Asynchronous Update Research Articles

Threshold model with anticonformity under random sequential updating.

We study an asymmetric version of the threshold model of binary decision making with anticonformity under an asynchronous update mode that mimics continuous time. We analyze this model on a complete graph using three different approaches: the mean-field approximation, Monte Carlo simulation, and the Markov chain approach. The latter approach yields analytical results for arbitrarily small systems, in contrast to the mean-field approach, which is strictly correct only for an infinite system. We show that, for sufficiently large systems, all three approaches produce the same results, as expected. We consider two cases: (1) homogeneous, in which all agents have the same tolerance threshold, and (2) heterogeneous, in which thresholds are given by a beta distribution parametrized by two positive shape parameters α and β. The heterogeneous case can be treated as a generalized model that reduces to a homogeneous model in special cases. We show that particularly interesting behaviors, including social hysteresis and critical mass reported in innovation diffusion, arise only for values of α and β that yield the shape of the distribution observed in reality.

Optimal Policy of Multiplayer Poker via Actor-Critic Reinforcement Learning

Poker has been considered a challenging problem in both artificial intelligence and game theory because poker is characterized by imperfect information and uncertainty, which are similar to many realistic problems like auctioning, pricing, cyber security, and operations. However, it is not clear that playing an equilibrium policy in multi-player games would be wise so far, and it is infeasible to theoretically validate whether a policy is optimal. Therefore, designing an effective optimal policy learning method has more realistic significance. This paper proposes an optimal policy learning method for multi-player poker games based on Actor-Critic reinforcement learning. Firstly, this paper builds the Actor network to make decisions with imperfect information and the Critic network to evaluate policies with perfect information. Secondly, this paper proposes a novel multi-player poker policy update method: asynchronous policy update algorithm (APU) and dual-network asynchronous policy update algorithm (Dual-APU) for multi-player multi-policy scenarios and multi-player sharing-policy scenarios, respectively. Finally, this paper takes the most popular six-player Texas hold ’em poker to validate the performance of the proposed optimal policy learning method. The experiments demonstrate the policies learned by the proposed methods perform well and gain steadily compared with the existing approaches. In sum, the policy learning methods of imperfect information games based on Actor-Critic reinforcement learning perform well on poker and can be transferred to other imperfect information games. Such training with perfect information and testing with imperfect information models show an effective and explainable approach to learning an approximately optimal policy.

Distributed Stochastic Inertial-Accelerated Methods with Delayed Derivatives for Nonconvex Problems

Stochastic gradient methods (SGMs) are predominant approaches for solving stochastic optimization. On smooth nonconvex problems, a few acceleration techniques have been applied to improve the convergence rate of SGMs. However, little exploration has been made on applying a certain acceleration technique to a stochastic subgradient method (SsGM) for nonsmooth nonconvex problems. In addition, few efforts have been made to analyze an (accelerated) SsGM with delayed derivatives. The information delay naturally happens in a distributed system, where computing workers do not coordinate with each other. In this paper, we propose an inertial proximal SsGM for solving nonsmooth nonconvex stochastic optimization problems. The proposed method can have guaranteed convergence even with delayed derivative information in a distributed environment. Convergence rate results are established for three classes of nonconvex problems: weakly convex nonsmooth problems with a convex regularizer, composite nonconvex problems with a nonsmooth convex regularizer, and smooth nonconvex problems. For each problem class, the convergence rate is $O(1/K^{\frac{1}{2}})$ in the expected value of the gradient norm square, for $K$ iterations. In a distributed environment, the convergence rate of the proposed method will be slowed down by the information delay. Nevertheless, the slow-down effect will decay with the number of iterations for the latter two problem classes. We test the proposed method on three applications. The numerical results clearly demonstrate the advantages of using the inertial-based acceleration. Furthermore, we observe higher parallelization speed-up in asynchronous updates over the synchronous counterpart, though the former uses delayed derivatives. Our source code is available at https://github.com/RPI-OPT/Inertial-SsGM.

