Computational Tasks Research Articles

Speed, Power and Area Optimized Monotonic Asynchronous Array Multipliers

Multiplication is a fundamental arithmetic operation in electronic processing units such as microprocessors and digital signal processors as it plays an important role in various computational tasks and applications. There exist many designs of synchronous multipliers in the literature. However, in the domain of Input–Output Mode (IOM) asynchronous design, there is relatively less published research on multipliers. Some existing works have considered quasi-delay-insensitive (QDI) asynchronous implementations of multipliers. However, the QDI asynchronous design paradigm, in general, is not area- and speed-efficient. This article presents an efficient alternative implementation of IOM asynchronous multipliers based on the concept of monotonic Boolean networks. The array multiplier architecture has been considered for demonstrating the usefulness of our proposition. The building blocks of the multiplier, such as the partial product generator, half adder, and full adder, were implemented monotonically. The popular dual-rail encoding scheme was considered for encoding the multiplier inputs and outputs, and four-phase return-to-zero handshaking (RZH) and return-to-one handshaking (ROH) were separately considered for communication. Compared to the best of the existing QDI asynchronous array multipliers, the proposed monotonic asynchronous array multiplier achieves the following reductions in design metrics: (i) a 40.1% (44.3%) reduction in cycle time (which is the asynchronous equivalent of synchronous clock timing), a 37.7% (37.7%) reduction in area, and a 4% (4.5%) reduction in power for 4 × 4 multiplication corresponding to RZH (ROH), and (ii) a 58.1% (60.2%) reduction in cycle time, a 45.2% (45.2%) reduction in area, and a 10.3% (11%) reduction in power for 8 × 8 multiplication corresponding to RZH (ROH). The multipliers were implemented using a 28 nm CMOS process technology.

Metaheuristics Method for Computation Offloading In Mobile Edge Computing: Survey

In recent years, edge computing has emerged as a computing paradigm to support the computationally intensive and latency-critical applications for resource limited devices. The main feature of edge computing is to push computation, networking, and storage facilities closer to the network edge. This enables user equipment (UE) to profit from the edge computing paradigm by mainly offloading their intensive computation tasks to edge resources. Because of some rising problems such as inherent software and hardware heterogeneity, restrictions, dynamism, and stochastic behavior of the ecosystem, the computation offloading issues consider as the essential challenging problems in the MEC environment. However, to the best of the author's knowledge, in spite of its significance, in Metaheuristic -based computation offloading mechanisms, there is not any systematic, comprehensive, and detailed survey in the MEC environment. In this paper, we provide a review on the Metaheuristic -based computation offloading mechanisms in the MEC environment in the form of a classical taxonomy to identify the contemporary mechanisms on this crucial topic and to offer open issues as well. The proposed taxonomy is classified into three main fields: genetic algorithm (GA)-based mechanisms, Partical Swarm Optimization(PSO)-based mechanisms, and Hybrid GA with PSO -based mechanisms. Next, these classes are compared with each other based on the essential features such as performance metrics, case studies, utilized techniques, and evaluation tools, and their advantages and weaknesses are discussed, as well. Finally, open issues and uncovered or inadequately covered future research challenges are argued, and the survey is concluded.

RGGC-UNet: Accurate Deep Learning Framework for Signet Ring Cell Semantic Segmentation in Pathological Images.

Semantic segmentation of Signet Ring Cells (SRC) plays a pivotal role in the diagnosis of SRC carcinoma based on pathological images. Deep learning-based methods have demonstrated significant promise in computer-aided diagnosis over the past decade. However, many existing approaches rely heavily on stacking layers, leading to repetitive computational tasks and unnecessarily large neural networks. Moreover, the lack of available ground truth data for SRCs hampers the advancement of segmentation techniques for these cells. In response, this paper introduces an efficient and accurate deep learning framework (RGGC-UNet), which is a UNet framework including our proposed residual ghost block with ghost coordinate attention, featuring an encoder-decoder structure tailored for the semantic segmentation of SRCs. We designed a novel encoder using the residual ghost block with proposed ghost coordinate attention. Benefiting from the utilization of ghost block and ghost coordinate attention in the encoder, the computational overhead of our model is effectively minimized. For practical application in pathological diagnosis, we have enriched the DigestPath 2019 dataset with fully annotated mask labels of SRCs. Experimental outcomes underscore that our proposed model significantly surpasses other leading-edge models in segmentation accuracy while ensuring computational efficiency.

