Power management is a cornerstone for many Cyber-Physical Systems (CPSs), which relies on low-power circuits, dynamic power management algorithms and energy-aware software to match their requirements in terms of energy. As CPSs evolve towards data-centric designs to more promptly accommodate AI models and integration, traditional power management techniques must also be improved. In this paper, we build on SmartData to introduce a data-centric Power Manager (PM) framework that allows CPSs to model energy in terms of data. SmartData defines a high-level interface for sensing, actuation, and control in data-centric CPSs. It abstracts the myriad of features of modern embedded platforms related to processing, scheduling, synchronization, and communication. These Energetic SmartData encapsulate the components of a CPS, which interact in a publish–subscribe fashion, declaring interest on other SmartData and responding to other SmartData interests. We introduce an algorithm to extract a Directed Acyclic Graph (DAG) from these Interest relationships, with vertices representing the involved components and edges representing the associated cost in terms of energy. We also introduce a Power Manager that uses such DAGs to monitor the state of the system, eventually overriding low-priority Interests to reach the specified lifetime. We evaluated the proposed framework through a case study with Ocean-Bottom Nodes (OBNs) under realistic, dynamic energy conditions. Results show that without any power management, the system fails 12 days before its target operational lifetime. The proposed data-driven PM was then benchmarked against a fixed-schedule Static PM and a reactive Threshold PM. Our approach was the only strategy to guarantee a 365-day lifetime in all scenarios. With an ideal initial battery capacity of 260 Ah, it achieved a high utility of 23.1%. It also proved its adaptability in an energy-deficit scenario with an initial capacity of 257 Ah, where it reduced utility to 2.8% to survive, a condition in which the other strategies failed.

The effectiveness of autonomous vehicles relies on reliable perception capabilities. Despite significant advancements in artificial intelligence and sensor fusion technologies, current single-vehicle perception systems continue to encounter limitations, notably visual occlusions and limited long-range detection capabilities. Collaborative Perception (CP), enabled by Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communication, has emerged as a promising solution to mitigate these issues and enhance the reliability of autonomous systems. Beyond advancements in communication, the computer vision community is increasingly focusing on improving vehicular perception through collaborative approaches. However, a systematic literature review that thoroughly examines existing work and reduces subjective bias is still lacking. Such a systematic approach helps identify research gaps, recognize common trends across studies, and inform future research directions. In response, this study follows the PRISMA 2020 guidelines and includes 106peer-reviewed articles. These publications are analyzed based on modalities, collaboration schemes, and key perception tasks. Through a comparative analysis, this review illustrates how different methods address practical issues such as pose errors, temporal latency, communication constraints, domain shifts, heterogeneity, and adversarial attacks. Furthermore, it critically examines evaluation methodologies, highlighting a misalignment between current metrics and CP’s fundamental objectives. By delving into all relevant topics in-depth, this review offers valuable insights into challenges, opportunities, and risks, serving as a reference for advancing research in vehicular collaborative perception.

As vehicles become increasingly interconnected, ensuring secure, low-latency communication in Intelligent Transport Systems (ITS) is crucial. Traditional ITS security models, typically based on Public Key Infrastructure (PKI), introduce significant latency. In this work, we adapt and evaluate a V2X secrecy forwarding protocol for ITS. The protocol is validated through a vehicular simulation in a realistic highway scenario with multiple gateways. Evaluation is conducted under two scenarios according to the communication ranges of IEEE 802.11p and 5G technologies. Simulation results demonstrate that the protocol achieves low latency, with an average of 3.16ms in the 500-meter scenario and 2.93ms in the 250-meter scenario. Network load overhead is, on average, at most 0.033% of the bandwidth per vehicle for the 500-meter scenario and 0.017% per vehicle for the 250-meter scenario. The results corroborate the protocol's potential to meet real-time requirements in ITS.

The rising number of truck-related fatalities on Brazilian highways, alongside global increases in heavy-duty vehicle (HDV) incidents, highlights the need for advanced adaptive safety systems. Responsibility-Sensitive Safety (RSS) provides a verifiable framework for autonomous driving but struggles with HDV challenges such as highly variable mass. This work proposes TruckRSS, an RSS extension for variable-mass vehicles, integrating mass estimation through Neural Networks (NN) and formal runtime verification using Signal Temporal Logic (STL). A data-driven approach employing Gated Recurrent Unit (GRU) models achieved a Mean Absolute Error (MAE) of 121.91 kg after post-processing. Experimental validation in the CARLA simulator demonstrated that TruckRSS adapts braking behavior based on real-time mass estimation, reducing unnecessary following distances and improving traffic flow efficiency compared to standard RSS. Real-time monitoring evaluations confirmed that TruckRSS can be enforced with minimal computational overhead, supporting its scalability for deployment in safety-critical HDV applications.

Industrial anomaly detection often faces a trade-off between the interpretability of physics-based models and the flexibility of data-driven methods. This paper proposes a novel residual-based framework for anomaly detection and recognition in dynamic systems. Our approach employs a Physics-Informed Neural Network trained on healthy data to generate residuals that quantify deviations from expected physical behavior. The approach enables highly effective interpretable anomaly detection by using Extreme Value Theory to define exceedance based on the modeled tail distributions of healthy residual features. A Siamese Neural Network, trained with triplet loss on residual features from known fault types, creates a similarity embedding space that allows open-set recognition of both known and unseen fault groups via K-Nearest Neighbors. The combined approach provides an interpretable pipeline where detection stems from physical model violations and recognition leverages learned residual similarity, enhancing operator understanding and decision-making. We demonstrate the approach on ring bearing data from the MaFaulDa dataset, achieving detection accuracy of 98.5% with 99.27% F1-score, and overall recognition accuracy and F1-score of 82% under open-set conditions.

