Partially observable Markov decision processes (POMDPs) are a general mathematical model for sequential decision-making in stochastic environments under state uncertainty. POMDPs are often solved online, which enables the algorithm to adapt to new information in real time. Online solvers typically use bootstrap particle filters based on importance resampling for updating the belief distribution. Since directly sampling from the ideal state distribution given the latest observation and previous state is infeasible, particle filters approximate the posterior belief distribution by propagating states and adjusting weights through prediction and resampling steps. However, in practice, the importance resampling technique often leads to particle degeneracy and sample impoverishment when the state transition model poorly aligns with the posterior belief distribution, especially when the received observation is noisy. We propose an approach that constructs a sequence of bridge distributions between the state-transition and optimal distributions through iterative Monte Carlo steps, better accommodating noisy observations in online POMDP solvers. Our algorithm demonstrates significantly superior performance compared to state-of-the-art methods when evaluated across multiple challenging POMDP domains.

Sequential decision-making in high-dimensional continuous action spaces, particularly in stochastic environments, faces significant computational challenges. We explore this challenge in the traditional offline RL setting, where an agent must learn how to make decisions based on data collected through a stochastic behavior policy. We present \textit{Latent Macro Action Planner} (L-MAP), which addresses this challenge by learning a set of temporally extended macro-actions through a state-conditional Vector Quantized Variational Autoencoder (VQ-VAE), effectively reducing action dimensionality. L-MAP employs a (separate) learned prior model that acts as a latent transition model and allows efficient sampling of plausible actions. During planning, our approach accounts for stochasticity in both the environment and the behavior policy by using Monte Carlo tree search (MCTS). In offline RL settings, including stochastic continuous control tasks, L-MAP efficiently searches over discrete latent actions to yield high expected returns. Empirical results demonstrate that L-MAP maintains low decision latency despite increased action dimensionality. Notably, across tasks ranging from continuous control with inherently stochastic dynamics to high-dimensional robotic hand manipulation, L-MAP significantly outperforms existing model-based methods and performs on par with strong model-free actor-critic baselines, highlighting the effectiveness of the proposed approach in planning in complex and stochastic environments with high-dimensional action spaces.

Many real-world applications require decision-making where the environmental dynamics evolve over time. These non-stationary environments pose significant challenges to traditional decision-making models, which typically assume stationary dynamics. Non-stationary Markov decision processes (NS-MDPs) offer a framework to model and solve decision problems under such changing conditions. However, there are no standardized simulation frameworks for NS-MDPs, as opposed to widely popular frameworks for stationary problems. We present NS-Gym, the first simulation toolkit designed explicitly for NS-MDPs, integrated within the popular Gymnasium framework. In NS-Gym, we segregate the evolution of the environmental parameters that characterize non-stationarity from the agent’s decision-making module, allowing for modular and flexible adaptations to dynamic environments. We review prior work in this domain and present a toolkit encapsulating key problem characteristics and types in NS-MDPs. This toolkit is the first effort to develop a set of standardized interfaces and benchmark problems to enable consistent and reproducible evaluation of algorithms under non-stationary conditions. We also benchmark several algorithmic approaches from prior work on NS-MDPs using NS-Gym. We envision that NS-Gym will enable researchers to study decision-making under non-stationarity by providing standardized interfaces, simulation frameworks, and benchmark problems.

In Partially Observable Markov Decision Processes (POMDPs), maintaining and updating belief distributions over possible underlying states provides a principled way to summarize action-observation history for effective decision-making under uncertainty. As environments grow more realistic, belief distributions develop complexity that standard mathematical models cannot accurately capture, creating a fundamental challenge in maintaining representational accuracy. Despite advances in deep learning and probabilistic modeling, existing POMDP belief approximation methods fail to accurately represent complex uncertainty structures such as high-dimensional, multi-modal belief distributions, resulting in estimation errors that lead to suboptimal agent behaviors. To address this challenge, we present ESCORT (Efficient Stein-variational and sliced Consistency-Optimized Representation for Temporal beliefs), a particle-based framework for capturing complex, multi-modal distributions in high-dimensional belief spaces. ESCORT extends SVGD with two key innovations: correlation-aware projections that model dependencies between state dimensions, and temporal consistency constraints that stabilize updates while preserving correlation structures. This approach retains SVGD's attractive-repulsive particle dynamics while enabling accurate modeling of intricate correlation patterns. Unlike particle filters prone to degeneracy or parametric methods with fixed representational capacity, ESCORT dynamically adapts to belief landscape complexity without resampling or restrictive distributional assumptions. We demonstrate ESCORT's effectiveness through extensive evaluations on both POMDP domains and synthetic multi-modal distributions of varying dimensionality, where it consistently outperforms state-of-the-art methods in terms of belief approximation accuracy and downstream decision quality.

Autonomous vehicles (AVs) are becoming integral to on-demand micro transit, offering the potential for safer, efficient, and sustainable transportation. However, AV deployment faces several challenges, including the lack of suitable roadways, varying travel conditions. Traditional routers prioritize speed and not reliability, leading to unpredictable operations and complications in planning. To address these, we introduce AVATAR, an autonomy-aware routing framework that prioritizes dependable, low-variance routes. Our approach encodes multiple objectives including road speed, speed variability, zoning areas, pedestrian encounters, and operator preferred roadways into edge-level routing engines. Objective optimized routes are generated, then scored using a multi-criteria decision-making process. User-configurable preference profiles, allow operators to define a balance between reliability and speed. AVATAR is a data-driven framework that supports both real-time AV operations and offline analysis, enabling transit operators to assess and refine routing strategies. Our experiments using real-world data from Silicon Valley, California, and Yokohama, Japan show that our approach significantly improves AV reliability and performance and advances the sustainable and scalable integration of AVs into future transportation networks.

Effective traffic incident management is critical for road safety and operational efficiency. Yet, many transportation agencies rely on reactionary methods, where incidents are reported by human agents and managed through rule-based frameworks like traditional Traffic Incident Management (TIM) systems. However, these are vulnerable to human error, oversight, and delays during high-stress conditions. Although recent initiatives incorporating real-time sensor data for corridor monitoring and enhanced roadway information systems represent strides toward modernization, these systems often still require substantial human intervention. Recent advancements in graph-based deep learning models offer promising potential for addressing the limitations of traditional methods. While state-of-the-art models exist, the complexities of incident localization within dynamic and interconnected road networks, along with limited availability of high-quality labeled data and variability in real-time traffic measurements, are still open challenges. To address these, we propose the Traffic Response Anomaly Capture Engine (TRACE), a novel approach that combines graph neural networks, transformers, and probabilistic normalizing flows to accurately detect and localize traffic anomalies in real time. TRACE captures spatial-temporal dependencies, manages data uncertainty, and enhances automation, supporting more precise and timely incident localization. Our approach is validated on real-world traffic data and improved incident localization by 0.6 miles (17%) than SOTA methods while maintaining similar incident detection accuracy and mean detection delay.

Public bus transit systems provide critical transportation services for large sections of modern communities. On-time performance and maintaining the reliable quality of service is therefore very important. Unfortunately, disruptions caused by overcrowding, vehicular failures, and road accidents often lead to service performance degradation. Though transit agencies keep a limited number of vehicles in reserve and dispatch them to relieve the affected routes during disruptions, the procedure is often ad-hoc and has to rely on human experience and intuition to allocate resources (vehicles) to affected trips under uncertainty. In this article, we describe a principled approach using non-myopic sequential decision procedures to solve the problem and decide (a) if it is advantageous to anticipate problems and proactively station transit buses near areas with high-likelihood of disruptions and (b) decide if and which vehicle to dispatch to a particular problem. Our approach was developed in partnership WeGo Public Transit, a public transportation agency based in Nashville, Tennessee and models the system as a semi-Markov decision problem (solved as a Monte-Carlo tree search procedure) and shows that it is possible to obtain an answer to these two coupled decision problems in a way that maximizes the overall reward (number of people served). We sample many possible futures from generative models; each is assigned to a tree and processed using root parallelization. We validate our approach with both real-world and scaled-up data from two agencies in Tennessee. Our experiments show that the proposed framework serves 2% more passengers while reducing deadhead miles by 40%. Finally, we introduce Vectura, a dashboard providing transit dispatchers a complete view of the transit system at a glance along with access to our developed tools.

Federated learning (FL) is a promising approach for edge/IoT-based distributed machine learning, where both privacy and bandwidth efficiency are essential. However, as time progresses, edge/IoT-based FL faces challenges such as unpredictable concept drift, leading to model performance degradation and the need for frequent retraining. To address these challenges, we propose a federated learning framework designed for heterogeneous IoT devices, capable of handling continuous data distribution changes while accounting for limited storage resources. Our framework introduces a server-side drift detection method to minimize bandwidth usage and optimize retraining times, conserving IoT device resources. We also present an efficient storage management strategy to mitigate catastrophic forgetting by selectively managing incoming data streams within device constraints. Additionally, we develop an exemplar-based online continual learning algorithm that leverages class prototypes in the deep feature space to further combat catastrophic forgetting. We evaluate our framework on image classification tasks using ImageNet and CIFAR-100 datasets across four model architectures, demonstrating significant improvements in adaptation to concept drift and long-term performance stability compared to baseline FL approaches.

Monte Carlo tree search (MCTS) is one of the most capable online search algorithms for sequential planning tasks, with significant applications in areas such as resource allocation and transit planning. Despite its strong performance in real-world deployment, the inherent complexity of MCTS makes it challenging to understand for users without technical background. This paper considers the use of MCTS in transportation routing services, where the algorithm is integrated to develop optimized route plans. These plans are required to meet a range of constraints and requirements simultaneously, further complicating the task of explaining the algorithm’s operation in real-world contexts. To address this critical research gap, we introduce a novel computation tree logic-based explainer for MCTS. Our framework begins by taking user-defined requirements and translating them into rigorous logic specifications through the use of language templates. Then, our explainer incorporates a logic verification and quantitative evaluation module that validates the states and actions traversed by the MCTS algorithm. The outcomes of this analysis are then rendered into human-readable descriptive text using a second set of language templates. The user satisfaction of our approach was assessed through a survey with 82 participants. The results indicated that our explanatory approach significantly outperforms other baselines in user preference.