WITHIN- AND BETWEEN-PERSON DIFFERENCES IN ACTIVITY FACTOR STRUCTURE: RESULTS FROM AN EMA STUDY

Abstract Analyses of activity participation scales are typically based on single time points and resulting factors focus on differences between participants. However, as real-world activity engagement varies at more micro-timescales, these analyses provide little insight into how activities cluster together within a person across moments or days. Ecological momentary assessment (EMA) studies capture within-person fluctuations in activity engagement and allow us to compare within-person variability to that observed across persons. Using multilevel factor analysis we examined the factor structure of activity participation within-persons (i.e., across days) and between participants. Using tablet-based assessments, 81 adults aged 41 to 94 years (M=61.26, SD=12.12) reported the activities they completed in the past 3-4 hours 5 times per day (4 at semi-randomly scheduled intervals and 1 at bedtime) for 14 days. Multilevel factor analysis simultaneously computed both intra-individual factors (within-person structure of activity in daily life) and inter-individual factors (between-person structure of activity engagement). A solution of 4 within-person and 4 between-person factors provided the best model fit, with three common factors across levels: 1) cognitive (e.g., read, write, computer tasks); 2) social (e.g., events, mentoring, providing care); and 3) passive (e.g., TV, games) factors. There were notable differences in the fourth factor however. Although there are similarities, the factor structure of activity participation between individuals is different than factors describing activity participation within persons from day to day. Researchers should be aware that common between-person activity factors will not unilaterally fit EMA within-person data and should conduct additional preparatory factor analyses.

Fuzzy Logic, Neural Network, and Adaptive Neuro-Fuzzy Inference System in Delegation of Standard Concrete Beam Calculations

Machine learning (ML) has been proven effective in various scientific and industrial domains. Nevertheless, its practical application in the construction industry requires further investigation. Leveraging ML capabilities conserves human resources, reduces errors, and speeds up computation and interpretation tasks. The efficacy of ML algorithms depends on factors like ability, result accuracy, analysis cost, and sensitivity to parameter count and available data volume. This study explores the potential of using ML to delegate structural calculation processes, which is an aspect with limited attention. Concrete beam section calculations based on the American Concrete Institute (ACI) standards were chosen as a case study to assess ML’s capacity to emulate a structural designer’s role. Initially, manual design steps and standard considerations for a concrete beam section were parametrically coded in MATLAB. Validation against structural design references ensured code accuracy in calculating shear and bending capacities. The parametric results served as initial data (lookup table) for training ML operators. Various ML techniques, including fuzzy logic (FL), neural network (NN), and adaptive neuro-fuzzy inference system (ANFIS), were coded in MATLAB. A comparative analysis of the three ML operators assessed their performance in replacing standard calculations. Parametric examples illustrated each operator’s precision in delegation compared to direct calculations. The study also explored the impact of the number of parameters and lookup table size on the accuracy of each ML operator. The findings revealed that while all three operators could delegate standard calculations, their precision varied. Notably, when the lookup table was optimal, ANFIS operators demonstrated the ability to represent standard calculations with varying parameter counts and high precision. Focused on beam calculations, this study provides insights into ML operator performance. The outcomes, including selecting the most capable operator and their sensitivity to parameters and lookup table size, offer valuable guidance for researchers interpreting experimental and numerical analysis results.

