we present a method that determines the registration that minimizes the expected number of registrations by looking ahead in the probable future paths of the mobile unit. The algorithm's time complexity has exponential dependence on the length of the look-ahead. The cost of search is independent of the choice, therefore the algorithm does not increase the search cost. We also consider an alternative cost model for the stochastic case and propose a preemptive and a nonpreemptive approach each of which incurs different numbers of hard and soft registration operations. Simulation results show a reduction of 25-30 percent in number of registrations over a random-choice scheme. This can be translated to 5-20 percent effective location management load reduction for most cases, subject to the call-to-mobility ratio (CMR) of a mobile unit and search-cost-to-update-cost ratio (CCR) in the network.

We analyze the role of the social group in a ubiquitous computing (Ubicomp) environment as a source of contextual information. A model is presented to address the social group member's perceptions of how devices in a ubicomp environment should aid them in collaboration. Based on the model a distributed context-aware group membership management scheme is developed. We then present a prototype implementation for a context-aware ephemeral group membership management scheme, along with a sample application, and experimental results that demonstrate the feasibility of our system.

In this paper, we propose an extension to the personal communication services (PCS) location management protocol which uses dynamically overlapped registration areas. The scheme is based on monitoring the aggregate mobility and call pattern of the users during each reconfiguration period and adapting to the mobility and call patterns by either expanding or shrinking registration areas at the end of each reconfiguration period. We analytically characterize the trade-off resulting from the inclusion or exclusion of a cell in a registration area in terms of expected change in aggregate database access cost and signaling overhead. This characterization is used to guide the registration area adaption in a manner in which the signaling and database access load on any given location register (LR) does not exceed a specified limit. Our simulation results show that it is useful to dynamically adapt the registration areas to the aggregate mobility and call patterns of the mobile units when the mobility pattern exhibits locality. For such mobility and call patterns, the proposed scheme can greatly reduce the average signaling and database access load on LRs. Further, the cost of adapting the registration areas is shown to be low in terms of memory and communication requirements.

In wireless sensor networks (WSN) the process of dissemination of data among various sensors (broadcast) and collection of data from all sensors (convergecast or data aggregation) are common communication operations. With increasing demands on efficient use of battery power, many efficient broadcast tree construction and channel allocation algorithms have been proposed. Generally convergecast is preceded by broadcast. Hence the tree used for broadcast is also used for convergecast. Our research shows that this approach is inefficient in terms of latency and energy consumption. In this paper we propose a heuristic solution for the problem of minimum energy convergecast which also works toward minimizing data latency. This algorithm constructs a tree using a greedy approach where new nodes are added to the tree such that weight on the branch to which it is added is less. The algorithm then allocates direct sequence spread spectrum or frequency hopping spread spectrum codes. Simulation results show that energy consumed and communication latency of our approach is lower than some of the existing approaches for convergecast. We have then used our algorithm to perform broadcast. Surprisingly our results show that this algorithms performance for broadcasting is better compared to other broadcast techniques.

In this paper we propose a distributed algorithm called S-REMiT for building an energy-efficient multicast tree in a wireless ad hoc network (WANET). S-REMiT employs a more realistic energy consumption model for wireless communication, which takes into account the energy losses not only due to radio propagation but also the energy losses in the transceiver electronics. This enables S-REMiT to adapt a given multicast tree for a wide variety of wireless networks irrespective of whether they use long-range radios or short-range radios. Our simulations show that it performs better than BIP/MIP and EWMA algorithms.

Propagation model plays a very important role in designing wireless communication systems. Current advances in semiconductor technology has made it possible to implant a network of bio-sensors inside the human body for health monitoring purposes [C. Furse, H.K. Lai, C. Estes, A. Mahadik, A. Duncan, 1999], [C. Furse, R. Mohan, A. Jakayar, S. Karidehal, B. McCleod, S. Going, 2001], [L. Schwiebert, S.K.S. Gupta, P.S.G. Auner, G. Abrams, R. Lezzi, P. McAlister, 2002]. For wireless communication inside the human body, the tissue medium acts as a channel through which the information is sent as electromagnetic (EM) radio frequency (RF) waves. A propagation model is necessary to determine the losses involved in the form of absorption of EM wave power by the tissue. Absorption of EM waves by the tissue body, which consists of mostly saline water, accounts for a major portion of the propagation loss. In this paper we present a propagation loss model (PMBA) for homogeneous tissue bodies. We have verified the model for the frequency range of our interest (900 MHz to 3 GHz) using a 3D EM simulation software, HFSS/spl trade/, and experimental measurements using saturated salt water.

