Correcting Climate Model Sea Surface Temperature Simulations with Generative Adversarial Networks:Climatology,Interannual Variability,and Extremes

Climate models are vital for understanding and projecting global climate change and its associated impacts.However,these models suffer from biases that limit their accuracy in historical simulations and the trustworthiness of future projections.Addressing these challenges requires addressing internal variability,hindering the direct alignment between model simulations and observations,and thwarting conventional supervised learning methods.Here,we employ an unsupervised Cycle-consistent Generative Adversarial Network(CycleGAN),to correct daily Sea Surface Temperature(SST)simulations from the Community Earth System Model 2(CESM2).Our results reveal that the CycleGAN not only corrects climatological biases but also improves the simulation of major dynamic modes including the El Niño-Southern Oscillation(ENSO)and the Indian Ocean Dipole mode,as well as SST extremes.Notably,it substantially corrects climatological SST biases,decreasing the globally averaged Root-Mean-Square Error(RMSE)by 58%.Intriguingly,the CycleGAN effectively addresses the well-known excessive westward bias in ENSO SST anomalies,a common issue in climate models that traditional methods,like quantile mapping,struggle to rectify.Additionally,it substantially improves the simulation of SST extremes,raising the pattern correlation coefficient(PCC)from 0.56 to 0.88 and lowering the RMSE from 0.5 to 0.32.This enhancement is attributed to better representations of interannual,intraseasonal,and synoptic scales variabilities.Our study offers a novel approach to correct global SST simulations and underscores its effectiveness across different time scales and primary dynamical modes.

Influence of network structure on spreading dynamics via tie range

There are various phenomena of malicious information spreading in the real society, which cause many negative impacts on the society. In order to better control the spreading, it is crucial to reveal the influence of network structure on network spreading. Motifs, as fundamental structures within a network, play a significant role in spreading. Therefore, it is of interest to investigate the influence of the structural characteristics of basic network motifs on spreading dynamics.Considering the edges of the basic network motifs in an undirected network correspond to different tie ranges, two edge removal strategies are proposed, short ties priority removal strategy and long ties priority removal strategy. The tie range represents the second shortest path length between two connected nodes. The study focuses on analyzing how the proposed strategies impact network spreading and network structure, as well as examining the influence of network structure on network spreading. Our findings indicate that the long ties priority removal strategy is most effective in controlling network spreading, especially in terms of spread range and spread velocity. In terms of network structure, the clustering coefficient and the diameter of network also have an effect on the network spreading, and the triangular structure as an important motif structure effectively inhibits the spreading.

Graph Attention Residual Network Based Routing and Fault-Tolerant Scheduling Mechanism for Data Flow in Power Communication Network

For permanent faults(PF)in the power communication network(PCN),such as link interruptions,the timesensitive networking(TSN)relied on by PCN,typically employs spatial redundancy fault-tolerance methods to keep service stability and reliability,which often limits TSN scheduling performance in fault-free ideal states.So this paper proposes a graph attention residual network-based routing and fault-tolerant scheduling mechanism(GRFS)for data flow in PCN,which specifically includes a communication system architecture for integrated terminals based on a cyclic queuing and forwarding(CQF)model and fault recovery method,which reduces the impact of faults by simplified scheduling configurations of CQF and fault-tolerance of prioritizing the rerouting of faulty time-sensitive(TS)flows;considering that PF leading to changes in network topology is more appropriately solved by doing routing and time slot injection decisions hop-by-hop,and that reasonable network load can reduce the damage caused by PF and reserve resources for the rerouting of faulty TS flows,an optimization model for joint routing and scheduling is constructed with scheduling success rate as the objective,and with traffic latency and network load as constraints;to catch changes in TSN topology and traffic load,a D3QN algorithm based on a multi-head graph attention residual network(MGAR)is designed to solve the problem model,where the MGAR based encoder reconstructs the TSN status into feature embedding vectors,and a dueling network decoder performs decoding tasks on the reconstructed feature embedding vectors.Simulation results show that GRFS outperforms heuristic fault-tolerance algorithms and other benchmark schemes by approximately 10%in routing and scheduling success rate in ideal states and 5%in rerouting and rescheduling success rate in fault states.