Task offloading and resource allocation for blockchain‐enabled mobile edge computing

AbstractMobile edge computing (MEC) has risen as an effective approach to support ubiquitous and prosperous mobile applications. Due to the strict delay requirements and the increasingly complex application environments, the computation efficiency and security have become the bottleneck that restricts the MEC system. Here, a blockchain‐enabled task offloading scheme is proposed, where the sensitive computation tasks of user terminals (UTs) can be offloaded to a blockchain‐assisted base station (BS). The MEC‐assisted BS helps UTs compute tasks while the blockchain consensus protocol ensures the security of the task offloading and computing process. To manage the allocation of computing resources between task offloading and blockchain consensus, the task offloading and resource allocation are formulated as a joint optimization problem. The aim of the problem is to minimize the energy consumption of UTs while guaranteeing the delay requirement. By transforming the original problem into a Markov decision process, a collective reinforcement learning algorithm is proposed to solve the problem in an online fashion. In the simulations, the convergence and the performance of the proposed scheme are evaluated. The simulation results show the effectiveness of the scheme.

Perspectives of physics-based machine learning strategies for geoscientific applications governed by partial differential equations

Abstract. An accurate assessment of the physical states of the Earth system is an essential component of many scientific, societal, and economical considerations. These assessments are becoming an increasingly challenging computational task since we aim to resolve models with high resolutions in space and time, to consider complex coupled partial differential equations, and to estimate uncertainties, which often requires many realizations. Machine learning methods are becoming a very popular method for the construction of surrogate models to address these computational issues. However, they also face major challenges in producing explainable, scalable, interpretable, and robust models. In this paper, we evaluate the perspectives of geoscience applications of physics-based machine learning, which combines physics-based and data-driven methods to overcome the limitations of each approach taken alone. Through three designated examples (from the fields of geothermal energy, geodynamics, and hydrology), we show that the non-intrusive reduced-basis method as a physics-based machine learning approach is able to produce highly precise surrogate models that are explainable, scalable, interpretable, and robust.

Distributed Data Proceeding Systems Architectures Resource Efficiency Improvement on the Basis of Apriory Data about the Jobs Late Completion Times

Purpose of research. The purpose of this study is to develop a method for improving the efficiency of distributed architectures of data processing systems operating in the fog and edge layers of the network. In conditions of high dynamics of both the network infrastructure and the load, the task of forming the architecture of data processing systems is solved regularly (migration of virtual machines, horizontal scalingб etc.) At the same time, the issue of the consumption of the residual resource of computing nodes is practically not considered, while the often used devices have relatively low capacity, and their high workload leads to a reduction in the service life. Therefore, the creation of methods for forming an architecture of a computing device system that is effective in terms of saving a computing resource is an urgent task.Methods. The main scientific methods used in this study are domain analysis, operations research methods, optimization methods and computer modeling, confirming the feasibility of the main aspects of the developed method. To improve the efficiency of placing computational tasks on the nodes of a network fragment, this paper formulated a multicriteria optimization problem, where each element of the vector objective function corresponds to an individual value of the probability of failure-free operation of a computing device. To obtain estimated values of the cost function, a priori estimates of the late completion of the solution of computational problems by nodes are used, since the resource allocated for solving depends on the allocated time, and the time for solving the problem, respectively, on the allocated computing resource. The value of the cost function is calculated on the basis of approximate a priori estimates, which leads to a positive effect in terms of the consumption of computing resources of devices.Results. The result of the study is a developed method for improving the efficiency of distributed architectures of data processing systems operating in the fog and edge layers of the network.Conclusion. The method proposed in this work allows to choose such a load distribution in order to reduce the workload of devices and thus reduce the consumption of computing resources of the devices.