Ensuring fast, deterministic data exchange is vital for Advanced Driver Assistance System (ADAS), making Time-Sensitive Networking (TSN) a key enabler in real-time automotive environments. ADAS heavily depends on Machine Learning and Computer Vision to analyze information from various sensors, such as LiDAR, radar, and cameras. These technologies support essential functions like adaptive cruise control, collision prevention, and lane-keeping assistance. However, the need to handle and transmit vast amounts of high-resolution sensor data presents substantial computational and networking challenges. This study introduces an predictive model to refine transient subscription management in a publish-subscribe TSN setup for ADAS. The proposed system utilizes predictor to anticipate how long temporary data subscriptions should persist, particularly when triggered by critical scenarios—such as detecting an object at the edge of a sensor’s Field-of-View. By enhancing data exchange efficiency and reliability, this approach bolsters safety-critical CV operations while maintaining the stability of ongoing communication streams. Ultimately, this method improves the resilience and scalability of ADAS in highly dynamic, real-time conditions.

Structural Health Monitoring (SHM) is crucial for ensuring the safety and longevity of critical infrastructures. Traditional methods for crack detection and damage assessment are often labor intensive and time consuming, highlighting the need for advanced technologies to enhance efficiency and accuracy. This paper introduces a novel approach that integrates continual learning frameworks within multi-layer recurrent neural networks to improve parameter estimation in SHM applications. By deploying the Generalized Expectation Maximization algorithm, we address challenges associated with dynamic operational environments and inherent uncertainties in sensor data. Our methodology enables real-time monitoring and adaptive learning, allowing the model to continuously refine its predictions based on new data. We demonstrate its effectiveness in automating structural anomaly detection from accelerometer readings, significantly enhancing the reliability of damage assessment. First results indicate that our framework not only improves crack detection accuracy, but also facilitates timely interventions, contributing to a more sustainable infrastructure management.

Power management is a cornerstone for many Cyber-Physical Systems (CPSs), which relies on low-power circuits, dynamic power management algorithms and energy-aware software to match their requirements in terms of energy. As CPSs evolve towards data-centric designs to more promptly accommodate AI models and integration, traditional power management techniques must also be improved. In this paper, we build on SmartData to introduce a data-centric Power Manager (PM) framework that allows CPSs to model energy in terms of data. SmartData defines a high-level interface for sensing, actuation, and control in data-centric CPSs. It abstracts the myriad of features of modern embedded platforms related to processing, scheduling, synchronization, and communication. These Energetic SmartData encapsulate the components of a CPS, which interact in a publish-subscribe fashion, declaring interest on other SmartData and responding to other SmartData interests. We introduce an algorithm to extract a Directed Acyclic Graph (DAG) from these Interest relationships, with vertices representing the involved components and edges representing the associated cost in terms of energy. We also introduce a Power Manager that uses such DAGs to monitor the state of the system, eventually overriding low-priority Interests to reach the specified lifetime. We evaluated the proposed framework through a case study with Ocean-Bottom Nodes (OBNs), demonstrating the system's ability to dynamically adapt to achieve its operational time. In an experiment with variability impacting the available energy budget, while the CPS without PM would exhaust its energy 12 days before the intended lifetime, the proposed PM successfully guaranteed the designed lifetime by only reconfiguring low-criticality Interest relationships, without canceling any CPS functionality.

In this study, we propose a generalizable approach for predicting the energy budget to sustain wireless communication in multiple scenarios. We achieve this by using predictive models to estimate the duration of transceiver modes (receive, idle, and transmit) in a future window. We applied our approach to distinct scenarios to evaluate its generalization capabilities. Through these experiments, we demonstrated the versatility of our approach and its ability to produce lightweight predictive models suitable for distinct applications. Our best-performing model, Multi-layer Perceptron (MLP), achieved a prediction error of less than 6 % across all scenarios, with an energy overhead of under 8 μ$J$and an inference time of less than 3.5 μs when embedded on a RISC-V single board computer. These results validate the effectiveness and practicality of our approach for predicting communication energy budgets in resource-constrained environments.

Much effort has been put into Time-Sensitive Networking for Cyber- Physical Systems. Methods and tools have been proposed to support the design and operation of such networks. However, the incorporation of novel technologies, such as computer vision, cloud integration, and decision-making for autonomy, requires an operation regimen that cannot always be modeled at design-time. In this paper, we introduce algorithms to determine whether the load imposed on a Time-Sensitive Networking is within bounds, and to extract formal properties from message headers in order to dynamically verify the network's temporal requirements. We also introduce a formalism based on Signal Temporal Logic to express such properties, a set of Time-Sensitive Networking-specific property monitors, and a lightweight verification engine that can check them at runtime with little overhead. These mechanisms are used by a Safety Enforcement Unit to continuously monitor the network, triggering actions such as best-effort and low-priority traffic cancellations whenever a property fails verification. We evaluated the proposed mechanisms on a prototype autonomous vehicle that uses a Time-Sensitive Networking to interconnect GNSS, IMU, LiDAR, RADAR, and Camera to an ECU. Results demon-strate that these mechanisms can run in real-time, consuming 3% of the processing power of one of the cores in the ECU.

