摘要：
Unmanned aerial vehicle (UAV) edge computing systems provide easy-to-deploy and low-cost services at those areas with inadequate infrastructure by deploying UAVs as moving edge servers for large-scale users. However, user devices are generally distributed unevenly in a large area, which makes it difficult for existing efforts to cope with this realistic scenario for optimal deployment of UAVs. Therefore, this paper considers a multiple UAV (Multi-UAV) Collaborative edge Computing (UCC) system by utilizing collaboration among them to split computation tasks at UAVs to balance the load and improve resource utilization. In order to maximize the energy-efficiency of the UCC system under the satisfaction of the delay constraint, we study the joint problem of UAV deployment, task collaborative offloading, computation and communication resource allocation in UCC system. We propose a bi-level optimization framework to solve the formulated non-convex mixed-integer optimization problem. In the upper level, the UAV deployment is optimized based on an improved differential evolution (DE) algorithm, and in the lower level the offloading decision and resource allocation are optimized based on a Reinforcement Learning (RL) algorithm with Twin Delayed Deep Deterministic policy gradient. Experimental results demonstrate the effectiveness and superiority of multi-UAV collaborative computing, with the proposed framework achieving a 32.4% reduction in energy consumption and an average 30% increase in task completion rate compared to DDPG, ToDeTaS, and other benchmark schemes.
摘要：
Unmanned Aerial Vehicles (UAVs) are heavily used in disaster or emergency scenarios. In this paper, we investigate the joint problem of task offloading, task scheduling, transmission power and computing resources allocation, and optimization of UAV deployment location for UAV-enabled Mobile Edge Computing (MEC), considering and highlighting the order of execution and transmission of different tasks. The corresponding optimization problem, which is a non-convex mixed-integer optimization problem, is formulated. In oder to solve this problem, the formulated problem is decomposed into three Sub-Problems (SP), and an iterative method based on Block Coordinate Descent (BCD) is proposed. Given the UAV location and resource allocation, the 1-st SP (SP1) of task offloading scheduling optimization is solved by greedy strategy optimization methods. Given the task offloading decision, task scheduling order, and resource allocation, the 2-nd SP (SP2) of optimizing the deployment location of UAV is solved by Successive Convex Approximation (SCA) optimization methods. Given the task offloading decision, task scheduling order, and UAV location, the 3-rd SP (SP3) of transmission and computing resources allocating is solved by convex optimization methods. Simulation results show that our proposed method can significantly reduce energy consumption compared to the benchmark schemes.
摘要：
Intelligent reflecting surface (IRS) enabled unmanned aerial vehicle (UAV) edge computing, a new communication technology, can provide sufficient capacity for edge computing system. However, due to the line-of-sight or the non line of sight of communicating environments will impact transmitting rate or delay, the IRS can be utilized to compensate the channel fading in the IRS-enabled UAV edge computing. In this article, the joint problem of IRS phase shift, UAV trajectory and power allocation in the system is investigated, aiming to maximize the energy efficient. The corresponding optimization problem, which consists of mixed integer nonlinear programming problem, is formulated. To solve the problem, the original problem is decomposed into two subproblems, and an iterative method framework based on convex optimization and deep reinforcement learning is proposed. Given the UAV trajectory and IRS phase shift, the convex optimization algorithm is used to solve the power allocation schemes. Then, given the power allocation schemes, the double deep Q network and deep deterministic policy gradient algorithms are utilized to solve the problem of optimal UAV trajectory and IRS phase shift. The simulation results demonstrate that our proposed method outperforms other schemes in terms of energy efficiency, providing significant enhancements.
关键词：
Array signal processing;Collaboration;Reconfigurable intelligent surfaces;Performance gain;Benchmark testing;Hybrid power systems;Resource management;Collaborative edge computing;deep reinforcement learning;reconfigurable intelligent surface;resource allocation;task offloading
摘要：
The problem of joint offloading decisions, resource allocation, and Reconfigurable Intelligent Surface (RIS) beamforming matrices for RIS-Assisted Edge Computing is a challenging issue. In this paper, user tasks can be either executed locally, or offloaded to a collaborative device or edge server with the assistance of the RIS, where RIS elements are grouped and assigned to all users to enable parallel services. The objective is formulated as a mixed integer nonlinear programming (MINLP) problem, where collaborative offloading decisions, RIS beamforming matrices, transmission power allocation, and computation resource allocation are jointly optimized to minimize the energy consumption. To address this problem, we propose a discrete-continuous Hybrid Action adapted Twin Delayed Deep Deterministic policy gradient (TD3) algorithm based on Deep Reinforcement Learning, named HAT. HAT constructs a latent representation space for the original discrete-continuous hybrid actions, fully considering the relations among highly coupled hybrid optimization variables. Experimental results demonstrate that HAT achieves significant performance gains over existing work (e.g., MELO, DDPG, PADDPG) and other benchmark schemes.