Enhancing trust and security in IoT computing offloading through game theory and blockchain‐based control strategy

SummaryCollaboration between IoT end‐devices and edge servers or idle devices enables offloading of computational tasks, providing an effective solution to address inherent limitations in computational resources, storage capacity, and energy efficiency. However, IoT network openness introduces security challenges, such as privacy breaches, data security, and “free‐riding” attack. Securing computational offloading is crucial for service quality and reliability. In this article, we introduce a comprehensive approach to address these challenges. First, trust metrics are performed at the level of resource requester and resource provider respectively, and the trust level of both parties is matched to reduce the adverse effects of malicious devices or servers on computing offloading. Then, a distributed decision‐making method based on game theory is designed to improve the performance of the algorithm and avoid the single‐point‐of‐failure problem through the joint participation of multiple edge servers in decision‐making. Finally, a blockchain‐based task offloading process control strategy is used to deal with the “free‐riding” attack. The results of simulation experiments show the effectiveness of our proposed offloading decision‐making method.

Fog Computing Task Scheduling of Smart Community Based on Hybrid Ant Lion Optimizer

Due to the problem of large latency and energy consumption of fog computing in smart community applications, the fog computing task-scheduling method based on Hybrid Ant Lion Optimizer (HALO) is proposed in this paper. This method is based on the Ant Lion Optimizer (ALO. Firstly, chaotic mapping is adopted to initialize the population, and the quality of the initial population is improved; secondly, the Adaptive Random Wandering (ARW) method is designed to improve the solution efficiency; finally, the improved Dynamic Opposite Learning Crossover (DOLC) strategy is embedded in the generation-hopping stage of the ALO to enrich the diversity of the population and improve the optimization-seeking ability of ALO. HALO is used to optimize the scheduling scheme of fog computing tasks. The simulation experiments are conducted under different data task volumes, compared with several other task scheduling algorithms such as the original algorithm of ALO, Genetic Algorithm (GA), Whale Optimizer Algorithm (WOA) and Salp Swarm Algorithm (SSA). HALO has good initial population quality, fast convergence speed, and high optimization-seeking accuracy. The scheduling scheme obtained by the proposed method in this paper can effectively reduce the latency of the system and reduce the energy consumption of the system.

ALGORITHM FOR PRIMARY OBJECT RECOGNITION IN THE WAREHOUSE MANAGEMENT SYSTEM

This article examines the peculiarities of warehouse management systems and presents the principles and implementation of an in-house software system for warehouse management using computer vision technology. A structural diagram of the application is developed, which consists of eight modules: image capture service, image storage, computer vision service, database, API server, client application, task scheduler, and task queue. The architecture is designed based on cloud technologies, namely Google Cloud Platform. A computer vision algorithm for determining the state of cells in the warehouse is proposed. A functional software product based on modern technologies has been developed. The purpose of this article is to reflect the results of the study of the subject area of warehouse management systems and to highlight the results of the implementation of a proprietary software system using computer vision. Keywords: Python, OpenCV, computer vision, Google Cloud, warehouse management system, cloud computing, serverless computing.

A Novel Inverse Algorithm To Solve the Integrated Optimization of Dose, Dose Rate, and Linear Energy Transfer of Proton FLASH Therapy With Sparse Filters

Purpose:The recently proposed Integrated Physical Optimization Intensity Modulated Proton Therapy (IPO-IMPT) framework allows simultaneous optimization of dose, dose rate, and linear energy transfer (LET) for FLASH treatment planning. Finding solutions to IPO-IMPT is difficult due to computational intensiveness. Nevertheless, an inverse solution that simultaneously specifies the geometry of a sparse filter and weights of a proton intensity map is desirable for both clinical and preclinical applications. Such solutions can reduce effective biological dose to organs at risk in cancer patients as well as reduce the number of animal irradiations needed to derive extra biological dose models in preclinical studies. Methods:Unlike the initial forward heuristic, this inverse IPO-IMPT solution includes simultaneous optimization of sparse range compensation, sparse range modulation, and spot intensity. The daunting computational tasks vital to this endeavor were resolved iteratively with a distributed computing framework to enable Simultaneous Intensity and Energy Modulation and Compensation (SIEMAC). SIEMAC was demonstrated on a human central lung cancer patient and a minipig. Results:SIEMAC simultaneously improves maps of spot intensities and patient-field-specific sparse range compensators and range modulators. For the lung cancer patient, at our maximum nozzle current of 300 nA, dose rate coverage above 100 Gy/s increased from 57% to 96% in the lung and from 93% to 100% in the heart, and LET coverage above 4 keV/μm dropped from 68% to 9% in the lung and from 26% to <1% in the heart. For a simple minipig plan, the full-width-half-maximum of the dose, dose rate, and LET distributions decreased by 30%, 1.6%, and 57%, respectively, again with similar target dose coverage, thus reducing uncertainty in these quantities for preclinical studies. Conclusion:The inverse solution to IPO-IMPT demonstrated the capability to simultaneously modulate sub-spot proton energy and intensity distributions for clinical and preclinical studies.

