With the rapid development of 5G technology,the proportion of video traffic on the Internet is increasing,bringing pressure on the network infrastructure.Edge computing technology provides a feasible solution for opti...With the rapid development of 5G technology,the proportion of video traffic on the Internet is increasing,bringing pressure on the network infrastructure.Edge computing technology provides a feasible solution for optimizing video content distribution.However,the limited edge node cache capacity and dynamic user requests make edge caching more complex.Therefore,we propose a recommendation-driven edge Caching network architecture for the Full life cycle of video streaming(FlyCache)designed to improve users’Quality of Experience(QoE)and reduce backhaul traffic consumption.FlyCache implements intelligent caching management across three key stages:before-playback,during-playback,and after-playback.Specifically,we introduce a cache placement policy for the before-playback stage,a dynamic prefetching and cache admission policy for the during-playback stage,and a progressive cache eviction policy for the after-playback stage.To validate the effectiveness of FlyCache,we developed a user behavior-driven edge caching simulation framework incorporating recommendation mechanisms.Experiments conducted on the MovieLens and synthetic datasets demonstrate that FlyCache outperforms other caching strategies in terms of byte hit rate,backhaul traffic,and delayed startup rate.展开更多
In this paper,unmanned aerial vehicle(UAV)is adopted to serve as aerial base station(ABS)and mobile edge computing(MEC)platform for wire-less communication systems.When Internet of Things devices(IoTDs)cannot cope wit...In this paper,unmanned aerial vehicle(UAV)is adopted to serve as aerial base station(ABS)and mobile edge computing(MEC)platform for wire-less communication systems.When Internet of Things devices(IoTDs)cannot cope with computation-intensive and/or time-sensitive tasks,part of tasks is offloaded to the UAV side,and UAV process them with its own computing resources and caching resources.Thus,the burden of IoTDs gets relieved under the satisfaction of the quality of service(QoS)require-ments.However,owing to the limited resources of UAV,the cost of whole system,i.e.,that is defined as the weighted sum of energy consumption and time de-lay with caching,should be further optimized while the objective function and the constraints are non-convex.Therefore,we first jointly optimize commu-nication resources B,computing resources F and of-floading rates X with alternating iteration and convex optimization method,and then determine the value of caching decision Y with branch-and-bound(BB)al-gorithm.Numerical results show that UAV assisting partial task offloading with content caching is supe-rior to local computing and full offloading mechanism without caching,and meanwhile the cost of whole sys-tem gets further optimized with our proposed scheme.展开更多
Efficient edge caching is essential for maximizing utility in video streaming systems,especially under constraints such as limited storage capacity and dynamically fluctuating content popularity.Utility,defined as the...Efficient edge caching is essential for maximizing utility in video streaming systems,especially under constraints such as limited storage capacity and dynamically fluctuating content popularity.Utility,defined as the benefit obtained per unit of cache bandwidth usage,degrades when static or greedy caching strategies fail to adapt to changing demand patterns.To address this,we propose a deep reinforcement learning(DRL)-based caching framework built upon the proximal policy optimization(PPO)algorithm.Our approach formulates edge caching as a sequential decision-making problem and introduces a reward model that balances cache hit performance and utility by prioritizing high-demand,high-quality content while penalizing degraded quality delivery.We construct a realistic synthetic dataset that captures both temporal variations and shifting content popularity to validate our model.Experimental results demonstrate that our proposed method improves utility by up to 135.9%and achieves an average improvement of 22.6%compared to traditional greedy algorithms and long short-term memory(LSTM)-based prediction models.Moreover,our method consistently performs well across a variety of utility functions,workload distributions,and storage limitations,underscoring its adaptability and robustness in dynamic video caching environments.展开更多
