To aware the topology of wireless sensor networks (WSN) with time-variety, and load-balance the resource of communication and energy, an opportunistic routing protocol for WSN based on Opportunistic Routing Entropy an...To aware the topology of wireless sensor networks (WSN) with time-variety, and load-balance the resource of communication and energy, an opportunistic routing protocol for WSN based on Opportunistic Routing Entropy and ant colony optimization, called ACO-TDOP, is proposed. At first, based on the second law of thermo-dynamics, we introduce the concept of Opportunistic Routing Entropy which is a parameter representing the transmission state of each node by taking into account the power left and the distance to the sink node. Then, it is proved that the problem of route thinking about Opportunistic Routing Entropy is shown to be NP-hard. So the protocol, ACO-TDOP, is proposed. At last, numerical results confirm that the ACO-TDOP is energy conservative and throughput gainful compared with other two existing routing protocols, and show that it is efficacious to analyze and uncover fundamental of message transmission with Opportunistic Routing in wireless network using the second law of thermodynamics.展开更多
To monitor the physical world, Equi-Frequency Sampling (EFS) methods are widely applied for data acquisition in sensor networks.Due to the noise and inherent uncertainty of the environment,EFS based data acquisition m...To monitor the physical world, Equi-Frequency Sampling (EFS) methods are widely applied for data acquisition in sensor networks.Due to the noise and inherent uncertainty of the environment,EFS based data acquisition may result in misconception to the physical world, and high frequency scheme produces massive sensed data, which consumes substantial cost for transmission. This paper proposes a novel sensed data model. Based on maximum likelihood estimation, the model can minimize measurement error. It is proved that the proposed model is asymptotic unbiased. Furthermore, this paper proposes Model based Adaptive Data Collection (MADC) Algorithm and designs a distributed lightweight computation algorithm named Distributed Adaptive Data Collection Algorithm (DADC). Based on the error of prediction, both algorithms can adaptively adjust the cycle of data collection. Performance evaluation verifies that the proposed algorithms have high performance in terms of accuracy and effectiveness.展开更多
Generative adversarial imitation learning(GAIL)directly imitates the behavior of experts from human demonstration instead of designing explicit reward signals like reinforcement learning.Meanwhile,GAIL overcomes the d...Generative adversarial imitation learning(GAIL)directly imitates the behavior of experts from human demonstration instead of designing explicit reward signals like reinforcement learning.Meanwhile,GAIL overcomes the defects of traditional imitation learning by using a generative adversary network framework and shows excellent performance in many fields.However,GAIL directly acts on immediate rewards,a feature that is reflected in the value function after a period of accumulation.Thus,when faced with complex practical problems,the learning efficiency of GAIL is often extremely low and the policy may be slow to learn.One way to solve this problem is to directly guide the action(policy)in the agents'learning process,such as the control sharing(CS)method.This paper combines reinforcement learning and imitation learning and proposes a novel GAIL framework called generative adversarial imitation learning based on control sharing policy(GACS).GACS learns model constraints from expert samples and uses adversarial networks to guide learning directly.The actions are produced by adversarial networks and are used to optimize the policy and effectively improve learning efficiency.Experiments in the autonomous driving environment and the real-time strategy game breakout show that GACS has better generalization capabilities,more efficient imitation of the behavior of experts,and can learn better policies relative to other frameworks.展开更多
Mobile-edge computing casts the computation-intensive and delay-sensitive applications of mobile devices onto network edges.Task offloading incurs extra communication latency and energy cost,and extensive efforts have...Mobile-edge computing casts the computation-intensive and delay-sensitive applications of mobile devices onto network edges.Task offloading incurs extra communication latency and energy cost,and extensive efforts have focused on offloading schemes.Many metrics of the system utility are defined to achieve satisfactory quality of experience.However,most existing works overlook the balance between throughput and fairness.This study investigates the problem of finding an optimal offloading scheme in which the objective of optimization aims to maximize the system utility for leveraging between throughput and fairness.Based on Karush-Kuhn-Tucker condition,the expectation of time complexity is analyzed to derive the optimal scheme.A gradient-based approach for utility-aware task offloading is given.Furthermore,we provide an increment-based greedy approximation algorithm with 1+1/(e-1)ratio.Experimental results show that the proposed algorithms can achieve effective performance in utility and accuracy.展开更多
文摘To aware the topology of wireless sensor networks (WSN) with time-variety, and load-balance the resource of communication and energy, an opportunistic routing protocol for WSN based on Opportunistic Routing Entropy and ant colony optimization, called ACO-TDOP, is proposed. At first, based on the second law of thermo-dynamics, we introduce the concept of Opportunistic Routing Entropy which is a parameter representing the transmission state of each node by taking into account the power left and the distance to the sink node. Then, it is proved that the problem of route thinking about Opportunistic Routing Entropy is shown to be NP-hard. So the protocol, ACO-TDOP, is proposed. At last, numerical results confirm that the ACO-TDOP is energy conservative and throughput gainful compared with other two existing routing protocols, and show that it is efficacious to analyze and uncover fundamental of message transmission with Opportunistic Routing in wireless network using the second law of thermodynamics.