Reliable multicast in wireless applications is gaining importance with the development in technology. Applications like multicast file transfer, distributed computing, chat and whiteboard applications need reliability. However, due to mobility and wireless channel characteristics, obtaining reliability in data transfer is a difficult and challenging task. IEEE 802.11 does not support reliable multicast due to its inability to exchange RTS/CTS and ACKS with multiple recipients. However, several MAC layer protocols have been proposed that provide reliable multicast. For example, J. Kuri et al. [July 2001] have proposed the leader-based, probability-based, and delay-based protocols. These protocols work around the problem of multiple CTSs/ACKs colliding by providing ways to have only one of the multicast recipient nodes respond with a CTS or an ACK. These protocols perform well in low mobility wireless LANs but the performance degenerates as the mobility of nodes increases. In this paper, we discuss the inherent drawbacks of these protocols and provide an alternative approach. We present an extension to the IEEE 802.11 MAC layer protocol to provide the link level reliability to both unicast as well as multicast data communications. The extension is NAK based and uses tones, instead of conventional packets, to signal a NAK. We also incorporate dual tones, proposed by J. Deng et al. [Oct. 1998], to prevent an incoming mobile node from interrupting an ongoing transmission. Simulation results suggest that our MAC performs better than those proposed by J. Kuri et al. [July 2001] in terms of both data throughput as well as reliability.

We present a distributed algorithm called L-REMiTfor extending the lifetime of a source-based multicast tree in wireless ad hoc networks (WANET). The lifetime of a multicast tree is the duration from the formation of the tree to the time when the first node fails due to battery energy exhaustion. L-REMiT assumes that the energy consumed to forward a packet is proportional to the forwarding distance and that WANET nodes can dynamically adjust their transmission power. The task of extending the lifetime of a multicast tree is formulated as the task of extending the lifetime of bottleneck nodes in the tree. The number of multicast packets which a bottleneck node can forward, as determined by its residual battery energy and the distance of its farthest child node, is minimum over all the nodes in the multicast tree. Lifetime of a bottleneck node is improved by reassigning its farthest children to other nodes in the tree with the goal of improving the lifetime of the multicast tree. Nodes only require information from their neighbors for refining the tree in a distributed manner. Simulation results show that L-REMiT has low overhead and performs better than BIP/MIP and EWMA algorithms

In this paper, we propose a distributed algorithm called G-REMiT for building an energy efficient multicast tree in a wireless ad hoc network (WANET). G-REMiT employs a more realistic energy consumption model for wireless communication which takes into account not only the energy losses due to radio propagation but also the energy losses in the transceiver electronics. We evaluate the performance of the protocol using two energy consumption model: long range radio and short range radio. We show that for long range radio model, G-REMiT algorithm can achieve better performance than other proposals such as MLU, MLiMST and MIP, and the energy overhead of for executing G-REMiT is negligible compared with the total energy consumption for the multicast communication. For short range radio, we find that existing energy saving scheme by adjusting node's transmission power is not suitable.

A wireless sensor network (WSN) consists of sensors implanted in an environment for collecting and transmitting data regarding changes in the environment based on the requests from a controlling device (called base station) using wireless communication. WSNs are being used in medical, military, and environment monitoring applications. Broadcast (dissemination of information from a central node) and convergecast (gathering of information towards a central node) are important communication paradigms across all application domains. Most sensor applications involve both convergecasting and broadcasting. The time taken to complete either of them has to be kept minimal. This can be accomplished by constructing an efficient tree for both broadcasting as well as convergecasting and allocating wireless communication channels to ensure collision-free communication. There exist several works on broadcasting in multihop radio networks (a.k.a. ad hoc networks), which can also be used for broadcasting in WSNs. These algorithms construct a broadcast tree and compute a schedule for transmitting and receiving for each node to achieve collision-free broadcasting. In this paper, we show that we need a new algorithm for applications, which involve both convergecasting and broadcasting since the broadcast tree may not be efficient for convergecasting. So we propose a heuristic algorithm (convergecasting tree construction and channel allocation algorithm (CTCCAA)), which constructs a tree with schedules assigned to nodes for collision free convergecasting. The algorithm is capable of code allocation (direct sequence spread spectrum (DSSS)/ frequency hopping spread spectrum (FHSS)), in case multiple codes are available, to minimize the total duration required for convergecasting. We also show that the same tree can be used for broadcasting and is as efficient as a tree exclusively constructed for broadcasting.

