MADDPG-D2: An Intelligent Dynamic Task Allocation Algorithm Based on Multi-Agent Architecture Driven by Prior Knowledge

Aiming at the problems of low solution accuracy and high decision pressure when facing large-scale dynamic task allocation(DTA)and high-dimensional decision space with single agent,this paper combines the deep reinforce-ment learning(DRL)theory and an improved Multi-Agent Deep Deterministic Policy Gradient(MADDPG-D2)algorithm with a dual experience replay pool and a dual noise based on multi-agent architecture is proposed to improve the efficiency of DTA.The algorithm is based on the traditional Multi-Agent Deep Deterministic Policy Gradient(MADDPG)algorithm,and considers the introduction of a double noise mechanism to increase the action exploration space in the early stage of the algorithm,and the introduction of a double experience pool to improve the data utilization rate;at the same time,in order to accelerate the training speed and efficiency of the agents,and to solve the cold-start problem of the training,the a priori knowledge technology is applied to the training of the algorithm.Finally,the MADDPG-D2 algorithm is compared and analyzed based on the digital battlefield of ground and air confrontation.The experimental results show that the agents trained by the MADDPG-D2 algorithm have higher win rates and average rewards,can utilize the resources more reasonably,and better solve the problem of the traditional single agent algorithms facing the difficulty of solving the problem in the high-dimensional decision space.The MADDPG-D2 algorithm based on multi-agent architecture proposed in this paper has certain superiority and rationality in DTA.

Multi-stage online task assignment driven by offline data under spatio-temporal crowdsourcing

In the era of the Internet of Things(IoT),the crowdsourcing process is driven by data collected by devices that interact with each other and with the physical world.As a part of the IoT ecosystem,task assignment has become an important goal of the research community.Existing task assignment algorithms can be categorized as offline(performs better with datasets but struggles to achieve good real-life results)or online(works well with real-life input but is difficult to optimize regarding in-depth assignments).This paper proposes a Cross-regional Online Task(CROT)assignment problem based on the online assignment model.Given the CROT problem,an Online Task Assignment across Regions based on Prediction(OTARP)algorithm is proposed.OTARP is a two-stage graphics-driven bilateral assignment strategy that uses edge cloud and graph embedding to complete task assignments.The first stage uses historical data to make offline predictions,with a graph-driven method for offline bipartite graph matching.The second stage uses a bipartite graph to complete the online task assignment process.This paper proposes accelerating the task assignment process through multiple assignment rounds and optimizing the process by combining offline guidance and online assignment strategies.To encourage crowd workers to complete crowd tasks across regions,an incentive strategy is designed to encourage crowd workers’movement.To avoid the idle problem in the process of crowd worker movement,a drop-by-rider problem is used to help crowd workers accept more crowd tasks,optimize the number of assignments,and increase utility.Finally,through comparison experiments on real datasets,the performance of the proposed algorithm on crowd worker utility value and the matching number is evaluated.

Object-oriented Battlefield Environment Simulation Process Object Model Based on Task-driven

Battlefield environment simulation process is an important part of battlefield environment information support, which needs to be built around the task process. At present, the interoperability between battlefield environment simulation system and command and control system is still imperfect, and the traditional simulation data model cannot meet war fighters’ high-efficient and accurate understanding and analysis on battlefield environment’s information. Therefore, a kind of task-orientated battlefield environment simulation process model needs to be construed to effectively analyze the key information demands of the command and control system. The structured characteristics of tasks and simulation process are analyzed, and the simulation process concept model is constructed with the method of object-orientated. The data model and formal syntax of GeoBML are analyzed, and the logical model of simulation process is constructed with formal language. The object data structure of simulation process is defined and the object model of simulation process which maps tasks is constructed. In the end, the battlefield environment simulation platform modules are designed and applied based on this model, verifying that the model can effectively express the real-time dynamic correlation between battlefield environment simulation data and operational tasks.

Makespan and reliability driven scheduling algorithm for independent tasks in Grids

In the dynamic, complex and unbounded Grid systems, failures of Grid resources caused by malicious attacks and hardware failures are inevitable and have an adverse effect on the execution of tasks. To mitigate this problem, a makespan and reliability driven （MRD） sufferage scheduling algorithm is designed and implemented. Different from the traditional Grid scheduling algorithms, the algorithm addresses the makespan as well as reliability of tasks. The simulation experimental results show that the MRD sufferage scheduling algorithm can increase reliability of tasks and can trade off reliability against makespan of tasks by adjusting the weighting parameter in its cost function. So it can be applied to the complex Grid computing environment well.

