In the evolving energy landscape where prosumers play an increasingly important role, establishing a secure data exchange architecture is essential for building a resilient and efficient energy infrastructure. Current privacy-preserving systems suffer from inadequate adversarial models, dependence on centralized components, and inability to adapt to evolving threats. This paper introduces the Privacy-Sensitive Distributed Optimization (PSDO) framework, a decentralized management scheme designed to prioritize privacy safeguards in prosumer-driven systems. To achieve this goal, the PSDO framework combines decentralized optimization techniques with differential privacy. This integration serves a dual purpose: preserving prosumers' control over their energy management and ensuring privacy of their sensitive information. By leveraging decentralized optimization, the PSDO framework enables prosumers to maximize the benefits derived from decentralized systems, promoting improved autonomy in energy management. Simultaneously, prosumers' sensitive data is protected through the implementation of differential privacy measures. Through implementation on the IEEE 33-bus radial distribution system, the PSDO algorithm demonstrated its capability to converge to the optimal solution while rigorously upholding differential privacy. PSDO advances beyond the chosen baseline (DP-ADMM) by delivering superior privacy protection while incurring minimal utility loss. Moreover, the framework successfully accommodates diverse privacy preferences while maintaining system-wide efficiency, establishing its effectiveness for heterogeneous prosumers.

Running a numerical weather model such as WRF at kilometre or sub-kilometre grid spacing over a regional domain is computationally expensive. We present physics-informed deeplearning models that ingest a single 9km WRF wind field and simultaneously predict two finer-scale wind fields at 3 km and 1 km resolution via dual decoder heads. Four representative architectures are benchmarked-Deep Residual U-Net (DeepRU), DEVINE, a bespoke 3-D Transformer, and a Fourier Neural Operator (FNO)-each trained with divergence-free, vorticity, and Navier-Stokes residual constraints plus Charbonnier and gradient perceptual losses. We train and validate our models on the city of Oslo for the year 2018. DeepRU achieves$R^{2}=0.94$(RMSE$=0.050$) at$\mathbf{3 k m}$and$R^{2}=0.89(\mathbf{R M S E}=0.065)$at 1 km. DEVINE, Transformer 3-D, and FNO yield 3 km scores of$0.91-0.93$, with$\mathbf{1} \mathbf{ k m}$scores lower by$0.02-0.08$, illustrating the increased difficulty of finer-scale reconstruction. Physicsinformed losses improve all models compared to MSE-only baselines, and the residual architecture (DeepRU) remains most effective for this dual-scale task.

Location-based vehicular traffic management faces significant challenges in protecting sensitive geographical data while maintaining utility for traffic management and fairness across regions. Existing state-of-the-art solutions often fail to meet the required level of protection against linkage attacks and demographic biases, leading to privacy leakage and inequity in data analysis. In this paper, we propose a novel algorithm designed to address the challenges regarding the balance of privacy, utility, and fairness in location-based vehicular traffic management systems. In this context, utility means providing reliable and meaningful traffic information, while fairness ensures that all regions and individuals are treated equitably in data use and decision-making. Employing differential privacy techniques, we enhance data security by integrating query-based data access with iterative shuffling and calibrated noise injection, ensuring that sensitive geographical data remains protected. We ensure adherence to epsilon-differential privacy standards by implementing the Laplace mechanism. We implemented our algorithm on vehicular location-based data from Norway, demonstrating its ability to maintain data utility for traffic management and urban planning while ensuring fair representation of all geographical areas without being overrepresented or underrepresented. Additionally, we have created a heatmap of Norway based on our model, illustrating the privatized and fair representation of the traffic conditions across various cities. Our algorithm provides privacy in vehicular traffic management by effectively balancing fairness and utility.

The development of automated home energy management (HEM) and peer-to-peer energy trading mechanisms encourages a greater number of energy consumers to switch roles and become providers. To sustain this trend and maintain their long-term commitment to energy platforms, we face the challenge of aligning the primary psychological motivators of prosumers with our developed energy services. Most existing approaches target maximizing prosumer utility based on extrinsic benefits, such as economic rewards. However, the intrinsic motivations which are inherently satisfying for prosumers, have not been thoroughly analyzed. This article explores both extrinsic and intrinsic motivations of prosumers from a psychological perspective and addresses these within the technological field. Self-determination theory is adopted as a psychological framework to analyze prosumer behavior in energy systems. The study quantifies prosumers’ motivations and proposes a quality-of-energy-service measure to reflect individual preferences. Additionally, a leader-follower-based optimization framework is introduced, enabling individual prosumers to make optimal decisions regarding their energy management and trading strategies in a P2P energy market. The proposed system features a deep reinforcement learning agent as the leader, targeting optimal HEM solutions, while the follower aims to find the optimal trading strategy for prosumers in an auction-based P2P trading environment. Numerical results demonstrate that our proposed model outperforms baseline models.