Multicast refers to the technique of sending data to a group of receivers. The use of multicast paradigm in wireless LANs brings significant advantages like savings in channel bandwidth and energy. Considerable research has been done with regard to issues like reliability, but they have not taken into consideration the operation in an insecure environment. We present schemes for secure multicast in wireless LANs, based on the notion of location based access control, wherein only a user present in specific locations can access the services provided. Location based access control is a significant requirement in the pervasive computing environments. These schemes make use of the broadcast nature of the medium for sending encrypted data to a group and for key management. Those schemes which are adaptive to the dynamics of the multicast group perform better than static schemes. Three schemes are presented in this paper. The three schemes vary according to whether the base station shares the same session key with all the members of its cell (SSK) or different session key for each one of the members (SSK), or a combination of the two schemes for efficient key management (Hybrid). The comparative performance of the three schemes based on the results of simulations are presented.

Time-varying channel error conditions of a wireless link do not allow for providing a steady service quality. Adaptability is one way to go around this problem since the quality of service (QoS) requirements can be changed as the channel status changes. In this paper, we propose a framework for adaptive voice over one-hop wireless communication between a source and a destination. Adaptability is achieved at two levels: (1) changing the voice-encoding rate, and (2) changing the signal modulation scheme. In addition to reacting to the channel conditions and hence achieving better quality, adaptation, will allow for the support of more of the offered load (i.e., higher multiplexing gain). This will introduce some issues and problems; the goal was to reach to a near-optimal operating point, where quality is not traded for bandwidth efficiency. We simulated a special case of the framework. Results show that the adaptive approach has a much less degradation in voice quality (DVQ) and allows for more voice communications to be supported.

A simple and energy efficient source coded on/off keying modulation and near optimal error detection scheme for wireless applications is presented in this paper. Many low-power battery operated radio systems, especially for microsensor applications, has a need for saving power both at the system level and circuit level implementation. Our main objective in this paper is to come up with energy efficient coded modulation scheme that consumes comparatively less power both at system and circuit level. A simple on/off keying (OOK) digital modulation scheme is used for this purpose. The basic idea of minimum energy coding (ME-coding) for source with known statistics (probabilities of occurrence of symbols) is obtained from [A.C. Erin and H.H. Asada, Dec. 1999]. In ME-coding scheme, source bits are mapped to constant length codes (ME-codes) which has less number of high-bits in it. Since the OOK transmitter consumes energy only when transmitting a high bit, mapping to ME-codes reduces the total energy consumed in RF transmitter. In this paper, we have come up with ME-coding scheme for sources with unknown statistics and we further propose a new method of code-by-code detection that can detect and correct certain errors in the codeword received. The inferior performance of OOK when compared to other simple modulation schemes is overcome by ME-coding. A total of about 6 dB improvement in signal-to-noise ratio (SNR) per bit is observed when a 3-bit message symbol is mapped to a 7-bit ME-code. It also performs 3 dB better than a Hamming (7,4)-coded BPSK.

Several multicast protocols such as Protocol Independent Multicast (PIM) (Deering et al., 1996) and Core-Based Trees (CBT) (Ballardie et al., 1993) use the notion of group-shared trees. The reason is that construction of minimal-cost tree spanning all members of the multicast group is expensive, hence these protocols use a core-based group-shared tree to distribute packets from all the sources. A core-based tree is a shortest-path tree rooted at some core node. The core node is also referred to as a center node or a rendezvous point. Core nodes may be chosen from some preselected set of nodes or some heuristics may be employed to select core nodes. We present distributed core selection and migration protocols for mobile ad hoc networks with dynamically changing network topology. Most protocols for core selection in static networks are not suitable for ad hoc networks, since these algorithms depend on knowledge of entire network topology, which is not available or is too expensive to maintain in an ad hoc network with dynamic topology. The proposed core location method is based on the notion of median node of the current multicast tree instead of the median node of the entire network. The rationale is that the mobile ad hoc network graphs are in general sparse and, hence, the multicast tree is a good approximation of the entire network for the current purpose. Our adaptive distributed core selection and migration method uses the fact that the median of a tree is equivalent to the centroid of that tree. The significance of this observation is due to the fact that the computation of a tree's centroids does not require any distance information. Mobile ad hoc networks have limited bandwidth which needs to be conserved. Hence, we use the cost of multicast tree as the sum of weights of all the links in the tree, which signifies the total bandwidth consumed for multicasting a packet. We compare the cost of shortest-path tree rooted at the tree median, Cost/sub TM/, with the cost of shortest-path tree rooted at the median of the graph, Cost/sub GM/, which requires complete topology information to compute. A network graph model for generating random ad hoc mobile networks is developed to perform this comparison. The simulation results show that for large size networks, the ratio Cost/sub TM//Cost/sub GM/ lies between 0.8 to 1.2 for different multicast groups. Further, as the size of the multicast group increases the ratio approaches 1.