摘要：
Unmanned aerial vehicle (UAV)-enabled mobile-edge computing (MEC) is expected to provide low-latency, ultrareliable, and highly robust network services to improve user service experience. In this article, the UAV deployment, task offloading, and resource allocation problem is investigated in a multi-UAV-enabled MEC system with task-intensive region. UAVs as edge servers to provide computing services for ground terminal devices (TDs). The time-sensitive tasks of TDs can be computed locally or offloaded to UAVs. The goal is to improve the utility of tasks, i.e., maximize the number of tasks offloaded to UAVs under conditions of ensuring a desired task computed success rate and satisfying the energy and latency constraints. The jointly optimizing problem of the 3-D deployment, elevation angle, computational resource allocation of the UAV, and task offloading decision is formulated. To this end, a two-layer optimization approach is proposed to solve the formulated problem. Specifically, the upper layer decides the UAV position, elevation angle, and transmission power of TDs based on the actual ground situation. The lower layer determines the computational resource allocation of UAVs and the task offloading decision based on the optimized results derived from the upper layer. Through the two-layer joint optimization, our goal is finally achieved. Simulation results demonstrate that our proposed algorithm effectively improves the number of tasks offloaded to UAVs and the task completion rate simultaneously with the flexible UAV deployment and well-designed task offloading strategy.
摘要：
Vehicular Edge Computing (VEC) is a promising paradigm for autonomous driving. It can reduce delay and energy consumption of tasks. The problem of joint task offloading scheduling and resource allocation in VEC is a challenge issue. In this paper, we investigate the problem of joint task offloading, task scheduling, and resource allocation in VEC, and the fast changing channel between a vehicle and an edge server. A target problem of joint considering task offloading scheduling, resource allocation and time-varying channel in VEC is formulated. The goal is to minimize the delay and energy consumption of tasks to guarantee the Quality of Service (QoS) of VEC. Constraints on the completion time, the energy consumption, and the computing capability are considered for each task. The resulting mixed integer optimization problem is decomposed into a two-layer optimization problem. In the upper layer, we use a Deep Q-Network (DQN) to solve the task offloading scheduling problem. In the lower level, the CPU frequency allocation is determined using the Gradient Descent (GD) method. Numerical results illustrate that the proposed algorithm can minimize the delay and energy consumption of VEC for different network parameter settings.
摘要：
The circRNAs and miRNAs play an important role in the development of human diseases, and they can be widely used as biomarkers of diseases for disease diagnosis. In particular, circRNAs can act as sponge adsorbers for miRNAs and act together in certain diseases. However, the associations between the vast majority of circRNAs and diseases and between miRNAs and diseases remain unclear. Computational-based approaches are urgently needed to discover the unknown interactions between circRNAs and miRNAs. In this paper, we propose a novel deep learning algorithm based on Node2vec and Graph ATtention network (GAT), Conditional Random Field (CRF) layer and Inductive Matrix Completion (IMC) to predict circRNAs and miRNAs interactions (NGCICM). We construct a GAT-based encoder for deep feature learning by fusing the talking-heads attention mechanism and the CRF layer. The IMC-based decoder is also constructed to obtain interaction scores. The Area Under the receiver operating characteristic Curve (AUC) of the NGCICM method is 0.9697, 0.9932 and 0.9980, and the Area Under the Precision-Recall curve (AUPR) is 0.9671, 0.9935 and 0.9981, respectively, using 2-fold, 5-fold and 10-fold Cross-Validation (CV) as the benchmark. The experimental results confirm the effectiveness of the NGCICM algorithm in predicting the interactions between circRNAs and miRNAs.