Distributed event‐triggered tracking consensus control for privacy preservation in multi‐agent systems with denial‐of‐service attacks

SummaryThis article investigates the distributed tracking consensus control problem based on event‐triggered strategy for privacy preservation in nonlinear multi‐agent systems which suffer from denial‐of‐service (DoS) attacks. To address the insecurity of information exposure in the distributed control strategy, the method of privacy preservation for initial information is developed by relying on output maps as masks. Due to the existence of nonlinear dynamics, the neural networks are introduced to deal with unknown nonlinear functions. Then, an event‐triggered communication strategy based on the exponential time‐varying vector is provided to regulate the information transmission under the situation of DoS attacks. Subsequently, combining the proposed event‐triggered strategy, an asynchronous update control scheme is structured to reduce the effect of DoS attacks. It is demonstrated that the tracking consensus can be achieved by utilizing the Lyapunov function and the induction method. Finally, the feasibility of the proposed control method is demonstrated by a simulation example.

Periodic decentralized event-triggered control for nonlinear systems with asynchronous update and dynamic quantization

Periodic decentralized event-triggered control for nonlinear systems with asynchronous update and dynamic quantization

Artificial Intelligence, Algorithm Design, and Pricing

We calculate the time path of prices generated by algorithmic pricing games that differ in their learning protocols. Asynchronous learning occurs when the algorithm only learns about the return from the action it actually took. Synchronous learning occurs when the artificial intelligence conducts counterfactuals to learn about the returns it would have earned had it taken an alternative action. In a simple market setting, we show that synchronous updating can lead to competitive pricing, while asynchronous updating can lead to pricing close to monopoly levels. However, building simple economic reasoning into the asynchronous algorithms significantly modifies the prices it generates.

Asynchronous Decentralized Federated Learning for Collaborative Fault Diagnosis of PV Stations

Due to the different losses caused by various photovoltaic (PV) array faults, accurate diagnosis of fault types is becoming increasingly important. Compared with a single one, multiple PV stations collect sufficient fault samples, but their data is not allowed to be shared directly due to potential conflicts of interest. Therefore, federated learning can be exploited to train a collaborative fault diagnosis model. However, the modeling efficiency is seriously affected by the model update mechanism since each PV station has a different computing capability and amount of data. Moreover, for the safe and stable operation of the PV system, the robustness of collaborative modeling must be guaranteed rather than simply being processed on a central server. To address these challenges, a novel asynchronous decentralized federated learning (ADFL) framework is proposed. Each PV station not only trains its local model but also participates in collaborative fault diagnosis by exchanging model parameters to improve the generalization without losing accuracy. The global model is aggregated distributedly to avoid central node failure. By designing the asynchronous update scheme, the communication overhead and training time are greatly reduced. Both the experiments and numerical simulations are carried out to verify the effectiveness of the proposed method.

Distributed consensus problem with caching on federated learning framework

Federated learning framework facilitates more applications of deep learning algorithms on the existing network architectures, where the model parameters are aggregated in a centralized manner. However, some of federated learning participants are often inaccessible, such as in a power shortage or dormant state. That will force us to explore the possibility that the parameter aggregation is operated in an ad hoc manner, which is based on consensus computing. On the contrary, since caching mechanism is indispensable to any federated learning mobile node, it is necessary to investigate the connection between it and consensus computing. In this article, we first propose a novel federated learning paradigm, which supports an ad hoc operation mode for federated learning participants. Second, a discrete-time dynamic equation and its control law are formulated to satisfy the demands from federated learning framework, with a quantized caching scheme designed to mask the uncertainties from both asynchronous updates and measurement noises. Then, the consensus conditions and the convergence of the consensus protocol are deduced analytically, and a quantized caching strategy to optimize the convergence speed is provided. Our major contribution is to give the basic theories of distributed consensus problem for federated learning framework, and the theoretical results are validated by numerical simulations.

A Secure Authentication Scheme for Wireless Sensor Networks Based on DAC and Intel SGX

