The integration of Energy Harvesting (EH) technology into Mobile Edge Computing (MEC) presents a promising solution to the energy limitations faced by end devices (EDs) when performing computation-intensive tasks, ultimately enhancing the EDs’ sustainability. However, the intermittent and unpredictable nature of harvested energy introduces significant uncertainty in energy availability, complicating dynamic task execution and resource management. In EH-MEC systems, managing task scheduling and offloading dynamically is crucial for optimizing application latency while ensuring long-term battery energy stability and task reliability. Existing approaches inadequately address the time-coupling between task decisions caused by long-term battery energy stability constraints, and often neglect task reliability considerations. To overcome these limitations, we propose decomposing the original problem into 1) a decoupling problem that transforms the optimization with long-term battery energy constraints into a series of deterministic optimizations within individual time slots, 2) a task scheduling problem that determines task-to-ES assignment and computing resource allocation of ESs to offloaded tasks, and 3) a task offloading problem that determines the optimal offloading decision to achieve minimal latency while meeting energy stability and server reliability constraints. To tackle these subproblems, we design a Lyapunov-based optimization method, a reliabilityaware task scheduling algorithm, and an efficient heuristic-based task offloading algorithm. Extensive simulations and experiments based on empirical data from a physical MEC testbed validate the efficacy of our approach.

Deep neural networks (DNNs) have demonstrated exceptional performance, leading to diverse applications across various mobile devices (MDs). Considering factors like portability and environmental sustainability, an increasing number of MDs are adopting energy harvesting (EH) techniques for power supply. However, the computational intensity of DNNs presents significant challenges for their deployment on these resource-constrained devices. Existing approaches often employ DNN partition or offloading to mitigate the time and energy consumption associated with running DNNs on MDs. Nonetheless, existing methods frequently fall short in accurately modeling the execution time of DNNs, and do not consider to use thread allocation for further latency and energy consumption optimization. To solve these problems, we propose a dynamic DNN partition and thread allocation method to optimize the latency and energy consumption of running DNNs on EH-enabled MDs. Specifically, we first investigate the relationship between DNN inference latency and allocated threads and establish an accurate DNN latency prediction model. Based on the prediction model, a DRL-based DNN partition (DDP) algorithm is designed to find the optimal partitions for DNNs. A thread allocation (TA) algorithm is proposed to reduce the inference latency. Experimental results from our test-bed platform demonstrate that compared to four benchmarking methods, our scheme can reduce DNN inference latency and energy consumption by up to 37.3% and 38.5%.

The widespread adoption of Deep Neural Networks (DNNs) across diverse applications has intensified the demand for efficient execution strategies on GPU-CPU heterogeneous devices. While existing device-oriented DNN partitioning methods optimize either energy consumption or execution latency in isolation, they often lack the capability to dynamically adapt partitioning strategies under real-world constraints. To address these limitations, we first formulate the DNN partitioning problem as an optimal execution path search on a directed acyclic graph (DAG), then propose an imitation learning (IL)-based DNN partitioning framework that dynamically allocates DNN layers across GPU-CPU processors to minimize energy consumption while satisfying time constraints. Specifically, we first design aProfiler, which analyzes the layer-wise characteristics such as the execution time and energy consumption of layers in DNNs executed on the GPU-CPU heterogeneous device. Then, we present anOracle Generatorthat generates high-quality partitioning solutions based on the Dijkstra algorithm to form a training datasetOracle.Oraclefrom the proposed generator is input to a proposed Trainer, which iteratively learns from theOracledata to obtain a regression model namedPredictor.Predictorcan predict the optimal partitioning strategy for DNNs in real time. Finally, we design aData Aggregator, which enhancesOracledata through continuous runtime feedback, thereby improving the prediction accuracy of the regression model. We evaluate the proposed IL-based DNN partitioning method on 3 NVIDIA Jetson platforms and 1 Huawei NPU platform. Experimental results demonstrate that compared to 3 benchmarking methods, our method reduces energy consumption by up to 73.15%.

