The computation resources at a single node in Edge Computing(EC)are commonly limited,which cannot execute large scale computation tasks.To face the challenge,an Offloading scheme leveraging on NEighboring node Resourc...The computation resources at a single node in Edge Computing(EC)are commonly limited,which cannot execute large scale computation tasks.To face the challenge,an Offloading scheme leveraging on NEighboring node Resources(ONER)for EC over Fiber-Wireless(FiWi)access networks is proposed in this paper.In the ONER scheme,the FiWi network connects edge computing nodes with fiber and converges wireless and fiber connections seamlessly,so that it can support the offloading transmission with low delay and wide bandwidth.Based on the ONER scheme supported by FiWi networks,computation tasks can be offloaded to edge computing nodes in a wider range of area without increasing wireless hops(e.g.,just one wireless hop),which achieves low delay.Additionally,an efficient Computation Resource Scheduling(CRS)algorithm based on the ONER scheme is also proposed to make offloading decision.The results show that more offloading requests can be satisfied and the average completion time of computation tasks decreases significantly with the ONER scheme and the CRS algorithm.Therefore,the ONER scheme and the CRS algorithm can schedule computation resources at neighboring edge computing nodes for offloading to meet the challenge of large scale computation tasks.展开更多
In order to reduce cost and complexity,fiber-wireless(FiWi)networks emerge,combining the huge amount of available bandwidth of fiber networks and the flexibility,mobility of wireless networks.However,there is still a ...In order to reduce cost and complexity,fiber-wireless(FiWi)networks emerge,combining the huge amount of available bandwidth of fiber networks and the flexibility,mobility of wireless networks.However,there is still a long way to go before taking fiber and wireless systems as fully integrated networks.In this paper,we propose a network visualization based seamless networking scheme for FiWi networks,including hierarchical model,service model,service implementation and dynamic bandwidth assignment(DBA).Then,we evaluate the performance changes after network virtualization is introduced.Throughput for nodes,bandwidth for links and overheads leaded by network virtualization are analyzed.The performance of our proposed networking scheme is evaluated by simulation and real implementations,respectively.The results show that,compared to traditional networking scheme,our scheme has a better performance.展开更多
We propose an access network that integrates fiber and wireless for mobile fronthaul(MFH)with simple protection capabilities,using dualmode orbital angular momentum(OAM)multiplexing.We experimentally demonstrate a 3.3...We propose an access network that integrates fiber and wireless for mobile fronthaul(MFH)with simple protection capabilities,using dualmode orbital angular momentum(OAM)multiplexing.We experimentally demonstrate a 3.35 Gbit/s DMT-32QAM preequalized system with 10 km and 15 km fiber links in the 5.9 GHz band;then there is a link of two channels with a 0.5 m wireless link.展开更多
The terahertz photonics technique has bright application prospects in future sixth-generation(6G)broadband communication.In this study,we have experimentally demonstrated a photonics-assisted record-breaking net bit r...The terahertz photonics technique has bright application prospects in future sixth-generation(6G)broadband communication.In this study,we have experimentally demonstrated a photonics-assisted record-breaking net bit rate of 417 Gbit/s per wavelength signals delivery in a fiber-wireless converged communication system supported by advanced digital-signalprocessing(DSP)algorithms and a polarization multiplexing-based multiple-input multiple-output(MIMO)scheme.In the experiment,up to 60 GBaud(480 Gbit/s)polarization-division-multiplexing 16-ary quadrature-amplitude-modulation(PDM16QAM)signals are transmitted over 20 km fibers and 3 m wireless 2×2 MIMO links at 318 GHz with the bit error rate(BER)under 1.56×10^(−2).It is the first demonstration to our knowledge of signals delivery exceeding 400 Gbit/s per wavelength in a photonics-assisted fiber-wireless converged 2×2 MIMO communication system.展开更多
The digital twin(DT)is envisaged as a catalyst for pioneering ecosystems of service provision within an immersive environment born from the convergence of virtual and physical realms.Specifically,DT could enhance the ...The digital twin(DT)is envisaged as a catalyst for pioneering ecosystems of service provision within an immersive environment born from the convergence of virtual and physical realms.Specifically,DT could enhance the performance of edge-intelligent connected vehicular networks by allocating network resources efficiently based on the key performance indicators(KPIs)of vehicular data traffic.Consequently,this work addresses the key challenge of computation and spectrum resource allocation for vehicular networks.To allocate the optimal resource allocation,we subdivided the problem into:traffic classification,collective learning,and resource allocation scheme.In order to do so,this paper concentrates on two crucial vehicular applications:brake application and lane-change application.We utilize a random forest model to collectively learn vehicular data traffic in the upcoming time slot.Thereafter,a time-ahead resource allocation algorithm is proposed to improve the quality of service(QoS)by intelligently offloading vehicular data traffic to a DT-based integrated fiber-wireless(Fi-Wi)connected vehicular network.We evaluate the performance of the resource allocation strategy in terms of resources required by the network alongside the packet loss rate.It was observed that there was a 44.74%increase in cost as the total computation resources increased from F=50 to 100 GHz,whereas the PLR of the network decreased by 71.43%.展开更多