Wireless sensor networks (WSNs) are widely implemented in military, intelligent medical, intelligent transportation, space exploration, and other fields. However, the authentication and communication of WSNs are carried out in the harsh external environment via a public channel, which is more vulnerable to various attacks than the traditional networks. Authentication is the key technology of security measures, but a common authentication scheme is not suitable for WSNs due to limitations of memory, computing, and energy consumption. Therefore, designing a secure and efficient authentication scheme is essential in WSNs. In recent years, several studies proved that the dynamic authentication credential (DAC) is efficient for enhancing the security of the authentication scheme. This article designs a secure authentication scheme for WSNs based on DAC and Intel software guard extensions (SGX). Compared with other DAC authentication schemes, our scheme provides the confirmation action of DAC rotation, which can effectively prevent the asynchronous update problem caused by packet loss. In order to resist the privileged user attack and the authentication table leakage attack, we choose the SGX, which can protect the data in use, as the trusted execution environment in the gateway node, and we adopt SGX to store the master key for protecting the authentication table. Finally, the security of our authentication scheme is verified by BAN logic, the simulation tool AVISPA, and informal security analysis. Through the consumption overhead analysis, the NS3 simulation result, and detailed comparison with other recent schemes, we conclude that our scheme is practical and achieves better security with less overhead.

Impact of resource-based conditional interaction on cooperation in spatial social dilemmas

Due to the contradiction between the finiteness of resources and people’s infinite demand for them, we cannot deny the impact of the limited resources on human behavior. To this end, we construct a novel resource-based conditional interaction model from a tiny perspective, in which not only can limited resources be redistributed among the population, but resources owned by players also affect whether they can interact with each other or not. To be specific, a player who successfully imitates his neighbor’s strategy will have to pay ɛ proportion of his resources to the opponent as the learning cost. In addition, if and only if the resource difference between the focal player x and one of his neighbors y is within an acceptable tolerance interval τ, they will indisputably interact with each other. We mainly resort to the prisoner’s dilemma game and asynchronous strategy update to verify the effectiveness of the model. By resorting to extensive Monte Carlo simulations, we find that there exists an optimal acceptable tolerance interval τ, varying with the value of cost-to-benefit ratio u, to make the promotion of cooperation the most obvious. We also confirm that players’ irrational behavior can be influenced by this resource-based partner selection. However, if we introduce one kind of minimal resource protection mechanism into our proposed model, the level of cooperation cannot be further elevated, or even be hindered when compared with the case without the minimal resource protection mechanism. In the end, we further verify the robustness and effectiveness of the proposed model through other social dilemmas, network topologies, and synchronous strategy update pattern. To a certain extent, we wish that our efforts can wipe out some barriers for researching the evolution of cooperation within the selfish population.

Area-wide traffic signal control based on a deep graph Q-Network (DGQN) trained in an asynchronous manner

Value-based reinforcement learning (RL) algorithms have been widely applied in traffic signal studies. There are, however, several problems in jointly controlling traffic lights for a large transportation network. First, the discrete action space exponentially explodes as the number of intersections to be jointly controlled increases. With its model structure, the original deep Q-network (DQN) could not accommodate a large action space. The problem was resolved by revising the output structure of a DQN holding the framework of a single-agent RL algorithm Second, when mapping traffic states into an action value, it is difficult to consider spatio-temporal correlations over a large transportation network. A deep graph Q-network (DGQN) was devised to efficiently accommodate spatio-temporal dependencies on a large scale. Finally, training the proposed DGQN with a large number of joint actions requires much time to converge. An asynchronous update methodology with multiple actor learners was devised for a DGQN to quickly reach an optimal policy. By combining these three remedies, a DGQN succeeded in jointly controlling the traffic lights in a large transportation network in Seoul. This approach outperformed other “state-of-the-art” RL algorithms as well as an actual fixed-signal operation. The proposed DGQN decreased the average delay of the current fixed operation to 55.7%, whereas those of reference models DQN-OGCN and DQN-FC were 72.5 and 92.0%, respectively.

STAFL: Staleness-Tolerant Asynchronous Federated Learning on Non-iid Dataset

With the development of the Internet of Things, edge computing applications are paying more and more attention to privacy and real-time. Federated learning, a promising machine learning method that can protect user privacy, has begun to be widely studied. However, traditional synchronous federated learning methods are easily affected by stragglers, and non-independent and identically distributed data sets will also reduce the convergence speed. In this paper, we propose an asynchronous federated learning method, STAFL, where users can upload their updates at any time and the server will immediately aggregate the updates and return the latest global model. Secondly, STAFL will judge the user’s data distribution according to the user’s update and dynamically change the aggregation parameters according to the user’s network weight and staleness to minimize the impact of non-independent and identically distributed data sets on asynchronous updates. The experimental results show that our method performs better on non-independent and identically distributed data sets than existing methods.