The rise of complex and sizeable Machine Learning (ML) models challenges traditional cloud computing models with respect to the high volume of incoming data which results in increased bandwidth usage and network congestion, as well as delays in inference. Such ML models are being rapidly developed thanks to advances in computing platforms and the real-time computing demands of ML-driven applications such as autonomous vehicles and video processing. To mitigate these challenges, ML model distribution and inference offloading to computing devices close to data sources have been explored, especially through partitioning the models across the IoT-Edge-Cloud continuum. Existing efforts in this area have not successfully mastered the fully automatic and efficient determination of optimal partition points. Additionally, they have not effectively integrated Early-Exit layers that allow for early termination of model inference at earlier stages when feasible. In this paper, we introduce a novel partitioning algorithm designed to distribute ML models across edge devices with the goal of reducing response time when facing high-rate input data streams. Our proposed approach leverages the principles of Dynamic Programming to determine optimal partition points and establish appropriate exit thresholds for Early-Exit layers. Our evaluation results reveal that, in the context of continuous, high-rate input data, our method consistently lowers the maximum round-trip time for processing inference requests compared to state-of-the-art methods such as NeuroSurgeon and Genetics.

Running computer vision applications, such as 3-D simultaneous localization and mapping (SLAM), on mobile devices requires low-latency responses and a massive amount of computation. Edge computing has been introduced to move Cloud features closer to end users, providing necessary computing and network resources for end devices. The heterogeneous edge devices, with different hardware architectures (e.g., CPUs and GPUs) and runtime environments, provide diverse resources to support processing tasks from end devices, resulting in different costs and quality of services. How to partition these computing tasks and distribute them over these heterogeneous hardware nodes is still an open research question. Considering these inherently heterogeneous hardware architectures, new approaches for service orchestration and task scheduling are required to meet the service-level agreement and reduce the overall cost of the system (e.g., facility utilization cost). This article presents a system framework, EDGE VISION, for computer vision applications partitioning and orchestration on heterogeneous edge computing platforms considering both CPUs and GPUs. EDGE VISION abstracts the heterogeneous hardware resources and the task runtime environments and divides the application into separate tasks to be orchestrated and deployed into the heterogeneous edge nodes. We also propose two scheduling algorithms in our framework, minimum latency task scheduling and minimum cost task scheduling, aiming to minimize the processing latency and the overall system cost. We evaluate our framework by implementing the edge-based 3-D SLAM application in our real testbed with ten heterogeneous edge devices. Evaluations show that EdgeVision can efficiently minimize the processing latency and the system overall cost and achieve up to 30% decrease in task processing latency and 15% more cost saving compared to the State-of-the-Art baselines.

The increasing penetration of renewable energy sources and electric vehicles (EVs) poses a significant challenge for the power grid operator in terms of increasing peak load and power quality reduction. Moreover, there is a growing demand for fast charging services in smart grids. Addressing the growing demand from fast charging services is challenging. To overcome this challenge, in this article, we propose a new computational architecture combining energy trading and demand responses based on cloud computing for managing virtual power plants (VPPs) in smart grids. In the proposed system, EVs can be charged at high charging rates without affecting the operation of the power grid by purchasing energy through the energy trading platform in the cloud. In addition, users with storage devices can sell energy surplus to the market. On the one hand, the energy trading platform can be regarded as an internal market of the VPP that aims to maximize its revenue. The interest of the EV owners, on the other hand, is to minimize the cost for charging. Therefore, we model the interactions between the EV owners and the VPP as a non-cooperative game. To search for the Nash equilibrium (NE) of the game, we design an algorithm and then analyze its computational complexity and communication overhead. We utilize real data from the California Independent System Operator (CAISO) to evaluate the performance of the proposed algorithm. Our results illustrate that the users with only storage devices can obtain nearly$200\%$200%higher revenue on average by participating in the proposed internal market. Moreover, users with only EVs can reduce their charging costs by nearly$50\%$50%in average. Users with both EVs and storage devices can reduce the charging costs even further by approximately$120\%$120%where the users get profit by utilizing the internal market.

In peer-to-peer (P2P) energy trading, the incorporation of distributed energy resources with unprotected data, originating from sources such as home energy management systems that are connected through the Internet, provokes vulnerabilities that can manifest security breaches. In this article, two threat scenarios based on a novel false data injection attack (FDIA) model in a local P2P energy trading system are explored. In these scenarios, an attacker gains free energy by manipulating prosumers’ consumption and demand. Precise and fast attack detection is needed to guarantee suitable countermeasures to prevent potential risks. We propose a novel instance-based machine learning (ML) classifier for detecting FDIAs. In contrast to black-box ML models, our algorithm provides a transparent decision-making procedure with significant predictive performance. We apply our detection model to a real-world dataset from Austin, Texas. Our experimental results show superior performance as compared to several popular interpretable and non-interpretable ML methods. On average, we achieve a 96.10 percent detection rate, a 96.18 percent accuracy rate, and a false negative rate of 1.97 percent with our approach.