As smart mobile applications increasingly demand timely situational awareness and energy efficiency, the Age of Information (AoI) metric plays a vital role in maintaining data freshness. This need is further supported by the End-Edge-Cloud Computing (EECC) paradigm, which enhances application performance by facilitating task offloading to the edge or the cloud. However, existing AoI optimization solutions focus solely on task offloading, often neglecting critical aspects such as system resource allocation and energy efficiency, which can lead to resource waste, increased energy consumption, compromised Quality of Service (QoS), and system performance degradation. Therefore, this paper investigates the joint optimization of task offloading, communication and computing resource allocation in EECC systems, aiming to minimize AoI and energy consumption under constraints of deadlines and capacity constraints. To address this problem, we divide the decision space into multiple non-intersecting decision areas based on the characteristics of the studied problem and design a task offloading and resource allocation algorithm based on slow-movement particle swarm optimization (SPSO) to handle each decision area individually. In the algorithm design, we customize the position, velocity, update rules, and fitness function for the optimization problem. Finally, extensive simulation-based and testbed experiment results show that the proposed algorithm can save up to 14.56% of energy consumption, shorten AoI by up to 27.80%, and improve utility (weighted sum of AoI and energy consumption) by up to 15.89% compared with existing algorithms.

This letter focuses on integrated CPU-GPU edge systems with renewable energy sources and studies the resource management problem to minimize the energy consumption of real-time tasks while ensuring temperature and reliability constraints. We propose an imitation learning (IL)-based resource management scheme, ILRM, implemented in two phases: 1) offline Oracle generation and 2) online IL. In the offline phase, we design a fast-converging heuristic to generate near-optimal solutions (i.e., Oracles) for training an online prediction model. In the online phase, we realize IL using the trained model that predicts the resource configuration policies for the incoming task sets to be scheduled. A data aggregation method is also developed to enhance the robustness of the prediction model. We validate ILRM through extensive experiments on both simulated and real integrated CPU-GPU edge platforms.

Deep learning as a service (DLaaS) that promotes deep learning-based applications by selling computing services from IT companies to end-users has introduced potential privacy leaks from users and cloud servers. Federated learning (FL) provides an emerging distributed paradigm that enables numerous users to collaboratively train deep-learning models while protecting user privacy and data security. However, many FL-related existing works only focus on improving communication bottlenecks due to frequent model parameter transmission, but ignore the performance degradation incurred by imbalanced user distribution and high inference latency due to the high complexity of deep-learning models in the emerging IoT-edge-cloud FL. In this paper, we propose an efficient user-distribution-aware hierarchical FL for communication-efficient training and fast inference in the IoT-edge-cloud DLaaS architecture. Specifically, we propose a user-distribution-aware hierarchical FL architecture to cope with the performance degradation owing to the imbalanced user distribution. The proposed architecture also features a lightweight deep neural network that adopts the designed lightweight fire modules as components and has a side branch for communication-efficient training and fast inference. Extensive experiments demonstrate that the proposed schemes significantly boost the accuracy by up to 67.12%, save 47.98% communication costs, and accelerate inference by up to 87.24$\boldsymbol{\times}$compared to benchmarking methods.

In recent decades, the rapid advances in information technology have promoted a widespread deployment of medical cyber-physical systems (MCPS), especially in the area of digital healthcare. In digital healthcare, medical edge devices empowered by CPU-GPU (Graphics Processing Unit) cooperative multiprocessor system-on-chips (MPSoCs) have a great potential in processing and managing the massive amounts of health-related data. However, most of the existing works on CPU-GPU cooperative MPSoCs cannot maintain a high-precision workload estimation since they simply leverage the worst-case execution cycles to pessimistically predict the workload of digital healthcare applications. Besides, they neglect the personalized requirements of individual healthcare applications and the lifetime reliability demands of heterogeneous CPU-GPU cores. As a result, the normal functions of medical edge devices and the quality-of-services (QoS) of digital healthcare applications are likely to suffer from underlying failures and degradation. In this paper, we explore CPU-GPU cooperative QoS optimization of personalized digital healthcare applications running on reliability guaranteed edge devices with the help of machine learning and swarm intelligence techniques. We first develop two novel predictors: one is a machine learning based predictor for application workload estimation, and the other is a feature-driven predictor for application QoS estimation. We then incorporate the two predictors into a swarm intelligent application scheduling scheme upon the cooperative dual-population evolutionary algorithm (c-DPEA) to find optimal application mapping and partitioning settings. Experimental results show that our solution not only augments the average QoS of whole digital healthcare applications by 15.7%, but also balances the QoS of individual digital healthcare applications by 64.3%.