Advances in semiconductor technology have made it possible to build miniature but reliable biosensors. A network of such biosensors can be implanted in humans for health monitoring and prosthesis. However, such networks are fundamentally different from other wireless networks. They have a continuous but very small source of power. This energy constraint necessitates the use of highly energy-efficient communications protocols. We present two such protocols in the context of a biomedical application we are working on, namely, retinal prosthesis. Our first approach is a cluster-based protocol in which only a small fraction of the nodes make expensive long distance transmits to the external base station. Our second approach is a tree-based protocol. We also analyse the energy efficiency of these protocols while varying parameters such as number of nodes in the system and distance between nodes. Our analysis shows that the cluster-based protocol has better energy performance.

THE need for “information anywhere anytime” has been a driving force for the increasing growth in Web and Internet technology, wireless communication, and portable computing devices. Mobile computing is the merger of recent advances in computing and communication technologies with the aim of providing a seamless and ubiquitous computing environment to mobile users. In such mobile environments, database applications are enhanced with useful features of wireless technology. For example, users are allowed to establish a mobile office where they can communicate with other users (mobile or stationary), access information from various sources, and manage their work while staying mobile. This feature is important for enabling of mobile workforces supporting ubiquitous services such as weather and forecasting services, financial market reporting, yellow pages, road maps and directions, telematics, point-of-sale applications, in-field work dispatch, law enforcement, military, and the like. By nature, mobile computing environments are characterized by severe resource constraints and unstable operating conditions; this adds a new dimension to the technical challenges for database systems and management. Many software problems associated with data management, transaction management, and data recovery have their origin in distributed database systems. In mobile computing, however, these problems become more difficult to solve, mainly because of the narrow bandwidth of the wireless communication channels, the relatively short active life of the power supply of mobile units, and the changing locations of required information (sometimes in cache, sometimes in air, sometimes at the server). Further, in many mobile database applications, data changes very rapidly (or even constantly). Users need to receive timely information in order to make critical decisions (e.g., stock market information and trading). Thus, response time becomes a much more key performance metric. In addition to the traditional response time, the active life of the user’s battery is also an important performance merit. Wireless networks differ from wired networks in many ways. Database users over a wired network remain connected not only to the network but also to a continuous power source. In a wireless network, however, both the response time and the active life of the user’s battery are important. In order to conserve energy and extend battery life, clients can slip into doze mode. Clients can be awakened from the doze mode when the server needs to communicate with the client. Mobile applications can be categorized as 1) vertical applications and 2) horizontal application. In vertical applications, users access data within a specific cell and access is denied to users outside of that cell. For example, users can obtain information on the location of doctors or emergency centers within a cell or parking availability data at an airport cell. In horizontal applications, users cooperate on accomplishing a task and they can handle data distributed throughout the system. The market for horizontal applications is growing; two types of applications that fall in this category are mail-enabled applications and information services to mobile users. These two types of applications differ in the type of data they manage. Public data is primarily managed by vertical applications, while shared data is used by horizontal applications, possibly with some replication. Copies of shared data may be stored both in base and mobile stations. This presents a variety of difficult problems in transaction management consistency, as well as in the integrity and scalability of the architecture. Data management is concerned with the modeling, efficient storage, retrieval, and manipulation of information. From a data management standpoint, mobility of the clients/nodes provides an interesting variation to distributed computing. Mobile databases can be distributed under two possible scenarios: 1) The entire database is distributed mainly among the wired components, possibly with full or partial replication. A base station manages its own database with a DBMS-like functionality, with additional functionality for locating mobile units and additional query and transaction management features to meet the requirements of mobile environments. 2) The database is distributed among wired and wireless components. Data management responsibility is shared among base stations and mobile units. In this environment, traditional distributed database techniques may not work. These different ways of managing data in mobile environments entail additional considerations and variation with regard to distributed database management. IEEE TRANSACTIONS ON COMPUTERS, VOL. 51, NO. 10, OCTOBER 2002 1121