Resilient Satellite Communication Networks Towards Highly Dynamic and Highly Reliable Transmission

As the key infrastructure of space-ground integrated information networks,satellite communication networks provide high-speed and reliable information transmission.In order to meet the burgeoning service demands of the IoT and the Internet,the low-latency LEO satellite network has developed rapidly.However,LEO satellites face inherent problems such as small coverage,fast moving speed and short overhead time,which will be more severe when serving high-dynamic users,e.g.high-speed rails and airplanes.The heterogeneous network composed of GEO,MEO and LEO satellites can provide various services,whose network management and resource allocation are also more challenging.

Channel-Feedback-Free Transmission for Downlink FD-RAN:A Radio Map Based Complex-Valued Precoding Network Approach

As the demand for high-quality services proliferates,an innovative network architecture,the fully-decoupled RAN(FD-RAN),has emerged for more flexible spectrum resource utilization and lower network costs.However,with the decoupling of uplink base stations and downlink base stations in FDRAN,the traditional transmission mechanism,which relies on real-time channel feedback,is not suitable as the receiver is not able to feedback accurate and timely channel state information to the transmitter.This paper proposes a novel transmission scheme without relying on physical layer channel feedback.Specifically,we design a radio map based complex-valued precoding network(RMCPNet)model,which outputs the base station precoding based on user location.RMCPNet comprises multiple subnets,with each subnet responsible for extracting unique modal features from diverse input modalities.Furthermore,the multimodal embeddings derived from these distinct subnets are integrated within the information fusion layer,culminating in a unified representation.We also develop a specific RMCPNet training algorithm that employs the negative spectral efficiency as the loss function.We evaluate the performance of the proposed scheme on the public DeepMIMO dataset and show that RMCPNet can achieve 16%and 76%performance improvements over the conventional real-valued neural network and statistical codebook approach,respectively.

Impact of asymptomatic infected individuals on epidemic transmission dynamics in multiplex networks with partial coupling

The theory of network science has attracted great interest of many researchers in the realm of biomathematics and public health,and numerous valuable epidemic models have been developed.In previous studies,it is common to set up a one-to-one correspondence between the nodes of a multi-layer network,ignoring the more complex situations in reality.In the present work,we explore this situation by setting up a partially coupled model of a two-layer network and investigating the impact of asymptomatic infected individuals on epidemics.We propose a self-discovery mechanism for asymptomatic infected individuals,taking into account situations such as nucleic acid testing in the community and individuals performing self-antigen testing during the epidemic.Considering these factors together,through the microscopic Markov chain approach(MMCA)and extensive Monte Carlo(MC)numerical simulations,we find that the greater the coupling between the networks,the more information dissemination is facilitated.In order to control the epidemics,more asymptomatic infected individuals should be made aware of their infection.Massive adoption of nucleic acid testing and individual adoption of antigenic self-testing can help to contain epidemic outbreaks.Meanwhile,the epidemic threshold of the proposed model is derived,and then miscellaneous factors affecting the epidemic threshold are also discussed.Current results are conducive to devising the prevention and control policies of pandemics.

Design of an Interconnection Architecture and Sizing of Two (2) EPC Core Networks: The Case of Orange-Guinea

With the arrival of the 4G and 5G,the telecommunications networks have experienced a large expansion of these networks.That enabled the integration of many services and adequate flow,thus enabling the operators to respond to the growing demand of users.This rapid evolution has given the operators to adapt,their methods to the new technologies that increase.This complexity becomes more important,when these networks include several technologies to access different from the heterogeneous network like in the 4G network.The dimensional new challenges tell the application and the considerable increase in demand for services and the compatibility with existing networks,the management of mobility intercellular of users and it offers a better quality of services.Thus,the proposed solution to meet these new requirements is the sizing of the EPC(Evolved Packet Core)core network to support the 5G access network.For the case of Orange Guinea,this involves setting up an architecture for interconnecting the core networks of Sonfonia and Camayenne.The objectives of our work are of two orders:(1)to propose these solutions and recommendations for the heart network EPC sizing and the deployment to be adopted;(2)supply and architectural interconnection in the heart network EPC and an existing heart network.In our work,the model of traffic in communication that we use to calculate the traffic generated with each technology has link in the network of the heart.

