As emerging two-dimensional(2D)materials,carbides and nitrides(MXenes)could be solid solutions or organized structures made up of multi-atomic layers.With remarkable and adjustable electrical,optical,mechanical,and el...As emerging two-dimensional(2D)materials,carbides and nitrides(MXenes)could be solid solutions or organized structures made up of multi-atomic layers.With remarkable and adjustable electrical,optical,mechanical,and electrochemical characteristics,MXenes have shown great potential in brain-inspired neuromorphic computing electronics,including neuromorphic gas sensors,pressure sensors and photodetectors.This paper provides a forward-looking review of the research progress regarding MXenes in the neuromorphic sensing domain and discussed the critical challenges that need to be resolved.Key bottlenecks such as insufficient long-term stability under environmental exposure,high costs,scalability limitations in large-scale production,and mechanical mismatch in wearable integration hinder their practical deployment.Furthermore,unresolved issues like interfacial compatibility in heterostructures and energy inefficiency in neu-romorphic signal conversion demand urgent attention.The review offers insights into future research directions enhance the fundamental understanding of MXene properties and promote further integration into neuromorphic computing applications through the convergence with various emerging technologies.展开更多
The advancement of flexible memristors has significantly promoted the development of wearable electronic for emerging neuromorphic computing applications.Inspired by in-memory computing architecture of human brain,fle...The advancement of flexible memristors has significantly promoted the development of wearable electronic for emerging neuromorphic computing applications.Inspired by in-memory computing architecture of human brain,flexible memristors exhibit great application potential in emulating artificial synapses for highefficiency and low power consumption neuromorphic computing.This paper provides comprehensive overview of flexible memristors from perspectives of development history,material system,device structure,mechanical deformation method,device performance analysis,stress simulation during deformation,and neuromorphic computing applications.The recent advances in flexible electronics are summarized,including single device,device array and integration.The challenges and future perspectives of flexible memristor for neuromorphic computing are discussed deeply,paving the way for constructing wearable smart electronics and applications in large-scale neuromorphic computing and high-order intelligent robotics.展开更多
High-entropy oxides(HEOs)have emerged as a promising class of memristive materials,characterized by entropy-stabilized crystal structures,multivalent cation coordination,and tunable defect landscapes.These intrinsic f...High-entropy oxides(HEOs)have emerged as a promising class of memristive materials,characterized by entropy-stabilized crystal structures,multivalent cation coordination,and tunable defect landscapes.These intrinsic features enable forming-free resistive switching,multilevel conductance modulation,and synaptic plasticity,making HEOs attractive for neuromorphic computing.This review outlines recent progress in HEO-based memristors across materials engineering,switching mechanisms,and synaptic emulation.Particular attention is given to vacancy migration,phase transitions,and valence-state dynamics—mechanisms that underlie the switching behaviors observed in both amorphous and crystalline systems.Their relevance to neuromorphic functions such as short-term plasticity and spike-timing-dependent learning is also examined.While encouraging results have been achieved at the device level,challenges remain in conductance precision,variability control,and scalable integration.Addressing these demands a concerted effort across materials design,interface optimization,and task-aware modeling.With such integration,HEO memristors offer a compelling pathway toward energy-efficient and adaptable brain-inspired electronics.展开更多
To support popular Internet of Things(IoT)applications such as virtual reality and mobile games,edge computing provides a front-end distributed computing archetype of centralized cloud computing with low latency and d...To support popular Internet of Things(IoT)applications such as virtual reality and mobile games,edge computing provides a front-end distributed computing archetype of centralized cloud computing with low latency and distributed data processing.However,it is challenging for multiple users to offload their computation tasks because they are competing for spectrum and computation as well as Radio Access Technologies(RAT)resources.In this paper,we investigate computation offloading mechanism of multiple selfish users with resource allocation in IoT edge computing networks by formulating it as a stochastic game.Each user is a learning agent observing its local network environment to learn optimal decisions on either local computing or edge computing with a goal of minimizing long term system cost by choosing its transmit power level,RAT and sub-channel without knowing any information of the other users.Since users’decisions are coupling at the gateway,we define the reward function of each user by considering the aggregated effect of other users.Therefore,a multi-agent reinforcement learning framework is developed to solve the game with the proposed Independent Learners based Multi-Agent Q-learning(IL-based MA-Q)algorithm.Simulations demonstrate that the proposed IL-based MA-Q algorithm is feasible to solve the formulated problem and is more energy efficient without extra cost on channel estimation at the centralized gateway.Finally,compared with the other three benchmark algorithms,it has better system cost performance and achieves distributed computation offloading.展开更多
An Interval Type-2(IT-2)fuzzy controller design approach is proposed in this research to simultaneously achievemultiple control objectives inNonlinearMulti-Agent Systems(NMASs),including formation,containment,and coll...An Interval Type-2(IT-2)fuzzy controller design approach is proposed in this research to simultaneously achievemultiple control objectives inNonlinearMulti-Agent Systems(NMASs),including formation,containment,and collision avoidance.However,inherent nonlinearities and uncertainties present in practical control systems contribute to the challenge of achieving precise control performance.Based on the IT-2 Takagi-Sugeno Fuzzy Model(T-SFM),the fuzzy control approach can offer a more effective solution for NMASs facing uncertainties.Unlike existing control methods for NMASs,the Formation and Containment(F-and-C)control problem with collision avoidance capability under uncertainties based on the IT-2 T-SFM is discussed for the first time.Moreover,an IT-2 fuzzy tracking control approach is proposed to solve the formation task for leaders in NMASs without requiring communication.This control scheme makes the design process of the IT-2 fuzzy Formation Controller(FC)more straightforward and effective.According to the communication interaction protocol,the IT-2 Containment Controller(CC)design approach is proposed for followers to ensure convergence into the region defined by the leaders.Leveraging the IT-2 T-SFM representation,the analysis methods developed for linear Multi-Agent Systems(MASs)are successfully extended to perform containment analysis without requiring the additional assumptions imposed in existing research.Notably,the IT-2 fuzzy tracking controller can also be applied in collision avoidance situations to track the desired trajectories calculated by the avoidance algorithm under the Artificial Potential Field(APF).Benefiting from the combination of vortex and source APFs,the leaders can properly adjust the system dynamics to prevent potential collision risk.Integrating the fuzzy theory and APFs avoidance algorithm,an IT-2 fuzzy controller design approach is proposed to achieve the F-and-C purposewhile ensuring collision avoidance capability.Finally,amulti-ship simulation is conducted to validate the feasibility and effectiveness of the designed IT-2 fuzzy controller.展开更多