The market penetration of Infrastructure-as-a-Service (IaaS) in cloud computing is increasing benefiting from its flexibility and scalability. One of the most important issues for IaaS cloud service providers is to minimize the monetary cost while meeting cloud user experience requirements such as makespan and security. Prior works on cloud service cost minimization ignore either security or makespan which is very important for user experience. In this paper, we propose a two-stage algorithm to solve the cloud service cost minimization problem at the premise of satisfying the security and makespan requirements of cloud users. Specifically, in the first stage, we propose a novel security service selection scheme to ensure system security by judiciously selecting security services with low cost for tasks under the constraints of time and security. In the second stage, to further reduce the cloud service cost, we design a workflow scheduling method based on an improved firefly algorithm (IFA). The IFA-based method schedules cloud service workflows to virtual machines of small cost at the premise of guaranteeing security and makespan. It can quickly find the workflow scheduling solution with minimized cost using our designed updating scheme and mapping operator. Extensive simulations are conducted on real-world workflows to verify the efficacy of the proposed two-stage method. Simulation results show that the proposed two-stage method outperforms the baseline and two benchmarking methods in terms of cost minimization without violating security and time constraints. Compared to benchmarking methods, the cloud service cost can be reduced by up to 57.6% by using our proposed approach.

In the era of the Internet of Things (IoT), spatially distributed IoT devices collect and store data in a distributed fashion for computational efficiency. However, in IoT networks, due to the fragile device, harsh deployment environment, and unreliable transmission, the possibility of missing data is increasing, which may significantly affect subsequent data processing. Traditional approaches to impute missing data in IoT distributed data sets bring huge communication overheads. In this article, we develop an efficient architecture for distributed IoT data imputation based on a designed multidiscriminator conditional generative adversarial network. The architecture intelligently learns the characteristics of the distributed data sets to accurately impute missing values. Our experiments are performed using three data sets under two different data missing mechanisms. The experimental results demonstrate that using three data sets, the proposed imputation technique can drastically reduce the imputation error by up to 88.66%, 94.27%, and 95.53% at the premise of low transmission cost, respectively, compared to five state-of-the-art methods.

Artificial intelligence-based cyber-physical systems (CPS) applications have been spread across various fields such as smart cities, medical services, and industrial controls. When CPS devices are connected to a cloud server, big data streams generated by CPS devices impose enormous bandwidth pressure and exert excessive compute loads to the cloud server. Due to unpredictable environments and uncertainty in reality, these issues are mainly attributed to a large amount of high noise data captured and uploaded by CPS devices. To overcome these issues, this paper proposes a cyber-physical-cloud based framework for distributed deep neural networks (DDNNs) to prevent high noise data from being uploaded to the cloud. The proposed framework features a lightweight data filtering module enabled by depthwise separable convolutions to identify and filter out the high noise data that the cloud cannot recognize. Extensive experimental results demonstrate that the proposed data filtering module can achieve an accuracy of up to 83.72% in identifying high noise data and the proposed framework can effectively save bandwidth of up to 63.42% as compared to benchmarking methods. Note to Practitioners—This paper is motivated by the problems of enormous bandwidth pressure and excessive cloud compute loads in cyber-physical-cloud distributed computing paradigms. These problems are mainly caused by high noise data generated by CPS devices, because CPS devices often work in disturbing and unstable environments and there are uncontrollable uncertainties in reality. Especially for the emerging artificial intelligence-driven cyber-physical-cloud distributed paradigms, there is no existing research to solve the unnecessary transmission and cloud compute loads caused by high noise data. To tackle the challenge, this paper develops a novel cyber-physical-cloud distributed framework with data filtering capabilities to prevent high noise data from being uploaded. The proposed framework supports two popular loosely coupled and closely coupled distributed computing paradigms. Extensive experiments confirm that the proposed cyber-physical-cloud distributed framework can efficiently filter out high noise data and alleviate unnecessary transmission and needless cloud compute loads introduced by high noise data.

