Query：
学者姓名：郭迎亚
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
Routing optimization, as a significant part of Traffic Engineering (TE), plays an important role in balancing network traffic and improving quality of service. With the application of Machine Learning (ML) in various fields, many neural network-based routing optimization solutions have been proposed. However, most existing ML-based methods need to retrain the model when confronted with a network unseen during training, which incurs significant time overhead and response delay. To improve the generalization ability of the routing model, in this paper, we innovatively propose a routing optimization method GROM which combines Deep Reinforcement Learning (DRL) and Graph Neural Networks (GNN), to directly generate routing policies under different and unseen network topologies without retraining. Specifically, for handling different network topologies, we transform the traffic-splitting ratio into element -level output of GNN model. To make the DRL agent easier to converge and well generalize to unseen topologies, we discretize the huge continuous trafficsplitting action space. Extensive simulation results on five real-world network topologies demonstrate that GROM can rapidly generate routing policies under different network topologies and has superior generalization ability.
Keyword ：
Graph neural networks Graph neural networks Reinforcement learning Reinforcement learning Software-defined networks Software-defined networks Traffic engineering Traffic engineering
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ding, Mingjie , Guo, Yingya , Huang, Zebo et al. GROM: A generalized routing optimization method with graph neural network and deep reinforcement learning [J]. | JOURNAL OF NETWORK AND COMPUTER APPLICATIONS , 2024 , 229 . |
| MLA | Ding, Mingjie et al. "GROM: A generalized routing optimization method with graph neural network and deep reinforcement learning" . | JOURNAL OF NETWORK AND COMPUTER APPLICATIONS 229 (2024) . |
| APA | Ding, Mingjie , Guo, Yingya , Huang, Zebo , Lin, Bin , Luo, Huan . GROM: A generalized routing optimization method with graph neural network and deep reinforcement learning . | JOURNAL OF NETWORK AND COMPUTER APPLICATIONS , 2024 , 229 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Network traffic prediction plays a significant role in network management. Previous network traffic prediction methods mainly focus on the temporal relationship between network traffic, and used time series models to predict network traffic, ignoring the spatial information contained in traffic data. Therefore, the prediction accuracy is limited, especially in long-term prediction. To improve the prediction accuracy of the dynamic network traffic in the long term, we propose an Attention -based Spatial-Temporal Graph Network (ASTGN) model for network traffic prediction to better capture both the temporal and spatial relations between the network traffic. Specifically, in ASTGN, we exploit an encoder-decoder architecture, where the encoder encodes the input network traffic and the decoder outputs the predicted network traffic sequences, integrating the temporal and spatial information of the network traffic data through the Spatio-Temporal Embedding module. The experimental results demonstrate the superiority of our proposed method ASTGN in long-term prediction.
Keyword ：
Attention mechanism Attention mechanism Encoder-decoder Encoder-decoder Graph neural network Graph neural network Network traffic prediction Network traffic prediction Temporal and spatial Temporal and spatial
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Peng, Yufei , Guo, Yingya , Hao, Run et al. Network traffic prediction with Attention-based Spatial-Temporal Graph Network [J]. | COMPUTER NETWORKS , 2024 , 243 . |
| MLA | Peng, Yufei et al. "Network traffic prediction with Attention-based Spatial-Temporal Graph Network" . | COMPUTER NETWORKS 243 (2024) . |
| APA | Peng, Yufei , Guo, Yingya , Hao, Run , Xu, Chengzhe . Network traffic prediction with Attention-based Spatial-Temporal Graph Network . | COMPUTER NETWORKS , 2024 , 243 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Hybrid Software Defined Networks (Hybrid SDNs), with a partial upgrade of legacy routers to SDN switches in traditional distributed networks, currently stand as a prevailing network architecture. Traffic Engineering (TE) in hybrid SDN requires the efficient and timely acquisition of a routing policy to adapt to dynamically changing traffic demands, which has recently become a hot topic. Ignoring the hidden relations of consecutive states and the compact representation of the network environment, previous Deep Reinforcement Learning (DRL)-based studies suffer from the convergence problem by only establishing the direct relationship between individual Traffic Matrix (TM) and routing policy. Therefore, to enhance TE performance in hybrid SDNs under dynamically changing traffic demands, we propose to integrate the Transformer model with DRL to establish the relationship between consecutive states and routing policies. The temporal characteristic among consecutive states can effectively assist DRL in solving the convergence problem. To obtain a compact and accurate description of the network environment, we propose to jointly consider TM, routing action, and reward in designing the state of the network environment. To better capture the temporal relations among consecutive states of the network environment, we design a multi-feature embedding module and achieve positional encodings in the Transformer model. The extensive experiments demonstrate that once the convergence problem is solved, the proposed Transformer-based DRL method can efficiently generate routing policies that adapt well to dynamic network traffic.