Mobile-edge computing(MEC)is a promising technology for the fifth-generation(5G)and sixth-generation(6G)architectures,which provides resourceful computing capabilities for Internet of Things(IoT)devices,such as virtua...Mobile-edge computing(MEC)is a promising technology for the fifth-generation(5G)and sixth-generation(6G)architectures,which provides resourceful computing capabilities for Internet of Things(IoT)devices,such as virtual reality,mobile devices,and smart cities.In general,these IoT applications always bring higher energy consumption than traditional applications,which are usually energy-constrained.To provide persistent energy,many references have studied the offloading problem to save energy consumption.However,the dynamic environment dramatically increases the optimization difficulty of the offloading decision.In this paper,we aim to minimize the energy consumption of the entireMECsystemunder the latency constraint by fully considering the dynamic environment.UnderMarkov games,we propose amulti-agent deep reinforcement learning approach based on the bi-level actorcritic learning structure to jointly optimize the offloading decision and resource allocation,which can solve the combinatorial optimization problem using an asymmetric method and compute the Stackelberg equilibrium as a better convergence point than Nash equilibrium in terms of Pareto superiority.Our method can better adapt to a dynamic environment during the data transmission than the single-agent strategy and can effectively tackle the coordination problem in the multi-agent environment.The simulation results show that the proposed method could decrease the total computational overhead by 17.8%compared to the actor-critic-based method and reduce the total computational overhead by 31.3%,36.5%,and 44.7%compared with randomoffloading,all local execution,and all offloading execution,respectively.展开更多
Cloud computing can offer a very powerful, reliable, predictable and scalable computing infrastructure for the execution of MAS （multi-agent systems） implementing complex agent-based applications such when modelling...Cloud computing can offer a very powerful, reliable, predictable and scalable computing infrastructure for the execution of MAS （multi-agent systems） implementing complex agent-based applications such when modelling, simulation and real-time running of complex systems must be provided. Multi-agent systems appears as an adequate approach to current challenges in many areas. Between important qualities of MAS also belongs to, that they are open, interoperable, and heterogenous systems. The agent is active, a program entity, has its own ideas how to perform the tasks of the own agenda. Agents： perceive, behave ＂reasonably＂, act in the environment, communicate with other agents. Cloud infrastructures can offer an ideal platform where run MAS systems simulations, applications and real-time running because of its large amount of processing and memory resources that can be dynamically configured for executing large agent-based software at unprecedented scale. Cloud computing can help chemical and food companies drive operational excellence; meet growing and changing customer demands; accelerate new product innovation and ramp-to-volume manufacturing in key markets; reduce IT spending; manage and mitigate supply chain risks; and enable faster and more flexible delivery of new IT system. Production type of SOC （service-oriented computing） can be inspired by a ＂Cloud＂, for the production of ＂Cloud＂ offers an attractive and natural solutions in several computing trends such as delivery system over the Internet, use of utilities, flexibility, virtualization, a ＂grid＂ distributed computing, outsourcing, Web 2.0, etc.. Production of the ＂Cloud＂ is also considered as a new multidisciplinary field that includes ＂network＂ production, virtual manufacturing, agile manufacturing, and of course cloud computing. Examples of cloud computing and MAS applications in food and chemistry development and industry, proposition of using multi-agent systems in the control of batch processes, modified ACO （ant colony optimization） approach for the diversified service allocation and scheduling mechanism in cloud paradigma, examples of applications in a business area were studied in the paper.展开更多
Satellite edge computing has garnered significant attention from researchers;however,processing a large volume of tasks within multi-node satellite networks still poses considerable challenges.The sharp increase in us...Satellite edge computing has garnered significant attention from researchers;however,processing a large volume of tasks within multi-node satellite networks still poses considerable challenges.The sharp increase in user demand for latency-sensitive tasks has inevitably led to offloading bottlenecks and insufficient computational capacity on individual satellite edge servers,making it necessary to implement effective task offloading scheduling to enhance user experience.In this paper,we propose a priority-based task scheduling strategy based on a Software-Defined Network(SDN)framework for satellite-terrestrial integrated networks,which clarifies the execution order of tasks based on their priority.Subsequently,we apply a Dueling-Double Deep Q-Network(DDQN)algorithm enhanced with prioritized experience replay to derive a computation offloading strategy,improving the experience replay mechanism within the Dueling-DDQN framework.Next,we utilize the Deep Deterministic Policy Gradient(DDPG)algorithm to determine the optimal resource allocation strategy to reduce the processing latency of sub-tasks.Simulation results demonstrate that the proposed d3-DDPG algorithm outperforms other approaches,effectively reducing task processing latency and thus improving user experience and system efficiency.展开更多
Cooperative multi-agent reinforcement learning(MARL)is a key technology for enabling cooperation in complex multi-agent systems.It has achieved remarkable progress in areas such as gaming,autonomous driving,and multi-...Cooperative multi-agent reinforcement learning(MARL)is a key technology for enabling cooperation in complex multi-agent systems.It has achieved remarkable progress in areas such as gaming,autonomous driving,and multi-robot control.Empowering cooperative MARL with multi-task decision-making capabilities is expected to further broaden its application scope.In multi-task scenarios,cooperative MARL algorithms need to address 3 types of multi-task problems:reward-related multi-task,arising from different reward functions;multi-domain multi-task,caused by differences in state and action spaces,state transition functions;and scalability-related multi-task,resulting from the dynamic variation in the number of agents.Most existing studies focus on scalability-related multitask problems.However,with the increasing integration between large language models(LLMs)and multi-agent systems,a growing number of LLM-based multi-agent systems have emerged,enabling more complex multi-task cooperation.This paper provides a comprehensive review of the latest advances in this field.By combining multi-task reinforcement learning with cooperative MARL,we categorize and analyze the 3 major types of multi-task problems under multi-agent settings,offering more fine-grained classifications and summarizing key insights for each.In addition,we summarize commonly used benchmarks and discuss future directions of research in this area,which hold promise for further enhancing the multi-task cooperation capabilities of multi-agent systems and expanding their practical applications in the real world.展开更多