Implanted biomedical devices ha ve the potential to revo-lutionize medicine. Smart sensors, whic hare created by combining sensing materials with integrated circuitry, are being considered for several biomedical applications such as a glucose level monitor or a retina prosthesis. These devices require the capability to communicate with an external com-puter system (base station) via a wireless interface. The lim-ited pow erand computational capabilities of smart sensor based biological implants presen t research challenges in sev-eral aspects of wireless netw orking due to the need for having a bio-compatible, fault-tolerant, energy-eÆcient, and scal-able design. Further, em bedding thesesensors in humans add additional requirements. For example, the wireless net-w orking solutions should be ultra-safe and reliable, w ork trouble-free in dierent geographical locations (although im-plants are typically not expected to move; they shouldn't restrict the movements of their human host), and require minimal maintenance. This necessitates application-specic solutions which are vastly dierent from traditional solu-tions. In this paper, w e describe the potential of biomedical smart sensors. We then explain the challenges for wire-less netw orking of human-embedded smart sensor arrays and our preliminary approach for wireless netw orking of a retina prosthesis. Our aim is to motivate vigorous research in this area by illustrating the need for more application-specic and novel approaches tow ard developing wireless network-ing solutions for human-implanted smart sensors.

Modern distributed systems involving large number of nonstationary clients (mobile hosts, MH) connected via unreliable low-bandwidth communication channels are very prone to frequent disconnections. This disconnection may occur because of different reasons: The clients may voluntarily switch off (to save battery power), or a client may be involuntarily disconnected due to its own movement in a mobile network (hand-off, wireless link failures, etc.). A mobile computing environment is characterized by slow wireless links and relatively underprivileged hosts with limited battery powers. Still, when data at the server changes, the client hosts must be made aware of this fact in order for them to invalidate their cache, otherwise the host would continue to answer queries with the cached values returning incorrect data. The nature of the physical medium coupled with the fact that disconnections from the network are very frequent in mobile computing environments demand a cache invalidation strategy with minimum possible overheads. In this paper, we present a new cache maintenance scheme, called AS. The objective of the proposed scheme is to minimize the overhead for the MHs to validate their cache upon reconnection, to allow stateless servers, and to minimize the bandwidth requirement. The general approach is (1) to use asynchronous invalidation messages and (2) to buffer invalidation messages from servers at the MH's Home Location Cache (HLC) while the MH is disconnected from the network and redeliver these invalidation messages to the MH when it gets reconnected to the network. Use of asynchronous invalidation messages minimizes access latency, buffering of invalidation messages minimizes the overhead of validating MH's cache after each disconnection and use of HLC off-loads the overhead of maintaining state of MH's cache from the servers. The MH can be disconnected from the server either voluntarily or involuntarily. We capture the effects of both by using a single parameter: The percentage of time a mobile host is disconnected from the network. We demonstrate the efficacy of our scheme through simulation and performance modeling. In particular, we show that the average data access latency and the number of uplink requests by a MH decrease by using the proposed strategy at the cost of using buffer space at the HLC. We provide analytical comparison between our proposed scheme and the existing scheme for cache management in a mobile environment. Extensive experimental results are provided to compare the schemes in terms of performance metrics like latency, number of uplink requests, etc., under both a high and a low rate of change of data at servers for various values of the parameters. A mathematical model for the scheme is developed which matches closely with the simulation results.

We present a new cache maintenance scheme, called AS, suitable for the wireless mobile environment. Our scheme integrates the mobility management scheme of Mobile IP with cache maintenance scheme used in the CODA file system. As opposed to broadcasting invalidation report schemes, AS supports arbitrary disconnection patterns and uses less wireless bandwidth. We present analytical and simulation results to show the superiority of our caching scheme.