Keyword ：
Deep Reinforcement Learning Deep Reinforcement Learning Dynamic traffic Dynamic traffic Hybrid SDN Hybrid SDN Traffic Engineering Traffic Engineering Transformer Transformer
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Bin , Guo, Yingya , Luo, Huan et al. TITE: A transformer-based deep reinforcement learning approach for traffic engineering in hybrid SDN with dynamic traffic [J]. | FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE , 2024 , 161 : 95-105 . |
| MLA | Lin, Bin et al. "TITE: A transformer-based deep reinforcement learning approach for traffic engineering in hybrid SDN with dynamic traffic" . | FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 161 (2024) : 95-105 . |
| APA | Lin, Bin , Guo, Yingya , Luo, Huan , Ding, Mingjie . TITE: A transformer-based deep reinforcement learning approach for traffic engineering in hybrid SDN with dynamic traffic . | FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE , 2024 , 161 , 95-105 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Hybrid Software Defined Networks (Hybrid SDNs), which combines the robustness of distributed network and the flexibility of centralized network, is now a prevailing network architecture. Previous hybrid SDN Traffic Engineering (TE) solutions search an optimal link weight setting or compute the splitting ratios of traffic leveraging heuristic algorithms. However, these methods cannot react timely to the fluctuating traffic demands in dynamic environments and suffer a hefty performance degradation when traffic demands change or network failures happen, especially when network scale is large. To cope with this, we propose a Multi- Agent reinforcement learning based TE method MATE that timely determines the route selection for network flows in dynamic hybrid SDNs. Through dividing the large-scale routing optimization problem into small-scale problem, MATE can better learn the mapping between the traffic demands and routing policy, and efficiently make online routing inference with dynamic traffic demands. To collaborate multiple agents and speed up the convergence in the training process, we innovatively design the actor network and introduce previous actions of all agents in the training of each agent. Extensive experiments conducted on different network topologies demonstrate our proposed method MATE has superior TE performance with dynamic traffic demands and is robust to network failures.
Keyword ：
Dynamic environment Dynamic environment Hybrid Software Defined Networks Hybrid Software Defined Networks Multi-agent reinforcement learning Multi-agent reinforcement learning Traffic Engineering Traffic Engineering
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Guo, Yingya , Ding, Mingjie , Zhou, Weihong et al. MATE: A multi-agent reinforcement learning approach for Traffic Engineering in Hybrid Software Defined Networks [J]. | JOURNAL OF NETWORK AND COMPUTER APPLICATIONS , 2024 , 231 . |
| MLA | Guo, Yingya et al. "MATE: A multi-agent reinforcement learning approach for Traffic Engineering in Hybrid Software Defined Networks" . | JOURNAL OF NETWORK AND COMPUTER APPLICATIONS 231 (2024) . |
| APA | Guo, Yingya , Ding, Mingjie , Zhou, Weihong , Lin, Bin , Chen, Cen , Luo, Huan . MATE: A multi-agent reinforcement learning approach for Traffic Engineering in Hybrid Software Defined Networks . | JOURNAL OF NETWORK AND COMPUTER APPLICATIONS , 2024 , 231 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Network traffic prediction plays a significant role in network management. Previous network traffic prediction methods mainly focus on the temporal relationship between network traffic, and used time series models to predict network traffic, ignoring the spatial information contained in traffic data. Therefore, the prediction accuracy is limited, especially in long-term prediction. To improve the prediction accuracy of the dynamic network traffic in the long term, we propose an Attention-based Spatial-Temporal Graph Network (ASTGN) model for network traffic prediction to better capture both the temporal and spatial relations between the network traffic. Specifically, in ASTGN, we exploit an encoder-decoder architecture, where the encoder encodes the input network traffic and the decoder outputs the predicted network traffic sequences, integrating the temporal and spatial information of the network traffic data through the Spatio-Temporal Embedding module. The experimental results demonstrate the superiority of our proposed method ASTGN in long-term prediction.