Named data networking(NDNs)is an idealized deployment of information-centric networking(ICN)that has attracted attention from scientists and scholars worldwide.A distributed in-network caching scheme can efficiently r...Named data networking(NDNs)is an idealized deployment of information-centric networking(ICN)that has attracted attention from scientists and scholars worldwide.A distributed in-network caching scheme can efficiently realize load balancing.However,such a ubiquitous caching approach may cause problems including duplicate caching and low data diversity,thus reducing the caching efficiency of NDN routers.To mitigate these caching problems and improve the NDN caching efficiency,in this paper,a hierarchical-based sequential caching(HSC)scheme is proposed.In this scheme,the NDN routers in the data transmission path are divided into various levels and data with different request frequencies are cached in distinct router levels.The aim is to cache data with high request frequencies in the router that is closest to the content requester to increase the response probability of the nearby data,improve the data caching efficiency of named data networks,shorten the response time,and reduce cache redundancy.Simulation results show that this scheme can effectively improve the cache hit rate(CHR)and reduce the average request delay(ARD)and average route hop(ARH).展开更多
Vehicular networks enable seamless connectivity for exchanging emergency and infotainment content.However,retrieving infotainment data from remote servers often introduces high delays,degrading the Quality of Service(...Vehicular networks enable seamless connectivity for exchanging emergency and infotainment content.However,retrieving infotainment data from remote servers often introduces high delays,degrading the Quality of Service(QoS).To overcome this,caching frequently requested content at fog-enabled Road Side Units(RSUs)reduces communication latency.Yet,the limited caching capacity of RSUs makes it impractical to store all contents with varying sizes and popularity.This research proposes an efficient content caching algorithm that adapts to dynamic vehicular demands on highways to maximize request satisfaction.The scheme is evaluated against Intelligent Content Caching(ICC)and Random Caching(RC).The obtained results show that our proposed scheme entertains more contentrequesting vehicles as compared to ICC and RC,with 33%and 41%more downloaded data in 28%and 35%less amount of time from ICC and RC schemes,respectively.展开更多
Increasing reliance on large-scale AI models has led to rising demand for intelligent services.The centralized cloud computing approach has limitations in terms of data transfer efficiency and response time,and as a r...Increasing reliance on large-scale AI models has led to rising demand for intelligent services.The centralized cloud computing approach has limitations in terms of data transfer efficiency and response time,and as a result many service providers have begun to deploy edge servers to cache intelligent services in order to reduce transmission delay and communication energy consumption.However,finding the optimal service caching strategy remains a significant challenge due to the stochastic nature of service requests and the bulky nature of intelligent services.To deal with this,we propose a distributed service caching scheme integrating deep reinforcement learning(DRL)with mobility prediction,which we refer to as DSDM.Specifically,we employ the D3QN(Deep Double Dueling Q-Network)framework to integrate Long Short-Term Memory(LSTM)predicted mobile device locations into the service caching replacement algorithm and adopt the distributed multi-agent approach for learning and training.Experimental results demonstrate that DSDM achieves significant performance improvements in reducing communication energy consumption compared to traditional methods across various scenarios.展开更多
With the rapid development of generative artificial intelligence technology,the traditional cloud-based centralized model training and inference face significant limitations due to high transmission latency and costs,...With the rapid development of generative artificial intelligence technology,the traditional cloud-based centralized model training and inference face significant limitations due to high transmission latency and costs,which restrict user-side in-situ Artificial Intelligence Generated Content(AIGC)service requests.To this end,we propose the Edge Artificial Intelligence Generated Content(Edge AIGC)framework,which can effectively address the challenges of cloud computing by implementing in-situ processing of services close to the data source through edge computing.However,AIGC models usually have a large parameter scale and complex computing requirements,which poses a huge challenge to the storage and computing resources of edge devices.This paper focuses on the edge intelligence model caching and resource allocation problems in the Edge AIGC framework,aiming to improve the cache hit rate and resource utilization of edge devices for models by optimizing the model caching strategy and resource allocation scheme,and realize in-situ AIGC service processing.With the optimization objectives of minimizing service request response time and execution cost in resource-constrained environments,we employ the Twin Delayed Deep Deterministic Policy Gradient algorithm for optimization.Experimental results show that,compared with other methods,our model caching and resource allocation strategies can effectively improve the cache hit rate by at least 41.06%and reduce the response cost as well.展开更多