In this paper we investigate the effect of local error recovery vs. end-to-end error recovery in reactive protocols. For this purpose, we analyze and compare the performance of two protocols: the Dynamic Source Routing protocol (DSR[2]), which does end-to-end error recovery when a route fails and the Witness Aided Routing protocol (WAR[1]), which uses local correction mechanisms to recover from route failures. We show that the performance of DSR degrades extremely fast as the route length increases (that is, DSR is not scalable), while WAR maintains both low latency and low resource consumption regardless of the route length.

When the nodes in a mobile ad hoc network move, existing links often no longer exist and/or new links are created. Any communication protocol designed for such multi-hop ad hoc networks must be able to tolerate such change in network topology that can occur anywhere in the network. Another characteristics of such networks is that bandwidth is a comparatively precious resource and needs to be conserved. Our purpose in the present paper is to explore the possibilities of applying the relatively new paradigm of self-stabilization in distributed fault tolerant algorithm design to tackle the problem of topology change in mobile networks. Self-stabilizing distributed algorithms converge to a global legitimate state in presence of any number of intermittent faults and still use only local knowledge for actions at each node. Our objective is to view the topology change as a change in the node adjacency information at one or more nodes and utilize the tools of self-stabilization to converge to a stable global state in the new network graph. We illustrate the concept by designing a new efficient distributed algorithm for multi-cast in a mobile network that can accommodate any change in the network topology due to node mobility.

Distributed dynamic channel allocation techniques are becoming important with the tremendous growth in mobile cellular communication and demand for wireless multimedia applications. These techniques can be categorized as search based or update based. Search based techniques have low messaging complexity and are suited for high system load and low request rates. On the other hand update based schemes have higher messaging complexity but are more suitable for low system load and high request rates. This paper presents a combined scheme, called UpdateSearch, which provides the advantages of both types of schemes. UpdateSearch is parameterized by the number of channel classes k, 1/spl les/k/spl les/n, where n is the total number of channels in the system. The parameter k can be adjusted to control the number of concurrent searches and degree of contention between cells competing for channels in the system. For k=1 and k=n the scheme respectively behaves as basic search and basic update scheme. A simple analytical model is used to compare the performance of UpdateSearch for various values of k with the basic update and search techniques in terms of channel allocation time and number of simultaneous channel selections allowed in the system under different system loading conditions.

This paper investigates the performance of IEEE 802.11 wireless local area network (WLAN) protocol's distributed coordination function (DCF) in the presence of mobile and hidden terminals. In order to study the joint effect of hidden terminals and user mobility on the performance of IEEE 802.11 DCF, we extend Tobagi and Kleinrock's (1975) hearing graph framework to model hidden terminals in a static environment. We derive a combined mobility and hidden terminal model using a Markov chain from the hearing graph of a given physical layout. The simple model uses two parameters: /spl alpha/, which controls the number of hidden terminals in the steady state, and /spl lambda/, which controls the rate of mobility of each terminal. By varying the values of /spl alpha/ and /spl lambda/ we can systematically generate scenario with different number of hidden terminals and different mobility rates for a particular physical layout with static obstructions. We have developed a discrete event simulator which uses the parameterized model to obtain the throughput and blocking probability behavior of an IEEE 802.11 based ad hoc network in the presence of certain static obstructions. Our simulations suggest that the IEEE 802.11 DCF protocol is robust enough to handle moderate conditions of hidden terminals and mobility, but the performance may degrade under extreme conditions. Carefully selecting protocol parameters (RTS and fragmentation threshold) can help improve the performance even under extreme conditions.

In this paper, we present a framework for synthesizing I/O efficient out-of-core programs for block recursive algorithms, such as the fast Fourier transform (FFT) and block matrix transposition algorithms. Our framework uses an algebraic representation which is based on tensor products and other matrix operations. The programs are optimized for the striped Vitter and Shriver's two-level memory model in which data can be distributed using various cyclic(B) distributions in contrast to the normally used physical track distribution cyclic(B/sub d/), where B/sub d/ is the physical disk block size. We first introduce tensor bases to capture the semantics of block-cyclic data distributions of out-of-core data and also data access patterns to out-of-core data. We then present program generation techniques for tensor products and matrix transposition. We accurately represent the number of parallel I/O operations required for the synthesized programs for tensor products and matrix transposition as a function of tensor bases and data distributions. We introduce an algorithm to determine the data distribution which optimizes the performance of the synthesized programs. Further, we formalize the procedure of synthesizing efficient out-of-core programs for tensor product formulas with various block-cyclic distributions as a dynamic programming problem. We demonstrate the effectiveness of our approach through several examples. We show that the choice of an appropriate data distribution can reduce the number of passes to access out-of-core data by as large as eight times for a tensor product and the dynamic programming approach can largely reduce the number of passes to access out-of-core data for the overall tensor product formulas.