Keyword ：
Attention Mechanism Attention Mechanism Encoder-Decoder Encoder-Decoder Graph Neural Network Graph Neural Network Network Traffic Prediction Network Traffic Prediction Temporal and Spatial Temporal and Spatial
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Peng, Yufei , Guo, Yingya , Hao, Run et al. Network Traffic Prediction with Attention-based Spatial-Temporal Graph Network [J]. | 2023 IEEE 24TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE SWITCHING AND ROUTING, HPSR , 2023 . |
| MLA | Peng, Yufei et al. "Network Traffic Prediction with Attention-based Spatial-Temporal Graph Network" . | 2023 IEEE 24TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE SWITCHING AND ROUTING, HPSR (2023) . |
| APA | Peng, Yufei , Guo, Yingya , Hao, Run , Lin, Junda . Network Traffic Prediction with Attention-based Spatial-Temporal Graph Network . | 2023 IEEE 24TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE SWITCHING AND ROUTING, HPSR , 2023 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Network traffic classification is the foundation for many network security and network management applications. Recently, to preserve the privacy of the data which are generated in the mobile ends, federated learning (FL)-based classification methods are being proposed. Unfortunately, the performance of FL-based methods can seriously degrade when the client data have skewness. This is particularly true for mobile network traffic classification where the environments in the mobile ends are highly heterogeneous. In this article, we first conduct a measurement study on traffic classification accuracy through FL using real-world network traffic trace and we observe serious accuracy degradation due to heterogeneous environments. We propose a novel federated analytics (FA) approach, FEAT, to improve the accuracy. Note that FL emphasizes on model training, yet our FA performs local analytic tasks that can estimate traffic data skewness and select appropriate clients for FL model training. Our analytics tasks are performed locally and in a federated manner; thus, we preserve privacy as well. Our approach has strong theoretical properties where we exploit Hoeffding inequality to infer traffic data skewness and we leverage the Thompson Sampling for client selection. We evaluate our approach through extensive experiments using real-world traffic data sets QUIC and ISCX. The extensive experiments demonstrate that FEAT can improve traffic classification accuracy in heterogeneous environments.