This work investigated two statistical properties, namely stationarity, and entropy, of a real-world publicly available battery dataset considering features like Current, Charge Capacity, Discharge Capacity, Temperature, and Voltage, with the objective of providing insights for the development of models that would be best suited for early End-of-life (EOL) prediction. From the characteristics of the data, we hypothesized that the lack of stationarity and higher entropy would deteriorate the performance of LSTM models while having less of an impact on CNNs. To fortify this hypothesis we developed 4 types of models and investigated their performances. The results for this case study indicate that CNN-based models are more robust to these properties of the data, while the LSTM-based ones are more sensible and therefore have worse performance. We discuss this sensibility by analyzing the correlation of these statistics with model performance. The paper presents a detailed process for preprocessing, model generation, and comparison. Our best LSTM-based model had 18.3% error while the best CNN-based model presented 3.5% error when considering unseen test data, using only the first 100 cycles of the batteries.

Safety Models for Autonomous Vehicles often neglect fault tolerance, relying on strong assumptions over vehicles’ actuation, such as Responsibility-Sensitive Safety (RSS), which relies on static notions over vehicle’ actuation. This paper proposes to enhance RSS’s proper responses to support fault tolerance during complex maneuvers, specifically overtaking. The proposed approach is carefully built to comply with the original RSS notion of evasive maneuvers. Thus, it can be applied to enable Fault-Tolerant capabilities without losing its original properties. Moreover, the proposed proper responses are modeled using Signal Temporal Logic to promote the verification of system traces using formal methods.

In many applications Internet of Things (IoT) supports decision taking on the base of continuous data acquisition. These data, usually streams of sensed data, are processed and analysed to produce high-level information. The latter task is usually achieved by means of artificial intelligence technologies. Among these, continual learning is emerging as a paradigm that combines well with IoT as it matches the ability of IoT to continuously produce new data. In this context, we address continual learning with Recurrent Neural Networks (RNN) under a stochastic perspective, in which we consider the RNN as a stationary state-space network. This led us to deploy the Generalized Expectation-Maximization algorithm, in a setting suitable for IoT. We demonstrate the effectiveness of our approach by considering a case study taken from digital agriculture, in which we adopt the continual learning model to assess the biomass prediction in the field of horticulture using IoT technology. Results demonstrate that RNNs embedded in the EM framework can learn on their own after a very short training phase covering a few time samples.

Modern embedded systems integrate software components onto a single computing platform to meet stringent non-functional requirements of cost, space, weight, and power consumption, amongst others. Moreover, the growing demand for computational power pushed for the adoption of multicore platforms. At the same time, those platforms are often connected to the external world to support a variety of applications. In this context, Machine Learning-based Intrusion Detection Systems (IDS) are of significant importance to guarantee the system’s security during its operation. One approach to be adopted by IDS is to model the behavior of the applications on an embedded system through Performance Monitoring Counters (PMC) and operate during runtime by detecting deviations to the modeled behavior. Notwithstanding, the execution of multiple tasks onto the same multicore platform often incurs shared-resource contention between tasks, which may impair the execution of software components and possibly affect the behavior observed through PMC. In this paper, we assess the impacts of lacking proper resource isolation mechanisms on multicore embedded systems over two Machine Learning-based Intrusion Detection Systems (IDS) solutions that rely on PMC. We use a relevant dataset in the scope of embedded systems control with both tasks monitored while executing without and with the interference of shared-resources contention. Results demonstrate that the lack of isolation can lead to the IDS mechanism losing the ability to recognize the behavior of target software components.

Cyber-Physical Systems (CPS) rely on sensing to control and optimize their operation. Nevertheless, sensing itself is prone to errors that can originate at several stages, from sampling to communication. In this context, several systems adopt multivariate predictors to assess the quality of the sensed data, to replace data from faulty sensors, or to derive variables that cannot be directly sensed. These predictors are often evaluated based on their accuracy and computing demands, however, such evaluations often do not consider the system's architecture from a broader perspective, ignoring the way components are interconnected and how they cascade as inputs of other Machine Learning (ML) models. In this work, we introduce a method to evaluate the performance of interdependent predictors based on the stability of the estimation error dynamics in faulty scenarios. The proposed method estimates the ability of a predictor to produce accurate predictions while accounting for the impacts of cascading predicted values as its inputs. The prediction correctness is estimated based solely on information acquired during the training of the multivariate predictors and mathematical properties of the ML activation functions. The proposed method is evaluated with a meaningful dataset in the scope of monitoring and control of a Cyber-Physical System, and the evaluation demonstrates the ability of the proposed method to account for the interdependence of data predictors.

Machine Learning solutions for anomaly detection can be applied in the industry to extend the lifetime of components by promoting actuation in real-time, like optimising machinery parameters to mitigate faults. The development of these approaches usually takes place on Cloud platforms. Nevertheless, Cloud platforms interacting with the real-time control loop add extraneous and unpredictable delays due to service availability and possible communication issues. Thus, embedding anomaly detection solutions in monitoring and control systems is an alternative to enable the aforementioned interaction. In a previous work, we investigated a Deep Autoencoder solution based on vibration data to detect anomalies in Wind Turbines. The solution is currently in usage in a Cloud platform and achieved promising results, which motivated its embedding. This paper demonstrates the process of embedding the solution while maintaining the detection performance metrics. The proposed embedding process reduced the execution time of the preprocessing steps to 18.09% of the original method while saving up to 54.59% of energy on average. An automatic search for low-cost configurations, while evaluating the impact of preprocessing steps, resulted in adequate configurations, improving the original anomaly detection performance and reducing memory utilisation up to 5.5x.

In this paper, we address the problem of intrusion detection in multicore embedded systems through a self-nonself discrimination scheme based on Artificial Immune Systems. We collect runtime data to build a model in which the T-cells work as detectors for the system’s sane behavior. The T-cells are represented by N-dimensional data points composed of samples of the N variables monitored during model building. A pre-established binding threshold is used for the T-cells generation. The difference between data points is measured as the distance between them. While training, whenever a collected sample fails to bind to an existing T-cell, it becomes a new one. After training, the threshold is adjusted to the maximum distance observed in the model. Therefore, the model definition follows an iterative clustering algorithm where each T-cell is a cluster centroid with threshold as the radius. Nonself detection consists of comparing collected samples to the T-cells in the model through a cluster membership verification. Whenever the incoming sample is not a member of any of the clusters, the sample is classified as nonself. A time complexity analysis indicates the suitability of the proposed technique for runtime operation, and offline experiments show this approach achieved a 97.17% nonself detection rate.