文摘To monitor the physical world, Equi-Frequency Sampling (EFS) methods are widely applied for data acquisition in sensor networks.Due to the noise and inherent uncertainty of the environment,EFS based data acquisition may result in misconception to the physical world, and high frequency scheme produces massive sensed data, which consumes substantial cost for transmission. This paper proposes a novel sensed data model. Based on maximum likelihood estimation, the model can minimize measurement error. It is proved that the proposed model is asymptotic unbiased. Furthermore, this paper proposes Model based Adaptive Data Collection (MADC) Algorithm and designs a distributed lightweight computation algorithm named Distributed Adaptive Data Collection Algorithm (DADC). Based on the error of prediction, both algorithms can adaptively adjust the cycle of data collection. Performance evaluation verifies that the proposed algorithms have high performance in terms of accuracy and effectiveness.
基金Supported in Part by the National Natural Science Foundation of China (U1808206)。
文摘Generative adversarial imitation learning(GAIL)directly imitates the behavior of experts from human demonstration instead of designing explicit reward signals like reinforcement learning.Meanwhile,GAIL overcomes the defects of traditional imitation learning by using a generative adversary network framework and shows excellent performance in many fields.However,GAIL directly acts on immediate rewards,a feature that is reflected in the value function after a period of accumulation.Thus,when faced with complex practical problems,the learning efficiency of GAIL is often extremely low and the policy may be slow to learn.One way to solve this problem is to directly guide the action(policy)in the agents'learning process,such as the control sharing(CS)method.This paper combines reinforcement learning and imitation learning and proposes a novel GAIL framework called generative adversarial imitation learning based on control sharing policy(GACS).GACS learns model constraints from expert samples and uses adversarial networks to guide learning directly.The actions are produced by adversarial networks and are used to optimize the policy and effectively improve learning efficiency.Experiments in the autonomous driving environment and the real-time strategy game breakout show that GACS has better generalization capabilities,more efficient imitation of the behavior of experts,and can learn better policies relative to other frameworks.
基金supported in part by the National Natural Science Foundation of China(Nos.61602084,61761136019,U1808206,61772112,and 61972083)the Post-Doctoral Science Foundation of China(No.2016M600202)+1 种基金the Doctoral Scientific Research Foundation of Liaoning Province(No.201601041)the Fundamental Research Fund for the Central Universities(No.DUT19JC53)。
文摘Mobile-edge computing casts the computation-intensive and delay-sensitive applications of mobile devices onto network edges.Task offloading incurs extra communication latency and energy cost,and extensive efforts have focused on offloading schemes.Many metrics of the system utility are defined to achieve satisfactory quality of experience.However,most existing works overlook the balance between throughput and fairness.This study investigates the problem of finding an optimal offloading scheme in which the objective of optimization aims to maximize the system utility for leveraging between throughput and fairness.Based on Karush-Kuhn-Tucker condition,the expectation of time complexity is analyzed to derive the optimal scheme.A gradient-based approach for utility-aware task offloading is given.Furthermore,we provide an increment-based greedy approximation algorithm with 1+1/(e-1)ratio.Experimental results show that the proposed algorithms can achieve effective performance in utility and accuracy.