Existing wireless networks are flooded with video data transmissions,and the demand for high-speed and low-latency video services continues to surge.This has brought with it challenges to networks in the form of conge...Existing wireless networks are flooded with video data transmissions,and the demand for high-speed and low-latency video services continues to surge.This has brought with it challenges to networks in the form of congestion as well as the need for more resources and more dedicated caching schemes.Recently,Multi-access Edge Computing(MEC)-enabled heterogeneous networks,which leverage edge caches for proximity delivery,have emerged as a promising solution to all of these problems.Designing an effective edge caching scheme is critical to its success,however,in the face of limited resources.We propose a novel Knowledge Graph(KG)-based Dueling Deep Q-Network(KG-DDQN)for cooperative caching in MEC-enabled heterogeneous networks.The KGDDQN scheme leverages a KG to uncover video relations,providing valuable insights into user preferences for the caching scheme.Specifically,the KG guides the selection of related videos as caching candidates(i.e.,actions in the DDQN),thus providing a rich reference for implementing a personalized caching scheme while also improving the decision efficiency of the DDQN.Extensive simulation results validate the convergence effectiveness of the KG-DDQN,and it also outperforms baselines regarding cache hit rate and service delay.展开更多
In dynamic 5G network environments,user mobility and heterogeneous network topologies pose dual challenges to the effort of improving performance of mobile edge caching.Existing studies often overlook the dynamic natu...In dynamic 5G network environments,user mobility and heterogeneous network topologies pose dual challenges to the effort of improving performance of mobile edge caching.Existing studies often overlook the dynamic nature of user locations and the potential of device-to-device(D2D)cooperative caching,limiting the reduction of transmission latency.To address this issue,this paper proposes a joint optimization scheme for edge caching that integrates user mobility prediction with deep reinforcement learning.First,a Transformer-based geolocation prediction model is designed,leveraging multi-head attention mechanisms to capture correlations in historical user trajectories for accurate future location prediction.Then,within a three-tier heterogeneous network,we formulate a latency minimization problem under a D2D cooperative caching architecture and develop a mobility-aware Deep Q-Network(DQN)caching strategy.This strategy takes predicted location information as state input and dynamically adjusts the content distribution across small base stations(SBSs)andmobile users(MUs)to reduce end-to-end delay inmulti-hop content retrieval.Simulation results show that the proposed DQN-based method outperforms other baseline strategies across variousmetrics,achieving a 17.2%reduction in transmission delay compared to DQNmethods withoutmobility integration,thus validating the effectiveness of the joint optimization of location prediction and caching decisions.展开更多
The influence of different solution and aging conditions on the microstructure,impact toughness,and crack initiation and propagation mechanisms of the novel α+β titanium alloy Ti6422 was systematically investigated....The influence of different solution and aging conditions on the microstructure,impact toughness,and crack initiation and propagation mechanisms of the novel α+β titanium alloy Ti6422 was systematically investigated.By adjusting the furnace cooling time after solution treatment and the aging temperature,Ti6422 alloy samples were developed with a multi-level lamellar microstructure,in-cluding microscaleαcolonies and α_(p) lamellae,as well as nanoscale α_(s) phases.Extending the furnace cooling time after solution treatment at 920℃ for 1 h from 240 to 540 min,followed by aging at 600℃ for 6 h,increased the α_(p) lamella content,reduced the α_(s) phase content,expanded theαcolonies and α_(p) lamellae size,and improved the impact toughness from 22.7 to 53.8 J/cm^(2).Additionally,under the same solution treatment,raising the aging temperature from 500 to 700℃ resulted in a decrease in the α_(s) phase content and a growth in the thickness of the α_(p) lamella and α_(s) phase.The impact toughness increased significantly with these changes.Samples with high α_(p) lamellae content or large α_(s) phase size exhibited high crack initiation and propagation energies.Impact deformation caused severe kinking of the α_(p) lamellae in crack initiation and propagation areas,leading to a uniform and high-density kernel average misorientation(KAM)distribu-tion,enhancing plastic deformation coordination and uniformity.Moreover,the multidirectional arrangement of coarserαcolonies and α_(p) lamellae continuously deflect the crack propagation direction,inhibiting crack propagation.展开更多
基金supported by the National Natural Science Foundation of China(NSFC)[Grant No.62072469].