摘要：
Numerous studies have shown that miRNAs play a crucial role in the investigation of complex human diseases. Identifying the connection between miRNAs and diseases is crucial for advancing the treatment of complex diseases. However, traditional methods are frequently constrained by the small sample size and high cost, so computational simulations are urgently required to rapidly and accurately forecast the potential correlation between miRNA and disease. In this paper, the DEJKMDR, a graph convolutional network (GCN)-based miRNA-disease association prediction model is proposed. The novelty of this model lies in the fact that DEJKMDR integrates biomolecular information on miRNA and illness, including functional miRNA similarity, disease semantic similarity, and miRNA and disease similarity, according to their Gaussian interaction attribute. In order to minimize overfitting, some edges are randomly destroyed during the training phase after DropEdge has been used to regularize the edges. JK-Net, meanwhile, is employed to combine various domain scopes through the adaptive learning of nodes in various placements. The experimental results demonstrate that this strategy has superior accuracy and dependability than previous algorithms in terms of predicting an unknown miRNA-disease relationship. In a 10-fold cross-validation, the average AUC of DEJKMDR is determined to be 0.9772.
摘要：
In this paper, we investigate the joint problem of task offloading, Unmanned Aerial Vehicle (UAV) trajectory design, and resource allocation for UAV-enabled edge computing, considering and highlighting the dependency among different tasks. The corresponding optimization problem, which is a mixed-integer problem, is formulated. To solve this problem, we propose an iterative method based on Block Coordinate Descent (BCD) to decompose the original problem into two subproblems. Given the offloading decision and resource allocation, the subproblem of UAV trajectory optimization is solved by convex optimization methods. Then, given the UAV trajectory, the subproblem of task offloading decision and the corresponding resource allocation is solved by dynamic programming and convex optimization methods. Simulation results show that our proposed method can significantly reduce energy consumption compared to the benchmark schemes.
摘要：
A growing number of studies have confirmed the important role of microRNAs (miRNAs) in human diseases and the aberrant expression of miRNAs affects the onset and progression of human diseases. The discovery of disease-associated miRNAs as new biomarkers promote the progress of disease pathology and clinical medicine. However, only a small proportion of miRNA-disease correlations have been validated by biological experiments. And identifying miRNA-disease associations through biological experiments is both expensive and inefficient. Therefore, it is important to develop efficient and highly accurate computational methods to predict miRNA-disease associations. A miRNA-disease associations prediction algorithm based on Graph Convolutional neural Networks and Principal Component Analysis (GCNPCA) is proposed in this paper. Specifically, the deep topological structure information is extracted from the heterogeneous network composed of miRNA and disease nodes by a Graph Convolutional neural Network (GCN) with an additional attention mechanism. The internal attribute information of the nodes is obtained by the Principal Component Analysis (PCA). Then, the topological structure information and the node attribute information are combined to construct comprehensive feature descriptors. Finally, the Random Forest (RF) is used to train and classify these feature descriptors. In the five-fold cross-validation experiment, the AUC and AUPR for the GCNPCA algorithm are 0.983 and 0.988 respectively.
摘要：
The joint problem of task offloading, collaborative computing, and resource allocation for multi-access edge computing (MEC) is a challenging issue. In this article, splitting computing tasks at MEC servers through collaboration among MEC servers and a cloud server, we investigate the joint problem of collaborative task offloading and resource allocation. A collaborative task offloading, computing resource allocation, and subcarrier and power allocation problem in MEC is formulated. The goal is to minimize the total energy consumption of the MEC system while satisfying a delay constraint. The formulated problem is a nonconvex mixed-integer optimization problem. In order to solve the problem, we propose a deep reinforcement learning (DRL)-based bilevel optimization framework. The task offloading decision, computing collaboration decision, and power and subcarriers allocation subproblems are solved at the upper level, whereas the computing resource allocation subproblem is solved at the lower level. We combine dueling-DQN and double-DQN and add adaptive parameter space noise to improve DRL performance in MEC. Simulation results demonstrate that the proposed algorithm achieves near-optimal performance in energy efficiency and task completion rate compared with other DRL-based approaches and other benchmark schemes under various network parameter settings.
