Based on the stress redistribution analysis of rock mass during the deep underground excavation, the unloading process of pre-flawed rock material was simulated by distinct element method (DEM). The effects of unloadi...Based on the stress redistribution analysis of rock mass during the deep underground excavation, the unloading process of pre-flawed rock material was simulated by distinct element method (DEM). The effects of unloading rate and flaw inclination angle on unloading strengths and cracking properties of pre-flawed rock specimens are numerically revealed. The results indicate that the unloading failure strength of pre-flawed specimen exhibits a power-function increase trend with the increase of unloading period. Moreover, combined with the stress state analysis on the flaws, it is found that the unloading failure strength increases with the increase of flaw inclination angle. The cracking distribution of pre-flawed specimens under the unloading condition closely depends on the flaw inclination angle, and three typical types of flaw coalescence are observed. Furthermore, at a faster unloading rate, the pre-flawed specimen experiences a sharper and quicker unloading failure process, resulting in more splitting cracks in the specimens.展开更多
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
基金Projects(41630642,11472311)supported by the National Natural Science Foundation of ChinaProject(2017zzts181)supported by the Cultivating Excellent Ph Ds of Central South University,ChinaProject(201806370062)supported by the China Scholarship Council
文摘Based on the stress redistribution analysis of rock mass during the deep underground excavation, the unloading process of pre-flawed rock material was simulated by distinct element method (DEM). The effects of unloading rate and flaw inclination angle on unloading strengths and cracking properties of pre-flawed rock specimens are numerically revealed. The results indicate that the unloading failure strength of pre-flawed specimen exhibits a power-function increase trend with the increase of unloading period. Moreover, combined with the stress state analysis on the flaws, it is found that the unloading failure strength increases with the increase of flaw inclination angle. The cracking distribution of pre-flawed specimens under the unloading condition closely depends on the flaw inclination angle, and three typical types of flaw coalescence are observed. Furthermore, at a faster unloading rate, the pre-flawed specimen experiences a sharper and quicker unloading failure process, resulting in more splitting cracks in the specimens.
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.