Exploration of a New Task-driven Model for Botany Field Practice

In the present context of increasing social demands for natural science education,increasing people s awareness of environmental biodiversity protection,and ecological civilization lifting to the state strategy,it is just the time to explore a new botany field practice model.The attempt of a new task-driven model for botany field practice will greatly enhance students thinking about plants and nature,plants and environment,and plant and ecological civilization,and will inevitably enhance students initiative awareness and practical ability to protect and rationally utilize plant resources.

Effect of power supply parameters on discharge characteristics and sterilization efficiency of magnetically driven rotating gliding arc

Plasma sterilization is a new generation of high-tech sterilization method that is fast,safe,and pollution free.It is widely used in medical,food,and environmental protection fields.Home air sterilization is an emerging field of plasma application,which puts higher requirements on the miniaturization,operational stability,and operating cost of plasma device.In this study,a novel magnetically driven rotating gliding arc(MDRGA)discharge device was used to sterilize Lactobacillus fermentation.Compared with the traditional gas-driven gliding arc,this device has a simple structure and a more stable gliding arc.Simulation using COMSOL Multiphysics showed that adding permanent magnets can form a stable magnetic field,which is conducive to the formation of gliding arcs.Experiments on the discharge performance,ozone concentration,and sterilization effect were conducted using different power supply parameters.The results revealed that the MDRGA process can be divided into three stages:starting,gliding,and extinguishing.Appropriate voltage was the key factor for stable arc gliding,and both high and low voltages were not conducive to stable arc gliding and ozone production.In this experimental setup,the sterilization effect was the best at 6.6 kV.A high modulation duty ratio was beneficial for achieving stable arc gliding.However,when the duty ratio exceeded a certain value,the improvement in the sterilization effect was slow.Therefore,considering the sterilization effect and energy factors comprehensively,we chose 80%as the optimal modulation duty ratio for this experimental device.

Data-driven modeling on anisotropic mechanical behavior of brain tissue with internal pressure

Brain tissue is one of the softest parts of the human body,composed of white matter and grey matter.The mechanical behavior of the brain tissue plays an essential role in regulating brain morphology and brain function.Besides,traumatic brain injury(TBI)and various brain diseases are also greatly influenced by the brain's mechanical properties.Whether white matter or grey matter,brain tissue contains multiscale structures composed of neurons,glial cells,fibers,blood vessels,etc.,each with different mechanical properties.As such,brain tissue exhibits complex mechanical behavior,usually with strong nonlinearity,heterogeneity,and directional dependence.Building a constitutive law for multiscale brain tissue using traditional function-based approaches can be very challenging.Instead,this paper proposes a data-driven approach to establish the desired mechanical model of brain tissue.We focus on blood vessels with internal pressure embedded in a white or grey matter matrix material to demonstrate our approach.The matrix is described by an isotropic or anisotropic nonlinear elastic model.A representative unit cell(RUC)with blood vessels is built,which is used to generate the stress-strain data under different internal blood pressure and various proportional displacement loading paths.The generated stress-strain data is then used to train a mechanical law using artificial neural networks to predict the macroscopic mechanical response of brain tissue under different internal pressures.Finally,the trained material model is implemented into finite element software to predict the mechanical behavior of a whole brain under intracranial pressure and distributed body forces.Compared with a direct numerical simulation that employs a reference material model,our proposed approach greatly reduces the computational cost and improves modeling efficiency.The predictions made by our trained model demonstrate sufficient accuracy.Specifically,we find that the level of internal blood pressure can greatly influence stress distribution and determine the possible related damage behaviors.

Effects of counter-current driven by electron cyclotron waves on neoclassical tearing mode suppression

Through theoretical analysis,we construct a physical model that includes the influence of counter-external driven current opposite to the plasma current direction in the neoclassical tearing mode(NTM).The equation is used with this model to obtain the modified Rutherford equation with co-current and counter-current contributions.Consistent with the reported experimental results,numerical simulations have shown that the localized counter external current can only partially suppress NTM when it is far from the resonant magnetic surface.Under some circumstances,the Ohkawa mechanism dominated current drive(OKCD)by electron cyclotron waves can concurrently create both co-current and counter-current.In this instance,the minimal electron cyclotron wave power that suppresses a particular NTM was calculated by the Rutherford equation.The result is marginally less than when taking co-current alone into consideration.As a result,to suppress NTM using OKCD,one only needs to align the co-current with a greater OKCD peak well with the resonant magnetic surface.The effect of its lower counter-current does not need to be considered because the location of the counter-current deviates greatly from the resonant magnetic surface.