The effects of dual screen layout on neck-shoulder muscle activity and head-neck posture variability during computer tasks.

Larger dual screens have been widely used during office work and their biomechanical exposure should be explored. To investigate the biomechanical effect of two dual screen layouts on neck-shoulder muscle activity and the variability of head-neck posture in computer users. A preliminary study of the user-preferred dual screen angles was carried out in V-shaped and L-shaped layouts. Twenty healthy participants aged 19 to 26 years were recruited and assigned to perform reading, typing, and searching tasks for 30 minutes in both workstation layouts. Electromyography was measured at bilateral cervical erector spinae (CES), sternocleidomastoid (SCM), and upper trapezius (UT). The head-neck lateral bending, rotation, and flexion angles were recorded. The visual analog scale (VAS) was used to evaluate visual strain. The muscle activity at the left UT and right CES sites when using the V-shaped layout was significantly higher than the L-shaped. There were significant differences in head-neck rotation and flexion angles between the two layouts in reading and typing tasks. In the searching task, there was no significant difference in the head-neck rotation and flexion angles between the two layouts. The visual strain score was significantly higher in the V-shaped layout. The CES and UT muscles displayed higher levels of activation while using the V-shaped layout in comparison to the L-shaped layout. The head-neck rotation and flexion angles differed due to varied types of work when using V-shaped and L-shaped layouts.

Neuroelectronics as neuromorphic and neurohybryd systems enabled by memristive technology

Due to its distinctive capability to replicate vital functions of synapses and neurons, memristive devices and arrays enable both the hardware implementation of neural networks and a significant advancement towards integrating artificial electronic and biological systems to address pressing issues in artificial intelligence (AI), robotics, and medicine. This research area is still nascent and can be viewed as part of the broader field of neuroelectronics. The aforementioned is a fusion of analog and digital solutions used for diverse computational tasks inspired by biology. Notably, analog neuromorphic systems that employ memristive components are distinctive features of this arena and they can significantly enhance throughput and energy efficiency in contrast to existing AI accelerators. Designing neuromorphic systems grounded on this fresh component base mandates coordinated and interdisciplinary research and development. The foundation of this scientific and technological field lies in the cross-cutting technology of memristive devices and circuits. This technology enables the development of a novel brain-like information and computing system infrastructure that can be applied in a diverse range of fields. Current perspectives include the seamless integration of memristive devices and arrays with CMOS circuits, and the co-optimization of materials, devices, and architectures to create prototypes for computing and information systems. These systems replicate computational features present in biological neural networks capable of solving cognitive tasks that are typically either intractable by traditional AI or highly time-consuming. Neuroelectronic solutions can integrate with the brain or living neuronal cultures to form neurohybrid systems. In this presentation, we discuss two distinct strategies for connecting memristive systems with biological neural networks both in vitro and in vivo. These include a perceptron using an array of programmable memristive weights represented by metal-oxide resistive-switching devices and a methodology leveraging memristive stochastic plasticity and neural synchrony, which is part of the brain’s spiking architecture. Finally, the concept of a memristive neurohybrid chip is presented to create a compact, multifunctional, bidirectional interface between biological neural networks and memristive electronics, combined with microelectrode and microfluidic systems on a single chip. The technological advancements in component base and the development of memristor-based neuroelectronic systems will diversify hardware for the continuous evolution and mass application of artificial intelligence technologies. This will enable the creation of hybrid intelligence based on the symbiosis of artificial and biological neural networks and allow for the establishment of novel tasks at an unprecedented level.