Keyword ：
Federated analytics (FA) Federated analytics (FA) federated learning (FL) federated learning (FL) heterogeneous environments heterogeneous environments network traffic classification network traffic classification
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Guo, Yingya , Wang, Dan . FEAT: A Federated Approach for Privacy-Preserving Network Traffic Classification in Heterogeneous Environments [J]. | IEEE INTERNET OF THINGS JOURNAL , 2023 , 10 (2) : 1274-1285 . |
| MLA | Guo, Yingya et al. "FEAT: A Federated Approach for Privacy-Preserving Network Traffic Classification in Heterogeneous Environments" . | IEEE INTERNET OF THINGS JOURNAL 10 . 2 (2023) : 1274-1285 . |
| APA | Guo, Yingya , Wang, Dan . FEAT: A Federated Approach for Privacy-Preserving Network Traffic Classification in Heterogeneous Environments . | IEEE INTERNET OF THINGS JOURNAL , 2023 , 10 (2) , 1274-1285 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Mobile edge computing (MEC) provides high-quality network service to mobile users. In a MEC network, the placement of edge servers not only affects the service experience of users, but also has a great influence on the energy consumption of the MEC system. In this paper, we study the edge server placement problem in dynamic MEC scenarios, to minimize the energy consumption of the MEC system in real time, so as to achieve the goal of energy saving at every time. We propose a reinforcement learning (RL) based approach called ESDR. Moreover, in order to make RL suitable for our proposed problem and enable the agent to explore better in MEC scenarios, we introduce Double Q-learning and delaying policy updates to improve the original RL framework. Furthermore, experiments are conducted using a real-world dataset. The results show that ESDR is outstanding in terms of energy saving with fewer edge servers than other approaches in dynamic MEC scenarios. © 2023 IEEE.
Keyword ：
Energy conservation Energy conservation Energy utilization Energy utilization Green computing Green computing Mobile edge computing Mobile edge computing Power management Power management Reinforcement learning Reinforcement learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Cen , Guo, Yingya . Energy-Aware Edge Server Placement in Dynamic Scenario Using Reinforcement Learning [C] . 2023 : 183-187 . |
| MLA | Chen, Cen et al. "Energy-Aware Edge Server Placement in Dynamic Scenario Using Reinforcement Learning" . (2023) : 183-187 . |
| APA | Chen, Cen , Guo, Yingya . Energy-Aware Edge Server Placement in Dynamic Scenario Using Reinforcement Learning . (2023) : 183-187 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Due to economic costs and hardware limitations of full SDN deployment, partially deploying Software-defined networking (SDN) switches in traditional networks has become the most popular network architecture nowadays. Traffic engineering (TE) promotes the improvement of hybrid SDN performance by optimizing route selection and balancing network flows. Previous TE methods in hybrid SDN focus on centrally searching for the best link weight settings and leveraging heuristic algorithms to calculate the optimal splitting ratio of traffic through SDN switches. Due to the fluctuation of network traffic, previous algorithms fail to learn a routing policy that can adapt to the fast-changing network flows and network performance degrades as a result. Therefore, in this paper, to better learn the traffic features and improve the routing performance, we innovatively propose a TE approach combining contrastive learning and reinforcement learning to optimize routing of network traffic in hybrid SDN. Each agent trains an encoder that well represents the traffic features through contrastive learning and the traffic features are fed into the training of the actor neural network for learning the map between the traffic and routing policy through reinforcement learning. After offline training, the agent deployed on the SDN switch can quickly infer an effective traffic splitting policy that determines the splitting ratio of traffic on the SDN switch. Extensive experiments on three different network topologies show that our proposed algorithm provides significant improvements over state-of-arts. © 2023 IEEE.
Keyword ：
Arts computing Arts computing Balancing Balancing Heuristic algorithms Heuristic algorithms Heuristic methods Heuristic methods Network architecture Network architecture Network routing Network routing Optimization Optimization Reinforcement learning Reinforcement learning Software defined networking Software defined networking
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Tang, Qi , Yang, Ruiyu , Guo, Yingya . Reinforcement Learning with Contrastive Unsupervised Representations for Traffic Engineering in Hybrid SDN [C] . 2023 : 118-122 . |
| MLA | Tang, Qi et al. "Reinforcement Learning with Contrastive Unsupervised Representations for Traffic Engineering in Hybrid SDN" . (2023) : 118-122 . |
| APA | Tang, Qi , Yang, Ruiyu , Guo, Yingya . Reinforcement Learning with Contrastive Unsupervised Representations for Traffic Engineering in Hybrid SDN . (2023) : 118-122 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Network traffic prediction is essential and significant to network management and network security. Existing prediction methods cannot well capture the temporal-spatial correlations hidden in the network traffic and suffer from a prediction accuracy degradation for two reasons. First, existing approaches concentrate on capturing the spatial relations and dependence in an explicit network topology graph, which fails to reflect the inherent relations in network traffic. Second, the common recurrent neural network models which are leveraged to learn the temporal relations in network traffic exhibit a poor performance in long-term prediction for its limited receptive field. To tackle these two problems, we propose an Attention-based Graph Convolutional Network model (AGCN) for capturing both the spatial and temporal correlations in network traffic. To catch the hidden spatial dependencies in network traffic, we combine graph attention network with graph convolutional network to mine the spatial relationships of network traffic. To efficiently learn the temporal long-term relations embedded in network traffic, we design a dilated convolution module to enable an exponentially growing receptive field for handling long sequences. Experimental results on three network traffic datasets show that AGCN has excellent performance in terms of prediction accuracy and inference time compared to current mainstream methods. © 2023 IEEE.