In smart grids, the large-scale integration of distributed renewable energy resources has enabled the provisioning of alternative sources of supply. Peer-to-peer (P2P) energy trading among local households is becoming an emerging technique that benefits both energy prosumers and operators. Since conventional energy supply is still needed to help fill the gap between local demand and supply when the local solar generation is not sufficient, demand–response management will keep playing an important role in the future P2P energy market. Blockchain and smart contract technology has gained increasing attention in P2P trading for its secure operation. The performance of blockchain-based P2P energy trading still remains to be improved, in terms of latency and cost of computation resources. This article studies the challenges of demand–response management in P2P energy trading and proposes a blockchain-empowered energy trading system for a community-based P2P market. The proposed demand–response mechanism is developed using two noncooperative games, in which dynamic pricing is applied for suppliers. The proposed energy trading system is prototyped on a cluster network, with a coordinator running as a smart contract in a Hyperledger blockchain. We implemented both on-chain and off-chain processing modes to study the system performance. The results from experiments with our prototype indicate that our proposed demand–response games have a great effect on reducing the net peak load, and at the same time, the off-chain processing mode provides lower latency and overhead compared to the on-chain mode while still keeping the same system integrity as the on-chain mode.

The power consumption of households has been constantly growing over the years. To cope with this growth, intelligent management of the consumption profile of the households is necessary, such that the households can save the electricity bills, and the stress to the power grid during peak hours can be reduced. However, implementing such a method is challenging due to the existence of randomness in the electricity price and the consumption of the appliances. To address this challenge, in this article, we employ a model-free method for the households, which works with limited information about the uncertain factors. More specifically, the interactions between households and the power grid can be modeled as a noncooperative stochastic game, where the electricity price is viewed as a stochastic variable. To search for the Nash equilibrium (NE) of the game, we adopt a method based on distributed deep reinforcement learning. Also, the proposed method can preserve the privacy of the households. We then utilize real-world data from Pecan Street Inc., which contains the power consumption profile of more than 1000 households, to evaluate the performance of the proposed method. In average, the results reveal that we can achieve around 12% reduction on peak-to-average ratio and 11% reduction on load variance. With this approach, the operation cost of the power grid and the electricity cost of the households can be reduced.

Wind power is a clean and widely deployed alternative to reducing our dependence on fossil fuel power generation. Under this trend, more turbines will be installed in wind farms. However, the inspection of the turbines in an offshore wind farm is a challenging task because of the harsh environment (e.g., rough sea, strong wind, and so on) that leads to high risk for workers who need to work at considerable height. Also, inspecting increasing number of turbines requires long man hours. In this regard, unmanned aerial vehicles (UAVs) can play an important role for automated inspection of the turbines for the operator, thus reducing the inspection time, man hours, and correspondingly the risk for the workers. In this case, the optimal number of UAVs enough to inspect all turbines in the wind farm is a crucial parameter. In addition, finding the optimal path for the UAVs' routes for inspection is also important and is equally challenging. In this article, we formulate a placement optimization problem to minimize the number of UAVs in the wind farm and a routing optimization problem to minimize the inspection time. Wind has an impact on the flying range and the flying speed of UAVs, which is taken into account for both problems. The formulated problems are NP-hard. We therefore design heuristic algorithms to find solutions to both problems, and then analyze the complexity of the proposed algorithms. The data of the Walney wind farm are then utilized to evaluate the performance of the proposed algorithms. Simulation results clearly show that the proposed methods can obtain the optimal routing path for UAVs during the inspection.

Uncoordinated charging of a rapidly growing number of electric vehicles (EVs) and the uncertainty associated with renewable energy resources may constitute a critical issue for the electric mobility (E-Mobility) in the transportation system especially during peak hours. To overcome this dire scenario, we introduce a stochastic game to study the complex interactions between the power grid and charging stations. In this context, existing studies have not taken into account the dynamics of customers’ preference on charging parameters. In reality, however, the choice of the charging parameters may vary over time, as the customers may change their charging preferences. We model this behavior of customers with another stochastic game. Moreover, we define a quality of service (QoS) index to reflect how the charging process influences customers’ choices on charging parameters. We also develop an online algorithm to reach the Nash equilibria for both stochastic games. Then, we utilize real data from the California Independent System Operator (CAISO) to evaluate the performance of our proposed algorithms. The results reveal that the electricity cost with the proposed method can result in a saving of about 20% compared to the benchmark method, while also yielding a higher QoS in terms of charging and waiting time. Our results can be employed as guidelines for charging service providers to make efficient decisions under uncertainty relative to power generation of renewable energy.