Optoelectronic memristor is generating growing research interest for high efficient computing and sensing-memory applications.In this work,an optoelectronic memristor with Au/a-C:Te/Pt structure is developed.Synaptic ...Optoelectronic memristor is generating growing research interest for high efficient computing and sensing-memory applications.In this work,an optoelectronic memristor with Au/a-C:Te/Pt structure is developed.Synaptic functions,i.e.,excita-tory post-synaptic current and pair-pulse facilitation are successfully mimicked with the memristor under electrical and optical stimulations.More importantly,the device exhibited distinguishable response currents by adjusting 4-bit input electrical/opti-cal signals.A multi-mode reservoir computing(RC)system is constructed with the optoelectronic memristors to emulate human tactile-visual fusion recognition and an accuracy of 98.7%is achieved.The optoelectronic memristor provides potential for developing multi-mode RC system.展开更多
This paper addresses the consensus problem of nonlinear multi-agent systems subject to external disturbances and uncertainties under denial-ofservice(DoS)attacks.Firstly,an observer-based state feedback control method...This paper addresses the consensus problem of nonlinear multi-agent systems subject to external disturbances and uncertainties under denial-ofservice(DoS)attacks.Firstly,an observer-based state feedback control method is employed to achieve secure control by estimating the system's state in real time.Secondly,by combining a memory-based adaptive eventtriggered mechanism with neural networks,the paper aims to approximate the nonlinear terms in the networked system and efficiently conserve system resources.Finally,based on a two-degree-of-freedom model of a vehicle affected by crosswinds,this paper constructs a multi-unmanned ground vehicle(Multi-UGV)system to validate the effectiveness of the proposed method.Simulation results show that the proposed control strategy can effectively handle external disturbances such as crosswinds in practical applications,ensuring the stability and reliable operation of the Multi-UGV system.展开更多
As an important complement to cloud computing, edge computing can effectively reduce the workload of the backbone network. To reduce latency and energy consumption of edge computing, deep learning is used to learn the...As an important complement to cloud computing, edge computing can effectively reduce the workload of the backbone network. To reduce latency and energy consumption of edge computing, deep learning is used to learn the task offloading strategies by interacting with the entities. In actual application scenarios, users of edge computing are always changing dynamically. However, the existing task offloading strategies cannot be applied to such dynamic scenarios. To solve this problem, we propose a novel dynamic task offloading framework for distributed edge computing, leveraging the potential of meta-reinforcement learning (MRL). Our approach formulates a multi-objective optimization problem aimed at minimizing both delay and energy consumption. We model the task offloading strategy using a directed acyclic graph (DAG). Furthermore, we propose a distributed edge computing adaptive task offloading algorithm rooted in MRL. This algorithm integrates multiple Markov decision processes (MDP) with a sequence-to-sequence (seq2seq) network, enabling it to learn and adapt task offloading strategies responsively across diverse network environments. To achieve joint optimization of delay and energy consumption, we incorporate the non-dominated sorting genetic algorithm II (NSGA-II) into our framework. Simulation results demonstrate the superiority of our proposed solution, achieving a 21% reduction in time delay and a 19% decrease in energy consumption compared to alternative task offloading schemes. Moreover, our scheme exhibits remarkable adaptability, responding swiftly to changes in various network environments.展开更多
This paper investigates the challenges associated with Unmanned Aerial Vehicle (UAV) collaborative search and target tracking in dynamic and unknown environments characterized by limited field of view. The primary obj...This paper investigates the challenges associated with Unmanned Aerial Vehicle (UAV) collaborative search and target tracking in dynamic and unknown environments characterized by limited field of view. The primary objective is to explore the unknown environments to locate and track targets effectively. To address this problem, we propose a novel Multi-Agent Reinforcement Learning (MARL) method based on Graph Neural Network (GNN). Firstly, a method is introduced for encoding continuous-space multi-UAV problem data into spatial graphs which establish essential relationships among agents, obstacles, and targets. Secondly, a Graph AttenTion network (GAT) model is presented, which focuses exclusively on adjacent nodes, learns attention weights adaptively and allows agents to better process information in dynamic environments. Reward functions are specifically designed to tackle exploration challenges in environments with sparse rewards. By introducing a framework that integrates centralized training and distributed execution, the advancement of models is facilitated. Simulation results show that the proposed method outperforms the existing MARL method in search rate and tracking performance with less collisions. The experiments show that the proposed method can be extended to applications with a larger number of agents, which provides a potential solution to the challenging problem of multi-UAV autonomous tracking in dynamic unknown environments.展开更多
The rise of large-scale artificial intelligence(AI)models,such as ChatGPT,Deep-Seek,and autonomous vehicle systems,has significantly advanced the boundaries of AI,enabling highly complex tasks in natural language proc...The rise of large-scale artificial intelligence(AI)models,such as ChatGPT,Deep-Seek,and autonomous vehicle systems,has significantly advanced the boundaries of AI,enabling highly complex tasks in natural language processing,image recognition,and real-time decisionmaking.However,these models demand immense computational power and are often centralized,relying on cloud-based architectures with inherent limitations in latency,privacy,and energy efficiency.To address these challenges and bring AI closer to real-world applications,such as wearable health monitoring,robotics,and immersive virtual environments,innovative hardware solutions are urgently needed.This work introduces a near-sensor edge computing(NSEC)system,built on a bilayer AlN/Si waveguide platform,to provide real-time,energy-efficient AI capabilities at the edge.Leveraging the electro-optic properties of AlN microring resonators for photonic feature extraction,coupled with Si-based thermo-optic Mach-Zehnder interferometers for neural network computations,the system represents a transformative approach to AI hardware design.Demonstrated through multimodal gesture and gait analysis,the NSEC system achieves high classification accuracies of 96.77%for gestures and 98.31%for gaits,ultra-low latency(<10 ns),and minimal energy consumption(<0.34 pJ).This groundbreaking system bridges the gap between AI models and real-world applications,enabling efficient,privacy-preserving AI solutions for healthcare,robotics,and next-generation human-machine interfaces,marking a pivotal advancement in edge computing and AI deployment.展开更多
To address the increasing demand for massive data storage and processing,brain-inspired neuromorphic comput-ing systems based on artificial synaptic devices have been actively developed in recent years.Among the vario...To address the increasing demand for massive data storage and processing,brain-inspired neuromorphic comput-ing systems based on artificial synaptic devices have been actively developed in recent years.Among the various materials inves-tigated for the fabrication of synaptic devices,silicon carbide(SiC)has emerged as a preferred choices due to its high electron mobility,superior thermal conductivity,and excellent thermal stability,which exhibits promising potential for neuromorphic applications in harsh environments.In this review,the recent progress in SiC-based synaptic devices is summarized.Firstly,an in-depth discussion is conducted regarding the categories,working mechanisms,and structural designs of these devices.Subse-quently,several application scenarios for SiC-based synaptic devices are presented.Finally,a few perspectives and directions for their future development are outlined.展开更多
