A deep learning driven hybrid beamforming method for millimeter wave MIMO system

The hybrid beamforming is a promising technology for the millimeter wave MIMO system,which provides high spectrum efficiency,high data rate transmission,and a good balance between transmission performance and hardware complexity.The most existing beamforming systems transmit multiple streams by formulating multiple orthogonal beams.However,the Neural network Hybrid Beamforming(NHB)adopts a totally different strategy,which combines multiple streams into one and transmits by employing a high-order non-orthogonal modulation strategy.Driven by the Deep Learning(DL)hybrid beamforming,in this work,we propose a DL-driven nonorthogonal hybrid beamforming for the single-user multiple streams scenario.We first analyze the beamforming strategy of NHB and prove it with better Bit Error Rate(BER)performance than the orthogonal hybrid beamforming even with the optimal power allocation.Inspired by the NHB,we propose a new DL-driven beamforming scheme to simulate the NHB behavior,which avoids time-consuming neural network training and achieves better BERs than traditional hybrid beamforming.Moreover,our simulation results demonstrate that the DL-driven nonorthogonal beamforming outperforms its traditional orthogonal beamforming counterpart in the presence of subconnected schemes and imperfect Channel State Information(CSI).

An intelligent task offloading algorithm(iTOA)for UAV edge computing network

Unmanned Aerial Vehicle(UAV)has emerged as a promising technology for the support of human activities,such as target tracking,disaster rescue,and surveillance.However,these tasks require a large computation load of image or video processing,which imposes enormous pressure on the UAV computation platform.To solve this issue,in this work,we propose an intelligent Task Offloading Algorithm(iTOA)for UAV edge computing network.Compared with existing methods,iTOA is able to perceive the network’s environment intelligently to decide the offloading action based on deep Monte Calor Tree Search(MCTS),the core algorithm of Alpha Go.MCTS will simulate the offloading decision trajectories to acquire the best decision by maximizing the reward,such as lowest latency or power consumption.To accelerate the search convergence of MCTS,we also proposed a splitting Deep Neural Network(sDNN)to supply the prior probability for MCTS.The sDNN is trained by a self-supervised learning manager.Here,the training data set is obtained from iTOA itself as its own teacher.Compared with game theory and greedy search-based methods,the proposed iTOA improves service latency performance by 33%and 60%,respectively.

iPAS:A deep Monte Carlo Tree Search-based intelligent pilot-power allocation scheme for massive MIMO system

Massive Multiple-Input-Multiple-Output(MIMO)is a promising technology to meet the demand for the connection of massive devices and high data capacity for mobile networks in the next generation communication system.However,due to the massive connectivity of mobile devices,the pilot contamination problem will severely degrade the communication quality and spectrum efficiency of the massive MIMO system.We propose a deep Monte Carlo Tree Search(MCTS)-based intelligent Pilot-power Allocation Scheme(iPAS)to address this issue.The core of iPAS is a multi-task deep reinforcement learning algorithm that can automatically learn the radio environment and make decisions on the pilot sequence and power allocation to maximize the spectrum efficiency with self-play training.To accelerate the searching convergence,we introduce a Deep Neural Network(DNN)to predict the pilot sequence and power allocation actions.The DNN is trained in a self-supervised learning manner,where the training data is generated from the searching process of the MCTS algorithm.Numerical results show that our proposed iPAS achieves a better Cumulative Distribution Function(CDF)of the ergodic spectral efficiency compared with the previous suboptimal algorithms.

File Wallet:A File Management System Based on IPFS and Hyperledger Fabric

Online file management systems enable cooperatively editing and sharing.However,due to the cost of communication and storage infrastructures,traditional online file management services,e.g.,Google Drive and OneDrive,usually provide limited storage space and relatively low download speed for free users.To achieve better performance,ordinary users have to purchase their expensive services.Moreover,these file management systems are based on centralized architecture and bear the privacy leakage risk,because users’personal files are stored and controlled by their servers.To address the above problems,we propose a peer-to-peer(P2P)file management system based on IPFS and Hyperledger Fabric,named as FileWallet,which can serve as a personal wallet for individual users or organizations to store and share their files in a secure manner.In FileWallet,the users form a P2P network and a Fabric network,where P2P network builds the connections and distributed storage network and the Fabric network sustains consistent blockchain ledgers to record file operation related transactions.In our FileWallet,the storage and communication costs are mitigated in the decentralized design,and the file owner can fully control the access permission of the file to preserve the file privacy.The design of the system architecture,main functionalities,and system implementations are presented in this paper.The performance of the system is evaluated through experiments,and the experimental results show its wide applicability and scalability.