Autonomous vehicles are complex Cyber-Physical Systems with strict timeliness constraints, where failure to meet expectations can lead to life-threatening situations. Misbehavior Detection Algorithms are designed to detect and filter misbehaving devices, thus avoiding the consumption of erroneous data. However, these detection algorithms tend to incur processing delays that may infringe on the timely consumption of the data before their expiry. The variable data volume and possible contention due to shared resources with other processes typical of VANETs can lead to even longer processing delays, where data would expire before verification is complete. We propose a Cooperative Misbehavior Detection Framework, where property monitors supervise data expiry. Misbehavior detection algorithms are modeled through Signal Temporal Logic. Property monitors are defined to verify, at run-time, that the timeliness and data correctness of the detection is respected before allowing data consumption. We model a VANET use-case with a threshold algorithm and simulate varying vehicle densities in the Luxembourg SUMO Traffic scenario. High vehicle density showed an increase in expired data due to the processing delay caused by the data volume. Nevertheless, the accuracy for each vehicle density was: low 96.508%, medium 98.348% and high 92.439%.

Contemporary Cyber-Physical Systems (CPS), such as autonomous vehicles, are driven mainly by data. Combining timing and data semantics in such Data-Driven systems is crucial to assure safety. This paper proposes an extension of SmartData to support online safety monitoring. By following a Data-Driven Design, we promote a specification of property monitors using Signal Temporal Logic (STL) encompassing Safety Models. Timing aspects from STL specification roots from the timed data intrinsic to SmartData. The property monitors are envisioned as an online monitoring method inside a Safety Enforcement Unit (SEU). The SEU periodically assures the satisfiability of timing and semantics. We demonstrate the proposed design through a case study of an autonomous vehicle modeled using SmartData. The case study considers Mobileye’s Responsibility-Sensitive Safety as a ruler for safety vehicle conditions. Finally, the design provides the online verification capabilities inside the SEU by exploring the interpretation of STL specification as property monitors following the RTAMT library.

In this work, we propose a secure bootstrap protocol for Cyber-Physical Systems (CPS) that compose IIoT Networks. The main contribution of our work is a solution to establish secure communication channels in CPSs through a protocol that enables authentication and confidentiality without the need for constant external verification or pre-stored keys. The proposed protocol relies on the unclonable property of Physical Unclonable Functions (PUF) to build authentication tokens to establish trust between the devices, the gateway, and the Cloud. Devices registration is triggered by an authenticated operator, which informs the PUF responses of the respective device to an External Security Agent (ESA) alongside the identification of the target gateway. ESA and gateway are mutually authenticated using a Certificate Authority and communicate via a secure channel built with HTTPS. The device registration relies on the properties of PUFs to avoid the establishment of security channels via key agreement protocols (e.g., ECDH) and the usage of pre-stored keys. In this way, the PUF challenge response can be used as a secret between the gateway and the device to build trust and establish a secure channel. The presented solution addresses attacks like message replication, Man-in-the-Middle (MITM), and nodes impersonation while supporting gateway integrity check solutions and being free of pre-stored key vulnerabilities.

Verifying the integrity of data to detect modification requires audit material of the original state of the data. Hash digests, Message Authentication Codes, or Digital Signatures are used as audit material while transmitting messages. However, when an Industrial Internet of Things gateway is present, the end-to-end security may need to be updated before forwarding. Whereby the integrity assurance relies on the trustfulness of the gateway. Given the risk of a compromised gateway the chain of trust is invariably broken. In this work, we explore alternatives to the audit data retrieval regimen of the Gateway Integrity Checking Protocol. We present three regimens and simulate their effects on a wireless network, measuring network lifetime expectation, total audit material generated, and the resulting detection rate of gateway misbehavior. We found that the regimens obtained an expected lifetime between 35.5 and 37.7 days while maintaining a similar detection rate.

In this article, we present an Online Learning Artificial Neural Network (ANN) model that is able to predict the performance of tasks in lower frequency levels and safely optimize real-time embedded systems’ power saving operations. The proposed ANN model is supported by feature selection, which provides the most relevant variables to describe shared resource contention in the selected multicore architecture. The variables are used at runtime to produce a performance trace that encompasses sufficient information for the ANN model to predict the impact of a frequency change on the performance of tasks. A migration heuristic encompassing a weighted activity vector is combined with the ANN model to dynamically adjust frequencies and also to trigger task migrations among cores, enabling further optimization by solving resource contentions and balancing the load among cores. The proposed solution achieved energy-savings of 24.97 percent on average when compared to the run-to-end approach, and it did it without compromising the criticality of any single task. The overhead incurred in terms of execution time was 0.1791 percent on average. Each prediction added 15.3585$\mu s$μson average and each retraining cycle triggered at frequency adjustments was never larger than 100$\mu s$μs.

