检索结果-内蒙古大学图书馆

Distributed resource scheduling for large-scale MEC systems: A multi-agent ensemble deep reinforcement learning with imitation acceleration

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Jiang, Feibo Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China Key Laboratory of Hunan Province for New Retail Virtual Reality Technology Hunan University of Commerce Changsha China Department of Computer and Information Sciences Northumbria University United Kingdom School of Computer Sciences and Electrical Engineering University of Essex ColchesterCO4 3SQ United Kingdom School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom

We consider the optimization of distributed resource scheduling to minimize the sum of task latency and energy consumption for all the Internet of things devices (IoTDs) in a large-scale mobile edge computing (MEC) system. To address this problem, we propose a distributed intelligent resource scheduling (DIRS) framework, which includes centralized training relying on the global information and distributed decision making by each agent deployed in each MEC server. More specifically, we first introduce a novel multi-agent ensemble-assisted distributed deep reinforcement learning (DRL) architecture, which can simplify the overall neural network structure of each agent by partitioning the state space and also improve the performance of a single agent by combining decisions of all the agents. Secondly, we apply action refinement to enhance the exploration ability of the proposed DIRS framework, where the near-optimal state-action pairs are obtained by a novel Lvy flight search. Finally, an imitation acceleration scheme is presented to pre-train all the agents, which can significantly accelerate the learning process of the proposed framework through learning the professional experience from a small amount of demonstration data. Extensive simulations are conducted to demonstrate that the proposed DIRS framework is efficient and outperforms the existing benchmark schemes. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

Stacking-Based Attention Temporal Convolutional network for Action Segmentation

学校读者我要写书评

暂无评论

Stacking-Based Attention Temporal Convolutional Network for ...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Liu Yang Yu Jiang Junkun Hong Zhenjie Wu Zhan Yang Jun Long School of Computer Science and Engineering Central South University China Big Data Institute Central South University Central South University China Network Resources Management and Trust Evaluation Key Laboratory of Hunan Province Central South University Changsha China

Action segmentation plays an important role in video understanding, which is implemented by frame-wise action classification. Recent works on action segmentation capture long-term dependencies by increasing temporal convolution layers in Temporal Convolution networks (TCNs). However, high layers in TCNs are more coarse access to video features, resulting in the loss of fine-grained information for frame-wise action classification. To address the above issues, we propose a novel Attention-based Temporal Convolution (ATC) block to capture fine-grained information of temporal dependencies for frame-wise action classification by self-attention mechanism. Via stacking ATC blocks, we design a Stacking-based Attention Temporal Convolutional network (SATC) to adaptively capture long-term and short-term dependencies, according to the semantic similarity of features on different temporal receptive fields simultaneously. The experimental results demonstrate that our SATC outperforms other baselines on all three challenging datasets: GTEA, 50Salads and Breakfast.

关键词： Convolution Stacking Semantics Acoustics Convolutional neural networks Speech processing

Multimode optomechanical cooling via general dark-mode control

学校读者我要写书评

暂无评论

Physical Review A 2022年第1期106卷 013526-013526页

作者： Jian Huang Deng-Gao Lai Cheng Liu Jin-Feng Huang Franco Nori Jie-Qiao Liao Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education Key Laboratory for Matter Microstructure and Function of Hunan Province Department of Physics and Synergetic Innovation Center for Quantum Effects and Applications Hunan Normal University Changsha 410081 China Theoretical Quantum Physics Laboratory RIKEN Cluster for Pioneering Research Wako-shi Saitama 351-0198 Japan RIKEN Center for Quantum Computing 2-1 Hirosawa Wako-shi Saitama 351-0198 Japan Physics Department University of Michigan Ann Arbor Michigan 48109-1040 USA

The dark-mode effect is a stubborn obstacle for ground-state cooling of multiple degenerate mechanical modes optomechanically coupled to a common cavity-field mode. Here we propose an auxiliary-cavity-mode method for simultaneous ground-state cooling of two degenerate or near-degenerate mechanical modes by breaking the dark mode. We find that the introduction of the auxiliary cavity mode not only breaks the dark-mode effect, but also provides a new cooling channel to extract the thermal excitations stored in the dark mode. Moreover, we study the general physical-coupling configurations for breaking the dark mode in a generalized network-coupled four-mode optomechanical system consisting of two cavity modes and two mechanical modes. We find the analytical dark-mode-breaking condition in this system. This method is general and it can be generalized to break the dark-mode effect and to realize the simultaneous ground-state cooling in a multiple-mechanical-mode optomechanical system. We also demonstrate the physical mechanism behind the dark-mode breaking by studying the breaking of dark-state effect in the N−type four-level atomic system. Our results not only provide a general method to control various dark-mode and dark-state effects in physics, but also present an opportunity to the study of macroscopic quantum phenomena and applications in multiple-mechanical-resonator systems.