Transferable adversarial slow feature extraction network for few-shot quality prediction in coal-to-ethylene glycol process

In the coal-to-ethylene glycol(CTEG)process,precisely estimating quality variables is crucial for process monitoring,optimization,and control.A significant challenge in this regard is relying on offline laboratory analysis to obtain these variables,which often incurs substantial monetary costs and significant time delays.The resulting few-shot learning scenarios present a hurdle to the efficient development of predictive models.To address this issue,our study introduces the transferable adversarial slow feature extraction network(TASF-Net),an innovative approach designed specifically for few-shot quality prediction in the CTEG process.TASF-Net uniquely integrates the slowness principle with a deep Bayesian framework,effectively capturing the nonlinear and inertial characteristics of the CTEG process.Additionally,the model employs a variable attention mechanism to identify quality-related input variables adaptively at each time step.A key strength of TASF-Net lies in its ability to navigate the complex measurement noise,outliers,and system interference typical in CTEG data.Adversarial learning strategy using a min-max game is adopted to improve its robustness and ability to model irregular industrial data accurately and significantly.Furthermore,an incremental refining transfer learning framework is designed to further improve few-shot prediction performance achieved by transferring knowledge from the pretrained model on the source domain to the target domain.The effectiveness and superiority of TASF-Net have been empirically validated using a real-world CTEG dataset.Compared with some state-of-the-art methods,TASF-Net demonstrates exceptional capability in addressing the intricate challenges for few-shot quality prediction in the CTEG process.

Multivariate Time Series Anomaly Detection Based on Spatial-Temporal Network and Transformer in Industrial Internet of Things

In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.

Quick Weighing of Passing Vehicles Using the Transfer-Learning-Enhanced Convolutional Neural Network

Transfer learning could reduce the time and resources required by the training of new models and be therefore important for generalized applications of the trainedmachine learning algorithms.In this study,a transfer learningenhanced convolutional neural network(CNN)was proposed to identify the gross weight and the axle weight of moving vehicles on the bridge.The proposed transfer learning-enhanced CNN model was expected to weigh different bridges based on a small amount of training datasets and provide high identification accuracy.First of all,a CNN algorithm for bridge weigh-in-motion(B-WIM)technology was proposed to identify the axle weight and the gross weight of the typical two-axle,three-axle,and five-axle vehicles as they crossed the bridge with different loading routes and speeds.Then,the pre-trained CNN model was transferred by fine-tuning to weigh themoving vehicle on another bridge.Finally,the identification accuracy and the amount of training data required were compared between the two CNN models.Results showed that the pre-trained CNN model using transfer learning for B-WIM technology could be successfully used for the identification of the axle weight and the gross weight for moving vehicles on another bridge while reducing the training data by 63%.Moreover,the recognition accuracy of the pre-trained CNN model using transfer learning was comparable to that of the original model,showing its promising potentials in the actual applications.

Stochastic Ranking Improved Teaching-Learning and Adaptive Grasshopper Optimization Algorithm-Based Clustering Scheme for Augmenting Network Lifetime in WSNs

In Wireless Sensor Networks(WSNs),Clustering process is widely utilized for increasing the lifespan with sustained energy stability during data transmission.Several clustering protocols were devised for extending network lifetime,but most of them failed in handling the problem of fixed clustering,static rounds,and inadequate Cluster Head(CH)selection criteria which consumes more energy.In this paper,Stochastic Ranking Improved Teaching-Learning and Adaptive Grasshopper Optimization Algorithm(SRITL-AGOA)-based Clustering Scheme for energy stabilization and extending network lifespan.This SRITL-AGOA selected CH depending on the weightage of factors such as node mobility degree,neighbour's density distance to sink,single-hop or multihop communication and Residual Energy(RE)that directly influences the energy consumption of sensor nodes.In specific,Grasshopper Optimization Algorithm(GOA)is improved through tangent-based nonlinear strategy for enhancing the ability of global optimization.On the other hand,stochastic ranking and violation constraint handling strategies are embedded into Teaching-Learning-based Optimization Algorithm(TLOA)for improving its exploitation tendencies.Then,SR and VCH improved TLOA is embedded into the exploitation phase of AGOA for selecting better CH by maintaining better balance amid exploration and exploitation.Simulation results confirmed that the proposed SRITL-AGOA improved throughput by 21.86%,network stability by 18.94%,load balancing by 16.14%with minimized energy depletion by19.21%,compared to the competitive CH selection approaches.