With the rapid development of Intelligent Transportation Systems(ITS),many new applications for Intelligent Connected Vehicles(ICVs)have sprung up.In order to tackle the conflict between delay-sensitive applications a...With the rapid development of Intelligent Transportation Systems(ITS),many new applications for Intelligent Connected Vehicles(ICVs)have sprung up.In order to tackle the conflict between delay-sensitive applications and resource-constrained vehicles,computation offloading paradigm that transfers computation tasks from ICVs to edge computing nodes has received extensive attention.However,the dynamic network conditions caused by the mobility of vehicles and the unbalanced computing load of edge nodes make ITS face challenges.In this paper,we propose a heterogeneous Vehicular Edge Computing(VEC)architecture with Task Vehicles(TaVs),Service Vehicles(SeVs)and Roadside Units(RSUs),and propose a distributed algorithm,namely PG-MRL,which jointly optimizes offloading decision and resource allocation.In the first stage,the offloading decisions of TaVs are obtained through a potential game.In the second stage,a multi-agent Deep Deterministic Policy Gradient(DDPG),one of deep reinforcement learning algorithms,with centralized training and distributed execution is proposed to optimize the real-time transmission power and subchannel selection.The simulation results show that the proposed PG-MRL algorithm has significant improvements over baseline algorithms in terms of system delay.展开更多
The rapid advent in artificial intelligence and big data has revolutionized the dynamic requirement in the demands of the computing resource for executing specific tasks in the cloud environment.The process of achievi...The rapid advent in artificial intelligence and big data has revolutionized the dynamic requirement in the demands of the computing resource for executing specific tasks in the cloud environment.The process of achieving autonomic resource management is identified to be a herculean task due to its huge distributed and heterogeneous environment.Moreover,the cloud network needs to provide autonomic resource management and deliver potential services to the clients by complying with the requirements of Quality-of-Service(QoS)without impacting the Service Level Agreements(SLAs).However,the existing autonomic cloud resource managing frameworks are not capable in handling the resources of the cloud with its dynamic requirements.In this paper,Coot Bird Behavior Model-based Workload Aware Autonomic Resource Management Scheme(CBBM-WARMS)is proposed for handling the dynamic requirements of cloud resources through the estimation of workload that need to be policed by the cloud environment.This CBBM-WARMS initially adopted the algorithm of adaptive density peak clustering for workloads clustering of the cloud.Then,it utilized the fuzzy logic during the process of workload scheduling for achieving the determining the availability of cloud resources.It further used CBBM for potential Virtual Machine(VM)deployment that attributes towards the provision of optimal resources.It is proposed with the capability of achieving optimal QoS with minimized time,energy consumption,SLA cost and SLA violation.The experimental validation of the proposed CBBMWARMS confirms minimized SLA cost of 19.21%and reduced SLA violation rate of 18.74%,better than the compared autonomic cloud resource managing frameworks.展开更多
Recently,one of the main challenges facing the smart grid is insufficient computing resources and intermittent energy supply for various distributed components(such as monitoring systems for renewable energy power sta...Recently,one of the main challenges facing the smart grid is insufficient computing resources and intermittent energy supply for various distributed components(such as monitoring systems for renewable energy power stations).To solve the problem,we propose an energy harvesting based task scheduling and resource management framework to provide robust and low-cost edge computing services for smart grid.First,we formulate an energy consumption minimization problem with regard to task offloading,time switching,and resource allocation for mobile devices,which can be decoupled and transformed into a typical knapsack problem.Then,solutions are derived by two different algorithms.Furthermore,we deploy renewable energy and energy storage units at edge servers to tackle intermittency and instability problems.Finally,we design an energy management algorithm based on sampling average approximation for edge computing servers to derive the optimal charging/discharging strategies,number of energy storage units,and renewable energy utilization.The simulation results show the efficiency and superiority of our proposed framework.展开更多
Large language models(LLMs)have emerged as powerful tools for addressing a wide range of problems,including those in scientific computing,particularly in solving partial differential equations(PDEs).However,different ...Large language models(LLMs)have emerged as powerful tools for addressing a wide range of problems,including those in scientific computing,particularly in solving partial differential equations(PDEs).However,different models exhibit distinct strengths and preferences,resulting in varying levels of performance.In this paper,we compare the capabilities of the most advanced LLMs—DeepSeek,ChatGPT,and Claude—along with their reasoning-optimized versions in addressing computational challenges.Specifically,we evaluate their proficiency in solving traditional numerical problems in scientific computing as well as leveraging scientific machine learning techniques for PDE-based problems.We designed all our experiments so that a nontrivial decision is required,e.g,defining the proper space of input functions for neural operator learning.Our findings show that reasoning and hybrid-reasoning models consistently and significantly outperform non-reasoning ones in solving challenging problems,with ChatGPT o3-mini-high generally offering the fastest reasoning speed.展开更多
基金supported by the NSFC(12474071)Natural Science Foundation of Shandong Province(ZR2024YQ051,ZR2025QB50)+6 种基金Guangdong Basic and Applied Basic Research Foundation(2025A1515011191)the Shanghai Sailing Program(23YF1402200,23YF1402400)funded by Basic Research Program of Jiangsu(BK20240424)Open Research Fund of State Key Laboratory of Crystal Materials(KF2406)Taishan Scholar Foundation of Shandong Province(tsqn202408006,tsqn202507058)Young Talent of Lifting engineering for Science and Technology in Shandong,China(SDAST2024QTB002)the Qilu Young Scholar Program of Shandong University。
文摘As emerging two-dimensional(2D)materials,carbides and nitrides(MXenes)could be solid solutions or organized structures made up of multi-atomic layers.With remarkable and adjustable electrical,optical,mechanical,and electrochemical characteristics,MXenes have shown great potential in brain-inspired neuromorphic computing electronics,including neuromorphic gas sensors,pressure sensors and photodetectors.This paper provides a forward-looking review of the research progress regarding MXenes in the neuromorphic sensing domain and discussed the critical challenges that need to be resolved.Key bottlenecks such as insufficient long-term stability under environmental exposure,high costs,scalability limitations in large-scale production,and mechanical mismatch in wearable integration hinder their practical deployment.Furthermore,unresolved issues like interfacial compatibility in heterostructures and energy inefficiency in neu-romorphic signal conversion demand urgent attention.The review offers insights into future research directions enhance the fundamental understanding of MXene properties and promote further integration into neuromorphic computing applications through the convergence with various emerging technologies.