Keyword ：
Convolution Convolution Convolutional neural networks Convolutional neural networks Forecasting Forecasting Graph neural networks Graph neural networks Network security Network security Recurrent neural networks Recurrent neural networks Topology Topology
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wan, Xia , Peng, Yufei , Hao, Run et al. Capturing Spatial-Temporal Correlations with Attention Based Graph Convolutional Networks for Network Traffic Prediction [C] . 2023 : 95-99 . |
| MLA | Wan, Xia et al. "Capturing Spatial-Temporal Correlations with Attention Based Graph Convolutional Networks for Network Traffic Prediction" . (2023) : 95-99 . |
| APA | Wan, Xia , Peng, Yufei , Hao, Run , Guo, Yingya . Capturing Spatial-Temporal Correlations with Attention Based Graph Convolutional Networks for Network Traffic Prediction . (2023) : 95-99 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
随着物联网(IoT)和 5G 技术的快速发展,移动边缘计算以其低访问延迟、低带宽成本和低能源消耗的优点引起了工业界和学术界的广泛关注.在移动边缘计算中,边缘服务器为移动端用户的请求提供服务,其放置位置对边缘计算性能和用户体验具有重要影响.目前边缘服务器的放置算法只考虑基站的地理位置,而缺乏对基站连接的用户数目因素的考虑.因此在实际用户分布不均的情况下,现有算法得到的服务器放置位置导致用户平均访问延迟较大.为了更好地解决上述问题,提出了基于谱聚类的延迟最小化边缘服务器放置算法 LAMP.该算法在考虑边缘服务器放置位置时,不仅考虑了基站的地理位置,而且考虑了不同基站连接的用户数目这一重要参数,能够有效地降低用户的平均访问时延,同时实现边缘服务器的工作负载均衡.在仿真实验中,使用了上海电信的真实基站数据集来测试 LAMP 算法的性能.大量的实验结果表明,在用户访问延迟方面,LAMP算法的性能比传统的K-means 算法提高了 37.9%.在负载均衡方面,LAMP算法的性能与K-means算法相比最大可提高 82.85%.LAMP算法在降低访问延迟和平衡边缘服务器工作负载方面均表现出了优越的性能.
Keyword ：
工作负载 工作负载 用户分布 用户分布 移动边缘计算 移动边缘计算 访问时延 访问时延 谱聚类算法 谱聚类算法 边缘服务器放置 边缘服务器放置
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 郭迎亚 , 王丽娟 , 耿海军 . 基于谱聚类的边缘服务器放置算法 [J]. | 计算机科学 , 2023 , 50 (10) : 248-257 . |
| MLA | 郭迎亚 et al. "基于谱聚类的边缘服务器放置算法" . | 计算机科学 50 . 10 (2023) : 248-257 . |
| APA | 郭迎亚 , 王丽娟 , 耿海军 . 基于谱聚类的边缘服务器放置算法 . | 计算机科学 , 2023 , 50 (10) , 248-257 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