Dynamic Offloading and Scheduling Strategy for Telematics Tasks Based on Latency Minimization

In current research on task offloading and resource scheduling in vehicular networks,vehicles are commonly assumed to maintain constant speed or relatively stationary states,and the impact of speed variations on task offloading is often overlooked.It is frequently assumed that vehicles can be accurately modeled during actual motion processes.However,in vehicular dynamic environments,both the tasks generated by the vehicles and the vehicles’surroundings are constantly changing,making it difficult to achieve real-time modeling for actual dynamic vehicular network scenarios.Taking into account the actual dynamic vehicular scenarios,this paper considers the real-time non-uniform movement of vehicles and proposes a vehicular task dynamic offloading and scheduling algorithm for single-task multi-vehicle vehicular network scenarios,attempting to solve the dynamic decision-making problem in task offloading process.The optimization objective is to minimize the average task completion time,which is formulated as a multi-constrained non-linear programming problem.Due to the mobility of vehicles,a constraint model is applied in the decision-making process to dynamically determine whether the communication range is sufficient for task offloading and transmission.Finally,the proposed vehicular task dynamic offloading and scheduling algorithm based on muti-agent deep deterministic policy gradient(MADDPG)is applied to solve the optimal solution of the optimization problem.Simulation results show that the algorithm proposed in this paper is able to achieve lower latency task computation offloading.Meanwhile,the average task completion time of the proposed algorithm in this paper can be improved by 7.6%compared to the performance of the MADDPG scheme and 51.1%compared to the performance of deep deterministic policy gradient(DDPG).

Joint Task Allocation and Resource Optimization for Blockchain Enabled Collaborative Edge Computing

Collaborative edge computing is a promising direction to handle the computation intensive tasks in B5G wireless networks.However,edge computing servers(ECSs)from different operators may not trust each other,and thus the incentives for collaboration cannot be guaranteed.In this paper,we propose a consortium blockchain enabled collaborative edge computing framework,where users can offload computing tasks to ECSs from different operators.To minimize the total delay of users,we formulate a joint task offloading and resource optimization problem,under the constraint of the computing capability of each ECS.We apply the Tammer decomposition method and heuristic optimization algorithms to obtain the optimal solution.Finally,we propose a reputation based node selection approach to facilitate the consensus process,and also consider a completion time based primary node selection to avoid monopolization of certain edge node and enhance the security of the blockchain.Simulation results validate the effectiveness of the proposed algorithm,and the total delay can be reduced by up to 40%compared with the non-cooperative case.

Task Offloading and Resource Allocation in NOMA-VEC:A Multi-Agent Deep Graph Reinforcement Learning Algorithm

Vehicular edge computing(VEC)is emerging as a promising solution paradigm to meet the requirements of compute-intensive applications in internet of vehicle(IoV).Non-orthogonal multiple access(NOMA)has advantages in improving spectrum efficiency and dealing with bandwidth scarcity and cost.It is an encouraging progress combining VEC and NOMA.In this paper,we jointly optimize task offloading decision and resource allocation to maximize the service utility of the NOMA-VEC system.To solve the optimization problem,we propose a multiagent deep graph reinforcement learning algorithm.The algorithm extracts the topological features and relationship information between agents from the system state as observations,outputs task offloading decision and resource allocation simultaneously with local policy network,which is updated by a local learner.Simulation results demonstrate that the proposed method achieves a 1.52%∼5.80%improvement compared with the benchmark algorithms in system service utility.

Task Offloading in Edge Computing Using GNNs and DQN

In a network environment composed of different types of computing centers that can be divided into different layers(clod,edge layer,and others),the interconnection between them offers the possibility of peer-to-peer task offloading.For many resource-constrained devices,the computation of many types of tasks is not feasible because they cannot support such computations as they do not have enough available memory and processing capacity.In this scenario,it is worth considering transferring these tasks to resource-rich platforms,such as Edge Data Centers or remote cloud servers.For different reasons,it is more exciting and appropriate to download various tasks to specific download destinations depending on the properties and state of the environment and the nature of the functions.At the same time,establishing an optimal offloading policy,which ensures that all tasks are executed within the required latency and avoids excessive workload on specific computing centers is not easy.This study presents two alternatives to solve the offloading decision paradigm by introducing two well-known algorithms,Graph Neural Networks(GNN)and Deep Q-Network(DQN).It applies the alternatives on a well-known Edge Computing simulator called PureEdgeSimand compares them with the two defaultmethods,Trade-Off and Round Robin.Experiments showed that variants offer a slight improvement in task success rate and workload distribution.In terms of energy efficiency,they provided similar results.Finally,the success rates of different computing centers are tested,and the lack of capacity of remote cloud servers to respond to applications in real-time is demonstrated.These novel ways of finding a download strategy in a local networking environment are unique as they emulate the state and structure of the environment innovatively,considering the quality of its connections and constant updates.The download score defined in this research is a crucial feature for determining the quality of a download path in the GNN training process and has not previously been proposed.Simultaneously,the suitability of Reinforcement Learning(RL)techniques is demonstrated due to the dynamism of the network environment,considering all the key factors that affect the decision to offload a given task,including the actual state of all devices.