基金supported by the NSFC(12474071)Natural Science Foundation of Shandong Province(ZR2024YQ051)+5 种基金Open Research Fund of State Key Laboratory of Materials for Integrated Circuits(SKLJC-K2024-12)the Shanghai Sailing Program(23YF1402200,23YF1402400)Natural Science Foundation of Jiangsu Province(BK20240424)Taishan Scholar Foundation of Shandong Province(tsqn202408006)Young Talent of Lifting engineering for Science and Technology in Shandong,China(SDAST2024QTB002)the Qilu Young Scholar Program of Shandong University.
文摘The advancement of flexible memristors has significantly promoted the development of wearable electronic for emerging neuromorphic computing applications.Inspired by in-memory computing architecture of human brain,flexible memristors exhibit great application potential in emulating artificial synapses for highefficiency and low power consumption neuromorphic computing.This paper provides comprehensive overview of flexible memristors from perspectives of development history,material system,device structure,mechanical deformation method,device performance analysis,stress simulation during deformation,and neuromorphic computing applications.The recent advances in flexible electronics are summarized,including single device,device array and integration.The challenges and future perspectives of flexible memristor for neuromorphic computing are discussed deeply,paving the way for constructing wearable smart electronics and applications in large-scale neuromorphic computing and high-order intelligent robotics.
基金financially supported by the National Natural Science Foundation of China(Grant No.12172093)the Guangdong Basic and Applied Basic Research Foundation(Grant No.2021A1515012607)。
文摘High-entropy oxides(HEOs)have emerged as a promising class of memristive materials,characterized by entropy-stabilized crystal structures,multivalent cation coordination,and tunable defect landscapes.These intrinsic features enable forming-free resistive switching,multilevel conductance modulation,and synaptic plasticity,making HEOs attractive for neuromorphic computing.This review outlines recent progress in HEO-based memristors across materials engineering,switching mechanisms,and synaptic emulation.Particular attention is given to vacancy migration,phase transitions,and valence-state dynamics—mechanisms that underlie the switching behaviors observed in both amorphous and crystalline systems.Their relevance to neuromorphic functions such as short-term plasticity and spike-timing-dependent learning is also examined.While encouraging results have been achieved at the device level,challenges remain in conductance precision,variability control,and scalable integration.Addressing these demands a concerted effort across materials design,interface optimization,and task-aware modeling.With such integration,HEO memristors offer a compelling pathway toward energy-efficient and adaptable brain-inspired electronics.
文摘To support popular Internet of Things(IoT)applications such as virtual reality and mobile games,edge computing provides a front-end distributed computing archetype of centralized cloud computing with low latency and distributed data processing.However,it is challenging for multiple users to offload their computation tasks because they are competing for spectrum and computation as well as Radio Access Technologies(RAT)resources.In this paper,we investigate computation offloading mechanism of multiple selfish users with resource allocation in IoT edge computing networks by formulating it as a stochastic game.Each user is a learning agent observing its local network environment to learn optimal decisions on either local computing or edge computing with a goal of minimizing long term system cost by choosing its transmit power level,RAT and sub-channel without knowing any information of the other users.Since users’decisions are coupling at the gateway,we define the reward function of each user by considering the aggregated effect of other users.Therefore,a multi-agent reinforcement learning framework is developed to solve the game with the proposed Independent Learners based Multi-Agent Q-learning(IL-based MA-Q)algorithm.Simulations demonstrate that the proposed IL-based MA-Q algorithm is feasible to solve the formulated problem and is more energy efficient without extra cost on channel estimation at the centralized gateway.Finally,compared with the other three benchmark algorithms,it has better system cost performance and achieves distributed computation offloading.
基金founded by the National Science and Technology Council of the Republic of China under contract NSTC113-2221-E-019-032.
文摘An Interval Type-2(IT-2)fuzzy controller design approach is proposed in this research to simultaneously achievemultiple control objectives inNonlinearMulti-Agent Systems(NMASs),including formation,containment,and collision avoidance.However,inherent nonlinearities and uncertainties present in practical control systems contribute to the challenge of achieving precise control performance.Based on the IT-2 Takagi-Sugeno Fuzzy Model(T-SFM),the fuzzy control approach can offer a more effective solution for NMASs facing uncertainties.Unlike existing control methods for NMASs,the Formation and Containment(F-and-C)control problem with collision avoidance capability under uncertainties based on the IT-2 T-SFM is discussed for the first time.Moreover,an IT-2 fuzzy tracking control approach is proposed to solve the formation task for leaders in NMASs without requiring communication.This control scheme makes the design process of the IT-2 fuzzy Formation Controller(FC)more straightforward and effective.According to the communication interaction protocol,the IT-2 Containment Controller(CC)design approach is proposed for followers to ensure convergence into the region defined by the leaders.Leveraging the IT-2 T-SFM representation,the analysis methods developed for linear Multi-Agent Systems(MASs)are successfully extended to perform containment analysis without requiring the additional assumptions imposed in existing research.Notably,the IT-2 fuzzy tracking controller can also be applied in collision avoidance situations to track the desired trajectories calculated by the avoidance algorithm under the Artificial Potential Field(APF).Benefiting from the combination of vortex and source APFs,the leaders can properly adjust the system dynamics to prevent potential collision risk.Integrating the fuzzy theory and APFs avoidance algorithm,an IT-2 fuzzy controller design approach is proposed to achieve the F-and-C purposewhile ensuring collision avoidance capability.Finally,amulti-ship simulation is conducted to validate the feasibility and effectiveness of the designed IT-2 fuzzy controller.