关键词： Optomechanics Quantum optics

Stacked auto encoder based Deep Reinforcement Learning for online resource scheduling in large-scale MEC networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Jiang, Feibo Wang, Kezhi Dong, Li Pan, Cunhua Yang, Kun Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China Department of Computer and Information Sciences Northumbria University United Kingdom Key Laboratory of Hunan Province for New Retail Virtual Reality Technology Hunan University of Commerce Changsha China School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom School of Computer Sciences and Electrical Engineering University of Essex ColchesterCO4 3SQ United Kingdom University of Electronic Science and Technology of China Chengdu China

An online resource scheduling framework is proposed for minimizing the sum of weighted task latency for all the mobile users, by optimizing offloading decision, transmission power, and resource allocation in the mobile edge computing (MEC) system. Towards this end, a deep reinforcement learning (DRL) method is proposed to obtain an online resource scheduling policy. Firstly, a related and regularized stacked auto encoder (2r-SAE) with unsupervised learning is proposed to perform data compression and representation for high dimensional channel quality information (CQI) data, which can reduce the state space for DRL. Secondly, we present an adaptive simulated annealing based approach (ASA) as the action search method of DRL, in which an adaptive h-mutation is used to guide the search direction and an adaptive iteration is proposed to enhance the search efficiency during the DRL process. Thirdly, a preserved and prioritized experience replay (2p-ER) is introduced to assist the DRL to train the policy network and find the optimal offloading policy. Numerical results are provided to demonstrate that the proposed algorithm can achieve near-optimal performance while significantly decreasing the computational time compared with existing benchmarks. It also shows that the proposed framework is suitable for resource scheduling problem in large-scale MEC networks, especially in the dynamic environment. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

A Reinforcement Learning-Based Virtual Machine Placement Strategy in Cloud Data Centers

学校读者我要写书评

暂无评论

A Reinforcement Learning-Based Virtual Machine Placement Str...

IEEE International Conference on High Performance computing and Communications (HPCC)

作者： Saiqin Long Zhetao Li Yun Xing Shujuan Tian Dongsheng Li Rong Yu Key Laboratory of Hunan Province for Internet of Things and Information Security Hunan International Scientific and Technological Cooperation Base of Intelligent network School of Computer Science Xiangtan University Xiangtan China School of Computer Science Xiangtan University Xiangtan China College of Computer National University of Defense Technology Changsha China School of Automation Guangdong University of Technology Guangzhou China

ISBN: (纸本)9781728176505

With the widespread use of cloud computing, energy consumption of cloud data centers is increasing which mainly comes from IT equipment and cooling equipment. This paper argues that once the number of virtual machines on the physical machines reaches a certain level, resource competition occurs, resulting in a performance loss of the virtual machines. Unlike most papers, we do not impose placement constraints on virtual machines by giving a CPU cap to achieve the purpose of energy savings in cloud data centers. Instead, we use the measure of performance loss to weigh. We propose a reinforcement learning-based virtual machine placement strategy(RLVMP) for energy savings in cloud data centers. The strategy considers the weight of virtual machine performance loss and energy consumption, which is finally solved with the greedy strategy. Simulation experiments show that our strategy has a certain improvement in energy savings compared with the other algorithms.