Mobile Crowdsourcing Task Allocation Based on Dynamic Self-Attention GANs

Crowdsourcing technology is widely recognized for its effectiveness in task scheduling and resource allocation.While traditional methods for task allocation can help reduce costs and improve efficiency,they may encounter challenges when dealing with abnormal data flow nodes,leading to decreased allocation accuracy and efficiency.To address these issues,this study proposes a novel two-part invalid detection task allocation framework.In the first step,an anomaly detection model is developed using a dynamic self-attentive GAN to identify anomalous data.Compared to the baseline method,the model achieves an approximately 4%increase in the F1 value on the public dataset.In the second step of the framework,task allocation modeling is performed using a twopart graph matching method.This phase introduces a P-queue KM algorithm that implements a more efficient optimization strategy.The allocation efficiency is improved by approximately 23.83%compared to the baseline method.Empirical results confirm the effectiveness of the proposed framework in detecting abnormal data nodes,enhancing allocation precision,and achieving efficient allocation.

Heterogeneous Task Allocation Model and Algorithm for Intelligent Connected Vehicles

With the development of vehicles towards intelligence and connectivity,vehicular data is diversifying and growing dramatically.A task allocation model and algorithm for heterogeneous Intelligent Connected Vehicle(ICV)applications are proposed for the dispersed computing network composed of heterogeneous task vehicles and Network Computing Points(NCPs).Considering the amount of task data and the idle resources of NCPs,a computing resource scheduling model for NCPs is established.Taking the heterogeneous task execution delay threshold as a constraint,the optimization problem is described as the problem of maximizing the utilization of computing resources by NCPs.The proposed problem is proven to be NP-hard by using the method of reduction to a 0-1 knapsack problem.A many-to-many matching algorithm based on resource preferences is proposed.The algorithm first establishes the mutual preference lists based on the adaptability of the task requirements and the resources provided by NCPs.This enables the filtering out of un-schedulable NCPs in the initial stage of matching,reducing the solution space dimension.To solve the matching problem between ICVs and NCPs,a new manyto-many matching algorithm is proposed to obtain a unique and stable optimal matching result.The simulation results demonstrate that the proposed scheme can improve the resource utilization of NCPs by an average of 9.6%compared to the reference scheme,and the total performance can be improved by up to 15.9%.

Prevalence and Tasks Associated with Respiratory Symptoms among Waste Electrical and Electronic Equipment Handlers in Ouagadougou, Burkina Faso in 2019

Introduction: The uncontrolled management of waste electrical and electronic equipment (W3E) causes respiratory problems in the handlers of this waste. The objective was to study the stains associated with respiratory symptoms in W3E handlers. Methods: The study was cross-sectional with an analytical focus on W3E handlers in the informal sector in Ouagadougou. A peer-validated questionnaire collected data on a sample of 161 manipulators. Results: the most common W3E processing tasks were the purchase or sale of W3E (67.70%), its repair (39.75%) and its collection (31.06%). The prevalence of cough was 21.74%, that of wheezing 14.91%, phlegm 12.50% and dyspnea at rest 10.56%. In bivariate analysis, there were significant associations at the 5% level between W3E repair and phlegm (p-value = 0.044), between W3E burning and wheezing (p-value = 0.011) and between W3E and cough (p-value = 0.01). The final logistic regression models suggested that the burning of W3E and the melting of lead batteries represented risk factors for the occurrence of cough with respective prevalence ratios of 4.57 and 4.63. Conclusion: raising awareness on the wearing of personal protective equipment, in particular masks adapted by W3E handlers, favoring those who are dedicated to the burning of electronic waste and the melting of lead could make it possible to reduce the risk of occurrence of respiratory symptoms.