基金supported by the National Natural Science Foundation of China(62162050)the Fundamental Research Funds for the Central Universities(No.N2217002)the Natural Science Foundation of Liaoning ProvincialDepartment of Science and Technology(No.2022-KF-11-04).
文摘Mobile-edge computing(MEC)is a promising technology for the fifth-generation(5G)and sixth-generation(6G)architectures,which provides resourceful computing capabilities for Internet of Things(IoT)devices,such as virtual reality,mobile devices,and smart cities.In general,these IoT applications always bring higher energy consumption than traditional applications,which are usually energy-constrained.To provide persistent energy,many references have studied the offloading problem to save energy consumption.However,the dynamic environment dramatically increases the optimization difficulty of the offloading decision.In this paper,we aim to minimize the energy consumption of the entireMECsystemunder the latency constraint by fully considering the dynamic environment.UnderMarkov games,we propose amulti-agent deep reinforcement learning approach based on the bi-level actorcritic learning structure to jointly optimize the offloading decision and resource allocation,which can solve the combinatorial optimization problem using an asymmetric method and compute the Stackelberg equilibrium as a better convergence point than Nash equilibrium in terms of Pareto superiority.Our method can better adapt to a dynamic environment during the data transmission than the single-agent strategy and can effectively tackle the coordination problem in the multi-agent environment.The simulation results show that the proposed method could decrease the total computational overhead by 17.8%compared to the actor-critic-based method and reduce the total computational overhead by 31.3%,36.5%,and 44.7%compared with randomoffloading,all local execution,and all offloading execution,respectively.
文摘Cloud computing can offer a very powerful, reliable, predictable and scalable computing infrastructure for the execution of MAS （multi-agent systems） implementing complex agent-based applications such when modelling, simulation and real-time running of complex systems must be provided. Multi-agent systems appears as an adequate approach to current challenges in many areas. Between important qualities of MAS also belongs to, that they are open, interoperable, and heterogenous systems. The agent is active, a program entity, has its own ideas how to perform the tasks of the own agenda. Agents： perceive, behave ＂reasonably＂, act in the environment, communicate with other agents. Cloud infrastructures can offer an ideal platform where run MAS systems simulations, applications and real-time running because of its large amount of processing and memory resources that can be dynamically configured for executing large agent-based software at unprecedented scale. Cloud computing can help chemical and food companies drive operational excellence; meet growing and changing customer demands; accelerate new product innovation and ramp-to-volume manufacturing in key markets; reduce IT spending; manage and mitigate supply chain risks; and enable faster and more flexible delivery of new IT system. Production type of SOC （service-oriented computing） can be inspired by a ＂Cloud＂, for the production of ＂Cloud＂ offers an attractive and natural solutions in several computing trends such as delivery system over the Internet, use of utilities, flexibility, virtualization, a ＂grid＂ distributed computing, outsourcing, Web 2.0, etc.. Production of the ＂Cloud＂ is also considered as a new multidisciplinary field that includes ＂network＂ production, virtual manufacturing, agile manufacturing, and of course cloud computing. Examples of cloud computing and MAS applications in food and chemistry development and industry, proposition of using multi-agent systems in the control of batch processes, modified ACO （ant colony optimization） approach for the diversified service allocation and scheduling mechanism in cloud paradigma, examples of applications in a business area were studied in the paper.
文摘Satellite edge computing has garnered significant attention from researchers;however,processing a large volume of tasks within multi-node satellite networks still poses considerable challenges.The sharp increase in user demand for latency-sensitive tasks has inevitably led to offloading bottlenecks and insufficient computational capacity on individual satellite edge servers,making it necessary to implement effective task offloading scheduling to enhance user experience.In this paper,we propose a priority-based task scheduling strategy based on a Software-Defined Network(SDN)framework for satellite-terrestrial integrated networks,which clarifies the execution order of tasks based on their priority.Subsequently,we apply a Dueling-Double Deep Q-Network(DDQN)algorithm enhanced with prioritized experience replay to derive a computation offloading strategy,improving the experience replay mechanism within the Dueling-DDQN framework.Next,we utilize the Deep Deterministic Policy Gradient(DDPG)algorithm to determine the optimal resource allocation strategy to reduce the processing latency of sub-tasks.Simulation results demonstrate that the proposed d3-DDPG algorithm outperforms other approaches,effectively reducing task processing latency and thus improving user experience and system efficiency.
基金The National Natural Science Foundation of China(62136008,62293541)The Beijing Natural Science Foundation(4232056)The Beijing Nova Program(20240484514).
文摘Cooperative multi-agent reinforcement learning(MARL)is a key technology for enabling cooperation in complex multi-agent systems.It has achieved remarkable progress in areas such as gaming,autonomous driving,and multi-robot control.Empowering cooperative MARL with multi-task decision-making capabilities is expected to further broaden its application scope.In multi-task scenarios,cooperative MARL algorithms need to address 3 types of multi-task problems:reward-related multi-task,arising from different reward functions;multi-domain multi-task,caused by differences in state and action spaces,state transition functions;and scalability-related multi-task,resulting from the dynamic variation in the number of agents.Most existing studies focus on scalability-related multitask problems.However,with the increasing integration between large language models(LLMs)and multi-agent systems,a growing number of LLM-based multi-agent systems have emerged,enabling more complex multi-task cooperation.This paper provides a comprehensive review of the latest advances in this field.By combining multi-task reinforcement learning with cooperative MARL,we categorize and analyze the 3 major types of multi-task problems under multi-agent settings,offering more fine-grained classifications and summarizing key insights for each.In addition,we summarize commonly used benchmarks and discuss future directions of research in this area,which hold promise for further enhancing the multi-task cooperation capabilities of multi-agent systems and expanding their practical applications in the real world.