An emergency responder management (ERM) system dispatches responders, such as ambulances, when it receives requests for medical aid. ERM systems can also proactively reposition responders between predesignated waiting locations to cover any gaps that arise due to the prior dispatch of responders or significant changes in the distribution of anticipated requests. Optimal repositioning is computationally challenging due to the exponential number of ways to allocate responders between locations and the uncertainty in future requests. The state-of-the-art approach in proactive repositioning is a hierarchical approach based on spatial decomposition and online Monte Carlo tree search, which may require minutes of computation for each decision in a domain where seconds can save lives. We address the issue of long decision times by introducing a novel reinforcement learning (RL) approach, based on the same hierarchical decomposition, but replacing online search with learning. To address the computational challenges posed by large, variable-dimensional, and discrete state and action spaces, we propose: (1) actor-critic based agents that incorporate transformers to handle variable-dimensional states and actions, (2) projections to fixed-dimensional observations to handle complex states, and (3) combinatorial techniques to map continuous actions to discrete allocations. We evaluate our approach using real-world data from two U.S. cities, Nashville, TN and Seattle, WA. Our experiments show that compared to the state of the art, our approach reduces computation time per decision by three orders of magnitude, while also slightly reducing average ambulance response time by 5 seconds.

In this work, we test the influence of several levels of communication and processing corresponding latency for traffic wave dissipation control. The approach uses Connected and Automated Vehicles (CAVs) that are controlled in simulation through reinforcement learning and non-reinforcement learning controllers, and compares their performance with a pure human driving scenario that has no control latency. We measure the performances with respect to average traffic speed (aspect of traffic mobility), traffic speed standard deviation (aspect of traffic smoothness), and percentage of compliance with a custom designed safety monitor (aspect of traffic safety). The work shows that reinforcement learned controllers can perform with almost no deterioration in performance with latencies of 1 s or less. Non-reinforcement learning controllers, which are not intentionally modeled with latency in mind, show rapid deterioration in performance with any unexpected latency, which shows that the motivating problem requires a solution that is robust to latency. The paper discusses the training and reward function modifications required in order to consider latency as part of the framework, and discusses how the results may be suitable for deployment on high-latency networks such as mobile phones, without a 5G deployment.

Public transit systems are paramount in lowering carbon emissions and reducing urban congestion for environmental sustainability. However, overcrowding has adverse effects on the quality of service, passenger experience, and overall efficiency of public transit causing a decline in the usage of public transit systems. Therefore, it is crucial to identify and forecast potential windows of overcrowding to improve passenger experience and encourage higher ridership. Predicting ridership is a complex task, due to the inherent noise of collected data and the sparsity of overcrowding events. Existing studies in predicting public transit ridership consider only a static depiction of bus networks. We address these issues by first applying a data processing pipeline that cleans noisy data and engineers several features for training. Then, we address sparsity by converting the network to a dynamic graph and using a graph convolutional network, incorporating temporal, spatial, and auto-regressive features, to learn generalizable patterns for each route. Finally, since conventional loss functions like categorical cross-entropy have limitations in addressing class imbalance inherent in ridership data, our proposed approach uses focal loss to refine the prediction focus on less frequent yet task-critical overcrowding instances. Our experiments, using real-world data from our partner agency, show that the proposed approach outperforms existing state-of-the-art baselines in terms of accuracy and robustness.

The increasing popularity of electronic vehicles has spurred a demand for EV charging infrastructure. In the United States alone, over 160,000 public and private charging ports have been installed. This has stoked fear of potential grid issues in the future. Meanwhile, companies, specifically building owners are also seeing the opportunity to leverage EV batteries as energy stores to serve as buffers against the electric grid. The main idea is to influence and control charging behavior to provide a certain level of energy resiliency and demand responsiveness to the building from grid events while ensuring that they meet the demands of EV users. However, managing and co-optimizing energy requirements of EVs and cost-saving measures of building owners is a difficult task. First, user behavior and grid uncertainty contribute greatly to the potential effectiveness of different policies. Second, different charger configurations can have drastically different effects on the cost. Therefore, we propose a complete end-to-end discrete event simulator for vehicle-to-building charging optimization. This software is aimed at building owners and EV manufacturers such as Nissan, looking to deploy their charging stations with state-of-the-art optimization algorithms. We provide a complete solution that allows the owners to train, evaluate, introduce uncertainty, and benchmark policies on their datasets. Lastly, we discuss the potential for extending our work with other vehicle-to-grid deployments.

No abstract available.

Modern smart cities need smart transportation solutions to quickly detect various traffic emergencies and incidents in the city to avoid cascading traffic disruptions. To materialize this, roadside units and ambient transportation sensors are being deployed to collect speed data that enables the monitoring of traffic conditions on each road segment. In this article, we first propose a scalable data-driven anomaly-based traffic incident detection framework for a city-scale smart transportation system. Specifically, we propose an incremental region growing approximation algorithm for optimal Spatio-temporal clustering of road segments and their data; such that road segments are strategically divided into highly correlated clusters. The highly correlated clusters enable identifying a Pythagorean Mean-based invariant as an anomaly detection metric that is highly stable under no incidents but shows a deviation in the presence of incidents. We learn the bounds of the invariants in a robust manner such that anomaly detection can generalize to unseen events, even when learning from real noisy data. Second, using cluster-level detection, we propose a folded Gaussian classifier to pinpoint the particular segment in a cluster where the incident happened in an automated manner. We perform extensive experimental validation using mobility data collected from four cities in Tennessee and compare with the state-of-the-art ML methods to prove that our method can detect incidents within each cluster in real-time and outperforms known ML methods.

Industrial electric power grid operation subject to an extreme event requires decision-making by human operators under stressful conditions. Decision making using system data informatics under adverse dynamic events, especially if forecasted, should be supplemented by intelligent proactive control. Power transmission system operation during wildfires requires resiliency-driven proactive control for load shedding, line switching, and resource allocation considering the dynamics of the wildfire and failure propagation to minimize the impact on the system. However, the possible number of line and load switching in an extensive industrial system during an event make traditional prediction-driven and stochastic approaches computationally intractable, leading operators to often use pre-planned or greedy algorithms. In this work, we model and solve the proactive control problem as a Markov decision process and introduce an integrated testbed for spatio-temporal wildfire propagation and proactive power-system operation. Our approach allows the controller to provide setpoints for all generation fleets in the power grid. We evaluate our approach utilizing the IEEE test system mapped onto a hypothetical terrain. Our results show that the proposed approach can help the operator to reduce load outage during an extreme event. It reduces power flow through lines that are to be de-energized, and adjusts the load demand by increasing power flow through other lines.

The offline pickup and delivery problem with time windows (PDPTW) is a classical combinatorial optimization problem in the transportation community, which has proven to be very challenging computationally. Due to the complexity of the problem, practical problem instances can be solved only via heuristics, which trade-off solution quality for computational tractability. Among the various heuristics, a common strategy is problem decomposition, that is, the reduction of a large-scale problem into a collection of smaller sub-problems, with spatial and temporal decompositions being two natural approaches. While spatial decomposition has been successful in certain settings, effective temporal decomposition has been challenging due to the difficulty of stitching together the sub-problem solutions across the decomposition boundaries. In this work, we introduce a novel temporal decomposition scheme for solving a class of PDPTWs that have narrow time windows, for which it is able to provide both fast and high-quality solutions. We utilize techniques that have been popularized recently in the context of online dial-a-ride problems along with the general idea of rolling horizon optimization. To the best of our knowledge, this is the first attempt to solve offline PDPTWs using such an approach. To show the performance and scalability of our framework, we use the optimization of paratransit services as a motivating example. Due to the lack of benchmark solvers similar to ours (i.e., temporal decomposition with an online solver), we compare our results with an offline heuristic algorithm using Google OR-Tools. In smaller problem instances (with an average of 129 requests per instance), the baseline approach is as competitive as our framework. However, in larger problem instances (approximately 2,500 requests per instance), our framework is more scalable and can provide good solutions to problem instances of varying degrees of difficulty, while the baseline algorithm often fails to find a feasible solution within comparable compute times.

Timely and accurate detection of events affecting the stability and reliability of power transmission systems is crucial for safe grid operation. This paper presents an efficient unsupervised machine-learning algorithm for event detection using a combination of discrete wavelet transform (DWT) and convolutional autoencoders (CAE) with synchrophasor phasor measurements. These measurements are collected from a hardware-in-the-loop testbed setup equipped with a digital real-time simulator. Using DWT, the detail coefficients of measurements are obtained. Next, the decomposed data is then fed into the CAE that captures the underlying structure of the transformed data. Anomalies are identified when significant errors are detected between input samples and their reconstructed outputs. We demonstrate our approach on the IEEE-14 bus system considering different events such as generator faults, line-to-line faults, line-to-ground faults, load shedding, and line outages simulated on a real-time digital simulator (RTDS). The proposed implementation achieves a classification accuracy of 97.7%, precision of 98.0%, recall of 99.5%, F1 Score of 98.7%, and proves to be efficient in both time and space requirements compared to baseline approaches.

The integration of computational capabilities with the electrical infrastructure of the grid can be envisioned as a societal scale Cyber Physical System (CPS). Middleware frameworks can act as a layer of abstraction that manages the interaction between disparate applications to facilitate intelligent control and management of energy production and consumption. This demonstration showcases Resilient Information Architecture Platform for Smart Grid (RIAPS), a distributed software platform that combines a domain specific modeling language with framework-level services such as communication, remote deployment of applications, distributed coordination, time synchronization, and fault tolerance, to develop and run distributed applications. An example of an energy demand curtailment scheme called load shedding is presented, to highlight how the RIAPS framework can be used to implement distributed algorithms to control elements of a power system, which runs as a simulation using OpenDSS.