Flexible Offloading and Task Scheduling for IoT Applications in Dynamic Multi-Access Edge Computing Environments

Nowadays, multi-access edge computing (MEC) has been widely recognized as a promising technology that can support a wide range of new applications for the Internet of Things (IoT). In dynamic MEC networks, the heterogeneous computation capacities of the edge servers and the diversified requirements of the IoT applications are both asymmetric, where and when to offload and schedule the time-dependent tasks of IoT applications remains a challenge. In this paper, we propose a flexible offloading and task scheduling scheme (FLOATS) to adaptively optimize the computation of offloading decisions and scheduling priority sequences for time-dependent tasks in dynamic networks. We model the dynamic optimization problem as a multi-objective combinatorial optimization problem in an infinite time horizon, which is intractable to solve. To address this, a rolling-horizon-based optimization mechanism is designed to decompose the dynamic optimization problem into a series of static sub-problems. A genetic algorithm (GA)-based computation offloading and task scheduling algorithm is proposed for each static sub-problem. This algorithm encodes feasible solutions into two-layer chromosomes, and the optimal solution can be obtained through chromosome selection, crossover and mutation operations. The simulation results demonstrate that the proposed scheme can effectively reduce network costs in comparison to other reference schemes.

DPAFD-net: A dual-path adaptive fusion dehazing network

Image dehazing is an ill-posed problem that has been extensively studied in recent years. Unfortunately, most existing deep dehazing models have high computational complexity and lack the dynamic adjustment of details, which hinders their application to high-resolution images in computational vision tasks. In this paper, we propose an efficient dual-path adaptive fusion dehazing network (DPAFD-Net) to directly restore a clear image from a hazy input. Moreover, we propose a pure subnetwork with encoder and decoder structures to further extract the structural information and progressively restore the haze-free image. To evaluate the effectiveness of the proposed method, we validate our approach on synthetic and real hazy images, where our method performs favourably against the state-of-the-art dehazing approaches.

A Survey on IoT Task Offloading Decisions in Multi-access Edge Computing: A Decision Content Perspective

The rapid development of Internet of Things (IoT) technologies has led to increasingly complex software systems on Terminal Devices (TDs). This increases the computational load and battery consumption of TDs. The emergence of Multi-access Edge Computing (MEC) and computing offloading technology allows TDs to delegate computing-intensive tasks to the MEC network for remote execution. However, the computing and communication resources of MEC networks are limited and heterogeneous. In addition, some TDs may have a higher mobility. Therefore, IoT networks need to dynamically decide to offload some or all of the computational tasks to appropriate nodes in the MEC network. Existing reviews do not fully cover the multiple decision-making content of task offloading, and some studies do not clearly define the boundary between task offloading decision-making and task offloading scheduling optimization. This study investigates the similarities and differences between the enabling technologies, deployment architectures, and decision items of various decision mechanisms from the perspective of offloading decision content. Thus, the development and existing challenges of task offloading decision-making methods are comprehensively demonstrated, and future research directions are proposed for IoT task offloading decision-making in MEC.