基金supported by the"Science and Technology Development Plan Project of Jilin Province,China"(Grant No.20240101018JJ)the Fundamental Research Funds for the Central Universities(Grant No.2412023YQ004)the National Natural Science Foundation of China(Grant Nos.52072065,52272140,52372137,and U23A20568).
文摘Optoelectronic memristor is generating growing research interest for high efficient computing and sensing-memory applications.In this work,an optoelectronic memristor with Au/a-C:Te/Pt structure is developed.Synaptic functions,i.e.,excita-tory post-synaptic current and pair-pulse facilitation are successfully mimicked with the memristor under electrical and optical stimulations.More importantly,the device exhibited distinguishable response currents by adjusting 4-bit input electrical/opti-cal signals.A multi-mode reservoir computing(RC)system is constructed with the optoelectronic memristors to emulate human tactile-visual fusion recognition and an accuracy of 98.7%is achieved.The optoelectronic memristor provides potential for developing multi-mode RC system.
基金The National Natural Science Foundation of China(W2431048)The Science and Technology Research Program of Chongqing Municipal Education Commission,China(KJZDK202300807)The Chongqing Natural Science Foundation,China(CSTB2024NSCQQCXMX0052).
文摘This paper addresses the consensus problem of nonlinear multi-agent systems subject to external disturbances and uncertainties under denial-ofservice(DoS)attacks.Firstly,an observer-based state feedback control method is employed to achieve secure control by estimating the system's state in real time.Secondly,by combining a memory-based adaptive eventtriggered mechanism with neural networks,the paper aims to approximate the nonlinear terms in the networked system and efficiently conserve system resources.Finally,based on a two-degree-of-freedom model of a vehicle affected by crosswinds,this paper constructs a multi-unmanned ground vehicle(Multi-UGV)system to validate the effectiveness of the proposed method.Simulation results show that the proposed control strategy can effectively handle external disturbances such as crosswinds in practical applications,ensuring the stability and reliable operation of the Multi-UGV system.
基金funded by the Fundamental Research Funds for the Central Universities(J2023-024,J2023-027).
文摘As an important complement to cloud computing, edge computing can effectively reduce the workload of the backbone network. To reduce latency and energy consumption of edge computing, deep learning is used to learn the task offloading strategies by interacting with the entities. In actual application scenarios, users of edge computing are always changing dynamically. However, the existing task offloading strategies cannot be applied to such dynamic scenarios. To solve this problem, we propose a novel dynamic task offloading framework for distributed edge computing, leveraging the potential of meta-reinforcement learning (MRL). Our approach formulates a multi-objective optimization problem aimed at minimizing both delay and energy consumption. We model the task offloading strategy using a directed acyclic graph (DAG). Furthermore, we propose a distributed edge computing adaptive task offloading algorithm rooted in MRL. This algorithm integrates multiple Markov decision processes (MDP) with a sequence-to-sequence (seq2seq) network, enabling it to learn and adapt task offloading strategies responsively across diverse network environments. To achieve joint optimization of delay and energy consumption, we incorporate the non-dominated sorting genetic algorithm II (NSGA-II) into our framework. Simulation results demonstrate the superiority of our proposed solution, achieving a 21% reduction in time delay and a 19% decrease in energy consumption compared to alternative task offloading schemes. Moreover, our scheme exhibits remarkable adaptability, responding swiftly to changes in various network environments.
基金supported by the National Natural Science Foundation of China(Nos.12272104,U22B2013).
文摘This paper investigates the challenges associated with Unmanned Aerial Vehicle (UAV) collaborative search and target tracking in dynamic and unknown environments characterized by limited field of view. The primary objective is to explore the unknown environments to locate and track targets effectively. To address this problem, we propose a novel Multi-Agent Reinforcement Learning (MARL) method based on Graph Neural Network (GNN). Firstly, a method is introduced for encoding continuous-space multi-UAV problem data into spatial graphs which establish essential relationships among agents, obstacles, and targets. Secondly, a Graph AttenTion network (GAT) model is presented, which focuses exclusively on adjacent nodes, learns attention weights adaptively and allows agents to better process information in dynamic environments. Reward functions are specifically designed to tackle exploration challenges in environments with sparse rewards. By introducing a framework that integrates centralized training and distributed execution, the advancement of models is facilitated. Simulation results show that the proposed method outperforms the existing MARL method in search rate and tracking performance with less collisions. The experiments show that the proposed method can be extended to applications with a larger number of agents, which provides a potential solution to the challenging problem of multi-UAV autonomous tracking in dynamic unknown environments.
基金the National Research Foundation(NRF)Singapore mid-sized center grant(NRF-MSG-2023-0002)FrontierCRP grant(NRF-F-CRP-2024-0006)+2 种基金A*STAR Singapore MTC RIE2025 project(M24W1NS005)IAF-PP project(M23M5a0069)Ministry of Education(MOE)Singapore Tier 2 project(MOE-T2EP50220-0014).
文摘The rise of large-scale artificial intelligence(AI)models,such as ChatGPT,Deep-Seek,and autonomous vehicle systems,has significantly advanced the boundaries of AI,enabling highly complex tasks in natural language processing,image recognition,and real-time decisionmaking.However,these models demand immense computational power and are often centralized,relying on cloud-based architectures with inherent limitations in latency,privacy,and energy efficiency.To address these challenges and bring AI closer to real-world applications,such as wearable health monitoring,robotics,and immersive virtual environments,innovative hardware solutions are urgently needed.This work introduces a near-sensor edge computing(NSEC)system,built on a bilayer AlN/Si waveguide platform,to provide real-time,energy-efficient AI capabilities at the edge.Leveraging the electro-optic properties of AlN microring resonators for photonic feature extraction,coupled with Si-based thermo-optic Mach-Zehnder interferometers for neural network computations,the system represents a transformative approach to AI hardware design.Demonstrated through multimodal gesture and gait analysis,the NSEC system achieves high classification accuracies of 96.77%for gestures and 98.31%for gaits,ultra-low latency(<10 ns),and minimal energy consumption(<0.34 pJ).This groundbreaking system bridges the gap between AI models and real-world applications,enabling efficient,privacy-preserving AI solutions for healthcare,robotics,and next-generation human-machine interfaces,marking a pivotal advancement in edge computing and AI deployment.
