Critical Real-time Applications Research Articles

Leveraging blockchain and federated learning in Edge-Fog-Cloud computing environments for intelligent decision-making with ECG data in IoT

Blockchain technology combined with Federated Learning (FL) offers a promising solution for enhancing privacy, security, and efficiency in medical IoT applications across edge, fog, and cloud computing environments. This approach enables multiple medical IoT devices at the network edge to collaboratively train a global machine learning model without sharing raw data, addressing privacy concerns associated with centralized data storage. This paper presents a blockchain and FL-based Smart Decision Making framework for ECG data in microservice-based IoT medical applications. Leveraging edge/fog computing for real-time critical applications, the framework implements a FL model across edge, fog, and cloud layers. Evaluation criteria including energy consumption, latency, execution time, cost, and network usage show that edge-based deployment outperforms fog and cloud, with significant advantages in energy consumption (0.1% vs. Fog, 0.9% vs. Cloud), network usage (1.1% vs. Fog, 31% vs. Cloud), cost (3% vs. Fog, 20% vs. Cloud), execution time (16% vs. Fog, 28% vs. Cloud), and latency (1% vs. Fog, 79% vs. Cloud).

QoS-Aware Power-Optimized Path Selection for Data Center Networks (Q-PoPS)

Data centers consume significant amounts of energy, contributing indirectly to environmental pollution through greenhouse gas emissions during electricity generation. According to the Natural Resources Defense Council, information and communication technologies and networks account for roughly 10% of global energy consumption. Reducing power consumption in Data Center Networks (DCNs) is crucial, especially given that many data center components operate at full capacity even under low traffic conditions, resulting in high costs for both service providers and consumers. Current solutions often prioritize power optimization without considering Quality of Service (QoS). Services such as video streaming and Voice over IP (VoIP) are particularly sensitive to loss or delay and require QoS to be maintained below certain thresholds. This paper introduces a novel framework called QoS-Aware Power-Optimized Path Selection (Q-PoPS) for software-defined DCNs. The objective of Q-PoPS is to minimize DCN power consumption while ensuring that an acceptable QoS is provided, meeting the requirements of DCN services. This paper describes the implementation of a prototype for the Q-PoPS framework that leverages the POX Software-Defined Networking (SDN) controller. The performance of the prototype is evaluated using the Mininet emulator. Our findings demonstrate the performance of the proposed Q-PoPS algorithm in three scenarios. Best-case: Enhancing real-time traffic protocol quality without increasing power consumption. midrange-case: Replacing bottleneck links while preserving real-time traffic quality. Worst-case: Identifying new paths that may increase power consumption but maintain real-time traffic quality. This paper underscores the need for a holistic approach to DCN management, optimizing both power consumption and QoS for critical real-time applications. We present the Q-PoPS framework as evidence that such an approach is achievable.

Tailor-made Virtualization Monitor Design for CPU Virtualization on LEON Processors

In recent decades, mixed-criticality systems have been widely adopted to reduce the complexity and development times of real-time critical applications. In these systems, applications run on a separation kernel hypervisor, a software element that controls the execution of the different operating systems, providing a virtualized environment and ensuring the necessary spatial and temporal isolation. The guest code can run unmodified and unaware of the hypervisor or be explicitly modified to have a tight coupling with the hypervisor. The former is known as full virtualization, while the latter is known as para-virtualization. Full virtualization offers better compatibility and flexibility than para-virtualization at the cost of a performance penalty. LEON is a processor family that implements the SPARC V8 architecture and whose use is widespread in the field of space systems. To the best of our knowledge, all separation kernel hypervisors designed to support the development of mixed-criticality systems for LEON employ para-virtualization, which hinders the adaptation of real-time operating systems. This article presents the design of a Virtualization Monitor that allows guest real-time operating systems to run virtualized on LEON-based systems without needing to modify their source code. It is designed as a stand-alone component within a hypervisor and incorporates a set of techniques such as static binary rewriting, automatic code generation, and the use of operating system profiles. To validate the proposed solution, tests and benchmarks have been implemented for three guest systems, RTEMS, FreeRTOS, and Zephyr, analyzing the overhead introduced in certain situations characteristic of real-time applications. Finally, the same benchmarks have been run on AIR, one of the hypervisors that uses para-virtualization. The results obtained show that the use of the proposed techniques allows us to obtain similar results to those obtained using para-virtualization without the need to modify the source code of the guest real-time operating systems.