Trainee psychotherapists’ emotion recognition accuracy during 1.5 years of psychotherapy education compared to a control group: no improvement after psychotherapy training

The ability to recognize and work with patients’ emotions is considered an important part of most psychotherapy approaches. Surprisingly, there is little systematic research on psychotherapists’ ability to recognize other people’s emotional expressions. In this study, we compared trainee psychotherapists’ nonverbal emotion recognition accuracy to a control group of undergraduate students at two time points: at the beginning and at the end of one and a half years of theoretical and practical psychotherapy training. Emotion recognition accuracy (ERA) was assessed using two standardized computer tasks, one for recognition of dynamic multimodal (facial, bodily, vocal) expressions and one for recognition of facial micro expressions. Initially, 154 participants enrolled in the study, 72 also took part in the follow-up. The trainee psychotherapists were moderately better at recognizing multimodal expressions, and slightly better at recognizing facial micro expressions, than the control group at the first test occasion. However, mixed multilevel modeling indicated that the ERA change trajectories for the two groups differed significantly. While the control group improved in their ability to recognize multimodal emotional expressions from pretest to follow-up, the trainee psychotherapists did not. Both groups improved their micro expression recognition accuracy, but the slope for the control group was significantly steeper than the trainee psychotherapists’. These results suggest that psychotherapy education and clinical training do not always contribute to improved emotion recognition accuracy beyond what could be expected due to time or other factors. Possible reasons for that finding as well as implications for the psychotherapy education are discussed.

DRL-Based Computation Offloading and Resource Allocation in Green MEC-Enabled Maritime-IoT Networks

The maritime Internet of Things (MIoT), a maritime version of the Internet of Things (IoT), is envisioned as a promising solution that can provide ubiquitous connectivity over land and sea. Due to the rapid development of maritime activities and the maritime economy, there is a growing demand for computing-intensive and latency-sensitive maritime applications requiring various energy consumption, communication, and computation resources, posing a significant challenge to MIoT devices due to their limited computational ability and battery capacity. Mobile Edge Computing (MEC), which can handle computation tasks at the network’s edge more efficiently and with less latency, is emerging as a paradigm for fulfilling the ever-increasing demands of MIoT applications. However, the exponential increase in the number of MIoT devices has increased the system’s energy consumption, resulting in increased greenhouse gas emissions and a negative impact on the environment. As a result, it is vital for MIoT networks to take traditional energy usage minimization into account. The integration of renewable energy-harvesting capabilities into base stations or MIoT devices possesses the potential to reduce grid energy consumption and carbon emissions. However, making an effective decision regarding task offloading and resource allocation is crucial for maximizing the utilization of the system’s potential resources and minimizing carbon emissions. In this paper, we first propose a green MEC-enabled maritime IoT network architecture to flexibly provide computing-intensive and latency-sensitive applications for MIoT users. Based on the architecture, we formulate the joint task offloading and resource allocation problem by optimizing the total system execution efficiency (including the total size of completed tasks, task execution latency, and the system’s carbon emissions) and then propose a deep-deterministic-policy-gradient-based joint optimization strategy to solve the problem, eventually obtaining an effective resolution through continuous action space learning in the changing environment. Finally, simulation results confirm that our proposal can yield good performance in system execution efficiency compared to other benchmarks; that is, it can significantly reduce the system’s carbon emissions and tasks’ delay and improve the total size of completed tasks.

System-centric energy efficient computation offloading and resource allocation in latency-sensitive MEC systems

Mobile edge computing (MEC) enables computation tasks of end users to be offloaded and processed at nearby edge servers, which is a promising technology that can effectively alleviate end users’ computing pressure. However, how to balance two important metrics for MEC computation offloading, i.e., latency and energy efficiency, is still a key challenge. In this paper, we investigate joint computation offloading and resource allocation for latency-sensitive applications in order to maximize system-centric computation energy efficiency (SCEE) in MEC systems. An optimization problem is formulated to maximize the sum computation energy efficiency of all users which contains the energy consumption at both user and edge server sides. Meanwhile, task completion latency constraints for all users are considered. We decompose the original optimization problem into two tractable subproblems. The optimal computation offloading as well as communication and computing resource allocation solutions are obtained by solving these subproblems. Furthermore, a hierarchical system-centric energy efficient computation offloading and resource allocation (SEECR) algorithm is developed. Numerical results show that compared with the benchmark schemes, the proposed algorithm can effectively improve the computation energy efficiency performance while guaranteeing the latency requirements of all users.