Design of Computer Multimedia Intelligent Platform Using Big Data Analysis

This exploration aims to transfer, process and store multimedia information timely, accurately and comprehensively through computer comprehensive technology processing, and organically combine various elements under the background of big data analysis, so as to form a complete intelligent platform design for multimedia information processing and application. In this exploration, the intelligent vehicle monitoring system is taken as an example. Data acquisition, data transmission, real-time data processing, data storage and data application are realized through the real-time data stream processing framework of [Formula: see text] of big data technology. Data interaction is realized through Spring, Spring MVC, VUE front-end framework, and Ajax asynchronous communication local update technology. Data storage is achieved through Red is cache database, and intelligent vehicle operation supervision system is achieved through multimedia information technology processing. Its purpose is to manage the vehicle information, real-time monitor the running state of the vehicle and give an alarm when there are some problems. The basic functions of vehicle operation monitoring and management system based on big data analysis are realized. The research on the design of vehicle operation monitoring and management system based on big data analysis shows that big data technology can be applied to the design of computer multimedia intelligent platform, and provides a reference case for the development of computer multimedia intelligent platform based on big data analysis.

Towards Communication-Efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things

Federated Edge Learning (FEL) allows edge nodes to train a global deep learning model collaboratively for edge computing in the Industrial Internet of Things (IIoT), which significantly promotes the development of Industrial 4.0. However, FEL faces two critical challenges: communication overhead and data privacy. FEL suffers from expensive communication overhead when training large-scale multi-node models. Furthermore, due to the vulnerability of FEL to gradient leakage and label-flipping attacks, the training process of the global model is easily compromised by adversaries. To address these challenges, we propose a communication-efficient and privacy-enhanced asynchronous FEL framework for edge computing in IIoT. First, we introduce an asynchronous model update scheme to reduce the computation time that edge nodes wait for global model aggregation. Second, we propose an asynchronous local differential privacy mechanism, which improves communication efficiency and mitigates gradient leakage attacks by adding well-designed noise to the gradients of edge nodes. Third, we design a cloud-side malicious node detection mechanism to detect malicious nodes by testing the local model quality. Such a mechanism can avoid malicious nodes participating in training to mitigate label-flipping attacks. Extensive experimental studies on two real-world datasets demonstrate that the proposed framework can not only improve communication efficiency but also mitigate malicious attacks while its accuracy is comparable to traditional FEL frameworks.

Asynchronous Networked Aggregative Games

We propose a fully asynchronous networked aggregative game (Asy-NAG) where each player minimizes a local cost function that depends on its own action and the aggregate of all players’ actions. In sharp contrast to the existing NAGs, each player in our Asy-NAG can compute an estimate of the aggregate action at any wall-clock time by only using (possibly stale) information from neighboring players of a directed network. Such an asynchronous update does not require any coordination among players. Moreover, we design a novel distributed algorithm with an aggressive mechanism for each player to adaptively adjust its optimization stepsize per update. Particularly, the slow players in terms of updating their estimates smartly increase their stepsizes to catch up with the fast ones. Then, we adopt an augmented network approach to address the asynchronicity and the information delays between players, and rigorously show the convergence to a Nash equilibrium of the Asy-NAG via a perturbed coordinate algorithm which is also of independent interest. Finally, we evaluate the performance of the distributed algorithm through numerical simulations.

An Asynchronous and Real-Time Update Paradigm of Federated Learning for Fault Diagnosis

The federated learning (FL) method based on model aggregation can balance data and protect data privacy, but the existing method is difficult to achieve the same effectiveness as the centralized learning method under data sharing. In addition, it is difficult for the existing federated model to realize the real-time update of the clients' network parameters, because it inhibits the optimal performance of the client. Therefore, this article proposes an asynchronous update paradigm of FL with real-time identification of the client's network parameters to tackle the shortcomings. First, we adopt the linear fusion method based on sequential filtering and fuse the parameters of federated center asynchronously considering communication delay, which can approach the diagnostic accuracy based on the centralized learning. Second, we establish the real-time identification method for the clients based on linear filtering with the new labeled samples obtained at nonequal intervals, which expects the client to acquire better performance. Finally, we test the fault classification ability of the proposed method based on the actual collected fault dataset and the test platform of bearing fault dataset.