文摘With the rapid development of 5G technology,the proportion of video traffic on the Internet is increasing,bringing pressure on the network infrastructure.Edge computing technology provides a feasible solution for optimizing video content distribution.However,the limited edge node cache capacity and dynamic user requests make edge caching more complex.Therefore,we propose a recommendation-driven edge Caching network architecture for the Full life cycle of video streaming(FlyCache)designed to improve users’Quality of Experience(QoE)and reduce backhaul traffic consumption.FlyCache implements intelligent caching management across three key stages:before-playback,during-playback,and after-playback.Specifically,we introduce a cache placement policy for the before-playback stage,a dynamic prefetching and cache admission policy for the during-playback stage,and a progressive cache eviction policy for the after-playback stage.To validate the effectiveness of FlyCache,we developed a user behavior-driven edge caching simulation framework incorporating recommendation mechanisms.Experiments conducted on the MovieLens and synthetic datasets demonstrate that FlyCache outperforms other caching strategies in terms of byte hit rate,backhaul traffic,and delayed startup rate.
基金supported by National Natural Science Foundation of China(No.61821001)Science and Technology Key Project of Guangdong Province,China(2019B010157001).
文摘In this paper,unmanned aerial vehicle(UAV)is adopted to serve as aerial base station(ABS)and mobile edge computing(MEC)platform for wire-less communication systems.When Internet of Things devices(IoTDs)cannot cope with computation-intensive and/or time-sensitive tasks,part of tasks is offloaded to the UAV side,and UAV process them with its own computing resources and caching resources.Thus,the burden of IoTDs gets relieved under the satisfaction of the quality of service(QoS)require-ments.However,owing to the limited resources of UAV,the cost of whole system,i.e.,that is defined as the weighted sum of energy consumption and time de-lay with caching,should be further optimized while the objective function and the constraints are non-convex.Therefore,we first jointly optimize commu-nication resources B,computing resources F and of-floading rates X with alternating iteration and convex optimization method,and then determine the value of caching decision Y with branch-and-bound(BB)al-gorithm.Numerical results show that UAV assisting partial task offloading with content caching is supe-rior to local computing and full offloading mechanism without caching,and meanwhile the cost of whole sys-tem gets further optimized with our proposed scheme.
文摘Efficient edge caching is essential for maximizing utility in video streaming systems,especially under constraints such as limited storage capacity and dynamically fluctuating content popularity.Utility,defined as the benefit obtained per unit of cache bandwidth usage,degrades when static or greedy caching strategies fail to adapt to changing demand patterns.To address this,we propose a deep reinforcement learning(DRL)-based caching framework built upon the proximal policy optimization(PPO)algorithm.Our approach formulates edge caching as a sequential decision-making problem and introduces a reward model that balances cache hit performance and utility by prioritizing high-demand,high-quality content while penalizing degraded quality delivery.We construct a realistic synthetic dataset that captures both temporal variations and shifting content popularity to validate our model.Experimental results demonstrate that our proposed method improves utility by up to 135.9%and achieves an average improvement of 22.6%compared to traditional greedy algorithms and long short-term memory(LSTM)-based prediction models.Moreover,our method consistently performs well across a variety of utility functions,workload distributions,and storage limitations,underscoring its adaptability and robustness in dynamic video caching environments.
基金supported in part by the National Natural Science Foundation of China under Grant 61972424 and 62372479in part by the High Value Intellectual Property Cultivation Project of Hubei Province,China,under grant D2021002094+1 种基金in part by JSPS KAKENHI under Grants JP16K00117 and JP19K20250in part by the Leading Initiative for Excellent Young Researchers(LEADER),MEXT,Japan,and KDDI Foundation.