Flexible Cyclic Queuing and Forwarding for Time-Sensitive Software-Defined Networks

Time-Sensitive Networking (TSN) is emerging to support critical real-time applications in Industry 4.0. Recent proposals leverage Cyclic Queuing and Forwarding (CQF) to achieve bounded-delay transmission for cyclic flows in TSN. However, the CQF is not flexible enough in two aspects. First, it cannot achieve zero jitter. The Ping-Pong queue-based model in CQF will introduce the jitter of two cycles, which is inapplicable to industrial automation scenarios where isochronous flows require zero jitter. Second, it may require setting the maximum queue length to a fixed value in advance and scheduling the flows offline, which is challenging for dynamic traffic scheduling. In this paper, we firstly present a time-aware cyclic-queuing (TACQ) mechanism to enable zero jitter for CQF. TACQ consists of a novel no-wait shaper (NWS) and a cyclic-queuing shaper (CQS). The NWS handles isochronous flows by strictly limiting the transmission time of flows that do not overlap on each output port and each period. The CQS is extended from CQF to schedule cyclic flows. Then, we propose a variable time slot mechanism and a novel incremental routing and scheduling (IRAS) algorithm based on software-defined networking (SDN) to online schedule dynamic flows. Simulation results show that TACQ significantly reduces the delay of isochronous flows and achieves zero jitter compared with CQF. And the IRAS algorithm approaches 96.1% of the optimal solution in scheduling 2000 flows with a feasible per-flow computational time.

Resource Provisioning Using Meta-Heuristic Methods for IoT Microservices With Mobility Management

The fog and edge computing paradigm provide a distributed architecture of nodes with processing capability for smart healthcare systems driven by Internet of Thing (IoT) applications. It also provides a method to reduce big data transmissions that cause latency and enhance the system’s efficiency. Resource provisioning and scheduling in edge and fog systems is a significant problem due to heterogeneity and dispersion of edge/fog/cloud resources. The goal of scheduling is to map tasks to appropriate resources, which belong to NP-hard problems, and it takes much time to find an optimal solution. Meta-heuristic methods achieve near-optimal solutions within a reasonable time. Current edge/fog resource allocation research does not sufficiently address resource allocation problems in mobility-aware microservice-based IoT applications. This paper proposes a meta-heuristic-based micro-service resource provisioning model with mobility management for smart healthcare systems. The proposed approach has been tested on an experimental set-up with a simulation of a critical real-time smart healthcare application with and without considering the mobility of the devices. It applies meta-heuristic methods such as modified genetic and flower pollination algorithms for resource management. The proposed method outperforms the existing solutions in energy consumption, network usage, cost, execution time, and latency by 17%, 20%, 22%, 17%, and 63%, respectively.

A Deep Neural Network Accelerator using Residue Arithmetic in a Hybrid Optoelectronic System

The acceleration of Deep Neural Networks (DNNs) has attracted much attention in research. Many critical real-time applications benefit from DNN accelerators but are limited by their compute-intensive nature. This work introduces an accelerator for Convolutional Neural Network (CNN) , based on a hybrid optoelectronic computing architecture and residue number system (RNS) . The RNS reduces the optical critical path and lowers the power requirements. In addition, the wavelength division multiplexing (WDM) allows high-speed operation at the system level by enabling high-level parallelism. The proposed RNS compute modules use one-hot encoding, and thus enable fast switching between the electrical and optical domains. We propose a new architecture that combines residue electrical adders and optical multipliers as the matrix-vector multiplication unit. Moreover, we enhance the implementation of different CNN computational kernels using WDM-enabled RNS based integrated photonics. The area and power efficiency of the proposed accelerator are 0.39 TOPS/s/mm 2 and 3.22 TOPS/s/W, respectively. In terms of computation capability, the proposed chip is 12.7× and 4.02× better than other optical implementation and memristor implementation, respectively. Our experimental evaluation using DNN benchmarks illustrates that our architecture can perform on average more than 72 times faster than GPU under the same power budget.

