To improve the quality of computation experience for mobile devices,mobile edge computing(MEC)is a promising paradigm by providing computing capabilities in close proximity within a sliced radio access network,which s...To improve the quality of computation experience for mobile devices,mobile edge computing(MEC)is a promising paradigm by providing computing capabilities in close proximity within a sliced radio access network,which supports both traditional communication and MEC services.However,this kind of intensive computing problem is a high dimensional NP hard problem,and some machine learning methods do not have a good effect on solving this problem.In this paper,the Markov decision process model is established to find the excellent task offloading scheme,which maximizes the long-term utility performance,so as to make the best offloading decision according to the queue state,energy queue state and channel quality between mobile users and BS.In order to explore the curse of high dimension in state space,a candidate network is proposed based on edge computing optimize offloading(ECOO)algorithm with the application of deep deterministic policy gradient algorithm.Through simulation experiments,it is proved that the ECOO algorithm is superior to some deep reinforcement learning algorithms in terms of energy consumption and time delay.So the ECOO is good at dealing with high dimensional problems.展开更多
The cohesion weakening and friction strengthening(CWFS)model for rock reveals the strength components mobilization process during progressive brittle failure process of rock,which is very helpful in understanding mech...The cohesion weakening and friction strengthening(CWFS)model for rock reveals the strength components mobilization process during progressive brittle failure process of rock,which is very helpful in understanding mechanical properties of rock.However,the used incremental cyclic loading−unloading compression test for the determination of strength components is very complicated,which limits the application of CWFS model.In this paper,incremental cyclic loading−unloading compression test was firstly carried out to study the evolution of deformation and the strength properties of Beishan granite after various temperatures treated under different confining pressures.We found the axial and lateral unloading modulus are closely related to the applied stress and damage state of rock.Based on these findings,we can accurately determine the plastic strain during the entire failure process using conventional tri-axial compression test data.Furthermore,a strength component(cohesive and frictional strength)determination method was developed using conventional triaxial compression test.Using this method,we analyzed the variation of strength mobilization and deformation properties of Beishan granite after various temperatures treated.At last,a non-simultaneous strength mobilization model for thermally treated granite was obtained and verified by numerical simulation,which demonstrated the effectiveness of the proposed strength determination method.展开更多
With the growth of maritime activities,the number of computationally complex applications is growing exponentially.Mobile edge computing(MEC)is widely recognized as a viable option to address the substantial need for ...With the growth of maritime activities,the number of computationally complex applications is growing exponentially.Mobile edge computing(MEC)is widely recognized as a viable option to address the substantial need for wireless communications and compute-intensive operations in maritime environments.To reduce the processing load and meet the demands of mobile terminals for high bandwidth,low latency and multiple access,MEC systems with unmanned aerial vehicles(UAVs)have been proposed and extensively explored.In this paper,a maritime MEC network that employs a top-UAV(T-UAV)for task offloading supported by digital twin(DT)is considered.To explore the task offloading strategy employed by the edge server,the flight trajectory and resource allocation strategy of the T-UAV is studied in detail.The objective of this study is to minimize latency costs while ensuring that the energy of the T-UAV is sufficient to fulfill services.In order to accomplish this objective,the joint optimization problem is described as a Markov decision process(MDP).To overcome this problem,the priority-based reinforcement learning(RL)algorithm for computation offloading and trajectory planning(PRL-COTP)is developed.The simulation results demonstrate that the proposed approach can significantlyreduce the overall cost of the system in comparison to other benchmarks.展开更多
基金National Natural Science Foundation of China(No.11461038)Science and Technology Support Program of Gansu Province(No.144NKCA040)。
文摘To improve the quality of computation experience for mobile devices,mobile edge computing(MEC)is a promising paradigm by providing computing capabilities in close proximity within a sliced radio access network,which supports both traditional communication and MEC services.However,this kind of intensive computing problem is a high dimensional NP hard problem,and some machine learning methods do not have a good effect on solving this problem.In this paper,the Markov decision process model is established to find the excellent task offloading scheme,which maximizes the long-term utility performance,so as to make the best offloading decision according to the queue state,energy queue state and channel quality between mobile users and BS.In order to explore the curse of high dimension in state space,a candidate network is proposed based on edge computing optimize offloading(ECOO)algorithm with the application of deep deterministic policy gradient algorithm.Through simulation experiments,it is proved that the ECOO algorithm is superior to some deep reinforcement learning algorithms in terms of energy consumption and time delay.So the ECOO is good at dealing with high dimensional problems.
基金Project(41902301)supported by the National Natural Science Foundation of ChinaProject(20201Y185)supported by the Science and Technology Foundation of Guizhou Province,China+2 种基金Project(Z018023)supported by the Open Research Fund of State Key Laboratory of Geomechanics and Geotechnical Engineering,IRSM,CASProject(201822)supported by the Foundation for Young Talents of Guizhou University,ChinaProject(2017-5402)supported by the Mountain Geohazard Prevention R&D Center of Guizhou Province,China。
文摘The cohesion weakening and friction strengthening(CWFS)model for rock reveals the strength components mobilization process during progressive brittle failure process of rock,which is very helpful in understanding mechanical properties of rock.However,the used incremental cyclic loading−unloading compression test for the determination of strength components is very complicated,which limits the application of CWFS model.In this paper,incremental cyclic loading−unloading compression test was firstly carried out to study the evolution of deformation and the strength properties of Beishan granite after various temperatures treated under different confining pressures.We found the axial and lateral unloading modulus are closely related to the applied stress and damage state of rock.Based on these findings,we can accurately determine the plastic strain during the entire failure process using conventional tri-axial compression test data.Furthermore,a strength component(cohesive and frictional strength)determination method was developed using conventional triaxial compression test.Using this method,we analyzed the variation of strength mobilization and deformation properties of Beishan granite after various temperatures treated.At last,a non-simultaneous strength mobilization model for thermally treated granite was obtained and verified by numerical simulation,which demonstrated the effectiveness of the proposed strength determination method.
基金Foundation items:National Natural Science Foundation of China(Nos.62301307 and 62072096)Shanghai Pujiang Program,China(No.23PJD041)Chenguang Program of Shanghai Education Development Foundation and Shanghai Municipal Education Commission,China(No.CGA60)。
文摘With the growth of maritime activities,the number of computationally complex applications is growing exponentially.Mobile edge computing(MEC)is widely recognized as a viable option to address the substantial need for wireless communications and compute-intensive operations in maritime environments.To reduce the processing load and meet the demands of mobile terminals for high bandwidth,low latency and multiple access,MEC systems with unmanned aerial vehicles(UAVs)have been proposed and extensively explored.In this paper,a maritime MEC network that employs a top-UAV(T-UAV)for task offloading supported by digital twin(DT)is considered.To explore the task offloading strategy employed by the edge server,the flight trajectory and resource allocation strategy of the T-UAV is studied in detail.The objective of this study is to minimize latency costs while ensuring that the energy of the T-UAV is sufficient to fulfill services.In order to accomplish this objective,the joint optimization problem is described as a Markov decision process(MDP).To overcome this problem,the priority-based reinforcement learning(RL)algorithm for computation offloading and trajectory planning(PRL-COTP)is developed.The simulation results demonstrate that the proposed approach can significantlyreduce the overall cost of the system in comparison to other benchmarks.