关键词： Weight measurement Cloud computing Data centers Energy consumption NP-hard problem High performance computing Virtual machining

Ai driven heterogeneous MEC system for dynamic environment - Challenges and solutions

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Jiang, Feibo Wang, Kezhi Dong, Li Pan, Cunhua Xu, Wei Yang, Kun Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China department of Computer and Information Sciences Northumbria University United Kingdom Key Laboratory of Hunan Province for New Retail Virtual Reality Technology Hunan University of Commerce Changsha China School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom NCRL Southeast University Nanjing China School of Computer Sciences and Electrical Engineering University of Essex ColchesterCO4 3SQ United Kingdom University of Electronic Science and Technology of China Chengdu China

—By taking full advantage of computing, Communication and Caching (3C) resources at the network edge, Mobile Edge computing (MEC) is envisioned as one of the key enablers for the next generation network and services. However, current fixed-location MEC architecture may not be able to make real-time decision in dynamic environment, especially in large-scale scenarios. To address this issue, in this paper, a Heterogeneous MEC (H-MEC) architecture is proposed, which is composed of fixed unit, i.e., Ground Stations (GSs) as well as moving nodes, i.e., Ground Vehicles (GVs) and Unmanned Aerial Vehicles (UAVs), all with 3C resource enabled. The key challenges in H-MEC, e.g., mobile edge node management, real-time decision making, user association and resource allocation along with the possible Artificial Intelligence (AI)-based solutions are discussed in this paper. In addition, an AI-based joint Resource schEduling (ARE) framework is proposed, with simulation results shown to verify the efficiency of our proposed framework. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

学校读者我要写书评

暂无评论

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Saiqin Long Zhetao Li Zihao Liu Qingyong Deng Sangyoon Oh Nobuyoshi Komuro Key Laboratory of Hunan Province for Internet of Things and Information Security Hunan International Scientific and Technological Cooperation Base of Intelligent network School of Computer Science Xiangtan University Xiangtan China Science and Technology on Parallel and Distributed Processing Laboratory (PDL) National University of Defense Technology Changsha China Ajou University Suwon South Korea Graduate School of Advanced Integration Science Chiba University Chiba Japan

ISBN: (数字)9781728190747

ISBN: (纸本)9781728183824

Deduplication is a data redundancy elimination technique, designed to save system storage resources by reducing redundant data in cloud storage systems. With the development of cloud computing technology, deduplication has been increasingly applied to cloud data centers. However, traditional technologies face great challenges in big data deduplication to properly weigh the two conflicting goals of deduplication throughput and high duplicate elimination ratio. This paper proposes a similarity clustering-based deduplication strategy (named SCDS), which aims to delete more duplicate data without significantly increasing system overhead. The main idea of SCDS is to narrow the query range of fingerprint index by data partitioning and similarity clustering algorithms. In the data preprocessing stage, SCDS uses data partitioning algorithm to classify similar data together. In the data deletion stage, the similarity clustering algorithm is used to divide the similar data fingerprint superblock into the same cluster. Repetitive fingerprints are detected in the same cluster to speed up the retrieval of duplicate fingerprints. Experiments show that the deduplication ratio of SCDS is better than some existing similarity deduplication algorithms, but the overhead is only slightly higher than some high throughput but low deduplication ratio methods.

关键词： Cloud computing Clustering algorithms Estimation Fingerprint recognition Throughput Partitioning algorithms Classification algorithms

Deep learning based joint resource scheduling algorithms for hybrid MEC networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Jiang, Feibo Wang, Kezhi Dong, Li Pan, Cunhua Xu, Wei Yang, Kun Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China Department of Computer and Information Sciences Northumbria University United Kingdom Key Laboratory of Hunan Province for New Retail Virtual Reality Technology Hunan University of Technology and Business Changsha China School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom NCRL Southeast University Nanjing China School of Computer Technology and Engineering Changchun Institute of Technology Changchun China School of Computer Sciences and Electrical Engineering University of Essex ColchesterCO4 3SQ United Kingdom