文摘Named data networking(NDNs)is an idealized deployment of information-centric networking(ICN)that has attracted attention from scientists and scholars worldwide.A distributed in-network caching scheme can efficiently realize load balancing.However,such a ubiquitous caching approach may cause problems including duplicate caching and low data diversity,thus reducing the caching efficiency of NDN routers.To mitigate these caching problems and improve the NDN caching efficiency,in this paper,a hierarchical-based sequential caching(HSC)scheme is proposed.In this scheme,the NDN routers in the data transmission path are divided into various levels and data with different request frequencies are cached in distinct router levels.The aim is to cache data with high request frequencies in the router that is closest to the content requester to increase the response probability of the nearby data,improve the data caching efficiency of named data networks,shorten the response time,and reduce cache redundancy.Simulation results show that this scheme can effectively improve the cache hit rate(CHR)and reduce the average request delay(ARD)and average route hop(ARH).
基金supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-DDRSP2504).
文摘Vehicular networks enable seamless connectivity for exchanging emergency and infotainment content.However,retrieving infotainment data from remote servers often introduces high delays,degrading the Quality of Service(QoS).To overcome this,caching frequently requested content at fog-enabled Road Side Units(RSUs)reduces communication latency.Yet,the limited caching capacity of RSUs makes it impractical to store all contents with varying sizes and popularity.This research proposes an efficient content caching algorithm that adapts to dynamic vehicular demands on highways to maximize request satisfaction.The scheme is evaluated against Intelligent Content Caching(ICC)and Random Caching(RC).The obtained results show that our proposed scheme entertains more contentrequesting vehicles as compared to ICC and RC,with 33%and 41%more downloaded data in 28%and 35%less amount of time from ICC and RC schemes,respectively.
基金supported by the National Natural Science Foundation of China under grants No.92267104 and 62372242。
文摘Increasing reliance on large-scale AI models has led to rising demand for intelligent services.The centralized cloud computing approach has limitations in terms of data transfer efficiency and response time,and as a result many service providers have begun to deploy edge servers to cache intelligent services in order to reduce transmission delay and communication energy consumption.However,finding the optimal service caching strategy remains a significant challenge due to the stochastic nature of service requests and the bulky nature of intelligent services.To deal with this,we propose a distributed service caching scheme integrating deep reinforcement learning(DRL)with mobility prediction,which we refer to as DSDM.Specifically,we employ the D3QN(Deep Double Dueling Q-Network)framework to integrate Long Short-Term Memory(LSTM)predicted mobile device locations into the service caching replacement algorithm and adopt the distributed multi-agent approach for learning and training.Experimental results demonstrate that DSDM achieves significant performance improvements in reducing communication energy consumption compared to traditional methods across various scenarios.
基金supported in part by the Shandong Provincial Natural Science Foundation under Grants ZR2023LZH017,ZR2022LZH015 and ZR2024MF066the National Natural Science Foundation of China under Grant 62471493+1 种基金the Tertiary Education Scientific research project of Guangzhou Municipal Education Bureau under Grant 2024312246the Guangzhou Higher Education Teaching Quality and Teaching Reform Project under Grant 2023KCJJD002。
文摘With the rapid development of generative artificial intelligence technology,the traditional cloud-based centralized model training and inference face significant limitations due to high transmission latency and costs,which restrict user-side in-situ Artificial Intelligence Generated Content(AIGC)service requests.To this end,we propose the Edge Artificial Intelligence Generated Content(Edge AIGC)framework,which can effectively address the challenges of cloud computing by implementing in-situ processing of services close to the data source through edge computing.However,AIGC models usually have a large parameter scale and complex computing requirements,which poses a huge challenge to the storage and computing resources of edge devices.This paper focuses on the edge intelligence model caching and resource allocation problems in the Edge AIGC framework,aiming to improve the cache hit rate and resource utilization of edge devices for models by optimizing the model caching strategy and resource allocation scheme,and realize in-situ AIGC service processing.With the optimization objectives of minimizing service request response time and execution cost in resource-constrained environments,we employ the Twin Delayed Deep Deterministic Policy Gradient algorithm for optimization.Experimental results show that,compared with other methods,our model caching and resource allocation strategies can effectively improve the cache hit rate by at least 41.06%and reduce the response cost as well.