Many Internet of Things (IoT) networks are created as an overlay over traditional ad-hoc networks such as Zigbee. Moreover, IoT networks can resemble ad-hoc networks over networks that support device-to-device (D2D) communication, e.g., D2D-enabled cellular networks and WiFi-Direct. In thesead-hoctypes of IoT networks, efficienttopology managementis a crucial requirement, and in particular in massive scale deployments. Traditionally,clusteringhas been recognized as a common approach for topology management in ad-hoc networks, e.g., in Wireless Sensor Networks (WSNs). Topology management in WSNs and ad-hoc IoT networks has many design commonalities as both need to transfer data to the destination hop by hop. Thus, WSN clustering techniques can presumably be applied for topology management in ad-hoc IoT networks. This requires a comprehensive study on WSN clustering techniques and investigating their applicability to ad-hoc IoT networks. In this article, we conduct a survey of this field based on theobjectivesfor clustering, such as reducing energy consumption and load balancing, as well as the network properties relevant for efficient clustering in IoT, such as network heterogeneity and mobility. Beyond that, we investigate the advantages and challenges of clustering when IoT is integrated with modern computing and communication technologies such as Blockchain, Fog/Edge computing, and 5G. This survey provides useful insights into research on IoT clustering, allows broader understanding of its design challenges for IoT networks, and sheds light on its future applications in modern technologies integrated with IoT.

With the exploitation of wind power, more turbines will be deployed at remote areas possibly with harsh working conditions (e.g., offshore wind farm). The adverse working environment may lead to massive operating and maintenance costs of turbines. Deploying unmanned aerial vehicles (UAVs) for turbine inspection is considered as a viable alternative to manual inspections. An important objective of automated UAV inspection is to minimize the flight time of the UAVs to inspect all the turbines. A first contribution of this paper is thus formulating an optimization problem to compute the optimal routes for turbine inspection satisfying the above goal. On the other hand, the limited computational capability on UAVs can be used to increase the power generation of wind turbine. Power generation from the turbines can be optimized by controlling the yaw angle of the turbines. Forecasting wind conditions such as wind speed and wind direction is crucial for solving both optimization problems. Therefore, UAVs can utilize their limited computational capability to perform wind forecasting. In this way, UAVs form edge intelligence in offshore wind farm. With the forecasted wind conditions, we design two algorithms to solve the formulated problems, and then evaluate the proposed methods with real-world data. The results reveal that the proposed methods offer an improvement of 44% of the power generation from the turbine compared to hour-ahead forecasting and 25% reduction of the flight time of the UAVs compared to the chosen baseline method.

The role of fog computing in future vehicular networks is becoming significant, enabling a variety of applications that demand high computing resources and low latency, such as augmented reality and autonomous driving. Fog-based computation offloading and service caching are considered two key factors in efficient execution of resource-demanding services in such applications. While some efforts have been made on computation offloading in fog computing, a limited amount of work has considered joint optimization of computation offloading and service caching. As fog platforms are usually equipped with moderate computing and storage resources, we need to judiciously decide which services to be cached when offloading computation tasks to maximize the system performance. The heterogeneity, dynamicity, and stochastic properties of vehicular networks also pose challenges on optimal offloading and resource allocation. In this paper, we propose an intelligent computation offloading architecture with service caching, considering both peer-pool and fog-pool computation offloading. An optimization problem of joint computation offloading and service caching is formulated to minimize the task processing time and long-term energy utilization. Finally, we propose an algorithm based on deep reinforcement learning to solve this complex optimization problem. Extensive simulations are undertaken to verify the feasibility of our proposed scheme. The results show that our proposed scheme exhibits an effective performance improvement in computation latency and energy consumption compared to the chosen baseline.

Wireless Sensor Networks (WSNs) typically include thousands of resource-constrained sensors to monitor their surroundings, collect data, and transfer it to remote servers for further processing. Although WSNs are considered highly flexible ad-hoc networks, network management has been a fundamental challenge in these types of networks given the deployment size and the associated quality concerns such as resource management, scalability, and reliability. Topology management is considered a viable technique to address these concerns. Clustering is the most well-known topology management method in WSNs, grouping nodes to manage them and/or executing various tasks in a distributed manner, such as resource management. Although clustering techniques are mainly known to improve energy consumption, there are various quality-driven objectives that can be realized through clustering. In this paper, we review comprehensively existing WSN clustering techniques, their objectives and the network properties supported by those techniques. After refining more than 500 clustering techniques, we extract about 215 of them as the most important ones, which we further review, catergorize and classify based on clustering objectives and also the network properties such as mobility and heterogeneity. In addition, statistics are provided based on the chosen metrics, providing highly useful insights into the design of clustering techniques in WSNs.