Industrial Internet of Things (IIoT) gateways connected to the Internet are often based on conventional operating systems such as Linux and on conventional communication protocols such as HTTPS and therefore are valuable targets for malicious attackers. When compromised, a malicious IIoT gateway can interfere with data exchanged between IIoT devices and systems running on servers or the Cloud. The Gateway Integrity Checking Protocol (GIP), proposed in previous work, defines a gossip mechanism to collect data from sets of IIoT devices to respond to security challenges issued by an External Security Agent (ESA) to assess a gateway's trustworthiness. GIP relies on a secure channel between IIoT devices and the ESA, which is achieved using a Public Key Infrastructure (PKI) for message authentication and encryption. In this article, we perform an analysis of the security measures employed by GIP, using formal descriptions to demonstrate that GIP is no less secure than the hash algorithm and the public key infrastructure used. Additionally, we simulate different configurations of GIP to measure detection rate and time to detect integrity faults.

In this paper, we introduce a Framework to Design and Implement Real-time Multicore Schedulers using Machine Learning techniques applied to the very own data such systems produce as they operate. The framework builds on sensors and event counters present in modern hardware platforms and on variables kept by the operating system to capture run-time data that are subsequently subjected to ML tools to produce scheduling heuristics targeting specific optimization goals. It provides non-intrusive mechanisms to collect such data while the system runs real task sets with real workloads, thus preserving the quality of the captured data. It abstracts the Performance Monitoring Unit, thermal sensing, energy monitoring, and Dynamic Voltage and Frequency Scaling available on such platforms through a lean, architecture-independent API. After describing the framework in details, we demonstrate its applicability with the implementation of an energy-efficient, load balancing, real-time, multicore heuristic for a PEDF scheduler. The measured overhead imposed by the framework on the tasks it schedule is at most 0,0003583% and the maximum added jitter is less than 40μs, corroborating the ability of the framework to support the development of effective domain-specific schedulers using machine learning techniques.

Wireless sensor networks (WSNs), often adhering to a single gateway architecture, constitute the communication backbone for many modern cyber-physical systems (CPSs). Consequently, fault-tolerance in CPS becomes a challenging task, especially when accounting for failures (potentially malicious) that incapacitate the gateway or disrupt the nodes-gateway communication, not to mention the energy, timeliness, and security constraints demanded by CPS domains. This paper aims at ameliorating the fault-tolerance of WSN-based CPS to increase system and data availability. To this end, we propose a replicated gateway architecture augmented with energy-efficient real-time Byzantine-resilient data communication protocols. At the sensors level, we introduce fault-tolerant trustful space-time protocol, a geographic routing protocol capable of delivering messages in an energy-efficient and timely manner to multiple gateways, even in the presence of voids caused by faulty and malicious sensor nodes. At the gateway level, we propose a multigateway synchronization protocol, which we call ByzCast, that delivers timely correct data to CPS applications, despite the failure or maliciousness of a number of gateways. We show, through extensive simulations, that our protocols provide better system robustness yielding an increased system and data availability while meeting CPS energy, timeliness, and security demands.

Blockchain technologies can enable decentralized and trustful features for the Internet of Things (IoT). Although, existing blockchain based solutions to provide data integrity verification for semi-trusted data storages (e.g. cloud providers) cannot respect the time determinism required by Cyber-Physical Systems (CPS). Additionally, they cannot be applied to resource-constrained IoT devices. We propose an architecture that can take advantage of blockchain features to allow further integrity verification of data produced by IoT devices even in the realm of CPS. Our architecture is divided into three levels, each of them responsible for tasks compatible with their resources capabilities. The first level, composed of sensors, actuators, and gateways, introduces the concept of Proof-of-Trust (PoT), an energy-efficient, time-deterministic and secure communication based on the Trustful Space-Time Protocol (TSTP). Upper levels are responsible for data persistence and integrity verification in the Cloud. The work also comprises a performance evaluation of the critical path of data to demonstrate that the architecture respect time-bounded operations demanded by the sense-decide-actuate cycle of CPSs. The additional delay of 5.894us added by our architecture is negligible for a typical TSTP with IEEE 802.15.4 radios which has communication latencies in the order of hundreds of milisseconds in each hop.

With the advent of the Internet of Things, new devices feature advanced capabilities that are used in homes, rooms, and offices for better comfort and to save user's time and energy. A complete smart space control system should automatically adjust settings to the user preferences based on data previously collected from such smart things. This paper describes a system that uses environmental data collected from sensors in smart devices to define contexts and user preferences to accomplish this requirement. Contextual data is fed to a context-aware decision engine, composed by a combination of machine learning and data mining techniques. The context-aware decision engine is capable of identifying important data relationships. This allows the use the environment's contextual information to make intelligent control decisions and adjust the environment's settings to user's preferences and reduce the overall power consumption, yielding better services to the user and improving human-technology interaction. We implemented and evaluated the system through a real case study. Results confirm the system's ability to automatically control a smart room with little overhead and latency, while promoting user comfort and energy savings.

Time synchronization is a keystone of Wireless Sensor Networks (WSN). It is fundamental to coordinate the action of nodes in a network and it is also a critical element of several security mechanisms. In this paper, we discuss and evaluate the time synchronization strategy behind the Trustful Space-Time Protocol (TSTP), which explores the protocol's cross-layer architecture to speculatively peek through the timestamps and geographic info present in message headers, implementing high-accuracy clock synchronization with minimal insertion of explicit messages. We evaluate the protocol analytically and experimentally. The analytic evaluation is based on the model defined by Schmid [15] for the Virtual High-resolution Time (VHT), while the experimental evaluation was performed on the IEEE 802.15.4-compliant EPOSMote platform running EPOS and TSTP. Our results demonstrate that nodes in the network can be consistently synchronized with sub-microsecond precision while exchanging far less messages than they would with an ordinary, non-speculative implementation, resulting in energy savings. Indeed, precision and energy savings are higher for networks with higher traffic, since more messages are available for peeking. In an experiment scenario in which messages were exchanged between devices every 15 seconds, nodes in the network achieved a synchronization error of approximately 15 microseconds in the worst case, while in a scenario in which messages were exchanged every 3 seconds, synchronization error was less than 0.5 microseconds in the worst case, and approximately 0.25 microseconds on average.