As the backbone of Industry 4.0, industrial cyber-physical systems (ICPSs) that are geographically dispersed, federated, cooperative, and security-critical systems become the center of interest from both industry and academia. In ICPS, there are huge amounts of devices, such as sensors and actuators, which are embedded and networked together to improve the performance of real-time monitoring and control. Reliability and temperature are two important concerns of these embedded and networked devices in ICPS due to their stringent requirement of reliable execution and long lifespan. In this article, we study the problem of maximizing soft-error reliability of CPU- and GPU-integrated embedded platforms deployed in ICPS under the temperature constraint. To speed up the estimation of soft-error rate (SER) and temperature, we train an artificial neural network (ANN) that is able to quickly and accurately derive the system’s SER and temperature. To solve the temperature-constrained reliability optimization problem, we propose a feedback control-based task scheduling scheme that adaptively determines the number of tasks admitted in the system and the number of replicas for the admitted tasks. We perform a series of simulation experiments to verify the efficacy of our scheme. The experimental results demonstrate that: 1) the estimated SER and temperature derived by our ANN-based method are very close to the ground-truth data and 2) our proposed feedback control-based task scheduling method can improve system reliability by up to 184.2% with a lower peak temperature when compared with one baseline and two state-of-the-art methods. Note to Practitioners—This article is motivated by the safety-critical industrial cyber-physical system (ICPS) applications necessitating reliable execution and long lifespan, which could be realized by increasing reliability and controlling operating temperature. Our goal is to improve the system reliability of CPU- and GPU-integrated multiprocessor systems-on-chip (MPSoCs) deployed in ICPS under the temperature constraint. Most of the existing papers target either reliability or temperature. A few recent papers have focused on reliability and temperature optimization simultaneously. However, they are not designed for ICPS and do not consider the widely accepted CPU- and GPU-integrated MPSoC platforms. This article proposes a machine learning-based approach that trains an artificial neural network (ANN) to facilitate the online estimation of system SER and temperature. Compared to the offline estimation using simulation tools, the online approach is more applicable to real-time ICPS applications. This article also designs a feedback control-based approach for improving system reliability and reducing peak temperature of the CPU- and GPU-integrated MPSoCs by determining the number of tasks to be admitted and the number of replicas for tasks.

Due to the great advancement in computation, communication, and control technologies, the Internet of Things (IoT) can provide ubiquitous connectivity for anyone and anything at any time and any place, leading to a revolution in an information society. Protecting devices against various security threats is one of the most important challenges in IoT since IoT applications are generally security-critical systems while IoT devices are often poorly secured. For IoT devices, employing security services provided by smart gateways or edge/cloud servers to defend against various threats is an effective way to enhance their security. However, the finite battery energy of devices and the limited fund of device users hinder the wide application of security services in IoT. This necessitates the demand for designing new methodologies to tackle the tradeoff among security, energy, and fund of IoT devices. Therefore, this article attempts to optimize system security of IoT devices under energy and fund constraints. Specifically, to formulate the energy and fund constrained security optimization problem, we first propose a pricing model for the security services provided by the smart gateway. We then formulate the problem as a mixed-integer linear programming (MILP) problem. Since using a solver to address the MILP problem may be time consuming, we leverage the swarm intelligence technique to design a new task scheduling scheme that can efficiently solve the optimization problem. Extensive experiments are conducted to validate our proposed MILP and swarm intelligence-based task scheduling algorithms. Simulation results show that our scheme outperforms two state-of-the-art methods in improving system quality of security and guaranteeing schedule feasibility.

Maximizing profit is a key goal for cloud service providers in the modern cloud business market. Service revenue and business cost are two major factors in determining profit and highly depend on multiserver configuration. Understanding the relationship between multiserver configuration and profit is important to service providers. Although existing articles have explored this issue, few of them consider deadline miss rate and soft error reliability of cloud services in multiserver configuration for profit maximization. Since deadline misses violate cloud services’ real-time requirements and soft error prevents successful processing of cloud services, it is necessary to consider the impact of deadline miss rate and soft error reliability on service providers’ profits when configuring the multiserver. This article introduces a deadline miss rate and soft error reliability aware multiserver configuration scheme for maximizing cloud service providers’ profit. Specifically, we derive the deadline miss rate considering the heterogeneity of cloud service requests, and propose an analytical method to compute the soft error reliability of multiserver systems. Based on the new deadline miss rate and soft error reliability models, we formulate the multiserver configuration optimization problem and introduce an augmented Lagrange multiplier-based iterative method to find the optimal multiserver configuration. Extensive experiments evaluate the efficacy of the proposed multiserver configuration approach. Compared with the two state-of-the-art methods, the profit gained by our scheme can be up to 11.92% higher.