The convergence of Internet of Things (IoT) and the Cloud has significantly facilitated the provision and management of services in large-scale applications, such as smart cities. With a huge number of IoT services accessible through clouds, it is very important to model and expose cloud-based IoT services in an efficient manner, promising easy and real-time delivery of cloud-based, data-centric IoT services. The existing work in this area has adopted a uniform and flat view to IoT services and their data, making it difficult to achieve the above goal. In this article, we propose a software framework, Context-driven And Real-time IoT (CARIoT) for real-time provisioning of cloud-based IoT services and their data, driven by their contextual properties. The main idea behind the proposed framework is to structure the description of data-centric IoT services and their real-time and historical data in a hierarchical form in accordance with the end-user application’s context model. CARIoT features design choices and software services to realize this service provisioning model and the supporting data structures for hierarchical IoT data access. Using this approach, end-user applications can access IoT services and subscribe to their real-time and historical data in an efficient manner at different contextual levels, e.g., from a municipal district to a street in smart city use cases. We leverage a popular cloud-based data storage platform, called Firebase, to implement the CARIoT framework and evaluate its efficiency. The evaluation results show that CARIoT’s hierarchical structure imposes no additional overhead with less data notification delay as compared to existing flat structures.

Application mobility is the paradigm where users can move their running applications to heterogeneous devices in a seamless manner. This mobility involves dynamic context changes of hardware, network resources, user environment, and user preferences. In order to continue multimedia processing under these context changes, applications need to adapt not only the collection of media streams, i.e., multimedia presentation, but also their internal configuration to work on different hardware. We present the performance analysis to adapt a videoconferencing prototype application in a proposed adaptation control loop to autonomously adapt multimedia pipelines. Results show that the time spent to create an adaptation plan and execute it is in the order of hundreds of milliseconds. The reconfiguration of pipelines, compared to building them from scratch, is approximately 1000 times faster when re-utilizing already instantiated hardware-dependent components. Therefore, we conclude that the adaptation of multimedia pipelines is a feasible approach for multimedia applications that adhere to application mobility.

A number of emerging multimedia applications, such as webinars, require users to interact by exchanging media streams. In such application there are multiple interacting participants which both produce and consume media content and a set of participants which are only consumers. Keeping the end-to-end latency as low as possible while not violating bandwidth constraints is one of the most important requirements for this type of application. While there exists solutions to this problem for applications such as multi-party video conferencing, they rely on dedicated infrastructures which may be expensive and not available to all users. On the other hand, decentralized P2P solutions have been focusing on single source media streaming, which does not consider multiple interactive participants. In this paper, we propose Maelstream, a self-organizing media streaming solution that supports multiple interacting participants as well as a large number of consumers. Maelstream uses gossip protocols to generate multiple latency-aware streaming trees on top of a P2P overlay. We have evaluated our solution with simulations implemented using Peersim and ns-3 simulators, and compared Maelstream with Chunkyspread, an unstructured protocol capable of fine-tuning latency. We show that Maelstream can achieve low end-to-end latency and scales well with the number of streams.

Application mobility is the paradigm where users can move parts of their running applications across multiple heterogeneous devices in a seamless manner. This mobility involves dynamic context changes of hardware, network resources, user environment and user preferences. State-of-the-art adaptive applications adapt in multiple ways to a subset of scenarios in application mobility, however, adaptation of multimedia presentations is rather limited to the selection of pre-processed variants of multimedia presentations. We propose DAMPAT for GStreamer to autonomously adapt multimedia pipelines for a given context. DAMPAT adopts the Dynamic Software Product Lines (DSPL) engineering approach, and separates the concerns of the system by following the Monitor, Analyze, Plan, and Execute (MAPE) model. DAMPAT limits the combinatorial explosion of pipelines variability by introducing architectural constraints. Results from evaluation show that DAMPAT can adapt multimedia pipelines adhering to the application mobility paradigm in the order of hundreds of milliseconds.

The potential of patient-centred care and a connected eHealth ecosystem can be developed through socially responsible innovative architectures. The purpose of this paper is to define key innovation needs. This is achieved through conceptual development of an architecture for common information spaces with emergent end-user applications by supporting intelligent processing of measurements, data and services at the Internet of Things (IoT) integration level. The scope is conceptual definition, and results include descriptions of social, legal and ethical requirements, an architecture, services and connectivity infrastructures for consumer-oriented healthcare systems linking co-existing healthcare systems and consumer devices. We conclude with recommendations based on an analysis of research challenges related to how to process the data securely and anonymously and how to interconnect participants and services with different standards and interaction protocols, and devices with heterogeneous hardware and software configurations.