Dynamic analysis of major public health emergency transmission considering the dual-layer coupling of community–resident complex networks

We construct a dual-layer coupled complex network of communities and residents to represent the interconnected risk transmission network between communities and the disease transmission network among residents. It characterizes the process of infectious disease transmission among residents between communities through the SE2IHR model considering two types of infectors. By depicting a more fine-grained social structure and combining further simulation experiments, the study validates the crucial role of various prevention and control measures implemented by communities as primary executors in controlling the epidemic. Research shows that the geographical boundaries of communities and the social interaction patterns of residents have a significant impact on the spread of the epidemic, where early detection, isolation and treatment strategies at community level are essential for controlling the spread of the epidemic. In addition, the study explores the collaborative governance model and institutional advantages of communities and residents in epidemic prevention and control.

Optimized operation scheme of flash-memory-based neural network online training with ultra-high endurance

With the rapid development of machine learning,the demand for high-efficient computing becomes more and more urgent.To break the bottleneck of the traditional Von Neumann architecture,computing-in-memory(CIM)has attracted increasing attention in recent years.In this work,to provide a feasible CIM solution for the large-scale neural networks(NN)requiring continuous weight updating in online training,a flash-based computing-in-memory with high endurance(10^(9) cycles)and ultrafast programming speed is investigated.On the one hand,the proposed programming scheme of channel hot electron injection(CHEI)and hot hole injection(HHI)demonstrate high linearity,symmetric potentiation,and a depression process,which help to improve the training speed and accuracy.On the other hand,the low-damage programming scheme and memory window(MW)optimizations can suppress cell degradation effectively with improved computing accuracy.Even after 109 cycles,the leakage current(I_(off))of cells remains sub-10pA,ensuring the large-scale computing ability of memory.Further characterizations are done on read disturb to demonstrate its robust reliabilities.By processing CIFAR-10 tasks,it is evident that~90%accuracy can be achieved after 109 cycles in both ResNet50 and VGG16 NN.Our results suggest that flash-based CIM has great potential to overcome the limitations of traditional Von Neumann architectures and enable high-performance NN online training,which pave the way for further development of artificial intelligence(AI)accelerators.

Anion exchange membranes with a semi-interpenetrating polymer network using 1,6-dibromohexane as bifunctional crosslinker

An anion exchange membrane(AEM)is generally expected to possess high ion exchange capacity(IEC),low water uptake(WU),and high mechanical strength when applied to electrodialysis desalination.Among different types of AEMs,semi-interpenetrating polymer networks(SIPNs)have been suggested for their structural superiorities,i.e.,the tunable local density of ion exchange groups for IEC and the restrained leaching of hygroscopic groups by insolubility for WU.Unfortunately,the conventional SIPN AEMs still struggle to balances IEC,WU,and mechanical strength simultaneously,due to the lack of the compact crosslinking region.In this work,we proposed a novel SIPN structure of polyvinylidene difluoride/polyvinylimidazole/1,6-dibromohexane(PVDF/PVIm/DBH).On the one hand,DBH with two cationic groups of imidazole groups are introduced to enhance the ion conductivity,which is different from the conventional monofunctional modifier with only one cationic group.On the other hand,DBH has the ability to bridge with PVIm,where the mechanical strength of the resulting AEM is increased by the increase of crosslinking degree.Results show that a low WU of 38.1%to 62.6%,high IEC of 2.12—2.22 mmol·g^(-1),and excellent tensile strength of 3.54—12.35 MPa for PVDF/PVIm/DBH membrane are achieved.This work opens a new avenue for achieving the high-quality AEMs.

