A game-theoretic approach for federated learning:A trade-off among privacy,accuracy and energy

Benefiting from the development of Federated Learning(FL)and distributed communication systems,large-scale intelligent applications become possible.Distributed devices not only provide adequate training data,but also cause privacy leakage and energy consumption.How to optimize the energy consumption in distributed communication systems,while ensuring the privacy of users and model accuracy,has become an urgent challenge.In this paper,we define the FL as a 3-layer architecture including users,agents and server.In order to find a balance among model training accuracy,privacy-preserving effect,and energy consumption,we design the training process of FL as game models.We use an extensive game tree to analyze the key elements that influence the players’decisions in the single game,and then find the incentive mechanism that meet the social norms through the repeated game.The experimental results show that the Nash equilibrium we obtained satisfies the laws of reality,and the proposed incentive mechanism can also promote users to submit high-quality data in FL.Following the multiple rounds of play,the incentive mechanism can help all players find the optimal strategies for energy,privacy,and accuracy of FL in distributed communication systems.

Distributed Nash Equilibrium Seeking Strategies Under Quantized Communication

This paper is concerned with distributed Nash equi librium seeking strategies under quantized communication. In the proposed seeking strategy, a projection operator is synthesized with a gradient search method to achieve the optimization o players' objective functions while restricting their actions within required non-empty, convex and compact domains. In addition, a leader-following consensus protocol, in which quantized informa tion flows are utilized, is employed for information sharing among players. More specifically, logarithmic quantizers and uniform quantizers are investigated under both undirected and connected communication graphs and strongly connected digraphs, respec tively. Through Lyapunov stability analysis, it is shown that play ers' actions can be steered to a neighborhood of the Nash equilib rium with logarithmic and uniform quantizers, and the quanti fied convergence error depends on the parameter of the quan tizer for both undirected and directed cases. A numerical exam ple is given to verify the theoretical results.

Mastering air combat game with deep reinforcement learning

Reinforcement learning has been applied to air combat problems in recent years,and the idea of curriculum learning is often used for reinforcement learning,but traditional curriculum learning suffers from the problem of plasticity loss in neural networks.Plasticity loss is the difficulty of learning new knowledge after the network has converged.To this end,we propose a motivational curriculum learning distributed proximal policy optimization(MCLDPPO)algorithm,through which trained agents can significantly outperform the predictive game tree and mainstream reinforcement learning methods.The motivational curriculum learning is designed to help the agent gradually improve its combat ability by observing the agent's unsatisfactory performance and providing appropriate rewards as a guide.Furthermore,a complete tactical maneuver is encapsulated based on the existing air combat knowledge,and through the flexible use of these maneuvers,some tactics beyond human knowledge can be realized.In addition,we designed an interruption mechanism for the agent to increase the frequency of decisionmaking when the agent faces an emergency.When the number of threats received by the agent changes,the current action is interrupted in order to reacquire observations and make decisions again.Using the interruption mechanism can significantly improve the performance of the agent.To simulate actual air combat better,we use digital twin technology to simulate real air battles and propose a parallel battlefield mechanism that can run multiple simulation environments simultaneously,effectively improving data throughput.The experimental results demonstrate that the agent can fully utilize the situational information to make reasonable decisions and provide tactical adaptation in the air combat,verifying the effectiveness of the algorithmic framework proposed in this paper.

Co-Harvest Phase-Change Enthalpy and Isomerization Energy for High-Energy Heat Output by Controlling Crystallization of Alkyl-Grafted Azobenzene Molecules

Photoisomerization-induced phase change are important for co-harvesting the latent heat and isomerization energy of azobenzene molecules.Chemically optimizing heat output and energy delivery at alternating temperatures are challenging because of the differences in crystallizability and isomerization.This article reports two series of asymmetrically alkyl-grafted azobenzene(Azo-g),with and without a methyl group,that have an optically triggered phase change.Three exothermic modes were designed to utilize crystallization enthalpy(△H_(c))and photothermal(isomerization)energy(△H_(p))at different temperatures determined by the crystallization.Azo-g has high heat output(275-303 J g^(-1))by synchronously releasing△H_(c)and△H_(p)over a wide temperature range(-79℃to 25℃).We fabricated a new distributed energy utilization and delivery system to realize a temperature increase of 6.6℃at a temperature of-8℃.The findings offer insight into selective utilization of latent heat and isomerization energy by molecular optimization of crystallization and isomerization processes.