In battery-powered Cognitive Machine-to-Machine\nCommunications (CM2M), the energy consumption, opportunis-\ntic data access capacity and interference to the licensed system\nneed to be optimized simultaneously. We consider this as joint\ncooperative spectrum sensing and power allocation, and model\nthis as a constraint multiobjective optimization problem of three\nobjectives. Our model helps to find a Pareto optimal variable\nset of sensing duration, detection threshold and transmission\npower for each individual sensor in cooperative spectrum sensing.\nThe evaluation of our model shows that energy consumption,\nopportunistic data capacity and interference are optimized\nsimultaneously while keeping the total cooperative spectrum\nsensing error lower than a predefined threshold. Pareto optimal\nresults show that better energy efficiency [bits/joule] makes lower\nharmful interference to the primary system.

The development of resource-constrained embedded systems that are naturally state-driven is still a challenging issue, especially in industrial applications -- developed on a bare-bone style runtime system with basic programming features. This is because of the complexity of state-driven design in embedded applications, such as parallel and complicated event-based activity flows, and complicated constraints for transitioning between program states. State machines are considered a systematic approach for such needs. However, existing approaches, in this area, either do not satisfactorily address the above complexity aspects, or force the developer to write code intermingling state handling logic with the functional code. To tackle these issues, we propose TOKEN IT, a state machine-based development framework for resource-constrained embedded systems. Using TOKEN IT, the programmer models the application as a set of parallel processes, where each process consists of sequenced activities with state constraints such as delayed transitions or interdependency between the states of parallel processes. TOKEN IT, then, processes the obtained model and associates a token to each sequential flow of activities, synthesizing them and executing state transitions according to the constraints expressed in the TOKEN IT model. The evaluation results show that TOKEN IT reduces significantly the complexity of state-driven programming in embedded systems at an acceptable memory cost and with no extra processing overhead.

The applications of Cyber-Physical Systems (CPSs) in large scale, mobile and distributed systems, such as transportation and healthcare systems, foster the development of novel cross-CPS applications. Services, in such applications, enable the emergence of multiple end-to-end cyber-physical scenarios, formed dynamically based on their demands, e.g., Disaster recovery systems. This calls for new distributed service composition models that integrate different CPS services from multiple application domains for a given purpose -- CPS ecosystems. The in-Cloud availability of CPSs can significantly improve the development process of such ecosystems thanks to the global and rapid accessibility of CPS services in the Cloud. However, a major challenge in this context is the highly dynamic nature of CPS services, making service composition a challenging issue. In this paper, we propose to exploit the concept of models at runtime in order to create a dynamic middleware framework that allows efficient composition of CPS services in dynamic and on-demand CPS ecosystems. This is achieved by obtaining the runtime models of CPS services and synthesizing software mediators that translate the communications between individual CPS services residing in the Cloud. The in-Cloud availability of CPS services will facilitate the design of such a middleware framework, and processing and maintaining the runtime models.

SUMMARY Nowadays, the computational devices are everywhere. In malls, offices, streets, cars, and even homes, we can find devices providing and consuming functionality to improve the user satisfaction. These devices include sensors that provide information about the environment state (e.g., temperature, occupancy, light levels), service providers (e.g., Internet TVs, GPS), smartphones (that contain user preferences), and actuators that act on the environment (e.g., closing the blinds, activating the alarm, changing the temperature). Although these devices exhibit communication capabilities, their integration into a larger monitoring system remains a challenging task, partly because of the strong heterogeneity of technologies and protocols. Therefore, in this article, we focus on home environments and propose a middleware solution, called DigiHome, that applies the Service Component Architecture (SCA) component model to integrate data and events generated by heterogeneous devices in this kind of environments. DigiHome exploits the SCA extensibility to incorporate the REpresentational State Transfer (REST) architectural style and, in this way, leverages on the integration of multiscale systems‐of‐systems (from wireless sensor networks to the Internet). Additionally, the platform applies Complex Event Processing technology that detects application‐specific situations. We claim that the modularization of concerns fostered by DigiHome and materialized in a service‐oriented architecture, makes it easier to incorporate new services and devices in smart home environments. The benefits of the DigiHome platform are demonstrated on smart home scenarios covering home automation, emergency detection, and energy saving situations. Copyright © 2011 John Wiley & Sons, Ltd.

Wireless reprogramming of sensor nodes is a critical requirement in long-lived wireless sensor networks (WSNs) addressing several concerns, such as fixing bugs, upgrading the operating system and applications, and adapting applications behavior according to the physical environment. In such resource-poor platforms, the ability to efficiently delimit and reconfigure the necessary portion of sensor software—instead of updating the full binary image—is of vital importance. However, most existing approaches in this field have not been adopted widely to date due to the extensive use of WSN resources or lack of generality. In this article, we therefore consider WSN programming models and runtime reconfiguration models as two interrelated factors and we present an integrated approach for addressing efficient reprogramming in WSNs. The middleware solution we propose,