Investigating Optical Transport Network Performance:A Recurrence Plot Approach

In future optical transport networks,lightpath performance analysis is of great practical significance for fully automated management.In general,the quality of transmission(QoT)of lightpaths,measured by optical quality factor or optical signal-to-noise ratio,has a complex time-varying process,along with the interactions of the other lightpath state parameters(LSPs),such as transmit power,chromatic dispersion,polarization mode dispersion.Current studies are mostly focused on lightpath QoT estimation,but ignoring lightpath-level data analytics.In this case,our article proposes a novel lightpath performance analysis method considering recurrence plot(RP)and cross recurrence plot(CRP).Firstly,we give a detailed interpretation on the recurrence patterns of LSPs via a qualitative 2-D RP representation and its quantitative measure.It can potentially enable the accurate and fast lightpath failure detection with a low computational burden.On the other hand,CRP is devoted to modeling the relationships between lightpath QoT and LSPs,and the correlation degree is determined by a geometric mean of multiple indexes of cross recurrence quantification analysis.From the view of application,such CRP analysis can provide the effective knowledge sharing to guarantee more credible QoT prediction.Extensive experiments on a real-world optical network dataset have clearly demonstrated the effectiveness of our proposal.

Network Configuration Entity Extraction Method Based on Transformer with Multi-Head Attention Mechanism

Nowadays,ensuring thequality of networkserviceshas become increasingly vital.Experts are turning toknowledge graph technology,with a significant emphasis on entity extraction in the identification of device configurations.This research paper presents a novel entity extraction method that leverages a combination of active learning and attention mechanisms.Initially,an improved active learning approach is employed to select the most valuable unlabeled samples,which are subsequently submitted for expert labeling.This approach successfully addresses the problems of isolated points and sample redundancy within the network configuration sample set.Then the labeled samples are utilized to train the model for network configuration entity extraction.Furthermore,the multi-head self-attention of the transformer model is enhanced by introducing the Adaptive Weighting method based on the Laplace mixture distribution.This enhancement enables the transformer model to dynamically adapt its focus to words in various positions,displaying exceptional adaptability to abnormal data and further elevating the accuracy of the proposed model.Through comparisons with Random Sampling(RANDOM),Maximum Normalized Log-Probability(MNLP),Least Confidence(LC),Token Entrop(TE),and Entropy Query by Bagging(EQB),the proposed method,Entropy Query by Bagging and Maximum Influence Active Learning(EQBMIAL),achieves comparable performance with only 40% of the samples on both datasets,while other algorithms require 50% of the samples.Furthermore,the entity extraction algorithm with the Adaptive Weighted Multi-head Attention mechanism(AW-MHA)is compared with BILSTM-CRF,Mutil_Attention-Bilstm-Crf,Deep_Neural_Model_NER and BERT_Transformer,achieving precision rates of 75.98% and 98.32% on the two datasets,respectively.Statistical tests demonstrate the statistical significance and effectiveness of the proposed algorithms in this paper.

A Novel Fractional Dengue Transmission Model in the Presence of Wolbachia Using Stochastic Based Artificial Neural Network

The purpose of this research work is to investigate the numerical solutions of the fractional dengue transmission model(FDTM)in the presence of Wolbachia using the stochastic-based Levenberg-Marquardt neural network(LM-NN)technique.The fractional dengue transmission model(FDTM)consists of 12 compartments.The human population is divided into four compartments;susceptible humans(S_(h)),exposed humans(E_(h)),infectious humans(I_(h)),and recovered humans(R_(h)).Wolbachia-infected and Wolbachia-uninfected mosquito population is also divided into four compartments:aquatic(eggs,larvae,pupae),susceptible,exposed,and infectious.We investigated three different cases of vertical transmission probability(η),namely when Wolbachia-free mosquitoes persist only(η=0.6),when both types of mosquitoes persist(η=0.8),and when Wolbachia-carrying mosquitoes persist only(η=1).The objective of this study is to investigate the effectiveness of Wolbachia in reducing dengue and presenting the numerical results by using the stochastic structure LM-NN approach with 10 hidden layers of neurons for three different cases of the fractional order derivatives(α=0.4,0.6,0.8).LM-NN approach includes a training,validation,and testing procedure to minimize the mean square error(MSE)values using the reference dataset(obtained by solving the model using the Adams-Bashforth-Moulton method(ABM).The distribution of data is 80% data for training,10% for validation,and,10% for testing purpose)results.A comprehensive investigation is accessible to observe the competence,precision,capacity,and efficiency of the suggested LM-NN approach by executing the MSE,state transitions findings,and regression analysis.The effectiveness of the LM-NN approach for solving the FDTM is demonstrated by the overlap of the findings with trustworthy measures,which achieves a precision of up to 10^(-4).