Large-scale traffic simulations are necessary for the planning, design, and operation of city-scale transportation systems. These simulations enable novel and complex transportation technology and services such as optimization of traffic control systems, supporting on-demand transit, and redesigning regional transit systems for better energy efficiency and emissions. For a city-wide simulation model, big data from multiple sources such as Open Street Map (OSM), traffic surveys, geo-location traces, vehicular traffic data, and transit details are integrated to create a unique and accurate representation. However, in order to accurately identify the model structure and have reliable simulation results, these traffic simulation models must be thoroughly calibrated and validated against real-world data. This paper presents a novel calibration approach for a city-scale traffic simulation model based on limited real-world speed data. The simulation model runs a microscopic and mesoscopic realistic traffic simulation from Chattanooga, TN (US) for a 24-hour period and includes various transport modes such as transit buses, passenger cars, and trucks. The experiment results presented demonstrate the effectiveness of our approach for calibrating large-scale traffic networks using only real-world speed data. This paper presents our proposed calibration approach that utilizes 2160 real-world speed data points, performs sensitivity analysis of the simulation model to input parameters, and genetic algorithm for optimizing the model for calibration.

Public transit is a vital mode of transportation in urban areas, and its efficiency is crucial for the daily commute of millions of people. To improve the reliability and predictability of transit systems, researchers have developed separate single-task learning models to predict the occupancy and delay of buses at the stop or route level. However, these models provide a narrow view of delay and occupancy at each stop and do not account for the correlation between the two. We propose a novel approach that leverages broader generalizable patterns governing delay and occupancy for improved prediction. We introduce a multitask learning toolchain that takes into account General Transit Feed Specification feeds, Automatic Passenger Counter data, and contextual temporal and spatial information. The toolchain predicts transit delay and occupancy at the stop level, improving the accuracy of the predictions of these two features of a trip given sparse and noisy data. We also show that our toolchain can adapt to fewer samples of new transit data once it has been trained on previous routes/trips as compared to state-of-the-art methods. Finally, we use actual data from Chattanooga, Tennessee, to validate our approach. We compare our approach against the state-of-the-art methods and we show that treating occupancy and delay as related problems improves the accuracy of the predictions. We show that our approach improves delay prediction significantly by as much as 4% in F1 scores while producing equivalent or better results for occupancy.

Route Planning Systems (RPS) are a core component of autonomous personal transport systems essential for safe and efficient navigation of dynamic urban environments with the support of edge-based smart city infrastructure, but they also raise concerns about user route privacy in the context of both privately owned and commercial vehicles. Numerous high-profile data breaches in recent years have fortunately motivated research on privacy-preserving RPS, but most of them are rendered impractical by greatly increased communication and processing overhead. We address this by proposing an approach called Hierarchical Privacy-Preserving Route Planning (HPRoP), which divides and distributes the route-planning task across multiple levels and protects locations along the entire route. This is done by combining Inertial Flow partitioning, Private Information Retrieval (PIR), and Edge Computing techniques with our novel route-planning heuristic algorithm. Normalized metrics were also formulated to quantify the privacy of the source/destination points ( endpoint location privacy ) and the route itself ( route privacy ). Evaluation on a simulated road network showed that HPRoP reliably produces routes differing only by ≤ 20% in length from optimal shortest paths, with completion times within ∼ 25 seconds, which is reasonable for a PIR-based approach. On top of this, more than half of the produced routes achieved near-optimal endpoint location privacy (∼ 1.0) and good route privacy (≥ 0.8).

The public commute is essential to all urban centers and is an efficient and environment-friendly way to travel. Transit systems must become more accessible and user-friendly. Since public transit is majorly designed statically, with very few improvements coming over time, it can get stagnated, unable to update itself with changing population trends. To better understand transportation demands and make them more usable, efficient, and demographic-focused, we propose a fast, multi-layered transit simulation that primarily focuses on public transit simulation (BTE-Sim). BTE-Sim is designed based on the population demand, existing traffic conditions, and the road networks that exist in a region. The system is versatile, with the ability to run different configurations of the existing transit routes, or inculcate any new changes that may seem necessary, or even in extreme cases, new transit network design as well. In all situations, it can compare multiple transit networks and provide evaluation metrics for them. It provides detailed data on each transit vehicle, the trips it performs, its on-time performance and other necessary factors. Its highlighting feature is the considerably low computation time it requires to perform all these tasks and provide consistently reliable results.

The ability to accurately predict public transit ridership demand benefits passengers and transit agencies. Agencies will be able to reallocate buses to handle under or over-utilized bus routes, improving resource utilization, and passengers will be able to adjust and plan their schedules to avoid overcrowded buses and maintain a certain level of comfort. However, accurately predicting occupancy is a non-trivial task. Various reasons such as heterogeneity, evolving ridership patterns, exogenous events like weather, and other stochastic variables, make the task much more challenging. With the progress of big data, transit authorities now have access to real-time passenger occupancy information for their vehicles. The amount of data generated is staggering. While there is no shortage in data, it must still be cleaned, processed, augmented, and merged before any useful information can be generated. In this paper, we propose the use and fusion of data from multiple sources, cleaned, processed, and merged together, for use in training machine learning models to predict transit ridership. We use data that spans a 2-year period (2020-2022) incorporating transit, weather, traffic, and calendar data. The resulting data, which equates to 17 million observations, is used to train separate models for the trip and stop level prediction. We evaluate our approach on real-world transit data provided by the public transit agency of Nashville, TN. We demonstrate that the trip level model based on Xgboost and the stop level model based on LSTM outperform the baseline statistical model across the entire transit service day.

While cloud computing is the current standard for outsourcing computation, it can be prohibitively expensive for cities and infrastructure operators to deploy services. At the same time, there are underutilized computing resources within cities and local edge-computing deployments. Using these slack resources may enable significantly lower pricing than comparable cloud computing; such resources would incur minimal marginal expenditure since their deployment and operation are mostly sunk costs. However, there are challenges associated with using these resources. First, they are not effectively aggregated or provisioned. Second, there is a lack of trust between customers and suppliers of computing resources, given that they are distinct stakeholders and behave according to their own interests. Third, delays in processing inputs may diminish the value of the applications. To resolve these chal-lenges, we introduce an architecture combining a distributed trusted computing mechanism, such as a blockchain, with an efficient messaging system like Apache Pulsar. Using this architecture, we design a decentralized computation market where customers and suppliers make offers to deploy and host applications. The proposed architecture can be realized using any trusted computing mechanism that supports smart contracts, and any messaging framework with the necessary features. This combination ensures that the market is robust without incurring the input processing delays that limit other blockchain based solutions. We evaluate the market protocol using game-theoretic analysis to show that deviation from the protocol is discouraged. Finally, we assess the performance of a prototype implementation based on experiments with a streaming computer-vision application.

High-resolution X-ray computed tomography (XCT) is an important technique for the inspection of additively manufactured (AM) parts. While XCT is typically used off-line to inspect a subset of manufactured parts, significantly accelerating measurement speed while retaining accuracy would enable use of XCT for in-line inspection to rapidly identify defects in each part as it is manufactured. Here, we propose a deep learning (DL) based approach that uses computer aided design (CAD) models of the AM parts and physics-based information to rapidly produce high-quality reconstructions from sparse XCT measurements without high quality ground truth data. Our approach uses a generative adversarial neural network (GAN) to produced realistic training data from the CAD-based simulations and a deep neural network that is trained using data from the first stage to produce accurate 3D reconstructions. Using experimental XCT data of metal parts, we demonstrate enhanced defect detection capabilities while dramatically reducing the scan time.

More than 5 million children under five years die from largely preventable or treatable medical conditions every year, with an overwhelmingly large proportion of deaths occurring in under-developed countries with low vaccination uptake. One of the United Nations' sustainable development goals (SDG 3) aims to end preventable deaths of newborns and children under five years of age. We focus on Nigeria, where the rate of infant mortality is appalling. We collaborate with HelpMum, a large non-profit organization in Nigeria, to design and optimize the allocation of heterogeneous health interventions under uncertainty to increase vaccination uptake, the first such collaboration in Nigeria. Our framework, ADVISER: AI-Driven Vaccination Intervention Optimiser, is based on an integer linear program that seeks to maximize the cumulative probability of successful vaccination. Our optimization formulation is intractable in practice. We present a heuristic approach that enables us to solve the problem for real-world use-cases. We also present theoretical bounds for the heuristic method. Finally, we show that the proposed approach outperforms baseline methods in terms of vaccination uptake through experimental evaluation. HelpMum is currently planning a pilot program based on our approach to be deployed in the largest city of Nigeria, which would be the first deployment of an AI-driven vaccination uptake program in the country and hopefully, pave the way for other data-driven programs to improve health outcomes in Nigeria.

Vehicle routing problems (VRPs) can be divided into two major categories: offline VRPs, which consider a given set of trip requests to be served, and online VRPs, which consider requests as they arrive in real-time. Based on discussions with public transit agencies, we identify a real-world problem that is not addressed by existing formulations: booking trips with flexible pickup windows (e.g., 3 hours) in advance (e.g., the day before) and confirming tight pickup windows (e.g., 30 minutes) at the time of booking. Such a service model is often required in paratransit service settings, where passengers typically book trips for the next day over the phone. To address this gap between offline and online problems, we introduce a novel formulation, the offline vehicle routing problem with online bookings. This problem is very challenging computationally since it faces the complexity of considering large sets of requests—similar to offline VRPs—but must abide by strict constraints on running time—similar to online VRPs. To solve this problem, we propose a novel computational approach, which combines an anytime algorithm with a learning-based policy for real-time decisions. Based on a paratransit dataset obtained from the public transit agency of Chattanooga, TN, we demonstrate that our novel formulation and computational approach lead to significantly better outcomes in this setting than existing algorithms.