Fault Tolerance Structures in Wireless Sensor Networks (WSNs): Survey, Classification, and Future Directions.

The Industrial Revolution 4.0 (IR 4.0) has drastically impacted how the world operates. The Internet of Things (IoT), encompassed significantly by the Wireless Sensor Networks (WSNs), is an important subsection component of the IR 4.0. WSNs are a good demonstration of an ambient intelligence vision, in which the environment becomes intelligent and aware of its surroundings. WSN has unique features which create its own distinct network attributes and is deployed widely for critical real-time applications that require stringent prerequisites when dealing with faults to ensure the avoidance and tolerance management of catastrophic outcomes. Thus, the respective underlying Fault Tolerance (FT) structure is a critical requirement that needs to be considered when designing any algorithm in WSNs. Moreover, with the exponential evolution of IoT systems, substantial enhancements of current FT mechanisms will ensure that the system constantly provides high network reliability and integrity. Fault tolerance structures contain three fundamental stages: error detection, error diagnosis, and error recovery. The emergence of analytics and the depth of harnessing it has led to the development of new fault-tolerant structures and strategies based on artificial intelligence and cloud-based. This survey provides an elaborate classification and analysis of fault tolerance structures and their essential components and categorizes errors from several perspectives. Subsequently, an extensive analysis of existing fault tolerance techniques based on eight constraints is presented. Many prior studies have provided classifications for fault tolerance systems. However, this research has enhanced these reviews by proposing an extensively enhanced categorization that depends on the new and additional metrics which include the number of sensor nodes engaged, the overall fault-tolerant approach performance, and the placement of the principal algorithm responsible for eliminating network errors. A new taxonomy of comparison that also extensively reviews previous surveys and state-of-the-art scientific articles based on different factors is discussed and provides the basis for the proposed open issues.

An improved incipient whale optimization algorithm based robust fault detection and diagnosis for sensorless brushless DC motor drive under external disturbances

In general, unexpected failures in sensorless brushless DC (BLDC) motors can result in production downtime, costly repairs, and safety concerns. BLDC motors are commonly used in home appliances, the medical sector, aerospace, small-scale, and large-scale industries under uncertain operating conditions. Therefore, the fault detection and diagnosis (FDD) of BLDC motor drives can play a very important role in increasing their performance, reliability, robustness control, and operational safety under uncertain operating conditions in critical real-time applications. To satisfy these issues of hall effect sensor, misplacement of a hall-effect sensor, inverter IGBT open-switch fault diagnosis, failure of hall effect sensor, lack of robustness speed control of BLDC motor, which has received substantial interest in academic and industry sectors to establish the proposed work optimization techniques approach FDD strategy for speed control of sensorless BLDC motor under uncertain operating conditions. The proposed optimization techniques such as Bat Algorithm (BA), Grey Wolf Optimization (GWO), and Whale Optimization Algorithm (WOA) approach FDD strategies for BLDC motor drives. These FDD strategies simulated by the above optimization techniques on a sensorless BLDC motor with numerical Matlab/Simulink 2020a simulation results are verified. From the simulation results, out of three optimization techniques, the WOA-based FDD strategies are very effective for both bearing and stator winding faults detection and diagnosis in sensorless BLDC motor drives.

Adaptive Multi-Applications Cryptographic System

Cryptography is the core method utilized to protect the communications between different applications, terminals, and agents distributed worldwide and connected via the internet. Yet, with the distribution of the low-energy and low-storage devices, in the Internet-of-Things (IoT), the cryptography protocols cannot be implemented because of the power constraints or because the implementation is beyond the time constraints that hindered their usability of these protocols in real-time critical applications. To solve this problem, an Adaptive Multi-Application Cryptography System is proposed in this paper. The proposed system consists of the requirements identifier and the implementer, implemented on the application and transportation layer. The requirement identifier examines the header of the data, determines the underlying application and its type. The requirements are then identified and encoded according to four options: high, moderate, low, and no security requirements. The inputs are processed, and ciphertext is produced based on the identified requirements and the suitable cryptography algorithm. The results showed that the proposed system reduces the delay by 97% relative to the utilized algorithms' upper-bound delay. Keywords: Cryptography, symmetric key encryption, block cipher, delay and performance, quantum computing.