FPSblo:A Blockchain Network Transmission Model Utilizing Farthest Point Sampling

Peer-to-peer(P2P)overlay networks provide message transmission capabilities for blockchain systems.Improving data transmission efficiency in P2P networks can greatly enhance the performance of blockchain systems.However,traditional blockchain P2P networks face a common challenge where there is often a mismatch between the upper-layer traffic requirements and the underlying physical network topology.This mismatch results in redundant data transmission and inefficient routing,severely constraining the scalability of blockchain systems.To address these pressing issues,we propose FPSblo,an efficient transmission method for blockchain networks.Our inspiration for FPSblo stems from the Farthest Point Sampling(FPS)algorithm,a well-established technique widely utilized in point cloud image processing.In this work,we analogize blockchain nodes to points in a point cloud image and select a representative set of nodes to prioritize message forwarding so that messages reach the network edge quickly and are evenly distributed.Moreover,we compare our model with the Kadcast transmission model,which is a classic improvement model for blockchain P2P transmission networks,the experimental findings show that the FPSblo model reduces 34.8%of transmission redundancy and reduces the overload rate by 37.6%.By conducting experimental analysis,the FPS-BT model enhances the transmission capabilities of the P2P network in blockchain.

Proppant transport in rough fracture networks using supercritical CO_(2)

Proppant transport within fractures is one of the most critical tasks in oil,gas and geothermal reservoir stimulation,as it largely determines the ultimate performance of the operating well.Proppant transport in rough fracture networks is still a relatively new area of research and the associated transport mechanisms are still unclear.In this study,representative parameters of rough fracture surfaces formed by supercritical CO_(2) fracturing were used to generate a rough fracture network model based on a spectral synthesis method.Computational fluid dynamics(CFD)coupled with the discrete element method(DEM)was used to study proppant transport in this rough fracture network.To reveal the turning transport mechanism of proppants into branching fractures at the intersections of rough fracture networks,a comparison was made with the behavior within smooth fracture networks,and the effect of key pumping parameters on the proppant placement in a secondary fracture was analyzed.The results show that the transport behavior of proppant in rough fracture networks is very different from that of the one in the smooth fracture networks.The turning transport mechanisms of proppant into secondary fractures in rough fracture networks are gravity-driven sliding,high velocity fluid suspension,and fracture structure induction.Under the same injection conditions,supercritical CO_(2)with high flow Reynolds number still has a weaker ability to transport proppant into secondary fractures than water.Thickening of the supercritical CO_(2)needs to be increased beyond a certain value to have a significant effect on proppant carrying,and under the temperature and pressure conditions of this paper,it needs to be increased more than 20 times(about 0.94 m Pa s).Increasing the injection velocity and decreasing the proppant concentration facilitates the entry of proppant into the branching fractures,which in turn results in a larger stimulated reservoir volume.The results help to understand the proppant transport and placement process in rough fracture networks formed by reservoir stimulation,and provide a theoretical reference for the optimization of proppant pumping parameters in hydraulic fracturing.

Resource Allocation in Multi-User Cellular Networks:A Transformer-Based Deep Reinforcement Learning Approach

To meet the communication services with diverse requirements,dynamic resource allocation has shown increasing importance.In this paper,we consider the multi-slot and multi-user resource allocation(MSMU-RA)in a downlink cellular scenario with the aim of maximizing system spectral efficiency while guaranteeing user fairness.We first model the MSMURA problem as a dual-sequence decision-making process,and then solve it by a novel Transformerbased deep reinforcement learning(TDRL)approach.Specifically,the proposed TDRL approach can be achieved based on two aspects:1)To adapt to the dynamic wireless environment,the proximal policy optimization(PPO)algorithm is used to optimize the multi-slot RA strategy.2)To avoid co-channel interference,the Transformer-based PPO algorithm is presented to obtain the optimal multi-user RA scheme by exploring the mapping between user sequence and resource sequence.Experimental results show that:i)the proposed approach outperforms both the traditional and DRL methods in spectral efficiency and user fairness,ii)the proposed algorithm is superior to DRL approaches in terms of convergence speed and generalization performance.