Investigation of system parameters towards safer impact based shock-to-detonation transition in a novel laser driven flyer plate prototype

Laser driven flyer plate technology offers improved safety and reliability for detonation of explosives in industrial applications ranging from mining and stone quarrying to the aerospace and defense industries.This study is based on developing a safer laser driven flyer plate prototype comprised of a laser initiator and a flyer plate subsystem that can be used with secondary explosives.System parameters were optimized to initiate the shock-to-detonation transition(SDT)of a secondary explosive based on the impact created by the flyer plate on the explosive surface.Rupture of the flyer was investigated at the mechanically weakened region located on the interface of these subsystems,where the product gases from the deflagration of the explosive provide the required energy.A bilayer energetic material was used,where the first layer consisted of a pyrotechnic component,zirconium potassium perchlorate(ZPP),for sustaining the ignition by the laser beam and the second layer consisted of an insensitive explosive,cyclotetramethylene-tetranitramine(HMX),for deflagration.A plexiglass interface was used to enfold the energetic material.The focal length of the laser beam from the diode was optimized to provide a homogeneous beam profile with maximum power at the surface of the ZPP.Closed bomb experiments were conducted in an internal volume of 10 cm^(3) for evaluation of performance.Dependency of the laser driven flyer plate system output on confinement,explosive density,and laser beam power were analyzed.Measurements using a high-speed camera resulted in a flyer velocity of 670±20 m/s that renders the prototype suitable as a laser detonator in applications,where controlled employment of explosives is critical.

Effects of pooling,specialization,and discretionary task completion on queueing performance

Pooling,unpooling/specialization,and discretionary task completion are typical operational strategies in queueing systems that arise in healthcare,call centers,and online sales.These strategies may have advantages and disadvantages in different operational environments.This paper uses the M/M/1 and M/M/2 queues to study the impact of pooling,specialization,and discretionary task completion on the average queue length.Closed-form solutions for the average M/M/2 queue length are derived.Computational examples illustrate how the average queue length changes with the strength of pooling,specialization,and discretionary task completion.Finally,several conjectures are made in the paper.

Generating Factual Text via Entailment Recognition Task

Generating diverse and factual text is challenging and is receiving increasing attention.By sampling from the latent space,variational autoencoder-based models have recently enhanced the diversity of generated text.However,existing research predominantly depends on summarizationmodels to offer paragraph-level semantic information for enhancing factual correctness.The challenge lies in effectively generating factual text using sentence-level variational autoencoder-based models.In this paper,a novel model called fact-aware conditional variational autoencoder is proposed to balance the factual correctness and diversity of generated text.Specifically,our model encodes the input sentences and uses them as facts to build a conditional variational autoencoder network.By training a conditional variational autoencoder network,the model is enabled to generate text based on input facts.Building upon this foundation,the input text is passed to the discriminator along with the generated text.By employing adversarial training,the model is encouraged to generate text that is indistinguishable to the discriminator,thereby enhancing the quality of the generated text.To further improve the factual correctness,inspired by the natural language inference system,the entailment recognition task is introduced to be trained together with the discriminator via multi-task learning.Moreover,based on the entailment recognition results,a penalty term is further proposed to reconstruct the loss of our model,forcing the generator to generate text consistent with the facts.Experimental results demonstrate that compared with competitivemodels,ourmodel has achieved substantial improvements in both the quality and factual correctness of the text,despite only sacrificing a small amount of diversity.Furthermore,when considering a comprehensive evaluation of diversity and quality metrics,our model has also demonstrated the best performance.

Online task planning method of anti-ship missile based on rolling optimization

Based on the wave attack task planning method in static complex environment and the rolling optimization framework, an online task planning method in dynamic complex environment based on rolling optimization is proposed. In the process of online task planning in dynamic complex environment,online task planning is based on event triggering including target information update event, new target addition event, target failure event, weapon failure event, etc., and the methods include defense area reanalysis, parameter space update, and mission re-planning. Simulation is conducted for different events and the result shows that the index value of the attack scenario after re-planning is better than that before re-planning and according to the probability distribution of statistical simulation method, the index value distribution after re-planning is obviously in the region of high index value, and the index value gap before and after re-planning is related to the degree of posture change.

Multi-Agent Collaborative Task Planning with Uncertain Task Requirements

In response to the uncertainty of information of the injured in post disaster situations,considering constraints such as random chance and the quantity of rescue resource,the split deliv-ery vehicle routing problem with stochastic demands(SDVRPSD)model and the multi-depot split delivery heterogeneous vehicle routing problem with stochastic demands(MDSDHVRPSD)model are established.A two-stage hybrid variable neighborhood tabu search algorithm is designed for unmanned vehicle task planning to minimize the path cost of rescue plans.Simulation experiments show that the solution obtained by the algorithm can effectively reduce the rescue vehicle path cost and the rescue task completion time,with high optimization quality and certain portability.