Deadline-Constrained Tasks’ Scheduling in Multi-core Systems Using Harmonic-Aware Load Balancing

In highly advanced real-time critical applications, the demand of multi-core processing is increasing as the tasks are assigned to cores in the most balanced manner. The balancing of tasks on the cores requires an efficient load balancing algorithm. To balance the loads amongst the cores, all harmonic tasks can be grouped together and shall be assigned on a single core. The concept of harmonic task set is effective as it tends to reach a utilization of one, and thus, the system achieves a higher utilization. The proposed paper is focused on harmonic-aware load balancing algorithm for a set of periodic real-time tasks having constrained deadlines, where the deadline of the tasks is less than the period of the tasks. The extensive analysis was performed to establish the superiority of harmonic task sets in real-time applications. The results of this analysis are reported in this paper. It was observed that by considering the tasks’ harmonic relationship, the proposed load balancing approach greatly improves the feasibility of real-time tasks on a multi-core processor to meet their deadlines.

Proposed Fuzzy Real-Time HaPticS Protocol Carrying Haptic Data and Multisensory Streams

Sensory and haptic data transfers to critical real-time applications over the Internet require better than best effort transport, strict timely and reliable ordered deliveries. Multi-sensory applications usually include video and audio streams with real-time control and sensory data, which aggravate and compress within real-time flows. Such real-time are vulnerable to synchronization to synchronization problems, if combined with poor Internet links. Apart from the use of differentiated QoS and MPLS services, several haptic transport protocols have been proposed to confront such issues, focusing on minimizing flows rate disruption while maintaining a steady transmission rate at the sender. Nevertheless, these protocols fail to cope with network variations and queuing delays posed by the Internet routers.
 This paper proposes a new haptic protocol that tries to alleviate such inadequacies using three different metrics: mean frame delay, jitter and frame loss calculated at the receiver end and propagated to the sender. In order to dynamically adjust flow rate in a fuzzy controlled manners, the proposed protocol includes a fuzzy controller to its protocol structure. The proposed FRTPS protocol (Fuzzy Real-Time haPticS protocol), utilizes crisp inputs into a fuzzification process followed by fuzzy control rules in order to calculate a crisp level output service class, denoted as Service Rate Level (SRL). The experimental results of FRTPS over RTP show that FRTPS outperforms RTP in cases of congestion incidents, out of order deliveries and goodput.

Time-Randomized Wormhole NoCs for Critical Applications

Wormhole-based NoCs (wNoCs) are widely accepted in high-performance domains as the most appropriate solution to interconnect an increasing number of cores in the chip. However, wNoCs suitability in the context of critical real-time applications has not been demonstrated yet. In this article, in the context of probabilistic timing analysis (PTA), we propose a PTA-compatible wNoC design that provides tight time-composable contention bounds. The proposed wNoC design builds on PTA ability to reason in probabilistic terms about hardware events impacting execution time (e.g., wNoC contention), discarding those sequences of events occurring with a negligible low probability. This allows our wNoC design to deliver improved guaranteed performance w.r.t. conventional time-deterministic setups. Our results show that performance guarantees of applications running on top of probabilistic wNoC designs improve by 40% and 93% on average for 4 × 4 and 6 × 6 wNoC setups, respectively.

An efficient method of computation offloading in an edge cloud platform

In a data-rich digital world, our hand-held resource-constrained mobile devices are restricted to performing small-to-medium-level computation processes and are incapable of performing high-computation processes. Computation offloading is a suitable solution for overcoming this shortcoming. Until recently, we have perceived cloud computing as an appropriate computation-offloading platform for mobile devices. However, cloud data centers, being far-end networks for mobile devices, increase the latency or network delay, which in turn affects the performance of real-time mobile Internet-of-Things applications. Hence, for critical real-time applications, a near-end network approach of computation offloading is required. Furthermore, the major hurdles for geographically distributed mobile devices are mobility and heterogeneity in the process of computation offloading. To overcome these challenges, the use of a deep-learning-based response-time-prediction framework is proposed in this paper to determine whether to offload in the nearby fog/edge node or neighbor fog/edge node, or cloud node. Furthermore, a restricted Boltzmann machines learning is applied to tackle the randomness in the availability of resources. We simulate the proposed model in MATLAB while considering the mobility and fluctuating resource demands of the end users. Implementing our deep-learning-based response-time-prediction framework improves the performance of the computation offloading because it facilitates a prompt selection of the offloading location.