This paper presents a design methodology for developing efficient distributed-memory parallel programs for block recursive algorithms such as the fast Fourier transform (FFT) and bitonic sort. This design methodology is specifically suited for most modern supercomputers having a distributed-memory architecture with a circuit-switched or wormhole routed mesh or a hypercube interconnection network. A mathematical framework based on the tensor product and other matrix operations is used for representing algorithms. Communication-efficient implementations with effectively overlapped computation and communication are achieved by manipulating the mathematical representation using the tensor product algebra. Performance results for FFT programs on the Intel Paragon are presented. © 1998 John Wiley & Sons, Ltd.

All-to-all personalized communication, or complete exchange, is at the heart of numerous applications in parallel computing. Several complete exchange algorithms have been proposed in the literature for wormhole meshes. However, these algorithms, when applied to tori, cannot take advantage of wrap-around interconnections to implement complete exchange with reduced latency. In this paper, a new diagonal-propagation approach is proposed to develop a set of complete exchange algorithms for 2D and 3D tori. This approach exploits the symmetric interconnections of tori and allows to develop a communication schedule consisting of several contention-free phases. These algorithms are indirect in nature and they use message combining to reduce the number of phases (message start-ups). It is shown that these algorithms effectively use the bisection bandwidth of a torus which is twice that for an equal sized mesh, to achieve complete exchange in time which is almost half of the best known complete exchange time on an equal sized mesh. The effectiveness of these algorithms is verified through simulation studies for varying system and technological parameters. It is also demonstrated that synchronous implementations of these algorithms (by introducing barriers between phases) lead to reduced latency for complete exchange with large messages, while the asynchronous ones are better for smaller messages.

All-to-all personalized communication, or complete exchange, is at the heart of numerous applications in parallel computing. It is one of the most dense communication patterns. In this paper, we consider this problem in a torus of any dimension with the wormhole-routing capability. We propose complete exchange algorithms that use optimal numbers of phases (if each side of the tori is a multiple of eight) or asymptotically optimal numbers of phases (otherwise). Interestingly, in order to achieve this, we only make weak assumptions-that a node is capable of sending and receiving at most one message at a time, and the network is capable of supporting the dimension-ordered (or e-cube) minimum routing.

This paper presents a design methodology for developing efficient distributed-memory parallel programs for block-recursive algorithms such as the fast Fourier transform and bitonic sort. This design methodology is specifically suited for most modern supercomputers having a distributed-memory architecture with circuit-switched or wormhole routed mesh or hypercube interconnection network. A mathematical framework based on the tenser product and other matrix operations is used for representing algorithms. Communication-efficient implementations with effectively overlapped computation and communication are achieved by manipulating the mathematical representation using the tenser algebra. Performance results for FFT programs on the Intel iPSC/860 and Intel Paragon are presented.

Presents EXTENT (EXpert system for TENsor product formula Translation) which is a programming environment for the automatic generation of parallel/vector programs from tensor product formulas. A tensor (Kronecker) product based programming methodology is used for designing high-performance programs on various architectures. In this programming methodology, block recursive algorithms such as the fast Fourier transform and Strassen's matrix multiplication algorithm are expressed as tensor product formulas involving tensor product and other matrix operations. A tensor product formula can be systematically translated into parallel and/or vector code for various parallel architectures. A prototype system which generates programs for the Cray Y-MP, Cray T3D and Intel Paragon has been developed. Performance results for some generated programs are presented.>

Efficient generation of communication sets and local index sets is important for evaluation of array expressions in scientific languages such as Fortran-90 and High Performance Fortran implemented on distributed-memory machines. We show that for arrays affinely aligned with templates that are distributed on multiple processors with a block-cyclic distribution, the local memory access sequence and communication sets can be efficiently enumerated using closed forms. First, closed form solutions are presented for arrays that are aligned with identity template that are distributed using block or cyclic distributions.