基金supported by National Natural Science Foundation of China(Grant No.61471053,61901052)Fundamental Research Funds for the Central Universities(Grant 2018RC03)Beijing Laboratory of Advanced Information Networks
文摘The computation resources at a single node in Edge Computing(EC)are commonly limited,which cannot execute large scale computation tasks.To face the challenge,an Offloading scheme leveraging on NEighboring node Resources(ONER)for EC over Fiber-Wireless(FiWi)access networks is proposed in this paper.In the ONER scheme,the FiWi network connects edge computing nodes with fiber and converges wireless and fiber connections seamlessly,so that it can support the offloading transmission with low delay and wide bandwidth.Based on the ONER scheme supported by FiWi networks,computation tasks can be offloaded to edge computing nodes in a wider range of area without increasing wireless hops(e.g.,just one wireless hop),which achieves low delay.Additionally,an efficient Computation Resource Scheduling(CRS)algorithm based on the ONER scheme is also proposed to make offloading decision.The results show that more offloading requests can be satisfied and the average completion time of computation tasks decreases significantly with the ONER scheme and the CRS algorithm.Therefore,the ONER scheme and the CRS algorithm can schedule computation resources at neighboring edge computing nodes for offloading to meet the challenge of large scale computation tasks.
基金supported by National Natural Science Foundation of China under Grant No.61240040
文摘In order to reduce cost and complexity,fiber-wireless(FiWi)networks emerge,combining the huge amount of available bandwidth of fiber networks and the flexibility,mobility of wireless networks.However,there is still a long way to go before taking fiber and wireless systems as fully integrated networks.In this paper,we propose a network visualization based seamless networking scheme for FiWi networks,including hierarchical model,service model,service implementation and dynamic bandwidth assignment(DBA).Then,we evaluate the performance changes after network virtualization is introduced.Throughput for nodes,bandwidth for links and overheads leaded by network virtualization are analyzed.The performance of our proposed networking scheme is evaluated by simulation and real implementations,respectively.The results show that,compared to traditional networking scheme,our scheme has a better performance.
基金supported by ZTE Industry-Academia-Research Cooperation Funds under Grant No.2016ZTE04-01.
文摘We propose an access network that integrates fiber and wireless for mobile fronthaul(MFH)with simple protection capabilities,using dualmode orbital angular momentum(OAM)multiplexing.We experimentally demonstrate a 3.35 Gbit/s DMT-32QAM preequalized system with 10 km and 15 km fiber links in the 5.9 GHz band;then there is a link of two channels with a 0.5 m wireless link.
基金partially supported by the National Natural Science Foundation of China(Nos.61935005,61835002,and62127802)。
文摘The terahertz photonics technique has bright application prospects in future sixth-generation(6G)broadband communication.In this study,we have experimentally demonstrated a photonics-assisted record-breaking net bit rate of 417 Gbit/s per wavelength signals delivery in a fiber-wireless converged communication system supported by advanced digital-signalprocessing(DSP)algorithms and a polarization multiplexing-based multiple-input multiple-output(MIMO)scheme.In the experiment,up to 60 GBaud(480 Gbit/s)polarization-division-multiplexing 16-ary quadrature-amplitude-modulation(PDM16QAM)signals are transmitted over 20 km fibers and 3 m wireless 2×2 MIMO links at 318 GHz with the bit error rate(BER)under 1.56×10^(−2).It is the first demonstration to our knowledge of signals delivery exceeding 400 Gbit/s per wavelength in a photonics-assisted fiber-wireless converged 2×2 MIMO communication system.
文摘The digital twin(DT)is envisaged as a catalyst for pioneering ecosystems of service provision within an immersive environment born from the convergence of virtual and physical realms.Specifically,DT could enhance the performance of edge-intelligent connected vehicular networks by allocating network resources efficiently based on the key performance indicators(KPIs)of vehicular data traffic.Consequently,this work addresses the key challenge of computation and spectrum resource allocation for vehicular networks.To allocate the optimal resource allocation,we subdivided the problem into:traffic classification,collective learning,and resource allocation scheme.In order to do so,this paper concentrates on two crucial vehicular applications:brake application and lane-change application.We utilize a random forest model to collectively learn vehicular data traffic in the upcoming time slot.Thereafter,a time-ahead resource allocation algorithm is proposed to improve the quality of service(QoS)by intelligently offloading vehicular data traffic to a DT-based integrated fiber-wireless(Fi-Wi)connected vehicular network.We evaluate the performance of the resource allocation strategy in terms of resources required by the network alongside the packet loss rate.It was observed that there was a 44.74%increase in cost as the total computation resources increased from F=50 to 100 GHz,whereas the PLR of the network decreased by 71.43%.