Novel Learning Algorithms for Efficient Mobile Sink Data Collection Using Reinforcement Learning in Wireless Sensor Network

Generally, wireless sensor network is a group of sensor nodes which is used to continuously monitor and record the various physical, environmental, and critical real time application data. Data traffic received by sink in WSN decreases the energy of nearby sensor nodes as compared to other sensor nodes. This problem is known as hot spot problem in wireless sensor network. In this research study, two novel algorithms are proposed based upon reinforcement learning to solve hot spot problem in wireless sensor network. The first proposed algorithm RLBCA, created cluster heads to reduce the energy consumption and save about 40% of battery power. In the second proposed algorithm ODMST, mobile sink is used to collect the data from cluster heads as per the demand/request generated from cluster heads. Here mobile sink is used to keep record of incoming request from cluster heads in a routing table and visits accordingly. These algorithms did not create the extra overhead on mobile sink and save the energy as well. Finally, the proposed algorithms are compared with existing algorithms like CLIQUE, TTDD, DBRkM, EPMS, RLLO, and RL‐CRC to better prove this research study.

High accuracy block-matching sub-pixel motion estimation through detection of error surface minima

The present paper focuses on high-accuracy block-based sub-pixel motion estimation utilizing a straightforward error minimization approach. In particular, the mathematics of bilinear interpolation are utilized for the selection of the candidate motion vectors that minimize the error criterion, by estimating local minima in the error surface with arbitrary accuracy. The implemented approach favors optimum accuracy over computational load demands, making it ideal as a benchmark for faster methods to compare against; however, it is not best suited to real-time critical applications (i.e. video compression). Other video processing needs relying on motion vectors and requiring high-resolution/accuracy can also take advantage of the proposed solution (and its simplified nature in terms of underlying theoretical complexity), such as motion-compensation filtering for super resolution image enhancement, motion analysis in sensitive areas (e.g. high-speed video monitoring, medical imaging, motion analysis in sport science, big-data visual surveillance, etc.). The proposed method is thoroughly evaluated using both real video and synthetic motion sequences from still images, adopting well-tested block-based motion estimation evaluation procedures. Assessment includes comparisons to a number of existing block-based methods with respect to PSNR and SSIM metrics over ground-truth samples. The conducted evaluation takes into consideration both the original (arbitrary-accuracy) and the truncated motion vectors (after rounding them to the nearest half, quarter, or eighth of a pixel), where superior performance with more accurate motion vector estimation is revealed. In this context, the degree to which sub-pixel motion estimation methods actually produce sub-pixel motion vectors is investigated, and the implications thereof are discussed.

Estimation of Remaining Useful Life of Bearings based on Support Vector Regression

The overall performance metric of rotating machineries are governed by the reliability of bearings. Bearings are vital components for all moving parts. It has its presence in most of the equipments and machineries. Also, these bearings contribute to most of the failures or breakdowns in an industry. Failures can be reduced to a greater extent by selecting appropriate bearings that suit to the application. Nevertheless, after selection of right bearings, the failure in the bearings tops the list. It becomes complicated when we want to trace out the reasons for failures. Condition monitoring techniques are being deployed in order to increase the uptime of the machineries. Objectives: Strengthening the predictive maintenance by estimating the remaing useful life of bearings. Method: This paper proposes a predictive model to address the remaining life of the bearing that suits to a real time application. This method is validated on a laboratory experiment wherein the bearing is tested till it fails naturally at stated conditions. Findings: Thus obtained results show the model built using Support Vector Regression method proves to be effective in predicting the remaining life of the bearings. Applications/Improvements: The proposed predictive model is validated with the new set of data taken from experiments. This model can be deployed in critical real time applications where the bearing failure affects the performance of the machine. Addittionaly this model can be horizontally deployed for other critical components where continuous monitoring is essential.