In this work, we propose a framework capable of transparently switching between multiple hardware and software implementations of embedded system components to cope with and adapt to dynamic runtime characteristics such as power, throughput and quality of service. The reconfiguration process is decomposed into small steps such that it is preemptable, transparent, dynamic and compliant with real-time requirements. We present a Private Automatic Branch eXchange(PABX) system as a case study for the framework, and investigate the dynamic reconfiguration of three of its components: an ADPCM codec, a DTMF detector, and an AES core. Our results with this case study show how our framework is able to perform reconfiguration of hardware/software components in the order of a few milliseconds, without taking excessive system resources, and without disrupting the execution of application threads.

In this paper, we introduce a cross-layer, application-oriented communication protocol for Wireless Sensor Networks (WSN). TSTP - Trustful Space-Time Protocol - integrates most services recurrently needed by WSN applications: Medium Access Control (MAC), spatial localization, geographic routing, time synchronization and security, and is tailored for geographical monitoring applications. By integrating shared data from multiple services into a single network layer, TSTP is able to eliminate replication of information across services, and achieve a very small overhead in terms of control messages. For instance, spatial localization data is shared by the MAC and routing scheme, the location estimator, and the application itself. Application-orientation allows synergistic co-operation of services and allows TSTP to deliver functionality efficiently while eliminating the need for additional, heterogeneous software layers that usually come with an integration cost.

Interrupt handling plays a fundamental role in Cyber-Physical Systems (CPS), particularly for those whose complexity cannot go with simplistic sensing-control-actuation loops designed around ordinary polling operations. Such systems usually rely on some sort of Real-Time Operating System (RTOS) to support the concurrent execution (or parallel execution, for multicore platforms) of periodic threads that interact with hardware devices mainly through interrupts. Since hardware interrupts are asynchronous with respect to the execution flow of threads, inappropriately handling them has the potential to disrupt the system's real-time specification, causing undesirable jitter and potential deadline losses. In this paper, we investigate interrupt handling strategies for RTOS considering CPSs designed around specific Models of Computation (MoC). We compare traditional Interrupt Service Routines (ISR), which perform both interrupt reception and the servicing all together, with a time-predictable mechanism that decouples interrupt reception from servicing, making the first deterministic in terms of time and scheduling the second along with other real-time threads. We compare them in terms of latency and jitter considering two different scenarios: that of systems designed around the Discrete Events (DE) MoC and that of those designed around the Time-Triggered (TT) MoC. Our results show that the time-predictable mechanism is essential for TT, while the traditional interrupt handling mechanism is more suitable for DE, thus demonstrating that RTOS need to be configurable in this respect in order to support forthcoming Cyber-Physical Systems.

In this paper we introduce X-Ware, a framework for computing whereby components used by an application can take different forms and characteristics across the lifetime of the system in order to adjust to dynamic application requirements. In particular, we explore two aspects of system mutability: dynamic choice of implementations for certain system components (e.g., leading to different trade-offs between quality and resource usage); and the change in non-functional characteristics of these components (e.g., speed and energy consumption) due to process and environmental variations. We demonstrate X-Ware with a library of mathematical APIs that can help components save up to 93% in energy and 94% in execution time by tolerating a small degradation in quality.

Modern multicore platforms feature multiple levels of cache memory placed between the processor and main memory to hide the latency of ordinary memory systems. The primary goal of this cache hierarchy is to improve average execution time (at the cost of predictability). The uncontrolled use of the cache hierarchy by real-time tasks may impact the estimation of their worst-case execution times (WCET). Software cache partitioning through page coloring has been considered a promising approach to isolate task workloads and thus improve WCET estimation. However, when real-time tasks share cache partitions due to false or true sharing, the inter-core delay caused by the cache coherence protocol may cause deadline losses. In this paper, we propose a Color-Aware task Partitioning (CAP) algorithm that assigns tasks to cores respecting their usage of cache partitions (i.e., colors). Tasks that share one or more colors are grouped together and the whole group is assigned to the same processor. Thus, it is possible to avoid inter-core interference. We compared the deadline miss ratio of several generated task sets partitioned by the CAP algorithm and by the worst-fit decreasing heuristic. We executed the partitioned task sets in a modern 8-core processor with shared L3-cache using a real-time operating system. Our results indicate that a color-aware task partitioning algorithm can avoid deadline misses in a multicore processor with shared cache.

Wireless Sensor Networks (WSNs) are rapidly becoming a necessary tool in many different application areas, such as environmental monitoring, security, safety, and so on. The heterogeneity of hardware is large, so there exists several different environments that support WSN programming. However, the great majority of such environments only target the sensors programming, forgetting about their real intent: the application. In this paper we propose an approach to satisfy the need of high level development methods in WSN applications, aiming to provide a clear link between the modelled WSN constraints and the programming entities. An important part of this proposal is the so-called Wireless Sensor Network (WiSeN) Profile, an UML profile devoted for WSN applications design in a Model-Drivel Development (MDD) paradigm.

The increasing complexity of current embedded systems is pushing their design to higher levels of abstraction, leading to a convergence between hardware and software design methodologies. In this paper, we aim at narrowing the gap between hardware and software design by introducing a strategy that handles both domains in a unified fashion. We leverage on aspect-oriented programming and object-oriented programming techniques in order to provide unified${\rm C}\! +\! + $descriptions of embedded system components. Such unified descriptions can be obtained through a careful design process focused on isolating aspects that are specific to hardware and software scenarios. Aspects that differ significantly in each domain, such as resource allocation and communication, were isolated in aspect programs that are applied to the unified descriptions before they are compiled to software binaries or synthesized to dedicated hardware using high-level synthesis tools. Our results show that our strategy leads to reusable and flexible components at the cost of an acceptable overhead when compared to software-only C/${\rm C} \!+ \! + $and hardware-only${\rm C} \!+ \! + $implementations.