With the standardization of SVC, the scalable extension of H.264/AVC, layered peer-to-peer streaming has attracted more and more attention as it offers adaptability to network fluctuations and heterogeneous end users. Although overlay construction is important for system performance, not much effort has been spent on unstructured overlay construction for layered peer-to-peer streaming. Related work concentrates on layered streaming algorithms, and assumes that a list of peers for data exchange, called neighbors, is provided by traditional membership management protocols, e.g., SCAMP. Our previous studies have demonstrated that a random overlay is not good enough for layered peer-to-peer streaming. In this paper, we propose a new membership management protocol, based on peer sampling services. The protocol is quality-aware as it constructs the overlay so that (1) high capacity peers will be located at good positions in the overlay, e.g., close to the server, and (2) peers having similar capacity are likely to connect to each other. Both features are necessary to maximize bandwidth utilization of peers and to mitigate layer bottlenecks. With implementation of the protocol in PeerSim, we evaluate important graph properties of the overlay, constructed by the proposed protocol, to understand how it evolves during the streaming session with peer churn. Evaluation results show that the overlay is (1) scalable: it is stable with different sizes, from hundreds up to 10000 peers; and (2) robust: the good features are maintained or recovered fast under a high peer churn rate, and it only becomes disconnected when more than 86% of the peers are removed from the network.

Wireless sensor networks (WSNs) are being extensively deployed today in various monitoring and control applications by enabling rapid deployments at low cost and with high flexibility. However, high-level software development is still one of the major challenges to wide-spread WSN adoption. The success of high-level programming approaches in WSNs is heavily dependent on factors such as ease of programming, code well-structuring, degree of code reusability, required software development effort and the ability to tune the sensor software for a particular application. Component-based programming has been recognized as an effective approach to satisfy such requirements. However, most of the componentization efforts in WSNs were ineffective due to various reasons, such as high resource demand or limited scope of use. In this article, we present Remora, a novel component-based approach to overcome the hurdles of WSN software implementation and configuration. Remora offers a well-structured programming paradigm that fits very well with resource limitations of embedded systems, including WSNs. Furthermore, the special attention to event handling in Remora makes our proposal more practical for embedded applications, which are inherently event-driven. More importantly, the mutualism between Remora and underlying system software promises a new direction towards separation of concerns in WSNs. This feature also offers a practical way to develop sensor middleware services which should be generic and developed close to the operating system. Additionally, it allows the customization of sensor software—deploying only application-required system-level services on nodes, instead of installing a fixed large system software image for any application. Our evaluation results show that the deployed Remora applications have an acceptable memory overhead and a negligible CPU cost compared with the state-of-the-art development models.

Layered streaming is being considered as the most promising approach to adapt to bandwidth variations and heterogeneous end users in streaming applications. The goal of a layered streaming protocol is not only to optimize the average playback skip rate as in single-layer streaming, but also to maximize possible quality level (quality satisfaction) based on the available bandwidth capacity at the end user. In unstructured layered peer-to-peer streaming, however, achieving high quality satisfaction is challenging due to content and bandwidth bottlenecks. With experiments, in this paper, we demonstrate the importance and identify unique challenges of neighbor selection to the system performance in terms of the average skip rate and quality satisfaction. Then, we propose a new neighbor selection technique that can offer good performance while keeping the scalability of the mesh overlay under network fluctuations. The core of the technique is a preemption rule that allows a higher capacity peer to replace a lower capacity peer to be a neighbor of another peer with a certain probability. This preemption rule gears high capacity peers to good locations in the overlay to maximize the use of their bandwidth capacity and available layers. Simulation results demonstrate the efficiency of the method.

Layered streaming can be used to adapt to the available download capacity of an end-user, and such adaptation is very much required in real world HTTP media streaming. The multiple layer codec has become more refined, as SVC (the scalable extension of the H.264/AVC standard) has been standardized with a bit rate overhead of around 10% and an indistinguishable visual quality, compared to the state of the art single layer codec. Peer-to-peer streaming systems have also become the reality. The important question is how such layered coding can be used in real world peer-to-peer streaming systems. This paper tries to explore the feasibility of using network coding to make layered peer-to-peer streaming much more realistic, by combining network coding and SVC in a fine granularity manner. We present Chameleon, our new peer-to-peer streaming algorithm designed to incorporate network coding seamlessly with SVC. Key components with different design options of Chameleon are presented and experimentally evaluated, with the objective of investigating benefits of network coding in combination with SVC. We carry out extensive experiments on real stream data to (i) evaluate the performance of Chameleon in terms of playback skips and delivered video quality, and (ii) understand its insights. Our results demonstrate the feasibility of the approach and bring us one step closer to real adaptive peer-to-peer streaming.