Computational Power of Asynchronously Tuned Automata Enhancing the Unfolded Edge of Chaos.

Asynchronously tuned elementary cellular automata (AT-ECA) are described with respect to the relationship between active and passive updating, and that spells out the relationship between synchronous and asynchronous updating. Mutual tuning between synchronous and asynchronous updating can be interpreted as the model for dissipative structure, and that can reveal the critical property in the phase transition from order to chaos. Since asynchronous tuning easily makes behavior at the edge of chaos, the property of AT-ECA is called the unfolded edge of chaos. The computational power of AT-ECA is evaluated by the quantitative measure of computational universality and efficiency. It shows that the computational efficiency of AT-ECA is much higher than that of synchronous ECA and asynchronous ECA.

Research on ASP. NET AJAX Framework and Its Application in Web Development

Web page requests is the common way for applications to implement human-computer interaction, but full page refreshing of the page reduces the effects of users’experience, increases the pressure of servers and slows down the speed of program response. Partial update pages with AJAX asynchronous transfer technology can increase the efficiency of program interactions and give user a friendly program interface. Microsoft’ s ASP. NET AJAX framework can greatly reduce the difficulty of programmers in developing AJAX applications. This paper introduces AJAX engine principle and ASP. NET AJAX framework firstly, and then describes ASP. NET AJAX configuration in the Web site, at the end we imported AJAX application in the design of online examination system in order to achieve asynchronous partial update , therefore a friendly user interactive interface is brought about.

Distributed Event-Triggered Model Predictive Control for Urban Traffic Lights

Effective traffic signal control strategies are critical for traffic management in urban traffic networks. Most existing optimization-based urban traffic control approaches update the traffic signal at regular time instants, where the length of the fixed update time interval is determined based on a trade-off between the computational efficiency and the control performance. Since event-triggered control (ETC) allows for more flexible and more efficient control than conventional time-triggered control by triggering the control action by events, and since it can refrain from redundant optimization while retaining a satisfactory behavior, we use an ETC scheme for traffic light control. In addition, based on the geographically distributed feature of traffic networks, a distributed paradigm is adopted to reduce the computational complexity for the optimization. We propose a distributed threshold-based event-triggered control strategy, where the independent triggering of agents leads to an asynchronous update of traffic signals in the system. The triggered agent then solves a mixed-integer linear programming problem and updates its traffic signals. The proposed approach is evaluated under various traffic demands by simulation, and is shown to yield the best trade-off between control performance and computational complexity compared to other control strategies.

Distributed fusion in harsh environments using multiple bearings-only sensors with out-of-sequence-refined measurements

This paper investigates a novel distributed fusion system for target tracking in three dimensional surveillance using multiple asynchronous BO sensors by simultaneously addressing the problems of target mis-detection and clutter disturbance as well as the out-of-sequence (OOS) information fusion. The proposed distributed fusion architecture consists of the local tracking and distributed fusion, wherein, the refined BO measurements output from the local tracking in each BO sensor are transmitted to the fusion center for subsequent distributed fusion. In the local tracking, instead of kinematic state, the target pseudo state is defined and tracked by operating the proposed pseudo state-integrated probabilistic data association (PS-IPDA) algorithm with an approximately linear pseudo state evolution model, resulting in greatly refined BO sensor measurements. In the fusion center, the sequential asynchronous IPDA-general one-step retrodiction update (SAIPDA-GORU) algorithm is proposed to effectively fuse the transmitted origin-unknown OOS refined measurements (OOSRMs) with the central tracks. The SAIPDA-GORU propagates the central track hybrid state to the OOS time by deploying a general one-step retrodiction technique, and mathematically formulates the OOSRMs-to-retrodicted central track association probabilities utilized to facilitate the fusing of currently filtered central track with OOSRMs. Numerical results show that the proposed PS-IPDA algorithm reduces the errors of target bearings measurement by around a half and eliminates more than 60% of the clutter measurements contained in raw detections, saving significant communication bandwidth between local sensors and fusion center. Furthermore, the proposed SAIPDA-GORU method tangibly improves the estimation accuracy and false track discrimination over the existing discarding method, with the potential to be implemented in real-time.