As the density of integrated circuits continues to increase, the possibility that real-time systems suffer from soft and hard errors rises significantly, resulting in a degraded availability of system. In this article, we investigate the dynamic modeling of cross-layer soft error rate based on the Back Propagation (BP) neural network, and propose optimization strategies for system availability based on Cross Entropy (CE) and Q-learning algorithms. Specifically, the BP neural network is trained using cross-layer simulation data obtained from SPICE simulation while the optimization for system availability is achieved by judiciously selecting an optimal supply voltage for processors under timing constraints. Simulation results show that the CE-based method can improve system availability by up to 32 percent compared to state-of-the-art methods, and the Q-learning-based algorithm can further enhance system availability by up to 20 percent compared to the proposed CE-based method.

In the past few years, the study on placing edge servers for response time optimization in mobile edge-cloud computing systems has become increasingly popular. Most of the existing schemes neglect two important aspects: one is the heterogeneity of edge/cloud servers and the other is the response time fairness of base stations, which may significantly degrade the system quality of services to mobile users. In this article, we conduct the study of deploying heterogeneous edge servers to optimize the expected response time of both the whole and individual base stations. We propose an approach consisting of offline and online stages. At the offline stage, the optimal placement strategy of heterogeneous edge servers is produced by using an integer linear programming technique. At the online stage, a mobility-aware game-theory-based method is developed to deal with the dynamic characteristic of user movement. Experimental results reveal that compared to benchmarking methods, our approach not only reduces system-expected response time by 47.37%, but also improves response time fairness of base stations by 71.60%.

Data mining techniques have been widely applied to various fields including industrial, business, and governmental applications. Missing data is a common occurrence in a number of real-world databases, which may substantially affect the accuracy of data processing. In this paper, we propose a novel approach for missing data estimation by efficiently exploring inter-sensor correlation. Namely, given multiple sensors for data collection, we attempt to recover the missing data of a few sensors by using the measurement data from other sensors. Towards this goal, we develop an iterative solver for missing data estimation. Our numerical experiments on two industrial datasets demonstrate that the proposed method can reduce the imputation error by up to 7.25× compared to a conventional method in the literature.

3-D multiprocessor system-on-chip (MPSoC) systems can offer higher integration density, lower interaction cost, better bandwidth, and greater performance. However, vertically stacked silicon layers and limited heat dissipation paths result in high peak temperature and large temperature variation, which incur reliability reduction, lifetime decay, and performance degradation. In this article, we propose an offline augmented cross-entropy (CE)-based task scheduling strategy to jointly optimize peak temperature and temperature variation under the constraint of timeliness. Specifically, based on the conventional CE method, a heuristic iterative sampling method is designed to explore task-to-core assignment for balanced heat distribution between the top-layer and the bottom-layer cores. Subsequently, thermal characteristics of 3-D MPSoC systems are used to judiciously swap tasks between the two layers to improve the conventional CE-based task assignment and accelerate the iterative process. The peak temperature of individual cores is further reduced via sequencing, splitting, and slacking task execution. The experimental results demonstrate that compared to the existing state-of-the-art methods, the proposed scheme can reduce peak temperature by up to 8.02 °C and temperature variation by up to 24.78% without violating the timeliness of tasks.

As the density of integrated circuits continues to increase, the possibility that real-time systems suffer from transient and permanent failures rises significantly, resulting in a degraded availability of system functionality. In this paper, we investigate the dynamic modeling of transient failure rate based on Back Propagation (BP) neural network, and propose an optimization strategy for system availability based on Cross Entropy (CE). Specifically, the neural network is trained using cross-layer simulation data obtained from SPICE simulation while the CE-based optimization for system functionality availability is achieved by judiciously selecting an optimal supply voltage for processors under timing constraints. Simulation results show that the proposed method can achieve system availability improvement of up to 32% compared to benchmarking methods.