It is a mistake to assume that each embedded object in the Internet of Things will implement a TCP/IP stack similar to those present in contemporary operating systems. Typical requirements of ordinary things, such as low power consumption, small size, and low cost, demand innovative solutions. In this article, we describe the design, implementation, and evaluation of a trustful infrastructure for the Internet of Things based on EPOSMote. The infrastructure was built around EPOS' second generation of motes, which features an ARM processor and an IEEE 802.15.4 radio transceiver. It is presented to end users through a trustful communication protocol stack compatible with TCP/IP. Trustfulness was tackled at MAC level by extending C-MAC, EPOS native MAC protocol, with AES capabilities that were used to encrypt and authenticate IP datagrams packets. Our authentication mechanism encompasses temporal information to protect the network against replay attacks. The prototype implementation was assessed for processing, memory, and energy consumption with positive results.

With system-on-chip (SoC) designs growing in complexity, system-level approaches that leverage on high-level synthesis (HLS) techniques are becoming the workhorse of current SoC design flows. In this scenario, we propose a component communication framework that allows for the seamless integration of hardware and software components in a HLS-capable environment. The proposed infrastructure relies on C++ static metaprogramming techniques to efficiently abstract communication details in high-level C++ implementations of components. We show how these mechanisms can be integrated with virtual platforms at different levels of abstraction, resulting in a design flow that enables the rapid design space exploration of SoC designs.

Shared cache partitioning is a well-known technique used in multicore real-time systems to isolate task workloads and improve system predictability. Presently, the state-of-the-art studies that evaluate shared cache partitioning on multicore processors lack two key issues. First, the cache partitioning mechanism is typically implemented either in a simulation environment or in a general-purpose OS, and so the impact of kernel activities, such as interrupt handlers and context switching, on the task partitions tend to be overlooked. Second, the evaluation is typically restricted to either a global or partitioned scheduler, thereby by falling to compare the performance of cache partitioning when tasks are scheduled by different schedulers. In this work, we design and implement a shared cache partitioning mechanism in a multicore component-based RTOS capable of assigning partitions to internal OS data structures, including task and system stacks and interrupt handlers data. We evaluate our shared cache partitioning mechanism running task sets under global (G-EDF) and partitioned (P-EDF) multicore real-time scheduling algorithms. Our results indicate that a lightweight RTOS does not impact real-time tasks, and shared cache partitioning has different behavior depending on the scheduler and the task's working set size.

Receiver-based MAC (RB-MAC) is a preamble-sampling MAC protocol for WSNs in which a receiver node is dynamically elected, among potential neighbors of the sender node, based on current channel conditions. In this paper, we evaluate the performance of RB-MAC and compare it with a senderbased preamble-sampling MAC protocol by using analytical methods, and implementation in real sensor nodes. We have used Configurable MAC (C-MAC), which is a framework to develop different MAC protocols in WSNs. This framework is realized as a component architecture that can produce application-specific communication protocols. The experimental results presented in the paper corroborate with the analytical and numerical results showing how RB-MAC outperforms sender-based MAC protocols in terms of transmission delay, and energy consumption.

WSNs, despite of its limited resources, are expected to operate without human interventions for a long period of time. Nevertheless, the environment might develop unpredicted characteristics or some network functionality might need some changes. Thus, it is necessary a mechanism which allows software reprogramming of the network nodes after its deployment. This paper presents the integration of a data dissemination protocol and ELUS, an OS support environment. The dissemination protocol is responsible for spreading the data across the network, while ELUS isolates the system components in memory position independent units, allowing their updating at execution time. We have evaluated our infrastructure, using real sensor nodes, in terms of memory consumption, dissemination, and reprogramming time.

This article describes the design, implementation and evaluation of a trustful infrastructure for the Internet of Things (IoT) based on EPOS Mote. The infrastructure was built around EPOS' second generation of motes, which features an ARM processor and an IEEE 802.15.4 radio transceiver. It is presented to end users through a trustful communication protocol stack compatible with TCP/IP. Trustfulness was tackled at MAC level by extending C-MAC, EPOS native MAC protocol, with Advanced Encryption Standard (AES) capabilities that were subsequently used to encrypt and authenticate packets containing IP data grams. Our authentication mechanism encompasses temporal information to protect the network against replay attacks. The infrastructure was designed bearing in mind the severe resource limitation typical of IoT devices. The prototype implementation was assessed for processing, memory, and energy consumption and strongly confirmed our assumptions.

This paper addresses an approach for accurately measuring energy consumption on battery-powered embedded systems which can be adequately tuned in order to enhance a set of timing and energy consumption metrics for mission critical systems. We introduce a software-based accounting scheme which is calibrated by low-precision battery state-of-charge reads through a battery voltage model. We then perform an offline multi-objective optimization procedure using NSGA-II to find good candidates to the period at which battery consumption information should be updated. Such candidates might guarantee timing constraints (i.e., no deadline misses), minimize residual energy after a pre-defined system lifetime, and maximize system utilization. We considered a simple scheduler which will reserve battery charge to run hard real-time tasks during a pre-defined lifetime and will prevent best-effort tasks from running whenever accounted battery state-of-charge is bellow the current reserve. We evaluated our approach by performing case-studies.