Evolutionary Neural Architecture Search and Its Applications in Healthcare

Most of the neural network architectures are based on human experience,which requires a long and tedious trial-and-error process.Neural architecture search(NAS)attempts to detect effective architectures without human intervention.Evolutionary algorithms(EAs)for NAS can find better solutions than human-designed architectures by exploring a large search space for possible architectures.Using multiobjective EAs for NAS,optimal neural architectures that meet various performance criteria can be explored and discovered efficiently.Furthermore,hardware-accelerated NAS methods can improve the efficiency of the NAS.While existing reviews have mainly focused on different strategies to complete NAS,a few studies have explored the use of EAs for NAS.In this paper,we summarize and explore the use of EAs for NAS,as well as large-scale multiobjective optimization strategies and hardware-accelerated NAS methods.NAS performs well in healthcare applications,such as medical image analysis,classification of disease diagnosis,and health monitoring.EAs for NAS can automate the search process and optimize multiple objectives simultaneously in a given healthcare task.Deep neural network has been successfully used in healthcare,but it lacks interpretability.Medical data is highly sensitive,and privacy leaks are frequently reported in the healthcare industry.To solve these problems,in healthcare,we propose an interpretable neuroevolution framework based on federated learning to address search efficiency and privacy protection.Moreover,we also point out future research directions for evolutionary NAS.Overall,for researchers who want to use EAs to optimize NNs in healthcare,we analyze the advantages and disadvantages of doing so to provide detailed guidance,and propose an interpretable privacy-preserving framework for healthcare applications.

Robust and Trustworthy Data Sharing Framework Leveraging On-Chain and Off-Chain Collaboration

The proliferation of Internet of Things(IoT)systems has resulted in the generation of substantial data,presenting new challenges in reliable storage and trustworthy sharing.Conventional distributed storage systems are hindered by centralized management and lack traceability,while blockchain systems are limited by low capacity and high latency.To address these challenges,the present study investigates the reliable storage and trustworthy sharing of IoT data,and presents a novel system architecture that integrates on-chain and off-chain data manage systems.This architecture,integrating blockchain and distributed storage technologies,provides high-capacity,high-performance,traceable,and verifiable data storage and access.The on-chain system,built on Hyperledger Fabric,manages metadata,verification data,and permission information of the raw data.The off-chain system,implemented using IPFS Cluster,ensures the reliable storage and efficient access to massive files.A collaborative storage server is designed to integrate on-chain and off-chain operation interfaces,facilitating comprehensive data operations.We provide a unified access interface for user-friendly system interaction.Extensive testing validates the system’s reliability and stable performance.The proposed approach significantly enhances storage capacity compared to standalone blockchain systems.Rigorous reliability tests consistently yield positive outcomes.With average upload and download throughputs of roughly 20 and 30 MB/s,respectively,the system’s throughput surpasses the blockchain system by a factor of 4 to 18.

Sparse Adversarial Learning for FDIA Attack Sample Generation in Distributed Smart

False data injection attack(FDIA)is an attack that affects the stability of grid cyber-physical system(GCPS)by evading the detecting mechanism of bad data.Existing FDIA detection methods usually employ complex neural networkmodels to detect FDIA attacks.However,they overlook the fact that FDIA attack samples at public-private network edges are extremely sparse,making it difficult for neural network models to obtain sufficient samples to construct a robust detection model.To address this problem,this paper designs an efficient sample generative adversarial model of FDIA attack in public-private network edge,which can effectively bypass the detectionmodel to threaten the power grid system.A generative adversarial network(GAN)framework is first constructed by combining residual networks(ResNet)with fully connected networks(FCN).Then,a sparse adversarial learning model is built by integrating the time-aligned data and normal data,which is used to learn the distribution characteristics between normal data and attack data through iterative confrontation.Furthermore,we introduce a Gaussian hybrid distributionmatrix by aggregating the network structure of attack data characteristics and normal data characteristics,which can connect and calculate FDIA data with normal characteristics.Finally,efficient FDIA attack samples can be sequentially generated through interactive adversarial learning.Extensive simulation experiments are conducted with IEEE 14-bus and IEEE 118-bus system data,and the results demonstrate that the generated attack samples of the proposed model can present superior performance compared to state-of-the-art models in terms of attack strength,robustness,and covert capability.