基金supported by the Natural Science Foundation of Zhejiang Province(Grant No.LQ24F040007)the National Natural Science Foundation of China(Grant No.U22A2075)the Opening Project of State Key Laboratory of Polymer Materials Engineering(Sichuan University)(Grant No.sklpme2024-1-21).
文摘To address the increasing demand for massive data storage and processing,brain-inspired neuromorphic comput-ing systems based on artificial synaptic devices have been actively developed in recent years.Among the various materials inves-tigated for the fabrication of synaptic devices,silicon carbide(SiC)has emerged as a preferred choices due to its high electron mobility,superior thermal conductivity,and excellent thermal stability,which exhibits promising potential for neuromorphic applications in harsh environments.In this review,the recent progress in SiC-based synaptic devices is summarized.Firstly,an in-depth discussion is conducted regarding the categories,working mechanisms,and structural designs of these devices.Subse-quently,several application scenarios for SiC-based synaptic devices are presented.Finally,a few perspectives and directions for their future development are outlined.
基金supported by Future Network Scientific Research Fund Project (FNSRFP-2021-ZD-4)National Natural Science Foundation of China (No.61991404,61902182)+1 种基金National Key Research and Development Program of China under Grant 2020YFB1600104Key Research and Development Plan of Jiangsu Province under Grant BE2020084-2。
文摘With the rapid development of Intelligent Transportation Systems(ITS),many new applications for Intelligent Connected Vehicles(ICVs)have sprung up.In order to tackle the conflict between delay-sensitive applications and resource-constrained vehicles,computation offloading paradigm that transfers computation tasks from ICVs to edge computing nodes has received extensive attention.However,the dynamic network conditions caused by the mobility of vehicles and the unbalanced computing load of edge nodes make ITS face challenges.In this paper,we propose a heterogeneous Vehicular Edge Computing(VEC)architecture with Task Vehicles(TaVs),Service Vehicles(SeVs)and Roadside Units(RSUs),and propose a distributed algorithm,namely PG-MRL,which jointly optimizes offloading decision and resource allocation.In the first stage,the offloading decisions of TaVs are obtained through a potential game.In the second stage,a multi-agent Deep Deterministic Policy Gradient(DDPG),one of deep reinforcement learning algorithms,with centralized training and distributed execution is proposed to optimize the real-time transmission power and subchannel selection.The simulation results show that the proposed PG-MRL algorithm has significant improvements over baseline algorithms in terms of system delay.
文摘The rapid advent in artificial intelligence and big data has revolutionized the dynamic requirement in the demands of the computing resource for executing specific tasks in the cloud environment.The process of achieving autonomic resource management is identified to be a herculean task due to its huge distributed and heterogeneous environment.Moreover,the cloud network needs to provide autonomic resource management and deliver potential services to the clients by complying with the requirements of Quality-of-Service(QoS)without impacting the Service Level Agreements(SLAs).However,the existing autonomic cloud resource managing frameworks are not capable in handling the resources of the cloud with its dynamic requirements.In this paper,Coot Bird Behavior Model-based Workload Aware Autonomic Resource Management Scheme(CBBM-WARMS)is proposed for handling the dynamic requirements of cloud resources through the estimation of workload that need to be policed by the cloud environment.This CBBM-WARMS initially adopted the algorithm of adaptive density peak clustering for workloads clustering of the cloud.Then,it utilized the fuzzy logic during the process of workload scheduling for achieving the determining the availability of cloud resources.It further used CBBM for potential Virtual Machine(VM)deployment that attributes towards the provision of optimal resources.It is proposed with the capability of achieving optimal QoS with minimized time,energy consumption,SLA cost and SLA violation.The experimental validation of the proposed CBBMWARMS confirms minimized SLA cost of 19.21%and reduced SLA violation rate of 18.74%,better than the compared autonomic cloud resource managing frameworks.
基金supported in part by the National Natural Science Foundation of China under Grant No.61473066in part by the Natural Science Foundation of Hebei Province under Grant No.F2021501020+2 种基金in part by the S&T Program of Qinhuangdao under Grant No.202401A195in part by the Science Research Project of Hebei Education Department under Grant No.QN2025008in part by the Innovation Capability Improvement Plan Project of Hebei Province under Grant No.22567637H
文摘Recently,one of the main challenges facing the smart grid is insufficient computing resources and intermittent energy supply for various distributed components(such as monitoring systems for renewable energy power stations).To solve the problem,we propose an energy harvesting based task scheduling and resource management framework to provide robust and low-cost edge computing services for smart grid.First,we formulate an energy consumption minimization problem with regard to task offloading,time switching,and resource allocation for mobile devices,which can be decoupled and transformed into a typical knapsack problem.Then,solutions are derived by two different algorithms.Furthermore,we deploy renewable energy and energy storage units at edge servers to tackle intermittency and instability problems.Finally,we design an energy management algorithm based on sampling average approximation for edge computing servers to derive the optimal charging/discharging strategies,number of energy storage units,and renewable energy utilization.The simulation results show the efficiency and superiority of our proposed framework.
基金supported by the ONR Vannevar Bush Faculty Fellowship(Grant No.N00014-22-1-2795).
文摘Large language models(LLMs)have emerged as powerful tools for addressing a wide range of problems,including those in scientific computing,particularly in solving partial differential equations(PDEs).However,different models exhibit distinct strengths and preferences,resulting in varying levels of performance.In this paper,we compare the capabilities of the most advanced LLMs—DeepSeek,ChatGPT,and Claude—along with their reasoning-optimized versions in addressing computational challenges.Specifically,we evaluate their proficiency in solving traditional numerical problems in scientific computing as well as leveraging scientific machine learning techniques for PDE-based problems.We designed all our experiments so that a nontrivial decision is required,e.g,defining the proper space of input functions for neural operator learning.Our findings show that reasoning and hybrid-reasoning models consistently and significantly outperform non-reasoning ones in solving challenging problems,with ChatGPT o3-mini-high generally offering the fastest reasoning speed.