An increasing number of research efforts on wireless sensor networks (WSNs) are now considering dynamic environments with heterogeneous sensor devices. Most of this research considers data, control, and management issues separately and not clearly within a common architecture. This paper presents our development of an architecture, namely DCM-Arch, to address these issues together. The architectureconsists of three-planes of functionalities (in the verticaldimension): 1) data, 2) control, and 3) management; and four-tiers of network infrastructures (in the horizontal dimension): 1) routing and network infrastructure, 2) logical network infrastructure, 3) adaptation middleware, and 4) component-based software application. The data plane handles the information storage, reduction, and dissemination in WSNs. The control plane deals with the lightweight sensor adaptation and reconfiguration middleware to cope with the dynamic changes of the environment. Finally, the management plane provides the context management functions, e.g. for collaboration and reasoning, to allow sensors, coordinators, and sinks to make good decisions about adaptation and reconfiguration. While the vertical dimension describes the functionalities of DCM-Arch, its four-tiers provide the required facilities to achieve those functionalities.

This paper addresses the problem of optimal cooperative spectrum sensing in a cognitive-enabled sensor network where cognitive sensors can cooperate in the sensing of the spectrum. Such sensor networks are assumed to be power resource constrained. With a given threshold for the accuracy of the spectrum detection, we find the optimal number of cognitive sensors participating in the cooperative spectrum sensing and the optimal sensing interval that minimize the total energy consumption of the cooperative sensing. First, the mathematical lower bound and upper bound for the number of cooperative cognitive sensors are found. Then the optimization problem to minimize the total energy consumed by a group of sensors is presented. Finally, an efficient approximate solution to the optimization problem is proposed. Numerical calculations validate the accuracy and the performance of the proposed scheme. The impact of the noise uncertainty, the choice of the energy detection threshold, and the spectrum bandwidth on the detection accuracy and the minimum total energy consumption is also studied.

Abstract Driven by the emergence of mobile and pervasive computing there is a growing demand for context‐aware software systems that can dynamically adapt to their run‐time environment. We present the results of project MADAM that has delivered a comprehensive solution for the development and operation of context‐aware, self‐adaptive applications. The main contributions of MADAM are (a) a sophisticated middleware that supports the dynamic adaptation of component‐based applications, and (b) an innovative model‐driven development methodology that is based on abstract adaptation models and corresponding model‐to‐code transformations. MADAM has demonstrated the viability of a general, integrated approach to application‐level adaptation. We discuss our experiences with two real‐world case studies that were built using the MADAM approach. Copyright © 2008 John Wiley & Sons, Ltd.

Real-Time content-based access to live video data requires content analysis applications that are able to process video streams in real-time and with an acceptable error rate. Statements such as this express quality of service (QoS) requirements. In general, control of the QoS provided can be achieved by sacrificing application quality in one QoS dimension for better quality in another, or by controlling the allocation of processing resources to the application. However, controlling QoS in video content analysis is particularly difficult, not only because main QoS dimensions like accuracy are nonadditive, but also becauseboththe communication- and the processing-resource requirements are challenging.This article presents techniques for QoS-aware composition of applications for real-time video content analysis, based on dynamic Bayesian networks. The aim of QoS-aware composition is to determine application deployment configurations which satisfy a given set of QoS requirements. Our approach consists of: (1) an algorithm for QoS-aware selection of configurations of feature extractor and classification algorithms which balances requirements for timeliness and accuracy against available processing resources, (2) a distributed content-based publish/subscribe system which provides application scalability at multiple logical levels of distribution, and (3) scalable solutions for video streaming, filtering/transformation, feature extraction, and classification.We evaluate our approach based on experiments with an implementation of a real-time motion vector based object-tracking application. The evaluation shows that the application largely behaves as expected when resource availability and selections of configurations of feature extractor and classification algorithms vary. The evaluation also shows that increasing QoS requirements can be met by allocating additional CPUs for parallel processing, with only minor overhead.

This technical demonstration shows that content-based networking is a promising technology for multireceiver video streaming. Each video receiver is provided with fine grained selectivity along different video dimensions, such as region of interest, quality, colors, and temporal resolution. Efficient delivery is maintained, in terms of network utilization and processing requirements. A prototype demonstrates the feasibility of this approach and is available as open source.

Real-time content-based access to live video data requires content analysis applications that are able to process the video data at least as fast as the video data is made available to the application and with an acceptable error rate. Statements as this express quality of service (QoS) requirements to the application. In order to provide some level of control of the QoS provided, the video content analysis application must be scalable and resource aware so that requirements of timeliness and accuracy can be met by allocating additional processing resources.In this paper we present a general architecture of video content analysis applications including a model for specifying requirements of timeliness and accuracy. The salient features of the architecture include its combination of probabilistic knowledge-based media content analysis with QoS and distributed resource management to handle QoS requirements, and its independent scalability at multiple logical levels of distribution. We also present experimental results with an algorithm for QoS-aware selection of configurations of feature extractor and classification algorithms that can be used to balance requirements of timeliness and accuracy against available processing resources. Experiments with an implementation of a real-time motion vector based object-tracking application, demonstrate the scalability of the architecture.