关键词：
Stability analysis;Correlation;Fractals;Informatics;Stability criteria;Analytical models;Reliability;Correlation dimension;cyber-physical systems (CPSs);stability analysis
摘要：
Cyber-physical systems (CPSs) realize the automatic control of entities through computing systems and networks. Stability is an important factor in CPS for system upgrading and troubleshooting. Traditional analysis methods focus on simulation and formal analysis, which have two major limitations: first, the current state information of CPS is difficult to obtain; second, most CPS face the state space explosion problem. These problems can be avoided and a good analysis can be provided based on empirical data. The main work of this article is summarized as follows: first, a phase space reconstruction method is designed to divide the dataset into several subsequences with the same shape; second, we propose a stability analysis method based on correlation dimensions. Results indicate that the proposed approach can obtain a stable correlation dimension. CPS perform better if the correlation dimension is maintained within a certain range; otherwise, a destabilizing factor exists. The proposed stability analysis has less complexity and running time.
摘要：
The important role of microRNA (miRNA) in human diseases has been confirmed by some studies. However, only using biological experiments has greater blindness, leading to higher experimental costs. In this paper a high-efficiency algorithm based on a variety of biological source information and applying a combination of a convolutional neural network (CNN) feature extractor and an extreme learning machine (ELM) classifier is proposed. Specifically, the semantic similarity of diseases, the gaussian interaction profile kernel similarity of the four biological information of miRNA, disease, long non-coding RNA (lncRNA) and environmental factors (EFs), and the similarities of miRNAs are fused together. Among them, miRNAs similarity is composed of miRNA target information, sequence information, family information, and function information. Then, the dimensionality of the data set is reduced by the autoencoder (AE). Finally, deep features are extracted through CNN, and then the association between miRNA and disease is predicted by ELM. The experimental results show that the average AUC value based on the multi-biological source information (MSCNE) model is 0.9630, which can reach higher performance than the other classic classifier, feature extractor mentioned and the other existing algorithms. The results show the MSCNE algorithm is effective to predict the correlation of miRNA-disease.
摘要：
Mobile edge computing (MEC) is an emergent architecture, which brings computation and storage resources to the edge of mobile network and provides rich services and applications near the end users. The joint problem of task offloading and resource allocation in the multi-user collaborative mobile edge computing network (C-MEC) based on Orthogonal Frequency-Division Multiple Access (OFDMA) is a challenging issue. In this paper, we investigate the offloading decision, collaboration decision, computing resource allocation and communication resource allocation problem in C-MEC. The delay-sensitive tasks of users can be computed locally, offloaded to collaborative devices or MEC servers. The goal is to minimize the total energy consumption of all mobile users under the delay constraint. The problem is formulated as a mixed-integer nonlinear programming (MINLP), which involves the joint optimization of task offloading decision, collaboration decision, subcarrier and power allocation, and computing resource allocation. A two-level alternation method framework is proposed to solve the formulated MINLP problem. In the upper level, a heuristic algorithm is used to handle the collaboration decision and offloading decisions under the initial setting; and in the lower level, the allocation of power, subcarrier, and computing resources is updated through deep reinforcement learning based on the current offloading decision. Simulation results show that the proposed algorithm achieves excellent performance in energy efficient and task completion rate (CR) for different network parameter settings.
作者机构：
[邝祝芳; 陈清林; 李林峰] School of Computer and Information Engineering, Central South University of Forestry and Technology, Changsha;410004, China;[邓晓衡; 陈志刚] School of Computer Science and Engineering, Central South University, Changsha;410083, China;[邝祝芳; 陈清林; 李林峰] 410004, China
通讯机构：
School of Computer and Information Engineering, Central South University of Forestry and Technology, Changsha, China
期刊：
Journal of Systems Architecture,2021年118:102167 ISSN：1383-7621
通讯作者：
Zhufang Kuang<&wdkj&>Zhihao Ma
作者机构：
[Li, Zhe; Kuang, Zhufang; Ma, Zhihao] Cent South Univ Forestry & Technol, Sch Comp & Informat Engn, Changsha 410004, Peoples R China.;[Deng, Xiaoheng] Cent South Univ, Sch Comp Sci & Engn, Changsha 410010, Peoples R China.
通讯机构：
[Zhufang Kuang; Zhihao Ma] S;School of Computer and Information Engineering, Central South University of Forestry and Technology, Changsha, 410004, China