Accurately predicting the ridership of public-transit routes provides substantial benefits to both transit agencies, who can dispatch additional vehicles proactively before the vehicles that serve a route become crowded, and to passengers, who can avoid crowded vehicles based on publicly available predictions. The spread of the coronavirus disease has further elevated the importance of ridership prediction as crowded vehicles now present not only an inconvenience but also a public-health risk. At the same time, accurately predicting ridership has become more challenging due to evolving ridership patterns, which may make all data except for the most recent records stale. One promising approach for improving prediction accuracy is to fine-tune the hyper-parameters of machine-learning models for each transit route based on the characteristics of the particular route, such as the number of records. However, manually designing a machine-learning model for each route is a labor-intensive process, which may require experts to spend a significant amount of their valuable time. To help experts with designing machine-learning models, we propose a neural-architecture and feature search approach, which optimizes the architecture and features of a deep neural network for predicting the ridership of a public-transit route. Our approach is based on a randomized local hyper-parameter search, which minimizes both prediction error as well as the complexity of the model. We evaluate our approach on real-world ridership data provided by the public transit agency of Chattanooga, TN, and we demonstrate that training neural networks whose architectures and features are optimized for each route provides significantly better performance than training neural networks whose architectures and features are generic.

Resource allocation under uncertainty is a classic problem in city-scale cyber-physical systems. Consider emergency response, where urban planners and first responders optimize the location of ambulances to minimize expected response times to incidents such as road accidents. Typically, such problems involve sequential decision making under uncertainty and can be modeled as Markov (or semi-Markov) decision processes. The goal of the decision maker is to learn a mapping from states to actions that can maximize expected rewards. While online, offline, and decentralized approaches have been proposed to tackle such problems, scalability remains a challenge for real world use cases. We present a general approach to hierarchical planning that leverages structure in city level CPS problems for resource allocation. We use emergency response as a case study and show how a large resource allocation problem can be split into smaller problems. We then use Monte Carlo planning for solving the smaller problems and managing the interaction between them. Finally, we use data from Nashville, Tennessee, a major metropolitan area in the United States, to validate our approach. Our experiments show that the proposed approach outperforms state-of-the-art approaches used in the field of emergency response.

Deep Neural Networks are actively being used in the design of autonomous Cyber-Physical Systems (CPSs). The advantage of these models is their ability to handle high-dimensional state-space and learn compact surrogate representations of the operational state spaces. However, the problem is that the sampled observations used for training the model may never cover the entire state space of the physical environment, and as a result, the system will likely operate in conditions that do not belong to the training distribution. These conditions that do not belong to training distribution are referred to as Out-of-Distribution (OOD). Detecting OOD conditions at runtime is critical for the safety of CPS. In addition, it is also desirable to identify the context or the feature(s) that are the source of OOD to select an appropriate control action to mitigate the consequences that may arise because of the OOD condition. In this article, we study this problem as a multi-labeled time series OOD detection problem over images, where the OOD is defined both sequentially across short time windows (change points) as well as across the training data distribution. A common approach to solving this problem is the use of multi-chained one-class classifiers. However, this approach is expensive for CPSs that have limited computational resources and require short inference times. Our contribution is an approach to design and train a single β -Variational Autoencoder detector with a partially disentangled latent space sensitive to variations in image features. We use the feature sensitive latent variables in the latent space to detect OOD images and identify the most likely feature(s) responsible for the OOD. We demonstrate our approach using an Autonomous Vehicle in the CARLA simulator and a real-world automotive dataset called nuImages.

Due to the high upfront cost of electric vehicles, many public transit agencies can afford only mixed fleets of internal combustion and electric vehicles. Optimizing the operation of such mixed fleets is challenging because it requires accurate trip-level predictions of electricity and fuel use as well as efficient algorithms for assigning vehicles to transit routes. We present a novel framework for the data-driven prediction of trip-level energy use for mixed-vehicle transit fleets and for the optimization of vehicle assignments, which we evaluate using data collected from the bus fleet of CARTA, the public transit agency of Chattanooga, TN. We first introduce a data collection, storage, and processing framework for system-level and high-frequency vehicle-level transit data, including domain-specific data cleansing methods. We train and evaluate machine learning models for energy prediction, demonstrating that deep neural networks attain the highest accuracy. Based on these predictions, we formulate the problem of minimizing energy use through assigning vehicles to fixed-route transit trips. We propose an optimal integer program as well as efficient heuristic and meta-heuristic algorithms, demonstrating the scalability and performance of these algorithms numerically using the transit network of CARTA.

Affordable public transit services are crucial for communities since they enable residents to access employment, education, and other services. Unfortunately, transit services that provide wide coverage tend to suffer from relatively low utilization, which results in high fuel usage per passenger per mile, leading to high operating costs and environmental impact. Electric vehicles (EVs) can reduce energy costs and environmental impact, but most public transit agencies have to employ them in combination with conventional, internal-combustion engine vehicles due to the high upfront costs of EVs. To make the best use of such a mixed fleet of vehicles, transit agencies need to optimize route assignments and charging schedules, which presents a challenging problem for large transit networks. We introduce a novel problem formulation to minimize fuel and electricity use by assigning vehicles to transit trips and scheduling them for charging, while serving an existing fixed-route transit schedule. We present an integer program for optimal assignment and scheduling, and we propose polynomial-time heuristic and meta-heuristic algorithms for larger networks. We evaluate our algorithms on the public transit service of Chattanooga, TN using operational data collected from transit vehicles. Our results show that the proposed algorithms are scalable and can reduce energy use and, hence, environmental impact and operational costs. For Chattanooga, the proposed algorithms can save $145,635 in energy costs and 576.7 metric tons of CO2 emission annually.

Emergency response is highly dependent on the time of incident reporting. Unfortunately, the traditional approach to receiving incident reports (e.g., calling 911 in the USA) has time delays. Crowdsourcing platforms such as Waze provide an opportunity for early identification of incidents. However, detecting incidents from crowdsourced data streams is difficult due to the challenges of noise and uncertainty associated with such data. Further, simply optimizing over detection accuracy can compromise spatial-temporal localization of the inference, thereby making such approaches infeasible for real-world deployment. This paper presents a novel problem formulation and solution approach for practitioner-centered incident detection using crowdsourced data by using emergency response management as a case-study. The proposed approach CROME (Crowdsourced Multi-objective Event Detection) quantifies the relationship between the performance metrics of incident classification (e.g., F1 score) and the requirements of model practitioners (e.g., 1 km. radius for incident detection). First, we show how crowdsourced reports, ground-truth historical data, and other relevant determinants such as traffic and weather can be used together in a Convolutional Neural Network (CNN) architecture for early detection of emergency incidents. Then, we use a Pareto optimization-based approach to optimize the output of the CNN in tandem with practitioner-centric parameters to balance detection accuracy and spatial-temporal localization. Finally, we demonstrate the applicability of this approach using crowdsourced data from Waze and traffic accident reports from Nashville, TN, USA. Our experiments demonstrate that the proposed approach outperforms existing approaches in incident detection while simultaneously optimizing the needs for real-world deployment and usability.

Deep Neural Networks (DNNs) are widely used in automotive Cyber-Physical Systems (CPSs) to implement autonomy related tasks. However, these networks have exhibited erroneous predictions to anomalous inputs that manifest either due to Out-of-Distribution (OOD) data or adversarial attacks. To detect these anomalies, a separate DNN called assurance monitor is used in parallel to the controller DNN, increasing the resource burden and latency. We hypothesize that a single network that can perform controller predictions and anomaly detection is necessary to reduce the resource requirements. Deep-Radial Basis Function (RBF) networks provide a rejection class alongside the class predictions, which can be used for anomaly detection. However, the use of RBF activation functions limits the applicability of these networks to only classification tasks. In this paper, we discuss the steps involved in detecting anomalies in CPS regression and classification tasks. Further, we design deep-RBF networks using popular DNNs such as NVIDIA DAVE-II and ResNet20 and then use the resulting rejection class for detecting physical and data poison adversarial attacks. We show that the deep-RBF network can effectively detect these attacks with limited resource requirements.

Public-transit systems face a number of operational challenges: (a) changing ridership patterns requiring optimization of fixed line services, (b) optimizing vehicle-to-trip assignments to reduce maintenance and operation codes, and (c) ensuring equitable and fair coverage to areas with low ridership. Optimizing these objectives presents a hard computational problem due to the size and complexity of the decision space. State-of-the-art methods formulate these problems as variants of the vehicle routing problem and use data-driven heuristics for optimizing the procedures. However, the evaluation and training of these algorithms require large datasets that provide realistic coverage of various operational uncertainties. This paper presents a dynamic simulation platform, called TRANSIT-GYM, that can bridge this gap by providing the ability to simulate scenarios, focusing on variation of demand models, variations of route networks, and variations of vehicle-to-trip assignments. The central contribution of this work is a domain-specific language and associated experimentation tool-chain and infrastructure to enable subject-matter experts to intuitively specify, simulate, and analyze large-scale transit scenarios and their parametric variations. Of particular significance is an integrated microscopic energy consumption model that also helps to analyze the energy cost of various transit decisions made by the transportation agency of a city.

The realization of edge-based cyber-physical systems (CPS) poses important challenges in terms of performance, robustness, security, etc. This paper examines a novel approach to providing a user-centric adaptive route planning service over a network of Road Side Units (RSUs) in smart cities. The key idea is to adaptively select routing task parameters such as privacy-cloaked area sizes and number of retained intersections to balance processing time, privacy protection level, and route accuracy for privacy-augmented distributed route search while also handling per-query user preferences. This is formulated as an optimization problem with a set of parameters giving the best result for a set of queries given system constraints. Processing Throughput, Privacy Protection, and Travel Time Accuracy were developed as the objective functions to be balanced. A Multi-Objective Genetic Algorithm based technique (NSGA-II) is applied to recover a feasible solution. The performance of this approach was then evaluated using traffic data from Osaka, Japan. Results show good performance of the approach in balancing the aforementioned objectives based on user preferences.

Emergency Response Management (ERM) necessitates the use of models capable of predicting the spatial-temporal likelihood of incident occurrence. These models are used for proactive stationing in order to reduce overall response time. Traditional methods simply aggregate past incidents over space and time; such approaches fail to make useful short-term predictions when the spatial region is large and focused on fine-grained spatial entities like interstate highway networks. This is partially due to the sparsity of incidents with respect to space and time. Further, accidents are affected by several covariates. Collecting, cleaning, and managing multiple streams of data from various sources is challenging for large spatial areas. In this paper, we highlight how this problem is being solved in collaboration with the Tennessee Department of Transportation (TDOT) to improve ERM in the state of Tennessee. Our pipeline, based on a combination of synthetic resampling, clustering, and data mining techniques, can efficiently forecast the spatio-temporal dynamics of accident occurrence, even under sparse conditions. Our pipeline uses data related to roadway geometry, weather, historical accidents, and traffic to aid accident forecasting. To understand how our forecasting model can affect allocation and dispatch, we improve and employ a classical resource allocation approach. Experimental results show that our approach can noticeably reduce response times and the number of unattended incidents in comparison to current approaches followed by first responders. The developed pipeline is efficacious, applicable in practice, and open-source.