Monitoring Surface Deformation Using Distributed Scatterers InSAR

In the past two decades,extensive and in-depth research has been conducted on Time Series InSAR technology with the advancement of high-performance SAR satellites and the accumulation of big SAR data.The introduction of distributed scatterers in Distributed Scatterers InSAR(DS-InSAR)has significantly expanded the application scenarios of InSAR geodetic measurement by increasing the number of measurement points.This study traces the history of DS-InSAR,presents the definition and characteristics of distributed scatterers,and focuses on exploring the relationships and distinctions among proposed algorithms in two crucial steps:statistically homogeneous pixel selection and phase optimization.Additionally,the latest research progress in this field is tracked and the possible development direction in the future is discussed.Through simulation experiments and two real InSAR case studies,the proposed algorithms are compared and verified,and the advantages of DS-InSAR in deformation measurement practice are demonstrated.This work not only offers insights into current trends and focal points for theoretical research on DS-InSAR but also provides practical cases and guidance for applied research.

Distributed fiber optic sensors for tunnel monitoring:A state-of-the-art review

Distributed fiber optic sensors(DFOSs)possess the capability to measure strain and temperature variations over long distances,demonstrating outstanding potential for monitoring underground infrastructure.This study presents a state-of-the-art review of the DFOS applications for monitoring and assessing the deformation behavior of typical tunnel infrastructure,including bored tunnels,conventional tunnels,as well as immersed and cut-and-cover tunnels.DFOS systems based on Brillouin and Rayleigh scattering principles are both considered.When implementing DFOS monitoring,the fiber optic cable can be primarily installed along transverse and longitudinal directions to(1)measure distributed strains by continuously adhering the fiber to the structure’s surface or embedding it in the lining,or(2)measure point displacements by spot-anchoring it on the lining surface.There are four critical aspects of DFOS monitoring,including proper selection of the sensing fiber,selection of the measuring principle for the specific application,design of an effective sensor layout,and establishment of robust field sensor instrumentation.These four issues are comprehensively discussed,and practical suggestions are provided for the implementation of DFOS in tunnel infrastructure monitoring.

Autonomous Vehicle Platoons In Urban Road Networks:A Joint Distributed Reinforcement Learning and Model Predictive Control Approach

In this paper, platoons of autonomous vehicles operating in urban road networks are considered. From a methodological point of view, the problem of interest consists of formally characterizing vehicle state trajectory tubes by means of routing decisions complying with traffic congestion criteria. To this end, a novel distributed control architecture is conceived by taking advantage of two methodologies: deep reinforcement learning and model predictive control. On one hand, the routing decisions are obtained by using a distributed reinforcement learning algorithm that exploits available traffic data at each road junction. On the other hand, a bank of model predictive controllers is in charge of computing the more adequate control action for each involved vehicle. Such tasks are here combined into a single framework:the deep reinforcement learning output(action) is translated into a set-point to be tracked by the model predictive controller;conversely, the current vehicle position, resulting from the application of the control move, is exploited by the deep reinforcement learning unit for improving its reliability. The main novelty of the proposed solution lies in its hybrid nature: on one hand it fully exploits deep reinforcement learning capabilities for decisionmaking purposes;on the other hand, time-varying hard constraints are always satisfied during the dynamical platoon evolution imposed by the computed routing decisions. To efficiently evaluate the performance of the proposed control architecture, a co-design procedure, involving the SUMO and MATLAB platforms, is implemented so that complex operating environments can be used, and the information coming from road maps(links,junctions, obstacles, semaphores, etc.) and vehicle state trajectories can be shared and exchanged. Finally by considering as operating scenario a real entire city block and a platoon of eleven vehicles described by double-integrator models, several simulations have been performed with the aim to put in light the main f eatures of the proposed approach. Moreover, it is important to underline that in different operating scenarios the proposed reinforcement learning scheme is capable of significantly reducing traffic congestion phenomena when compared with well-reputed competitors.