In this paper, we consider a hybrid mobile edge computing (H-MEC) platform, which includes ground stations (GSs), ground vehicles (GVs) and unmanned aerial vehicle (UAVs), all with mobile edge cloud installed to enable user equipments (UEs) or Internet of thing (IoT) devices with intensive computing tasks to offload. Our objective is to obtain an online offloading algorithm to minimize the energy consumption of all the UEs, by jointly optimizing the positions of GVs and UAVs, user association and resource allocation in real-time, while considering the dynamic environment. To this end, we propose a hybrid deep learning based online offloading (H2O) framework where a large-scale path-loss fuzzy c-means (LSFCM) algorithm is first proposed and used to predict the optimal positions of GVs and UAVs. Secondly, a fuzzy membership matrix U-based particle swarm optimization (U-PSO) algorithm is applied to solve the mixed integer nonlinear programming (MINLP) problems and generate the sample datasets for the deep neural network (DNN) where the fuzzy membership matrix can capture the small-scale fading effects and the information of mutual interference. Thirdly, a DNN with the scheduling layer is introduced to provide user association and computing resource allocation under the practical latency requirement of the tasks and limited available computing resource of H-MEC. In addition, different from traditional DNN predictor, we only input one UEs information to the DNN at one time, which will be suitable for the scenarios where the number of UE is varying and avoid the curse of dimensionality in DNN. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

A Novel Lncrna, Lncery, Interacts with Wdr82 to Regulate Erythroid Differentiation By Promoting Globin Gene Transcription

学校读者我要写书评

暂无评论

BLOOD 2020年 136卷 2-2页

作者： Yang, Shangda Sun, Guohuan Wu, Peng Kuang, Yijin Chen, Cong Zheng, Zhaofeng Gu, Quan Zhu, Caiying Gou, Fanglin Yang, Zining Zhao, Xiangnan Yang, Liu Lu, Shihong Lihong, Shi Lv, Xue Dong, Fang Shi, Lihong Ng, Lai Guang Liu, Jing Cheng, Hui Cheng, Tao Institute of Hematology & Blood Diseases Hospital State Key Laboratory of Experimental Hematology National Clinical Research Center for Blood Diseases Institute of Hematology & Blood Diseases Hospital Chinese Academy of Medical Science & Peking Union Medical College Tianjin China State Key Laboratory of Experimental Hematology National Clinical Research Center for Blood Diseases Institute of Hematology & Blood Diseases Hospital Chinese Academy of Medical Sciences & Peking Union Medical College Tianjin China University of Pittsburgh School of Medicine Tianjin China Molecular Biology Research Center Center for Medical Genetics Hunan Province Key Laboratory of Basic and Applied Hematology School of Life Sciences Central South University Changsha China State Key Laboratory of Experimental Hematology Tianjin China State Key Laboratory of Experimental Hematology National Clinical Research Center for Blood Diseases Institute of Hematology & Blood Diseases Hospital Chinese Academy of Medical Science & Peking Union Medical College Tianjin China State Key Laboratory of Hematology Institute of Hematology & Blood Diseases Hospital Tianjin China Institute of Hematology & Blood Diseases Hospital Chinese Academy of Medical Sciences & Peking Union Medical College Tianjin China Singapore Immunology Network Agency for Science Technology and Research Biopolis Singapore Department of Hematology Third Xiangya Hospital of Central South University Changsha China

Hematopoietic differentiation is controlled by both genetic and epigenetic regulators. Long non-coding RNAs (lncRNAs) have been demonstrated to be important for normal hematopoiesis, but their function in erythropoiesis needs to be further explored. Here, we profiled the transcriptome of 17 murine hematopoietic cell populations by deep sequencing and identified a novel lncRNA, that was highly expressed in erythroid-related progenitors and erythrocytes. For this reason, we named it lncEry. We also identified a novel lncEry isoform, which was the principal transcript and has not been reported before. Furthermore, we found that nearly 90% of lncEry molecules localized to the nucleus. Next, we performed knockdown and knockout assays to study the function of lncEry, and found that lncEry depletion impaired erythroid differentiation. RNA sequencing analysis showed that lncEry depletion decreased the expression of erythrocyte homeostasis or differentiation related genes, including globin genes, thus indicating its important role in regulating erythroid differentiation. Mechanistically, we performed RNA-pulldown assays and found that lncEry could interact with Wdr82, a component of the Set1A histone H3-Lys4 methyltransferase complex. In addition, a series of molecular assays indicated that lncEry could stabilize the localization of Set1A/Wdr82 complex to facilitate H3K4me3 on the promoter region of globin genes and participate in regulating erythropoiesis. These findings identify lncEry as an important player in the transcriptional regulation of globin genes to coordinate erythropoiesis. Disclosures No relevant conflicts of interest to declare.

关键词：