Power grids are evolving at an unprecedented pace due to the rapid growth of distributed energy resources (DER) in communities. These resources are very different from traditional power sources, as they are located closer to loads and thus can significantly reduce transmission losses and carbon emissions. However, their intermittent and variable nature often results in spikes in the overall demand on distribution system operators (DSO). To manage these challenges, there has been a surge of interest in building decentralized control schemes, where a pool of DERs combined with energy storage devices can exchange energy locally to smooth fluctuations in net demand. Building a decentralized market for transactive microgrids is challenging, because even though a decentralized system provides resilience, it also must satisfy requirements such as privacy, efficiency, safety, and security, which are often in conflict with each other. As such, existing implementations of decentralized markets often focus on resilience and safety but compromise on privacy. In this article, we describe our platform, called TRANSAX, which enables participants to trade in an energy futures market, which improves efficiency by finding feasible matches for energy trades, enabling DSOs to plan their energy needs better. TRANSAX provides privacy to participants by anonymizing their trading activity using a distributed mixing service, while also enforcing constraints that limit trading activity based on safety requirements, such as keeping planned energy flow below line capacity. We show that TRANSAX can satisfy the seemingly conflicting requirements of efficiency, safety, and privacy. We also provide an analysis of how much trading efficiency is lost. Trading efficiency is improved through the problem formulation, which accounts for temporal flexibility, and system efficiency is improved using a hybrid-solver architecture. Finally, we describe a testbed to run experiments and demonstrate its performance using simulation results.

Perception-based deep neural networks used in Cyber Physical Systems are known to fail when faced with inputs that are out-of-distribution (ODD). ODD detection is a complex problem as we need to first identify the shift in the test data from the training distribution and then we need to isolate the responsible generative factor(s) (weather, lighting levels, traffic density, etc.), Unlike the state of the art that uses multi-chained one-class classifiers, we propose an efficient single monitor that uses the principle of disentanglement to train the latent space of a variational autoencoder to be sensitive to distribution shifts in different generative factors. We demonstrate our approach using an end-to-end driving controller in the CARLA simulator.

Deep Learning (DL) model-based AI services are increasingly offered in a variety of predictive analytics services such as computer vision, natural language processing, speech recognition. However, the quality of the DL models can degrade over time due to changes in the input data distribution, thereby requiring periodic model updates. Although cloud data-centers can meet the computational requirements of the resource-intensive and time-consuming model update task, transferring data from the edge devices to the cloud incurs a significant cost in terms of network bandwidth and are prone to data privacy issues. With the advent of GPU-enabled edge devices, the DL model update can be performed at the edge in a distributed manner using multiple connected edge devices. However, efficiently utilizing the edge resources for the model update is a hard problem due to the heterogeneity among the edge devices and the resource interference caused by the colocation of the DL model update task with latency-critical tasks running in the background. To overcome these challenges, we present Deep-Edge, a load- and interference-aware, fault-tolerant resource management framework for performing model update at the edge that uses distributed training. This paper makes the following contributions. First, it provides a unified framework for monitoring, profiling, and deploying the DL model update tasks on heterogeneous edge devices. Second, it presents a scheduler that reduces the total re-training time by appropriately selecting the edge devices and distributing data among them such that no latency-critical applications experience deadline violations. Finally, we present empirical results to validate the efficacy of the framework using a real-world DL model update case-study based on the Caltech dataset and an edge AI cluster testbed.

Memory corruption attacks such as code injection, code reuse, and non-control data attacks have become widely popular for compromising safety-critical Cyber-Physical Systems (CPS). Moving target defense (MTD) techniques such as instruction set randomization (ISR), address space randomization (ASR), and data space randomization (DSR) can be used to protect systems against such attacks. CPS often use time-triggered architectures to guarantee predictable and reliable operation. MTD techniques can cause time delays with unpredictable behavior. To protect CPS against memory corruption attacks, MTD techniques can be implemented in a mixed time and event-triggered architecture that provides capabilities for maintaining safety and availability during an attack. This paper presents a mixed time and event-triggered MTD security approach based on the ARINC 653 architecture that provides predictable and reliable operation during normal operation and rapid detection and reconfiguration upon detection of attacks. We leverage a hardware-in-the-loop testbed and an advanced emergency braking system (AEBS) case study to show the effectiveness of our approach.

Recent advancements in cloud computing have driven rapid development in data-intensive smart city applications by providing near real time processing and storage scalability. This has resulted in efficient centralized route planning services such as Google Maps, upon which millions of users rely. Route planning algorithms have progressed in line with the cloud environments in which they run. Current state of the art solutions assume a shared memory model, hence deployment is limited to multiprocessing environments in data centers. By centralizing these services, latency has become the limiting parameter in the technologies of the future, such as autonomous cars. Additionally, these services require access to outside networks, raising availability concerns in disaster scenarios. Therefore, this paper provides a decentralized route planning approach for private fog networks. We leverage recent advances in federated learning to collaboratively learn shared prediction models online and investigate our approach with a simulated case study from a mid-size U.S. city.

Due to increasing concerns about environmental impact, operating costs, and energy security, public transit agencies are seeking to reduce their fuel use by employing electric vehicles (EVs), However, because of the high upfront cost of EVs, most agencies can afford only mixed fleets of internal-combustion and electric vehicles. Making the best use of these mixed fleets presents a challenge for agencies since optimizing the assignment of vehicles to transit routes, scheduling charging, etc. require accurate predictions of electricity and fuel use. Recent advances in sensor-based technologies, data analytics, and machine learning enable remedying this situation; however, to the best of our knowledge, there exists no framework that would integrate all relevant data into a route-level prediction model for public transit. In this paper, we present a novel framework for the data-driven prediction of route-level energy use for mixed-vehicle transit fleets, which we evaluate using data collected from the bus fleet of CARTA, the public transit authority of Chattanooga, TN. We present a data collection and storage framework, which we use to capture system-level data, including traffic and weather conditions, and high-frequency vehicle-level data, including location traces, fuel or electricity use, etc. We present domain-specific methods and algorithms for integrating and cleansing data from various sources, including street and elevation maps. Finally, we train and evaluate machine learning models, including deep neural networks, decision trees, and linear regression, on our integrated dataset. Our results show that neural networks provide accurate estimates, while other models can help us discover relations between energy use and factors such as road and weather conditions.

This paper presents a data-driven approach for predicting the propagation of traffic congestion at road segments as a function of the congestion in their neighboring segments. In the past, this problem has mostly been addressed by modelling the traffic congestion over some standard physical phenomenon through which it is difficult to capture all the modalities of such a dynamic and complex system. While other recent works have focused on applying a generalized data-driven technique on the whole network at once, they often ignore intersection characteristics. On the contrary, we propose a city-wide ensemble of intersection level connected LSTM models and propose mechanisms for identifying congestion events using the predictions from the networks. To reduce the search space of likely congestion sinks we use the likelihood of congestion propagation in neighboring road segments of a congestion source that we learn from the past historical data. We validated our congestion forecasting framework on the real world traffic data of Nashville, USA and identified the onset of congestion in each of the neighboring segments of any congestion source with an average precision of 0.9269 and an average recall of 0.9118 tested over ten congestion events.

This demo showcases the features of an adaptive middleware framework for resource constrained autonomous robots like DeepNNCar (Figure 1). These robots use Learning Enabled Components (LECs), trained with deep learning models to perform control actions. However, these LECs do not provide any safety guarantees and testing them is challenging. To overcome these challenges, we have developed an adaptive middleware framework that (1) augments the LEC with safety controllers that can use different weighted simplex strategies to improve the systems safety guarantees, and (2) includes a resource manager to monitor the resource parameters (temperature, CPU Utilization), and offload tasks at runtime. Using DeepNNCar we will demonstrate the framework and its capability to adaptively switch between the controllers and strategies based on its safety and speed performance.

The modern electric grid is a complex, decentralized cyber-physical system requiring higher-level control techniques to balance the demand and supply of energy to optimize the overall energy usage. The concept of Transactive Energy utilizes distributed system principle to address this challenge. In this demonstration we show the usage of the distributed application management platform RIAPS in the implementation of one such Transactive Energy approach to control elements of a power system, which runs as a a simulation using the Gridlab-d simulation solver.

The vision of the `Smart Grid' assumes a distributed real-time embedded system that implements various monitoring and control functions. As the reliability of the power grid is critical to modern society, the software supporting the grid must support fault tolerance and resilience in the resulting cyber-physical system. This paper describes the fault-tolerance features of a software framework called Resilient Information Architecture Platform for Smart Grid (RIAPS). The framework supports various mechanisms for fault detection and mitigation and works in concert with the applications that implement the grid-specific functions. The paper discusses the design philosophy for and the implementation of the fault tolerance features and presents an application example to show how it can be used to build highly resilient systems.

Smart infrastructure demands resilient data storage, and emerging applications execute queries on this data over time. Typically, time-series databases serve these queries; however, cloud-based time-series storage can be prohibitively expensive. As smart devices proliferate, the amount of computing power and memory available in our connected infrastructure provides the opportunity to move resilient time-series data storage and analytics to the edge. This paper proposes time-series storage in a Distributed Hash Table (DHT), and a novel key-generation technique that provides time-indexed reads and writes for key-value pairs. Experimental results show this technique meets demands for smart infrastructure situations.