Distributed Multicircular Circumnavigation Control for UAVs with Desired Angular Spacing

This paper addresses a multicircular circumnavigation control for UAVs with desired angular spacing around a nonstationary target.By defining a coordinated error relative to neighboring angular spacing,under the premise that target information is perfectly accessible by all nodes,a centralized circular enclosing control strategy is derived for multiple UAVs connected by an undirected graph to allow for formation behaviors concerning the moving target.Besides,to avoid the requirement of target’s states being accessible for each UAV,fixed-time distributed observers are introduced to acquire the state estimates in a fixed-time sense,and the upper boundary of settling time can be determined offline irrespective of initial properties,greatly releasing the burdensome communication traffic.Then,with the aid of fixed-time distributed observers,a distributed circular circumnavigation controller is derived to force all UAVs to collaboratively evolve along the preset circles while keeping a desired angular spacing.It is inferred from Lyapunov stability that all errors are demonstrated to be convergent.Simulations are offered to verify the utility of proposed protocol.

GRU-integrated constrained soft actor-critic learning enabled fully distributed scheduling strategy for residential virtual power plant

In this study,a novel residential virtual power plant(RVPP)scheduling method that leverages a gate recurrent unit(GRU)-integrated deep reinforcement learning(DRL)algorithm is proposed.In the proposed scheme,the GRU-integrated DRL algorithm guides the RVPP to participate effectively in both the day-ahead and real-time markets,lowering the electricity purchase costs and consumption risks for end-users.The Lagrangian relaxation technique is introduced to transform the constrained Markov decision process(CMDP)into an unconstrained optimization problem,which guarantees that the constraints are strictly satisfied without determining the penalty coefficients.Furthermore,to enhance the scalability of the constrained soft actor-critic(CSAC)-based RVPP scheduling approach,a fully distributed scheduling architecture was designed to enable plug-and-play in the residential distributed energy resources(RDER).Case studies performed on the constructed RVPP scenario validated the performance of the proposed methodology in enhancing the responsiveness of the RDER to power tariffs,balancing the supply and demand of the power grid,and ensuring customer comfort.

Enhancing Security and Privacy in Distributed Face Recognition Systems through Blockchain and GAN Technologies

The use of privacy-enhanced facial recognition has increased in response to growing concerns about data securityand privacy in the digital age. This trend is spurred by rising demand for face recognition technology in a varietyof industries, including access control, law enforcement, surveillance, and internet communication. However,the growing usage of face recognition technology has created serious concerns about data monitoring and userprivacy preferences, especially in context-aware systems. In response to these problems, this study provides a novelframework that integrates sophisticated approaches such as Generative Adversarial Networks (GANs), Blockchain,and distributed computing to solve privacy concerns while maintaining exact face recognition. The framework’spainstaking design and execution strive to strike a compromise between precise face recognition and protectingpersonal data integrity in an increasingly interconnected environment. Using cutting-edge tools like Dlib for faceanalysis,Ray Cluster for distributed computing, and Blockchain for decentralized identity verification, the proposedsystem provides scalable and secure facial analysis while protecting user privacy. The study’s contributions includethe creation of a sustainable and scalable solution for privacy-aware face recognition, the implementation of flexibleprivacy computing approaches based on Blockchain networks, and the demonstration of higher performanceover previous methods. Specifically, the proposed StyleGAN model has an outstanding accuracy rate of 93.84%while processing high-resolution images from the CelebA-HQ dataset, beating other evaluated models such asProgressive GAN 90.27%, CycleGAN 89.80%, and MGAN 80.80%. With improvements in accuracy, speed, andprivacy protection, the framework has great promise for practical use in a variety of fields that need face recognitiontechnology. This study paves the way for future research in privacy-enhanced face recognition systems, emphasizingthe significance of using cutting-edge technology to meet rising privacy issues in digital identity.

Observer-based dynamic event-triggered control for distributed parameter systems over mobile sensor-plus-actuator networks

We develop a policy of observer-based dynamic event-triggered state feedback control for distributed parameter systems over a mobile sensor-plus-actuator network.It is assumed that the mobile sensing devices that provide spatially averaged state measurements can be used to improve state estimation in the network.For the purpose of decreasing the update frequency of controller and unnecessary sampled data transmission, an efficient dynamic event-triggered control policy is constructed.In an event-triggered system, when an error signal exceeds a specified time-varying threshold, it indicates the occurrence of a typical event.The global asymptotic stability of the event-triggered closed-loop system and the boundedness of the minimum inter-event time can be guaranteed.Based on the linear quadratic optimal regulator, the actuator selects the optimal displacement only when an event occurs.A simulation example is finally used to verify that the effectiveness of such a control strategy can enhance the system performance.