Software-controlled caches, often called scratch-pad memories (SPM), are being increasingly used due to their efficiency. And to exploit all the advantages of SPMs an efficient allocation must be done in software. In this work we propose a runtime operating system management approach for SPMs that do not require compiler support, application profiling or hardware support. The OS will use annotations, inserted into the code by the programmer, as hints to choose the most appropriate level in the memory hierarchy to allocate the data. The results showed that we were able to implement a run-time SPM allocation technique without adding any significant overhead to the system when compared with manual allocation.

Embedded systems usually run dedicated applications in highly restricted environments. This paper describes our approach to configure and generate embedded systems and a tool to assist this process that is being used with EPOS (Embedded and Parallel Operating System), an OS developed using AOSD. This tool receives a high level specification of the application and builds the necessary computational support for it. This paper describes some improvements to the tool that are enabling this process to be done automatically. Co-design, design space exploration and partitioning techniques were modeled as independent components, which allow to modify the implementation technique used in each step of this process and to use it to compose a new tool without changing the whole developing chain. Our main contribution is in the development of highly portable and application-oriented embedded systems using AOSD in a semi-automatized process guided by our tool.

Deeply embedded systems are designed to perform a certain set of tasks, and present limitations regarding processing and memory capabilities. In many cases, these systems are powered by batteries, requiring efficient power management. In this paper, we present a dynamic power manager with no significant overhead to the application. This manager uses the power management infrastructures present in the EPOS operating system, and is able to save power in different application scenarios.

Embedded software often needs to be ported from one system to another. This may happen for a number of reasons among which are the need for using less expensive hardware or the need for extra resources. Application portability can be achieved through an architecture-independent software/hardware interface. This is not a straight-forward task in the realm of embedded systems, since they often have very specific platforms. This work shows how an application-oriented component-based operating system was developed to allow system and application portability. Case studies present two embedded applications running in different platforms, showing that application source code is totally free of architecture-dependencies

Nowadays development strategies are not suitable for the design of many embedded systems applications, because they do not guide the developer in the use of nowadays software engineering concepts as aspects and generic programming. The present work shows the pros and cons of application-oriented system design (AOSD) strategy used in the design of a case study embedded system, aiming at AOSD methodology improvement. The disadvantages found in this case study may contribute to improve hardware generation according to AOSD.

Due to modularity and heterogeneity in wireless sensor networks sensing devices, a sensor application developed for a given platform will seldom be portable to a different one, unless the run-time support systems on those platforms deliver mechanisms that abstract and encapsulate the sensor platform in an adequate manner. In this article we propose a software/hardware interface that is able to abstract families of sensing devices in an uniform fashion. We define classes of sensing devices based on their finality (e.g. sensing acceleration, sensing temperature), and establish a common substrate for each class. Each individual device in a class is able to describe itself and its properties, in a similar fashion to the IEEE 1451 standard sensors transducer electronic data sheet. A thin software layer adapts individual devices to fit the minimal requirements of its sensor class. Software-based self-description allows applications to use individual sensors' extended characteristics. We show that this strategy does not incur in excessive overhead, and presents a significant advantage with relation to solutions found in other operating system for sensor networks

In this paper we study the problem of determining the location of nodes in a wireless sensor network, describing a fully decentralized algorithm called HECOPS, where every node estimates its own position after interacting with other nodes. Only a limited number of nodes have exact knowledge of their position coordinates. Any node can, however, be selected as a reference. We establish a ranking system to determine the reliability of each estimated position. This leads to a novel approach for position calculation that uses fewer but more reliable landmarks, thus reducing data communication and limiting error propagation. We present heuristics that are used to reduce the effects of measurement errors, including a scheme to calibrate range measurements by comparing, whenever possible, the estimated distance with the actual distance between a pair of nodes. Experiments demonstrate that the algorithm is superior to a previously proposed method in terms of its ability to compute correct coordinates under a wider variety of conditions and its robustness to measurement errors.

Summary form only given. This paper presents an alternative to achieve automatic run-time system generation based on the application oriented systems design method. Our approach relies on a static configuration mechanism that allows the generation of optimized versions of the operating system for particular classes of applications, promoting a better utilization of available resources. The EPOS operating system, with its strategies and tools, is taken as a case-study along the text to exemplify and corroborate the proposed ideas.

The growing complexity of embedded applications has motivated system designers to search for methods and tools that enable the automatic generation of embedded systems. This paper outlines a strategy for generating customized run-time support systems and specific hardware platforms for dedicated applications. Based on the application-oriented system design methodology, the approached strategy proposes the use of hardware mediators - an original portability artifact - as the basis for creating IP-based SoCs that match, in association with a run-time support system, the requirements of dedicated applications. The several steps involved in this process are presented in a detailed case study using an experimental application-oriented operating system instance

This paper presents a high performance communication system based on generic programming. The system adapts itself according to the protocol being used on communication, simplifying the development of libraries. In order to validate the concepts, a MPI implementation has been developed and it is compared to a traditional implementation - MPICH-GM. It is demonstrated that the same functionality and interface can be offered with similar performance, but with much less programming effort. That is evidence that the large size of traditional MPI implementations is due to the limitations of conventional communication systems.

Most of the communication systems used to support high performance computing in clusters of workstations have been designed focusing on "the best" solution for a certain network architecture. However, a definitive best solution, independently of how well tuned to the underlying hardware it is, cannot exist, for parallel applications communicate in quite different ways. In this paper we describe a novel design method that supports the construction of run time systems as an assemblage of components that can be configured to closely match the demands of any given application. We also describe how this method has been deployed in the development of a communication system in the realm of EPOS, a project that aims at delivering automatically, generated application-oriented run-rime support systems. The communication system in question has been implemented for a cluster of PCs interconnected with Myrinet, and corroborates the effectiveness of the proposed design method.