Learning enabled components (LECs) trained using data-driven algorithms are increasingly being used in autonomous robots commonly found in factories, hospitals, and educational laboratories. However, these LECs do not provide any safety guarantees, and testing them is challenging. In this paper, we introduce a framework that performs weighted simplex strategy based supervised safety control, resource management and confidence estimation of autonomous robots. Specifically, we describe two weighted simplex strategies: (a) simple weighted simplex strategy (SW-Simplex) that computes a weighted controller output by comparing the decisions between a safety supervisor and an LEC, and (b) a context-sensitive weighted simplex strategy (CSW-Simplex) that computes a context-aware weighted controller output. We use reinforcement learning to learn the contextual weights. We also introduce a system monitor that uses the current state information and a Bayesian network model learned from past data to estimate the probability of the robotic system staying in the safe working region. To aid resource constrained robots in performing complex computations of these weighted simplex strategies, we describe a resource manager that offloads tasks to an available fog nodes. The paper also describes a hardware testbed called DeepNNCar, which is a low cost resource-constrained RC car, built to perform autonomous driving. Using the hardware, we show that both SW-Simplex and CSW-Simplex have 40% and 60% fewer safety violations, while demonstrating higher optimized speed during indoor driving (~ 0.40 m/s) than the original system (using only LECs).

Fog/'Edge computing is increasingly used to support a wide range of latency-sensitive Internet of Things (IoT) applications due to its elastic computing capabilities that are offered closer to the users. Despite this promise, IoT applications with user mobility face many challenges since offloading the application functionality from the edge to the fog may not always be feasible due to the intermittent connectivity to the fog, and could require application migration among fog nodes due to user mobility. Likewise, executing the applications exclusively on the edge may not be feasible due to resource constraints and battery drain. To address these challenges, this paper describes URMILA, a resource management middleware that makes effective tradeoffs between using fog and edge resources while ensuring that the latency requirements of the IoT applications are met. We evaluate URMILA in the context of a real-world use case on an emulated but realistic IoT testbed.

Cyber-Physical Systems (CPS) are used in many applications where they must perform complex tasks with a high degree of autonomy in uncertain environments. Traditional design flows based on domain knowledge and analytical models are often impractical for tasks such as perception, planning in uncertain environments, control with ill-defined objectives, etc. Machine learning based techniques have demonstrated good performance for such difficult tasks, leading to the introduction of Learning-Enabled Components (LEC) in CPS. Model based design techniques have been successful in the development of traditional CPS, and toolchains which apply these techniques to CPS with LECs are being actively developed. As LECs are critically dependent on training and data, one of the key challenges is to build design automation for them. In this paper, we examine the development of an autonomous Unmanned Underwater Vehicle (UUV) using the Assurance-based Learning-enabled Cyber-physical systems (ALC) Toolchain. Each stage of the development cycle is described including architectural modeling, data collection, LEC training, LEC evaluation and verification, and system-level assurance.

In this paper we focus on application of data-driven methods for remaining useful life estimation in components where past failure data is not uniform across devices, i.e. there is a high variance in the minimum and maximum value of the key parameters. The system under study is the hard disks used in computing cluster. The data used for analysis is provided by Backblaze as discussed later. In the article, we discuss the architecture of of the long short term neural network used and describe the mechanisms to choose the various hyper-parameters. Further, we describe the challenges faced in extracting effective training sets from highly unorganized and class-imbalanced big data and establish methods for online predictions with extensive data pre-processing, feature extraction and validation through online simulation sets with unknown remaining useful lives of the hard disks. Our algorithm performs especially well in predicting RUL near the critical zone of a device approaching failure. With the proposed approach we are able to predict whether a disk is going to fail in next ten days with an average precision of 0.8435. We also show that the architecture trained on a particular model is generalizable and transferable as it can be used to predict RUL for devices in other models from same manufacturer.

The rise in deep learning models in recent years has led to various innovative solutions for intelligent transportation technologies. Use of personal and on-demand mobility services puts a strain on the existing road network in a city. To mitigate this problem, city planners need a simulation framework to evaluate the effect of any incentive policy in nudging commuters towards alternate modes of travel, such as bike and car-share options. In this paper, we leverage MATSim, an agent-based simulation framework, to integrate agent preference models that capture the altruistic behavior of an agent in addition to their disutility proportional to the travel time and cost. These models are learned in a data-driven approach and can be used to evaluate the sensitivity of an agent to system-level disutility and monetary incentives given, e.g., by the transportation authority. This framework provides a standardized environment to evaluate the effectiveness of any particular incentive policy of a city, in nudging its residents towards alternate modes of transportation. We show the effectiveness of the approach and provide analysis using a case study from the Metropolitan Nashville area.

Edge and Fog computing paradigms are used to process big data generated by the increasing number of IoT devices. These paradigms have enabled cities to become smarter in various aspects via real-time data-driven applications. While these have addressed some flaws of cloud computing some challenges remain particularly in terms of privacy and security. We create a testbed based on a distributed processing platform called the Information flow of Things (IFoT) middleware. We briefly describe a decentralized traffic speed query and routing service implemented on this framework testbed. We configure the testbed to test countermeasure systems that aim to address the security challenges faced by prior paradigms. Using this testbed, we investigate a novel decentralized anomaly detection approach for time-sensitive distributed smart transportation systems.

Internet of Things (IoT), edge/fog computing, and the cloud are fueling rapid development in smart connected cities. Given the increasing rate of urbanization, the advancement of these technologies is a critical component of mitigating demand on already constrained transportation resources. Smart transportation systems are most effectively implemented as a decentralized network, in which traffic sensors send data to small low-powered devices called Roadside Units (RSUs). These RSUs host various computation and networking services. Data driven applications such as optimal routing require precise real-time data, however, data-driven approaches are susceptible to data integrity attacks. Therefore we propose a multi-tiered anomaly detection framework which utilizes spare processing capabilities of the distributed RSU network in combination with the cloud for fast, real-time detection. In this paper we present a novel real time anomaly detection framework. Additionally, we focus on implementation of our framework in smart-city transportation systems by providing a constrained clustering algorithm for RSU placement throughout the network. Extensive experimental validation using traffic data from Nashville, TN demonstrates that the proposed methods significantly reduce computation requirements while maintaining similar performance to current state of the art anomaly detection methods.

Power grids are undergoing major changes due to rapid growth in renewable energy and improvements in battery technology. Prompted by the increasing complexity of power systems, decentralized IoT solutions are emerging, which arrange local communities into transactive microgrids. The core functionality of these solutions is to provide mechanisms for matching producers with consumers while ensuring system safety. However, there are multiple challenges that these solutions still face: privacy, trust, and resilience. The privacy challenge arises because the time series of production and consumption data for each participant is sensitive and may be used to infer personal information. Trust is an issue because a producer or consumer can renege on the promised energy transfer. Providing resilience is challenging due to the possibility of failures in the infrastructure that is required to support these market based solutions. In this paper, we develop a rigorous solution for transactive microgrids that addresses all three challenges by providing an innovative combination of MILP solvers, smart contracts, and publish-subscribe middleware within a framework of a novel distributed application platform, called Resilient Information Architecture Platform for Smart Grid. Towards this purpose, we describe the key architectural concepts, including fault tolerance, and show the trade-off between market efficiency and resource requirements.

Transportation management platforms provide communities the ability to integrate the available mobility options and localized transportation demand management policies. A central component of a transportation management platform is the mobility planning application. Given the societal relevance of these platforms, it is necessary to ensure that they operate resiliently. Modularity and extensibility are also critical properties that are required for manageability. Modularity allows to isolate faults easily. Extensibility enables update of policies and integration of new mobility modes or new routing algorithms. However, state of the art mobility planning applications like open trip planner, are monolithic applications, which makes it difficult to scale and modify them dynamically. This paper describes a microservices based modular multi-modal mobility platform Mobilytics, that integrates mobility providers, commuters, and community stakeholders. We describe our requirements, architecture, and discuss the resilience challenges, and how our platform functions properly in presence of failure. Conceivably, the patterns and principles manifested in our system can serve as guidelines for current and future practitioners in this field.

Unpredictability is one of the top reasons that prevent people from using public transportation. To improve the on-time performance of transit systems, prior work focuses on updating schedule periodically in the long-term and providing arrival delay prediction in real-time. But when no real-time transit and traffic feed is available (e.g., one day ahead), there is a lack of effective contextual prediction mechanism that can give alerts of possible delay to commuters. In this paper, we propose a generic tool-chain that takes standard General Transit Feed Specification (GTFS) transit feeds and contextual information (recurring delay patterns before and after big events in the city and the contextual information such as scheduled events and forecasted weather conditions) as inputs and provides service alerts as output. Particularly, we utilize shared route segment networks and multi-task deep neural networks to solve the data sparsity and generalization issues. Experimental evaluation shows that the proposed toolchain is effective at predicting severe delay with a relatively high recall of 76% and F1 score of 55%.

If last decade viewed computational services as a utility then surely this decade has transformed computation into a commodity . Computation is now progressively integrated into the physical networks in a seamless way that enables cyber-physical systems (CPS) and the Internet of Things (IoT) meet their latency requirements. Similar to the concept of “platform as a service” or “software as a service”, both cloudlets and fog computing have found their own use cases. Edge devices (that we call end or user devices for disambiguation) play the role of personal computers , dedicated to a user and to a set of correlated applications. In this new scenario, the boundaries between the network node, the sensor, and the actuator are blurring, driven primarily by the computation power of IoT nodes like single board computers and the smartphones. The bigger data generated in this type of networks needs clever, scalable, and possibly decentralized computing solutions that can scale independently as required. Any node can be seen as part of a graph, with the capacity to serve as a computing or network router node, or both. Complex applications can possibly be distributed over this graph or network of nodes to improve the overall performance like the amount of data processed over time. In this paper, we identify this new computing paradigm that we call Social Dispersed Computing , analyzing key themes in it that includes a new outlook on its relation to agent based applications. We architect this new paradigm by providing supportive application examples that include next generation electrical energy distribution networks, next generation mobility services for transportation, and applications for distributed analysis and identification of non-recurring traffic congestion in cities. The paper analyzes the existing computing paradigms (e.g., cloud, fog, edge, mobile edge, social, etc.), solving the ambiguity of their definitions; and analyzes and discusses the relevant foundational software technologies, the remaining challenges, and research opportunities.