Distributed Dynamic Load in Structural Dynamics by the Impulse-Based Force Estimation Algorithm

This paper proposes a novel approach for identifying distributed dynamic loads in the time domain.Using polynomial andmodal analysis,the load is transformed intomodal space for coefficient identification.This allows the distributed dynamic load with a two-dimensional form in terms of time and space to be simultaneously identified in the form of modal force,thereby achieving dimensionality reduction.The Impulse-based Force Estimation Algorithm is proposed to identify dynamic loads in the time domain.Firstly,the algorithm establishes a recursion scheme based on convolution integral,enabling it to identify loads with a long history and rapidly changing forms over time.Secondly,the algorithm introduces moving mean and polynomial fitting to detrend,enhancing its applicability in load estimation.The aforementioned methodology successfully accomplishes the reconstruction of distributed,instead of centralized,dynamic loads on the continuum in the time domain by utilizing acceleration response.To validate the effectiveness of the method,computational and experimental verification were conducted.

Q-Learning-Assisted Meta-Heuristics for Scheduling Distributed Hybrid Flow Shop Problems

The flow shop scheduling problem is important for the manufacturing industry.Effective flow shop scheduling can bring great benefits to the industry.However,there are few types of research on Distributed Hybrid Flow Shop Problems(DHFSP)by learning assisted meta-heuristics.This work addresses a DHFSP with minimizing the maximum completion time(Makespan).First,a mathematical model is developed for the concerned DHFSP.Second,four Q-learning-assisted meta-heuristics,e.g.,genetic algorithm(GA),artificial bee colony algorithm(ABC),particle swarm optimization(PSO),and differential evolution(DE),are proposed.According to the nature of DHFSP,six local search operations are designed for finding high-quality solutions in local space.Instead of randomselection,Q-learning assists meta-heuristics in choosing the appropriate local search operations during iterations.Finally,based on 60 cases,comprehensive numerical experiments are conducted to assess the effectiveness of the proposed algorithms.The experimental results and discussions prove that using Q-learning to select appropriate local search operations is more effective than the random strategy.To verify the competitiveness of the Q-learning assistedmeta-heuristics,they are compared with the improved iterated greedy algorithm(IIG),which is also for solving DHFSP.The Friedman test is executed on the results by five algorithms.It is concluded that the performance of four Q-learning-assisted meta-heuristics are better than IIG,and the Q-learning-assisted PSO shows the best competitiveness.

Trust Score-Based Malicious Vehicle Detection Scheme in Vehicular Network Environments

Advancements in the vehicular network technology enable real-time interconnection,data sharing,and intelligent cooperative driving among vehicles.However,malicious vehicles providing illegal and incorrect information can compromise the interests of vehicle users.Trust mechanisms serve as an effective solution to this issue.In recent years,many researchers have incorporated blockchain technology to manage and incentivize vehicle nodes,incurring significant overhead and storage requirements due to the frequent ingress and egress of vehicles within the area.In this paper,we propose a distributed vehicular network scheme based on trust scores.Specifically,the designed architecture partitions multiple vehicle regions into clusters.Then,cloud supervision systems(CSSs)verify the accuracy of the information transmitted by vehicles.Additionally,the trust scores for vehicles are calculated to reward or penalize them based on the trust evaluation model.Our proposed scheme demonstrates good scalability and effectively addresses the main cause of malicious information distribution among vehicles.Both theoretical and experimental analysis show that our scheme outperforms the compared schemes.