Sparse frame DOA estimations via a rank-one correlation model for low SNR and limited snapshots

As a typical problem of sparse frame representations or compressed sensing with frames, direction of arrival (DOA) estimations, via sparse recovery methodologies such as nonlinear optimizations or various greedy algorithms, suffer seriously under severe noisy measurement without proper treatment. In this article, a crucial and effective correlation operation is outlined to mitigate the severe noise effect from the sparse representation point of view. A fast and super resolution method for DOA estimations is therefore established under very low signal-to-noise ratio, and by a sparse recovery technique of null space tuning in the context of compressed sensing and sparse representations. Improvement to the technique using the thresholding difference and alternating grid refinements are also outlined to estimate the source/target numbers dynamically and to improve the precision. Another characteristic is that only a very small number of snapshots are needed in comparison with other techniques. Simulation results demonstrate apparent advantages of the proposed technique over known approaches. The proposed method has the effectiveness at simultaneous high resolution, robustness to noise, and source number estimations. The algorithm is also computationally efficient, which is critical for large array systems and/or mission critical real-time applications.

Reliability and Performance Analysis of Architecture-Based Software Implementing Restarts and Retries Subject to Correlated Component Failures

High reliability and performance are essential attributes of software systems designed for critical real-time applications. To improve the reliability and performance of software, many systems incorporate some form of fault recovery mechanism. However, contemporary models of software reliability and performance rarely consider these fault recovery mechanisms. Another notable shortcoming of many software models is that they make the simplifying assumption that component failures are statistically independent, which disagrees with several experimental studies that have shown that the failures of software components can exhibit correlation. This paper presents an architecture-based model of software reliability and performance that explicitly considers a two-stage fault recovery mechanism implementing component restarts and application-level retries. The application architecture is characterized by a Discrete Time Markov Chain (DTMC) to represent the dynamic branching behavior of control between the components of the application. Correlations between the component failures are computed with an efficient numerical algorithm for a multivariate Bernoulli (MVB) distribution. We illustrate the utility of the model through a case study of an embedded software application. The results suggest that the model can be used to quantify the impact of software fault recovery and correlated component failures on application reliability and performance.

LFDS: Scalable and High Performance Logging for Mission Critical Real Time Applications

In the world of connected enterprises and Internet of Things (IOT), millions of users and devices are connecting and transacting online simultaneously. Further, introduction of multi-core hardware platforms resulted in multi-fold increase in processing speed and volumes. To support the increasing volumes generated, building end-end-end scalable business applications has become the key focus of these service organizations. The reliability expectation of these systems is 100% and hence persisting of transaction information and key activities information is crucial to the success of the business applications. However, the performance of such software applications is inherently limited by disk input/output (I/O). Often, CPU activity gets suspended till I/O activity completes. Redesigning and tuning I/O can enhance application performance significantly. This paper presents our approach of ‘Log Flush Daemon Service’ (LFDS) in which application takes control of the I/O by taking it off the main transaction path along with hybrid of approaches from the techniques for optimization of the ancillary tasks of logging. This helps to enhance the performance, reduce the jitter and outliers.

Priority-Based Dynamic Spectrum Management in a Smart Grid Network Environment

The heterogeneous smart grid (SG) poses two major challenges for wireless networks, namely, providing sufficient bandwidth for a wide variety of applications and high reliability for critical real-time applications. To address these challenges, the impact of communication outage on the demand response management as a typical SG application is analyzed in this paper. A dynamic spectrum management (DSM) technique is proposed to allocate resources, considering the QoS and application priorities. Vacant digital TV frequency bands are utilized to support SG applications. An algorithm to estimate the SG capacity is introduced, which can be applied to various user distributions and SG environments. This is used in conjunction with a low-complexity coloring theory algorithm to allocate the spectrum. The results presented show that DSM provides better performance than traditional fixed spectrum management, in terms of QoS and secondary spectrum utilization.