An emerging trend in Internet of Things (IoT) applications is to move the computation (cyber) closer to the source of the data (physical). This paradigm is often referred to as edge computing . If edge resources are pooled together, they can be used as decentralized shared resources for IoT applications, providing increased capacity to scale up computations and minimize end-to-end latency. Managing applications on these edge resources is hard, however, due to their remote, distributed, and (possibly) dynamic nature, which necessitates autonomous management mechanisms that facilitate application deployment, failure avoidance, failure management, and incremental updates. To address these needs, we present CHARIOT, which is orchestration middleware capable of autonomously managing IoT systems consisting of edge resources and applications. CHARIOT implements a three-layer architecture. The topmost layer comprises a system description language, the middle layer comprises a persistent data storage layer and the corresponding schema to store system information, and the bottom layer comprises a management engine that uses information stored persistently to formulate constraints that encode system properties and requirements, thereby enabling the use of satisfiability modulo theory solvers to compute optimal system (re)configurations dynamically at runtime. This article describes the structure and functionality of CHARIOT and evaluates its efficacy as the basis for a smart parking system case study that uses sensors to manage parking spaces.

Non-recurring traffic congestion is caused by temporary disruptions, such as accidents, sports games, adverse weather, etc. We use data related to real-time traffic speed, jam factors (a traffic congestion indicator), and events collected over a year from Nashville, TN to train a multi-layered deep neural network. The traffic dataset contains over 900 million data records. The network is thereafter used to classify the real-time data and identify anomalous operations. Compared with traditional approaches of using statistical or machine learning techniques, our model reaches an accuracy of 98.73 percent when identifying traffic congestion caused by football games. Our approach first encodes the traffic across a region as a scaled image. After that the image data from different timestamps is fused with event- and time-related data. Then a crossover operator is used as a data augmentation method to generate training datasets with more balanced classes. Finally, we use the receiver operating characteristic (ROC) analysis to tune the sensitivity of the classifier. We present the analysis of the training time and the inference time separately.

The emerging Fog Computing paradigm provides an additional computational layer that enables new capabilities in real-time data-driven applications. This is especially interesting in the domain of Smart Grid as the boundaries between traditional generation, distribution, and consumer roles are blurring. This is a reflection of the ongoing trend of intelligence distribution in Smart Systems. In this paper, we briefly describe a component-based decentralized software platform called Resilient Information Architecture Platform for Smart Systems (RIAPS) which provides an infrastructure for such systems. We briefly describe some initial applications built using this platform. Then, we focus on the design and integration choices for a resilient Discovery Manager service that is a critical component of this infrastructure. The service allows applications to discover each other, work collaboratively, and ensure the stability of the Smart System.

Emerging smart services, such as indoor smart parking or patient monitoring and tracking in hospitals, incur a significant technical roadblock stemming primarily from a lack of cost-effective and easily deployable localization framework that impedes their widespread deployment. To address this concern, in this paper we present a low-cost, indoor localization and navigation system, which performs continuous and real-time processing of Bluetooth Low Energy (BLE) and IEEE 802.15.4a compliant Ultra-wideband (UWB) sensor data to localize and navigate the concerned entity to its desired location. Our approach depends upon fusing the two feature sets, using the UWB to calibrate the BLE localization mechanism.

This paper presents the time synchronization infrastructure for a low-cost run-time platform and application framework specifically targeting Smart Grid applications. Such distributed applications require the execution of reliable and accurate time-coordinated actions and observations both within islands of deployments and across geographically distant nodes. The time synchronization infrastructure is built on well-established technologies: GPS, NTP, PTP, PPS and Linux with real-time extensions, running on low-cost BeagleBone Black hardware nodes. We describe the architecture, implementation, instrumentation approach, performance results and present an example from the application domain. Also, we discuss an important finding on the effect of the Linux RT_PREEMPT real-time patch on the accuracy of the PPS subsystem and its use for GPS-based time references.

Data generated by GPS-equipped probe vehicles, especially public transit vehicles can be a reliable source for traffic speed estimation. Traditionally, this estimation is done by learning the parameters of a model that describes the relationship between the speed of the probe vehicle and the actual traffic speed. However, such approaches typically suffer from data sparsity issues. Furthermore, most state of the art approaches does not consider the effect of weather and the driver of the probe vehicle on the parameters of the learned model. In this paper, we describe a multivariate predictive multi-model approach called SpeedPro that (a) first identifies similar clusters of operation from the historic data that includes the real-time position of the probe vehicle, the weather data, and anonymized driver identifier, and then (b) uses these different models to estimate the traffic speed in real-time as a function of current weather, driver and probe vehicle speed. When the real-time information is not available our approach uses a different model that uses the historical weather and traffic information for estimation. Our results show that the purely historical data is less accurate than the model that uses the real-time information.

The on-time arrival performance of vehicles at stops is a critical metric for both riders and city planners to evaluate the reliability of a transit system. However, it is a non-trivial task for transit agencies to adjust the existing bus schedule to optimize the on-time performance for the future. For example, severe weather conditions and special events in the city could slow down traffic and cause bus delay. Furthermore, the delay of previous trips may affect the initial departure time of consecutive trips and generate accumulated delay. In this paper, we formulate the problem as a single-objective optimization task with constraints and propose a greedy algorithm and a genetic algorithm to generate bus schedules at timepoints that improve the bus on-time performance at timepoints which is indicated by whether the arrival delay is within the desired range. We use the Nashville bus system as a case study and simulate the optimization performance using historical data. The comparative analysis of the results identifies that delay patterns change over time and reveals the efficiency of the greedy and genetic algorithms.

Effective public transit operations are one of the fundamental requirements for a modern community. Recently, a number of transit agencies have started integrating automated vehicle locators in their fleet, which provides a real-time estimate of the time of arrival. In this paper, we use the data collected over several months from one such transit system and show how this data can be potentially used to learn long term patterns of travel time. More specifically, we study the effect of weather and other factors such as traffic on the transit system delay. These models can later be used to understand the seasonal variations and to design adaptive and transient transit schedules. Towards this goal, we also propose an online architecture called DelayRadar. The novelty of DelayRadar lies in three aspects: (1) a data store that collects and integrates real-time and static data from multiple data sources, (2) a predictive statistical model that analyzes the data to make predictions on transit travel time, and (3) a decision making framework to develop an optimal transit schedule based on variable forecasts related to traffic, weather, and other impactful factors. This paper focuses on identifying the model with the best predictive accuracy to be used in DelayRadar. According to the preliminary study results, we are able to explain more than 70% of the variance in the bus travel time and we can make future travel predictions with an out-of-sample error of 4.8 minutes with information on the bus schedule, traffic, and weather.

Cyber-physical systems (CPS) are systems with a tight integration between the computational (also referred to as software or cyber) and physical (hardware) components. While the reliability evaluation of physical systems is well-understood and well-studied, reliability evaluation of CPS is difficult because software systems do not degrade and follow a well-defined failure model like physical systems. In this paper, we propose a framework for formulating the CPS reliability evaluation as a dependence problem derived from the software component dependences, functional requirements and physical system dependences. We also consider sensor failures, and propose a method for estimating software failures in terms of associated hardware and software inputs. This framework is codified in a domain-specific modeling language, where every system-level function is mapped to a set of required components using functional decomposition and function-component association; this provides details about operational constraints and dependences. We also illustrate how the encoded information can be used to make reconfiguration decisions at runtime. The proposed methodology is demonstrated using a smart parking system, which provides localization and guidance for parking within indoor environments.

Public bus transit plays an important role in city transportation infrastructure. However, public bus transit is often difficult to use because of lack of real- time information about bus locations and delay time, which in the presence of operational delays and service alerts makes it difficult for riders to predict when buses will arrive and plan trips. Precisely tracking vehicle and informing riders of estimated times of arrival is challenging due to a number of factors, such as traffic congestion, operational delays, varying times taken to load passengers at each stop. In this paper, we introduce a public transportation decision support system for both short-term as well as long-term prediction of arrival bus times. The system uses streaming real-time bus position data, which is updated once every minute, and historical arrival and departure data - available for select stops to predict bus arrival times. Our approach combines clustering analysis and Kalman filters with a shared route segment model in order to produce more accurate arrival time predictions. Experiments show that compared to the basic arrival time prediction model that is currently being used by the city, our system reduces arrival time prediction errors by 25% on average when predicting the arrival delay an hour ahead and 47% when predicting within a 15 minute future time window.

Wider adoption, availability and ubiquity of wireless networking technologies, integrated sensors, actuators, and edge computing devices is facilitating a paradigm shift by allowing us to transition from traditional statically configured vertical silos of Cyber-Physical Systems (CPS) to next generation CPS that are more open, dynamic and extensible. Fractionated spacecraft, smart cities computing architectures, Unmanned Aerial Vehicle (UAV) clusters are all examples of extensible CPS wherein extensibility is implied by the dynamic aggregation of physical resources, affect of physical dynamics on availability of computing resources, and various multi-domain applications hosted on these systems. However, realization of extensible CPS requires resolving design-time and runtime challenges emanating from properties specific to these systems. In this paper, we first describe different properties of extensible CPS - dynamism, extensibility, remote deployment, security, heterogeneity and resilience. Then we identify different design-time challenges stemming from heterogeneity and resilience requirements. We particularly focus on software heterogeneity arising from availability of various communication middleware. We then present appropriate solutions in the context of a novel domain specific language and describe how this language and its features have evolved from our past work.

Cyber-physical systems increasingly rely on distributed computing platforms where sensing, computing, actuation, and communication resources are shared by a multitude of applications. Such 'cyber-physical cloud computing platforms' present novel challenges because the system is built from mobile embedded devices, is inherently distributed, and typically suffers from highly fluctuating connectivity among the modules. Architecting software for these systems raises many challenges not present in traditional cloud computing. Effective management of constrained resources and application isolation without adversely affecting performance are necessary. Autonomous fault management and real-time performance requirements must be met in a verifiable manner. It is also both critical and challenging to support multiple end-users whose diverse software applications have changing demands for computational and communication resources, while operating on different levels and in separate domains of security. The solution presented in this paper is based on a layered architecture consisting of a novel operating system, a middleware layer, and component-structured applications. The component model facilitates the construction of software applications from modular and reusable components that are deployed in the distributed system and interact only through well-defined mechanisms. The complexity of creating applications and performing system integration is mitigated through the use of a domain-specific model-driven development process that relies on a domain-specific modeling language and its accompanying graphical modeling tools, software generators for synthesizing infrastructure code, and the extensive use of model-based analysis for verification and validation.