With the advent of heterogeneous multiprocessor architectures, efficient scheduling for high performance has been of significant importance. However, joint considerations of reliability, temperature, and stochastic characteristics of precedence-constrained tasks for performance optimization make task scheduling particularly challenging. In this paper, we tackle this challenge by using an affinity (i.e., probability)-driven task allocation and scheduling approach that decouples schedule lengths and thermal profiles of processors. Specifically, we separately model the affinity of a task for processors with respect to schedule lengths and the affinity of a task for processors with regard to chip thermal profiles considering task reliability and stochastic characteristics of task execution time and intertask communication time. Subsequently, we combine the two types of affinities, and design a scheduling heuristic that assigns a task to the processor with the highest joint affinity. Extensive simulations based on randomly generated stochastic and real-world applications are performed to validate the effectiveness of the proposed approach. Experiment results show that the proposed scheme can reduce the system makespan by up to 30.1% without violating the temperature and reliability constraints compared to benchmarking methods.

EtherCAT has become one of the leading real-time Ethernet solutions for networked industrial systems, where a reliable communication infrastructure is needed due to highly error-prone environments. However, existing work on EtherCAT mainly focuses on clock synchronization and timeliness improvement. The reliability of EtherCAT-based networked systems has largely been ignored. In this paper, we present a proportional integral derivative (PID)-based feedback control scheme that aims at enhancing reliability of networked systems under timing and system resource constraints. Instead of retransmitting data upon error detection, we use forward error control technique based on inequality of arithmetic and geometric means to achieve the required system reliability at a low deadline miss rate of messages. We further optimize the forward error control technique and design a fast and fair error resilient mechanism by using a cooperative game. In addition to reliability enhancement, our PID-based error control scheme can also improve the stability of a system in terms of deadline miss rate in the presence of burst errors. Simulation results show that the proposed scheme can achieve reliability enhancement of up to 91% compared to benchmarking methods.

EtherCAT has become one of the leading real-time Ethernet solutions for networked industrial systems where a reliable communication infrastructure is needed due to highly error-prone environments. However, existing work on EtherCAT mainly focuses on clock synchronization and timeliness improvement. The reliability of EtherCAT-based networked systems has largely been ignored. In this paper, we present a PID-based feedback control scheme that aims at enhancing reliability of networked systems under timing and system resource constraints. Instead of automatic repeat request method (ARQ), a forward error control technique is introduced to achieve the required system reliability at a lower deadline miss rate of messages. The PID-based feedback control scheme can also improve the stability of a system in terms of deadline miss rate in the presence of bursty errors. Simulation results show that the proposed scheme can achieve reliability enhancement of up to 79% compared to benchmarking methods.

With the rapid deployment of cloud computing infrastructures, understanding the economics of cloud computing has become a pressing issue for cloud service providers. However, existing pricing models rarely consider the dynamic interactions between user requests and the cloud service provider. Thus, the law of supply and demand in marketing is not fully explored in these pricing models. In this paper, we propose a dynamic pricing model based on the concept of user perceived value that accurately captures the real supply and demand relationship in the cloud service market. Subsequently, a profit maximization scheme is designed based on the dynamic pricing model that optimizes profit of the cloud service provider without violating service-level agreement. Finally, a dynamic closed loop control scheme is developed to adjust the cloud service price and multiserver configurations according to the dynamics of the cloud computing environment such as fluctuating electricity and rental fees. Extensive simulations using the data extracted from real-world applications validate the effectiveness of the proposed user perceived value-based pricing model and the dynamic profit maximization scheme. Our algorithm can achieve up to 31.32 percent profit improvement compared to a state-of-the-art approach.

With the rapid deployment of cloud computing infrastructures, understanding the economics of cloud computing has becoming a pressing issue for cloud service providers. However, existing pricing models rarely consider the dynamic interaction between user requests and the cloud service provider, thus can not accurately reflect the law of supply and demand in marketing. In this paper, we propose a pricing model based on the concept of user perceived value in the domain of economics that accurately capture the real supply and demand situation in the cloud service market. We then design a profit maximization scheme based on the presented dynamic pricing model that optimizes profit of the cloud service provider without violating user service-level agreement. Extensive experiments using data extracted from real-world applications validate the effectiveness of the proposed user perceived value-based pricing model. The proposed profit maximization scheme achieves 24.44% more profit as compared to the state of the art benchmarking methods.