基金supported by the National Natural Science Foundation of China(Nos.62201419,62372357)the Natural Science Foundation of Chongqing(CSTB2023NSCQ-LMX0032)the ISN State Key Laboratory.
文摘Existing wireless networks are flooded with video data transmissions,and the demand for high-speed and low-latency video services continues to surge.This has brought with it challenges to networks in the form of congestion as well as the need for more resources and more dedicated caching schemes.Recently,Multi-access Edge Computing(MEC)-enabled heterogeneous networks,which leverage edge caches for proximity delivery,have emerged as a promising solution to all of these problems.Designing an effective edge caching scheme is critical to its success,however,in the face of limited resources.We propose a novel Knowledge Graph(KG)-based Dueling Deep Q-Network(KG-DDQN)for cooperative caching in MEC-enabled heterogeneous networks.The KGDDQN scheme leverages a KG to uncover video relations,providing valuable insights into user preferences for the caching scheme.Specifically,the KG guides the selection of related videos as caching candidates(i.e.,actions in the DDQN),thus providing a rich reference for implementing a personalized caching scheme while also improving the decision efficiency of the DDQN.Extensive simulation results validate the convergence effectiveness of the KG-DDQN,and it also outperforms baselines regarding cache hit rate and service delay.
基金supported by the Liaoning Provincial Education Department Fund,grant number JYTZD2023083.
文摘In dynamic 5G network environments,user mobility and heterogeneous network topologies pose dual challenges to the effort of improving performance of mobile edge caching.Existing studies often overlook the dynamic nature of user locations and the potential of device-to-device(D2D)cooperative caching,limiting the reduction of transmission latency.To address this issue,this paper proposes a joint optimization scheme for edge caching that integrates user mobility prediction with deep reinforcement learning.First,a Transformer-based geolocation prediction model is designed,leveraging multi-head attention mechanisms to capture correlations in historical user trajectories for accurate future location prediction.Then,within a three-tier heterogeneous network,we formulate a latency minimization problem under a D2D cooperative caching architecture and develop a mobility-aware Deep Q-Network(DQN)caching strategy.This strategy takes predicted location information as state input and dynamically adjusts the content distribution across small base stations(SBSs)andmobile users(MUs)to reduce end-to-end delay inmulti-hop content retrieval.Simulation results show that the proposed DQN-based method outperforms other baseline strategies across variousmetrics,achieving a 17.2%reduction in transmission delay compared to DQNmethods withoutmobility integration,thus validating the effectiveness of the joint optimization of location prediction and caching decisions.
基金supported by the National Natural Science Foundation of China(No.52090041).
文摘The influence of different solution and aging conditions on the microstructure,impact toughness,and crack initiation and propagation mechanisms of the novel α+β titanium alloy Ti6422 was systematically investigated.By adjusting the furnace cooling time after solution treatment and the aging temperature,Ti6422 alloy samples were developed with a multi-level lamellar microstructure,in-cluding microscaleαcolonies and α_(p) lamellae,as well as nanoscale α_(s) phases.Extending the furnace cooling time after solution treatment at 920℃ for 1 h from 240 to 540 min,followed by aging at 600℃ for 6 h,increased the α_(p) lamella content,reduced the α_(s) phase content,expanded theαcolonies and α_(p) lamellae size,and improved the impact toughness from 22.7 to 53.8 J/cm^(2).Additionally,under the same solution treatment,raising the aging temperature from 500 to 700℃ resulted in a decrease in the α_(s) phase content and a growth in the thickness of the α_(p) lamella and α_(s) phase.The impact toughness increased significantly with these changes.Samples with high α_(p) lamellae content or large α_(s) phase size exhibited high crack initiation and propagation energies.Impact deformation caused severe kinking of the α_(p) lamellae in crack initiation and propagation areas,leading to a uniform and high-density kernel average misorientation(KAM)distribu-tion,enhancing plastic deformation coordination and uniformity.Moreover,the multidirectional arrangement of coarserαcolonies and α_(p) lamellae continuously deflect the crack propagation direction,inhibiting crack propagation.