Mobile clouds such as network-connected vehicles and satellite clusters are an emerging class of systems that are extensions to traditional real-time embedded systems: they provide long-term mission platforms made up of dynamic clusters of heterogeneous hardware nodes communicating over ad hoc wireless networks. Besides the inherent complexities entailed by a distributed architecture, developing software and testing these systems is difficult due to a number of other reasons, including the mobile nature of such systems, which can require a model of the physical dynamics of the system for accurate simulation and testing. This paper describes a rapid development and testing framework for a distributed satellite system. Our solutions include a modeling language for configuring and specifying an application's interaction with the middleware layer, a physics simulator integrated with hardware in the loop to provide the system's physical dynamics and the integration of a network traffic tool to dynamically vary the network bandwidth based on the physical dynamics.

Component-based programming models are well-suited to the design of large-scale, distributed applications because of the ease with which distributed functionality can be developed, deployed, and validated using the models' compositional properties. Existing component models supported by standardized technologies, such as the OMG's CORBA Component Model (CCM), however, incur a number of limitations in the context of cyber physical systems (CPS) that operate in highly dynamic, resource-constrained, and uncertain environments, such as space environments, yet require multiple quality of service (QoS) assurances, such as timeliness, reliability, and security. To overcome these limitations, this paper presents the design of a novel component model called F6COM that is developed for applications operating in the context of a cluster of fractionated spacecraft. Although F6COM leverages the compositional capabilities and port abstractions of existing component models, it provides several new features. Specifically, F6COM abstracts the component operations as tasks, which are scheduled sequentially based on a specified scheduling policy. The infrastructure ensures that at any time at most one task of a component can be active - eliminating race conditions and deadlocks without requiring complicated and error-prone synchronization logic to be written by the component developer. These tasks can be initiated due to (a) interactions with other components, (b) expiration of timers, both sporadic and periodic, and (c) interactions with input/output devices. Interactions with other components are facilitated by ports. To ensure secure information flows, every port of an F6COM component is associated with a security label such that all interactions are executed within a security context. Thus, all component interactions can be subjected to Mandatory Access Control checks by a Trusted Computing Base that facilitates the interactions. Finally, F6COM provides capabilities to monitor task execution deadlines and to configure component-specific fault mitigation actions.

Complex real-time software systems require an active fault management capability. While testing, verification and validation schemes and their constant evolution help improve the dependability of these systems, an active fault management strategy is essential to potentially mitigate the unacceptable behaviors at run-time. In our work we have applied the experience gained from the field of Systems Health Management towards component-based software systems. The software components interact via well-defined concurrency patterns and are executed on a real-time component framework built upon ARINC-653 platform services. In this paper, we present the lessons learned in architecting and applying a two-level health management strategy to assemblies of software components.

Distributed real-time and embedded (DRE) systems are a class of real-time systems formed through a composition of predominantly legacy, closed and statically scheduled real-time subsystems, which comprise over-provisioned resources to deal with worst-case failure scenarios. The formation of the system-of-systems leads to a new range of faults that manifest at different granularities for which no statically defined fault tolerance scheme applies. Thus, dynamic and adaptive fault tolerance mechanisms are needed which must execute within the available resources without compromising the safety and timeliness of existing real-time tasks in the individual subsystems. To address these requirements, this paper describes a middleware solution called Safe Middleware Adaptation for Real-Time Fault Tolerance (SafeMAT), which opportunistically leverages the available slack in the over-provisioned resources of individual subsystems. SafeMAT comprises three primary artifacts: (1) a flexible and configurable distributed, runtime resource monitoring framework that can pinpoint in real-time the available slack in the system that is used in making dynamic and adaptive fault tolerance decisions, (2) a safe and resource aware dynamic failure adaptation algorithm that enables efficient recovery from different granularities of failures within the available slack in the execution schedule while ensuring real-time constraints are not violated and resources are not overloaded, and (3) a framework that empirically validates the correctness of the dynamic mechanisms and the safety of the DRE system. Experimental results evaluating SafeMAT on an avionics application indicates that SafeMAT incurs only 9-15% runtime fail over and 2-6% processor utilization overheads thereby providing safe and predictable failure adaptability in real-time.

Large-scale component-based enterprise applications that leverage Cloud resources expect Quality of Service(QoS) guarantees in accordance with service level agreements between the customer and service providers. In the context of Cloud computing, auto scaling mechanisms hold the promise of assuring QoS properties to the applications while simultaneously making efficient use of resources and keeping operational costs low for the service providers. Despite the perceived advantages of auto scaling, realizing the full potential of auto scaling is hard due to multiple challenges stemming from the need to precisely estimate resource usage in the face of significant variability in client workload patterns. This paper makes three contributions to overcome the general lack of effective techniques for workload forecasting and optimal resource allocation. First, it discusses the challenges involved in auto scaling in the cloud. Second, it develops a model-predictive algorithm for workload forecasting that is used for resource auto scaling. Finally, empirical results are provided that demonstrate that resources can be allocated and deal located by our algorithm in a way that satisfies both the application QoS while keeping operational costs low.

For service providers of multi-tiered component-based applications, such as web portals, assuring high performance and availability to their customers without impacting revenue requires effective and careful capacity planning that aims at minimizing the number of resources, and utilizing them efficiently while simultaneously supporting a large customer base and meeting their service level agreements. This paper presents a novel, hybrid capacity planning process that results from a systematic blending of 1) analytical modeling, where traditional modeling techniques are enhanced to overcome their limitations in providing accurate performance estimates; 2) profile-based techniques, which determine performance profiles of individual software components for use in resource allocation and balancing resource usage; and 3) allocation heuristics that determine minimum number of resources to allocate software components. Our results illustrate that using our technique, performance (i.e., bounded response time) can be assured while reducing operating costs by using 25% less resources and increasing revenues by handling 20% more clients compared to traditional approaches.

SUMMARY The size and complexity of software in safety‐critical systems is increasing at a rapid pace. One technology that can be used to mitigate this complexity is component‐based software development. However, in spite of the apparent benefits of a component‐based approach to development, little work has been done in applying these concepts to hard real‐time systems. This paper improves the state of the art by making three contributions: (1) we present a component model for hard real‐time systems and define the semantics of different types of component interactions; (2) we present an implementation of a middleware that supports this component model. This middleware combines an open‐source CORBA Component Model (CCM) implementation (MICO) with ARINC‐653: a state‐of‐the‐art real‐time operating systems (RTOS) standard, (3) finally; we describe a modeling environment that enables design, analysis, and deployment of component assemblies. We conclude with a discussion of the lessons learned during this exercise. Our experiences point toward extending both the CCM as well as revising the ARINC‐653. Copyright © 2011 John Wiley & Sons, Ltd.

The complexity of software in systems like aerospace vehicles has reached the point where new techniques are needed to ensure system dependability while improving the productivity of developers. One possible approach is to use precisely defined software execution platforms that (1) enable the system to be composed from separate components, (2) restrict component interactions and prevent fault propagation, and (3) whose compositional properties are well-known. In this paper we describe the initial steps towards building a platform that combines component-based software construction with hard real-time operating system services. Specifically, the paper discusses how the CORBA Component Model (CCM) could be combined with the ARINC-653 platform services and the lessons learned from this experiment. The results point towards both extending the CCM as well as revising the ARINC-653.

This paper describes an integrated monitoring and control framework for managing performance of distributed enterprise systems.

Developing large-scale distributed real-time and embedded (DRE) systems is hard in part due to complex deployment and configuration issues involved in satisfying multiple quality for service (QoS) properties, such as real-timeliness and fault tolerance. This paper makes three contributions to the study of deployment and configuration middleware for DRE systems that satisfy multiple QoS properties. First, it describes a novel task allocation algorithm for passively replicated DRE systems to meet their real-time and fault-tolerance QoS properties while consuming significantly less resources. Second, it presents the design of a strategizable allocation engine that enables application developers to evaluate different allocation algorithms. Third, it presents the design of a middleware agnostic configuration framework that uses allocation decisions to deploy application components/replicas and configure the underlying middleware automatically on the chosen nodes. These contributions are realized in the DeCoRAM (Deployment and Configuration Reasoning and Analysis via Modeling) middleware. Empirical results on a distributed testbed demonstrate DeCoRAM’s ability to handle multiple failures and provide efficient and predictable real-time performance.

Fault-tolerant frameworks for large scale computing clusters require sensor programs, which are executed periodically to facilitate performance and fault management. By construction, these clusters use general purpose operating systems such as Linux that are built for best average case performance and do not provide deterministic scheduling guarantees. Consequently, periodic applications show jitter in execution times relative to the expected execution time. Obtaining a deterministic schedule for periodic tasks in general purpose operating systems is difficult without using kernel-level modifications such as RTAI and RTLinux. However, due to performance and administrative issues kernel modification cannot be used in all scenarios. In this paper, we address the problem of jitter compensation for periodic tasks that cannot rely on modifying the operating system kernel. ; Towards that, (a) we present motivating examples; (b) we present a feedback controller based approach that runs in the user space and actively compensates periodic schedule based on past jitter; This approach is platform-agnostic i.e. it can be used in different operating systems without modification; and (c) we show through analysis and experiments that this approach is platform-agnostic i.e. it can be used in different operating systems without modification and also that it maintains a stable system with bounded total jitter.

Large scientific computing clusters require a distributed dependability subsystem that can provide fault isolation and recovery and is capable of learning and predicting failures, to improve the reliability of scientific workflows. In this paper, we outline the key ideas in the design of a Scientific Computing Autonomic Reliability Framework (SCARF) for large computing clusters used in the Lattice Quantum Chromo Dynamics project at Fermi Lab.