A Tutorial on Federated Learning from Theory to Practice:Foundations,Software Frameworks,Exemplary Use Cases,and Selected Trends

When data privacy is imposed as a necessity,Federated learning(FL)emerges as a relevant artificial intelligence field for developing machine learning(ML)models in a distributed and decentralized environment.FL allows ML models to be trained on local devices without any need for centralized data transfer,thereby reducing both the exposure of sensitive data and the possibility of data interception by malicious third parties.This paradigm has gained momentum in the last few years,spurred by the plethora of real-world applications that have leveraged its ability to improve the efficiency of distributed learning and to accommodate numerous participants with their data sources.By virtue of FL,models can be learned from all such distributed data sources while preserving data privacy.The aim of this paper is to provide a practical tutorial on FL,including a short methodology and a systematic analysis of existing software frameworks.Furthermore,our tutorial provides exemplary cases of study from three complementary perspectives:i)Foundations of FL,describing the main components of FL,from key elements to FL categories;ii)Implementation guidelines and exemplary cases of study,by systematically examining the functionalities provided by existing software frameworks for FL deployment,devising a methodology to design a FL scenario,and providing exemplary cases of study with source code for different ML approaches;and iii)Trends,shortly reviewing a non-exhaustive list of research directions that are under active investigation in the current FL landscape.The ultimate purpose of this work is to establish itself as a referential work for researchers,developers,and data scientists willing to explore the capabilities of FL in practical applications.

Combined CNN-LSTM Deep Learning Algorithms for Recognizing Human Physical Activities in Large and Distributed Manners:A Recommendation System

Recognizing human activity(HAR)from data in a smartphone sensor plays an important role in the field of health to prevent chronic diseases.Daily and weekly physical activities are recorded on the smartphone and tell the user whether he is moving well or not.Typically,smartphones and their associated sensing devices operate in distributed and unstable environments.Therefore,collecting their data and extracting useful information is a significant challenge.In this context,the aimof this paper is twofold:The first is to analyze human behavior based on the recognition of physical activities.Using the results of physical activity detection and classification,the second part aims to develop a health recommendation system to notify smartphone users about their healthy physical behavior related to their physical activities.This system is based on the calculation of calories burned by each user during physical activities.In this way,conclusions can be drawn about a person’s physical behavior by estimating the number of calories burned after evaluating data collected daily or even weekly following a series of physical workouts.To identify and classify human behavior our methodology is based on artificial intelligence models specifically deep learning techniques like Long Short-Term Memory(LSTM),stacked LSTM,and bidirectional LSTM.Since human activity data contains both spatial and temporal information,we proposed,in this paper,to use of an architecture allowing the extraction of the two types of information simultaneously.While Convolutional Neural Networks(CNN)has an architecture designed for spatial information,our idea is to combine CNN with LSTM to increase classification accuracy by taking into consideration the extraction of both spatial and temporal data.The results obtained achieved an accuracy of 96%.On the other side,the data learned by these algorithms is prone to error and uncertainty.To overcome this constraint and improve performance(96%),we proposed to use the fusion mechanisms.The last combines deep learning classifiers tomodel non-accurate and ambiguous data to obtain synthetic information to aid in decision-making.The Voting and Dempster-Shafer(DS)approaches are employed.The results showed that fused classifiers based on DS theory outperformed individual classifiers(96%)with the highest accuracy level of 98%.Also,the findings disclosed that participants engaging in physical activities are healthy,showcasing a disparity in the distribution of physical activities between men and women.

Big Data Application Simulation Platform Design for Onboard Distributed Processing of LEO Mega-Constellation Networks

Due to the restricted satellite payloads in LEO mega-constellation networks(LMCNs),remote sensing image analysis,online learning and other big data services desirably need onboard distributed processing(OBDP).In existing technologies,the efficiency of big data applications(BDAs)in distributed systems hinges on the stable-state and low-latency links between worker nodes.However,LMCNs with high-dynamic nodes and long-distance links can not provide the above conditions,which makes the performance of OBDP hard to be intuitively measured.To bridge this gap,a multidimensional simulation platform is indispensable that can simulate the network environment of LMCNs and put BDAs in it for performance testing.Using STK's APIs and parallel computing framework,we achieve real-time simulation for thousands of satellite nodes,which are mapped as application nodes through software defined network(SDN)and container technologies.We elaborate the architecture and mechanism of the simulation platform,and take the Starlink and Hadoop as realistic examples for simulations.The results indicate that LMCNs have dynamic end-to-end latency which fluctuates periodically with the constellation movement.Compared to ground data center networks(GDCNs),LMCNs deteriorate the computing and storage job throughput,which can be alleviated by the utilization of erasure codes and data flow scheduling of worker nodes.